One of the most important challenges in the Machine and Deep Learning areas today is to build good models using small datasets, because sometimes it is not possible to have large ones. Several techniques have been proposed in the literature to address this challenge. This paper aims at studying the different available Deep Learning techniques and performing a thorough experimentation to analyze which technique or combination thereof improves the performance and effectiveness of the models. A complete comparison with classical Machine Learning techniques was carried out, to contrast the results obtained using both techniques when working with small datasets. Thirteen algorithms were implemented and trained using three different small datasets (MNIST, Fashion MNIST, and CIFAR-10). Each experiment was evaluated using a well-established set of metrics (Accuracy, Precision, Recall, F1, and the Matthews correlation coefficient). The experimentation allowed concluding that it is possible to find a technique or combination of them to mitigate a lack of data, but this depends on the nature of the dataset, the amount of data, and the metrics used to evaluate them.

Background: Computed tomography examinations have produced high radiation doses to patients, especially the CT brain. This study aimed to optimize the radiation dose and image quality in adult CT brain protocol. Materials and Methods: Images were acquired by Catphan 700 phantom. Radiation doses were recorded as CTDIvol and dose length product (DLP). CT brain protocols were optimized by varying parameters such as kVp, mAs, signal-to-noise ratio (SNR) level, and Clearview iterative reconstruction (IR). Image quality were also evaluataion by The AutoQA Plus software. Results: CT Number accuracy and linearity had a robust positive correlation with the linear attenuation coefficient (µ) and showed more inaccurate CT numbers when using 80 kVp. MTF showed a higher value in 100 and 120 kVp protocols, while high contrast spatial resolution showed a higher value in 80 and 100 kVp protocols. Low contrast detectability and CNR tended to increase when using high mAs, SNR and Clearview IR protocol. Noise decreased when using a high radiation dose and a high percentage of Clearview IR. CTDIvol and DLP were increased with increasing kVp, mAs, and SNR levels, while the increasing percentage of Clearview did not affect the radiation dose. Conclusion: Optimized protocols, including radiation dose and image quality, should be evaluated to preserve diagnostic capability. The recommended parameter settings include kVp set between 100-120 kVp, mAs ranging from 200-300 mAs, SNR level within the range of 0.7-1.0, and an iterative reconstruction value of 30% Clearview to 60% or higher.

.Purpose: This paper presents a comparative analysis of state-of-the-art DIR algorithms in the context of head and neck squamous cell carcinoma (HNSCC) radiation therapy. Materials and Methods: We used a dataset of head and neck cancer patients within the Cancer Image Archive, which includes 31 patients with 3D CT image data from pre-treatment, mid-treatment, and post-treatment stages of radiotherapy. We applied DIR algorithms to two datasets, one for pre-treatment to mid-treatment registration and another for mid-treatment to post-treatment registration, by aligning one CT image to another CT image. To quantitatively analyze the patient data, we focused on the spinal cord, optic nerve, brain stem, cochlea, and PTV as the OAR datasets. To verify the DIR algorithm, we used two non-learning-based methods, SyN and NiftyReg, as well as three deep learning-based methods, Voxelmorph, Cyclemorph, and Transmorph. We trained a deep learning model by adjusting the ratio of the training dataset, validation dataset, and test dataset to 7:1:2. Results: The average DSCs of SyN and NiftyReg, the non-learning-based methods, were 0.74±0.06 and 0.70±0.12, respectively. The deep learning-based methods, Voxelmorph, Cyclemorph, and Transmorph, had average DSCs of 0.72±0.08, 0.68±0.11, and 0.69±0.13, respectively. The deep learning DIR algorithm produced transformed outputs of OAR/PTV in a shorter time than other models, including commercial and conventional mathematical algorithms (At Inference(sec/images), Voxelmorph: 0.36, Cyclemorph: 0.3, Transmorph: 5.1, SyN: 140, NiftyReg: 40.2). Conclusions: In conclusion, our study provides a comprehensive comparison of commercial DIR algorithms with traditional and deep learning-based DIR methods. Our results demonstrate that commercial DIR algorithms outperform traditional DIR methods in terms of accuracy and efficiency. However, we also show that deep learning-based DIR methods have the potential to achieve similar performance to commercial algorithms with proper training and optimization. Our findings suggest that both commercial and deep learning-based DIR methods have their respective advantages and limitations, and the choice of method should depend on the specific requirements of the clinical application. Overall, our study contributes to ongoing efforts to improve the accuracy and efficiency of DIR methods for better patient outcomes.

Image compression is a top priority today due to the need for faster encoding and decoding. To achieve this, the present study has proposed the use of Canonical Huffman Coding (CHC) as an entropy coder, which has a lower decoding time complexity than binary Huffman codes. For image compression, combining of the Discrete Wavelet Transform (DWT) and CHC with Principal Component Analysis (PCA) has been recommended. The lossy method has been introduced by using PCA, followed by DWT and CHC to enhance compression efficiency. By using DWT and CHC instead of PCA alone, the reconstructed image has been found to have a better peak signal-to-noise ratio (PSNR) value. This study has developed a hybrid compression model combining the advantages of DWT, CHC and PCA. With the increasing use of image data, better image compression techniques are necessary for efficient use of storage space. The proposed technique has achieved up to 60% compression while maintaining high visual quality. This method has also outperformed the currently available techniques in terms of both PSNR (in dB) and bit-per-pixel (bpp) scores. This approach has been tested on various color images, including Peppers 512×512 and Couple 256×256, showing improvement by 17 dB and 22 dB, respectively, while reducing bpp by 0.56 and 0.10, respectively. For grayscale images, i.e., Lena 512×512 and Boat 256×256, the proposed method has shown an improvement by 5 dB and 8 dB, respectively, with a decrease of 0.02 bpp in both cases.

Precipitation processes are technologies commonly used in hydrometallurgical plants to recover metals or to treat wastewaters. Moreover, solid-liquid separation technologies, such as thickening or filtering, are relevant unit operations, included in the precipitation technologies. These methods are strongly dependent on the characteristics of the solid precipitates formed during the specific precipitation reaction. One of these characteristics is the particle size distribution (PSD) of the solid precipitates which are fed into a solid-liquid separation process. Therefore, PSD determination is a typical practice for the characterization of the slurries generated in a precipitation plant. Furthermore, the precipitates generated in these processes have a colloidal or aggregation behavior, depending on the operational conditions. Nevertheless, the conventional methods used to estimate PSD (e.g., laser diffraction and/or ciclosizer) have not been designed to measure particles that tend to aggregate or disaggregate, since they include external forces (e.g., centrifugal, agitation, pumping and sonication). These forces affect the true size of the aggregates formed in a unit operation, thereby losing representativity in terms of aggregates particle size. This study presents an alternative method of measuring the size distribution of particles with aggregation behavior, particularly, by using non-invasive microscopy and image processing and analysis. The samples used have been obtained from an experimental precipitation process by applying sulfidization to treat the cyanide-copper complexes contained in a cyanidation solution. This method has been validated with statistical tools and compared with a conventional analysis based on laser diffraction. Our results show significant differences between the methods analyzed, demonstrating that image processing and analysis by microscopy is an excellent and non-invasive alternative to obtaining size distribution of aggregates in precipitation processes.

Apoptosis is associated with numerous phenotypical characteristics, and is thus studied with many tools. In this study, we compared two broadly used apoptotic assays: TUNEL and staining with an antibody targeting the activated form of an effector caspase. To compare them, we developed a protocol based on commonly used tools such as filters, zprojection and thresholding. Even though it is commonly used in imageprocessing protocols, thresholding remains a recurring problem. Here we analyzed the impact of processing parameters and readout choice on the accuracy of apoptotic signal quantification. Our results show that TUNEL is quite robust, even if image processing parameters can allow or not to detect subtle differences of the apoptotic rate. On the contrary, images from anticleaved caspase staining are more sensitive to handle and proved to necessitate to be processed more carefully. We then developed an open source Fiji macro automatizing most steps of the image processing and quantification protocol. It is noteworthy that the field of application of this macro is wider than apoptosis as it can perfectly be used to treat and quantify other kind of images.

The essence of cross-modal generation and retrieval modeling for image-text interactions lies in semantic consistency. Among these, cross-modal representation alignment serves as the foundational requirement for achieving cross-modal semantic consistency. The crux of our proposed method entails the collaborative training of an image captioning model(referred to as the ’captioner’) and a pair of contrastive encoders for image-text matching(referred to as the ’concoder’). This synergistic approach yields concurrent enhancements in concoder’s performance, captioner’s proficiency, and cross-modal semantic coherence. We coin the proposed method as ‘ReCap’. To begin, we initialize the concoder through knowledge distillation from a pre-trained model. During the training process, we use the output of the initialized concoder as input to a residual attention network, jointly training it with the captioner to achieve semantic consistency. Subsequently, we iteratively update the concoder during the image-text momentum encoding phase using the residual attention network, creating a closed-loop for semantic consistency resolution. Upon completion of training, the concoder and captioner modules can be used independently to perform tasks related to cross-modal retrieval and cross-modal generation of text and images. In order to substantiate the efficacy of our proposed method, we initially conducted empirical experiments encompassing image-text retrieval and image captioning tasks, employing a widely recognized benchmark dataset, MSCOCO. Subsequently, we assessed the fine-grained cross-modal alignment performance of the concoder through an image classification task on the iNaturalist 2018 dataset. The achieved performance metrics notably surpassed those achieved by several incumbent state-of-the-art models, thus validating the proficiency of our method. Finally, motivated by the practical requirements of handling the nature conservation image data, we performed caption annotation for the iNaturalist 2018 dataset. Subsequently, we trained the ReCap on this annotated data. Experimental results demonstrate that our proposed method can maintain semantic consistency between cross-modal retrieval and image caption generation for species with similar visual features but distinct semantics. This achievement signifies a meaningful exploration in the field of cross-modal semantic consistency representation, holding significant practical value in the domain of biological research.

End-to-end learned image compression codecs have notably emerged in recent years. These codecs have demonstrated superiority over conventional methods, showcasing remarkable flexibility and adaptability across diverse data domains while supporting new distortion losses. Despite challenges such as computational complexity, learned image compression methods inherently align with learning-based data processing and analytic pipelines due to their well-suited internal representations. The concept of Video Coding for Machines has garnered significant attention from both academic researchers and industry practitioners. This concept reflects the growing need to integrate data compression with computer vision applications. In light of these developments, we present a comprehensive survey and review of lossy image compression methods. Additionally, we provide a concise overview of two prominent international standards, MPEG Video Coding for Machines and JPEG AI. These standards are designed to bridge the gap between data compression and computer vision, catering to practical industry use cases.

In the last years, more and more studies highlight the advantages of complementing traditional master classes with additional activities that improve students´ learning experience. This combination of teaching techniques is specially advised in the field of structural engineering, where intuition of the structural response it is of vital importance to understand the studied concepts. This paper deals with the introduction of a new (and more encouraging) educational tool to introduce intuitively students in the dynamic response of structures excited with an educational shaking table. Most of the educational structural health monitoring systems use sensors to determine the dynamic response of the structure. The proposed tool is based on a radically different approach, as it is based on low-cost image-recognition techniques. In fact, it only requires the use an amateur camera, a black background and a computer. In this study, the effects of both the camera location and the image quality are also evaluated. Finally, to validate the applicability of the proposed methodology, the dynamic response of small-scale buildings with different typologies is analyzed. In addition, a series of surveys were conducted in order to evaluate the activity based on student´s satisfaction and the actual acquisition and strengthening of knowledge.

Recent technological advances have significantly increased the data volume obtained from deep space exploration missions, making the downlink rate a primary limiting factor. Particularly, JAXA’s Martian Moons eXploration (MMX) mission encounters this problem when identifying safe and scientifically valuable landing sites on Phobos using high-resolution images. A strategic approach in which we effectively reduce image data volumes without compromising essential scientific information is thus required. In this work, we investigate the influence of image data compression, especially as it concerns the accuracy of generating the local Digital Terrain Models (DTMs) that will be used to determine MMX’s landing sites. We obtain simulated images of Phobos that are compressed using the CCSDS-120 with integer/float-point discrete wavelet transform (DWT), candidate algorithms for the MMX mission. Accordingly, we show that, if the compression ratio is 70% or lower, the effect of image compression remains constrained, and local DTMs can be generated within altitude errors of 40 cm on the surface of Phobos, which is ideal for selecting safe landing spots. We conclude that the compression ratio can be increased as high as 70%, and such compression enables us to facilitate critical phases in the MMX mission even with the limited downlink rate.

: On earth, plants play the most important part. Every organ of a plant plays a vital role in the ecological field as well as the medicinal field. But on the whole earth there are several species of plants are available. Different plants have different diseases. Therefore it is needed to identify the plants and their diseases to prevent loss. Now to identify the plants and their diseases manually is very time consuming. In this research an automatic plant and their disease detection system is proposed. For experimental purposes, high-quality leaf images are accepted for training and testing. For detecting the healthy and diseased area in a leaf, region-based and color-based region thresholding techniques were used. For feature selection Histogram Oriented Gradient (HOG) and Local Binary Pattern (LBP) method were applied. Finally for classification two-class and multi-class Support Vector Machine (SVM) was used. It is observed that both feature selection processes with SVM give 99% accuracy. Finally to understand the automated system a graphical user interface was created for all users.

Diabetic retinopathy (DR), a major complication of prolonged diabetes, poses a significant risk of vision loss. Early detection is critical for effective treatment, yet traditional diagnostic methods by ophthalmologists are time-consuming, costly, and subject to variability. This study introduces a novel approach employing a hybrid Convolutional Neural Network-Radial Basis Function (CNN-RBF) classifier integrated with Multi-Scale Discriminative Robust Local Binary Pattern (MS-DRLBP) features for enhanced DR detection. We implemented advanced image preprocessing techniques, including noise reduction, morphological operations, and Otsu’s thresholding, to optimize blood vessel segmentation from retinal images. Our method demonstrates exceptional performance in screening DR, achieving an average of 96.10% precision, 95.35% sensitivity, 97.06% specificity, and 96.10% accuracy. These results significantly outperform traditional methods and offer a promising tool for remote and efficient screening of DR. Applied to publicly available datasets, this research contributes to the development of accessible, accurate diagnostic methods in ophthalmology, potentially reducing the global burden of diabetic vision loss.

Analytical instruments used for scientific research and education are often expensive. This limitation poses a challenge for schools and educators in low-income countries to provide practical science training to students. To address this problem, the improvisation of analytical instruments and instructional materials has emerged as a viable solution. By incorporating practical experiments into science education, students have the opportunity to engage directly with scientific instruments, conduct investigations, and collect data. This hands-on approach fosters a deeper understanding of scientific principles, enhances critical thinking skills, and cultivates scientific mindsets among students. Herein, we review and discuss, step-by-step, the approach of using a smartphone for quantitative analysis, referred to as smartphone digital image colorimetry (SDIC). SDIC, with its practicality and accessibility, utilizes smartphone digital cameras for image acquisition and the freely available image processing programs, such as ImageJ and smartphone Apps, for image quantification. Using SDIC can enable students in low-income countries to develop essential scientific skills, including critical thinking, data interpretation, and an evidence-based approach to scientific research. By leveraging the ubiquity and affordability of smartphone technology, SDIC offers an accessible and cost-effective approach to practical science education, bridging the gap between theory and practice in resource-constrained settings.

Plant phenotype plays an important role in crop breeding and planting. Leaf phenotype is an important part of plant phenotype. In order to analyze the leaf phenotype, the target leaf is required to be segmented from the complex background image. In this paper, an automatic soybean leaf segmentation method based on object detection and interactive segmentation models is proposed. Firstly, the Libra R-CNN object detection algorithm is used to detect all soybean leaves in the image. Then, based on the idea that the target soybean leaf is located in the center of the image and the area is large, the detection bounding box of the target leaf is selected. In order not to destroy the segmentation result, the bounding box is optimized to completely enclose the whole leaf. Finally, according to the optimized bounding box, the prior channels of foreground and background are constructed using Gaussian model. The two channels together with the original image are as the input of the interactive object segmentation with inside-outside guidance model to segment the target soybean leaf. A large number of qualitative and quantitative experimental results show that the method has high segmentation accuracy and strong generalization capacity.

Objective tools to track medication adherence are lacking. A tool to monitor pill intake that can be implemented in mHealth apps without the need for additional devices was developed. We propose a pill intake detection tool that uses digital image processing to analyze images of a blister to detect the presence of pills. The tool uses the circular Hough transform as a feature extraction technique and is therefore primarily useful for the detection of pills with a round shape. This pill detection tool is composed of two steps. First, the registration of a full blister and storing of reference values in a local database. Second, the detection and classification of taken and remaining pills in similar blisters, to determine the actual number of untaken pills. In the registration of round pills in full blisters, 100% of pills in gray blisters or blisters with a transparent cover were successfully detected. In counting of untaken pills in partially opened blisters, 95.2% of remaining and 95.1% of taken pills were detected in gray blisters, while 88.2% of remaining and 80.8% of taken pills were detected in blisters with a transparent cover. The proposed tool provides promising results for the detection of round pills. However, the classification of taken and remaining pills need to be further improved, in particular for the detection of pills with non-oval shapes.

This paper presents a two-stage hierarchical neural network using image classification and object detection algorithms as key building blocks for a system that automatically detects a potential design right infringement. This neural network is trained to return the Top-N original design right records that highly resemble the input image of a counterfeit. Design rights specify the unique aesthetic characteristics of a product. Due to the rapid change of trends, new design rights are continuously generated. This work proposes an Ensemble Neural Network (ENN), an artificial neural network model that aims to deal with a large amount of counterfeit data and design right records that are frequently added and deleted. At first, we performed image classification and objection detection learning per design right using the existing models with a proven track record of high accuracy. The distributed models form the backbone of the ENN and yield intermediate results aggregated at a master neural network. This master neural network is a deep residual network paired with a fully connected network. This ensemble layer is trained to determine the sub-models that return the best result for a given input image of a product. In the final stage, the ENN model multiples the inferred similarity coefficients to the weighted input vectors produced by the individual sub-models to assess the similarity between the test input image and the existing product design rights to see any sign of violation. Given 84 design rights and the sample product images taken meticulously under various conditions, our ENN model achieved average Top-1 and Top-3 accuracies of 98.409% and 99.460%, respectively. Upon introducing new design rights data, a partial update of the inference model was done an order of magnitude faster than the single model. ENN maintained a high level of accuracy as it scaled out to handle more design rights. Therefore, the ENN model is expected to offer practical help to the inspectors in the field, such as the customs at the border that deal with a swarm of products.

Deep learning classification is the state-of-the-art of machine learning approach. Earlier work proves that the deep convolutional neural network has successfully and brilliantly in different applications such as images or video data. Recognizing and clarifying the remote sensing aspect of the earth's surface and exploit land cover and land use (LCLU). First, this article summarized the remote sensing emerging application and challenges for deep learning methods. Second, we propose four approaches to learn efficient and effective CNNs to transfer image representation on the ImageNet dataset to recognize LCLU datasets. We use VGG16, Inception-ResNet-V2, Inception-V3, and DenseNet201 models to extract features from the EACC dataset. We use pre-trained CNNs on ImageNet to extract features. For feature selection we proposed principal component analysis (PCA) to improve accuracy and speed up the model. We train our model by multi-layer perceptron (MLP) as a classifier. Lastly, we apply the multi-granularity encoding ensemble model. We achieve an overall accuracy of 92.3% for the nine-class classification problem. This work will help remote sensing scientists understand deep learning tools and apply them in large-scale remote sensing challenges

: Image guided superficial radiation therapy (IGSRT) combines superficial radiation therapy (SRT) with full dermal visualization (FDV) via high resolution dermal ultrasound (HRDUS) for the treatment of non-melanoma skin cancer (NMSC). The gold standard for IGSRT delivery includes a comprehensive cancer care model with support for the dermatologists by a multidisciplinary team. When delivered in this model, IGSRT can achieve cure rates of 99% for treatment of NMSC. This paper focuses on the benefits of IGSRT during therapy. Medical records from 7 dermatology clinics of 883 patients with 1,507 cases of NMSC treated with IGSRT be-tween 2017 and 2018 were retrospectively reviewed. 92% of the NMSC lesions showed daily depth fluctuations, 60.32% of lesions did not require changes during therapy, and nearly 40% of lesions required at least one compensatory change during therapy. 83% of NMSC lesions were labeled high-risk based on the 2024 NCCN guidelines. Increasing and decreasing tumor depth measurements during IGSRT inform dermatologists when adaptive changes in energy (kV), TDF and dose will result in more efficacy and less toxicity, respectively.

Chaotic theory is commonly being researched for application in image encryption scheme (IES). In this paper, a novel two-dimensional cross hyperchaotic Sine-modulation-Logistic map (2D-CHSLM) based on the famous Sine and Logistic maps. The hyperchaotic behaviors of 2D-CHSLM is testified with the help of their bifurcation diagrams, trajectory plots, Lyapunov exponents, sample entropy, C0 complexity, permutation entropy and 0-1 test. A new bit-level IES with traditional encryption structure is proposed utilizing 2D-CHSLM. The 2D-CHSLM-IES performs a 2D-CHSLM-based bit-level confusion using zig-zag transform and a 2D-CHSLM-based cross coupled diffusion operations for generating a highly secure cipher-image. Then the simulations and security analyses are further carried out with the help of key space, key sensitivity, histogram, correlation, information entropy, differential attack, noise and data loss attacks, prove that the security of the proposed 2D-CHSLM-IES

Image encryption is increasingly becoming an important area of research in information security and network communications, as digital images are widely used in various applications and are vulnerable to various types of attacks. In this research work, a color image cryptosystem that is based on a 3-layer permutation-substitution network (PSN) is proposed. For every layer, an encryption key and an S-box are generated and utilized. Those are based on a four-dimensional (4D) dynamical Chen system of a fractional-order, the Mersenne Twister, OpenSLL, Rule 30 Cellular Automata and Intel’s MKL. The sequential application of Shannon’s ideas of diffusion and confusion for 3 times guarantees a total distortion of any input plain image, resulting in a totally encrypted one. Apart from the excellent and comparable performance to counterpart algorithms from the literature, showcasing resistance to visual, statistical, entropy, differential, known plaintext and brute-force attacks, the proposed image cryptosystem provides an exceptionally superior performance in 2 aspects: a vast key space of 2^1658 and an average encryption rate of 3.34 Mbps. Furthermore, the proposed image cryptosystem is shown to successfully pass all the tests of the NIST SP 800 suite.

To reduce the redundant counting of TDC in high-speed applications and thus reduce power consumption, a TDC architecture is proposed to quantify the difference between two adjacent rows of pixel signals. This structure can remove the identical part between two rows of pixel signals by adjusting the start and stop signal of the TDC, which will reduce the number of flipping of D flip-flops in the TDC. In the 110nm CMOS process, simulation results show that this design achieves an effective number of bits (ENOB) of 4.72 bits and a Figure of Merit (FoM) of 104.7 fJ/step - 162.3 fJ/step with a power consumption ranging from 60 µW to 93 µW. Compared with traditional counting methods, the proposed TDC can reduce counting power consumption by 30%.

Electron Beam Melting (EBM) is an increasingly used Additive Manufacturing (AM) technique employed by many industrial sectors, including the medical device and aerospace industries. In EBM process monitoring, data analysis for processed layer quality evaluation is currently focused on the extraction of information from the raw data collected in-EBM process, i.e. thermal/ optical / electronic images, and the comparison between the collected data and the Computed Tomography (CT)/ microscopy images generated post-EBM process. This article postulates that a stack of bitmaps could be generated from the 3D model at a range of Z heights during file preparation of the EBM process, and serve as a reference image set. In-EBM process comparison between that and the workpiece images collected during the EBM process could then be used for quality assessment purposes. In addition, despite the extensive literature on 3D model slicing and contour generation for AM process preparation, no methods regarding image generation from cross sections of the 3D models have been disseminated in details. This article aims to address this by presenting a piece of 3D model-image generation software. The software is capable of generating binary 3D model reference images with user-defined Region-of-Interest (ROI) of the processing area, and Z heights of the model. It is envisaged that this 3D model-reference image generation ability opens up new opportunities in quality assessment for the in-process monitoring of the EBM process.

One of the frequently used classes of the sparse reconstruction algorithms is based on the iterative shrinkage/thresholding procedure, where the thresholding parameter controls a trade-off between the algorithm accuracy and the execution time. In order to avoid this trade-off, we propose using a fast intersection of confidence interval method in order to adaptively control the threshold value through the reconstruction algorithm iterations. We have upgraded the two-step iterative shrinkage thresholding algorithm with a such procedure, improving its performance. The proposed algorithm, denoted as the FICI-TwIST, along with a few selected state-of-the-art sparse reconstruction algorithms have been tested on the classical problem of image recovery by emphasizing the image sparsity in the discrete cosine and the discrete wavelet domain. Furthermore, we have derived a single wavelet transformation matrix which avoids wrapping effects achieving significantly faster execution times when compared to more traditional function based transformation. The obtained results indicate competitive performance of the proposed algorithm, even in cases where all algorithm parameters have been individually fine-tuned for best performances.

Pedestrian object detection plays a significant role in intelligent systems such as intelligent traffic and monitoring. Traditional machine learning methods on pedestrian detection have shown various drawbacks, \eg{} low accuracy, slow speed, \etc The Convolutional Neural Network (CNN) based object detection algorithms have demonstrated remarkable advantages in the field of pedestrian detection. However, the mainstream CNNs still face the problems of slow speed and low detection accuracy, especially on small and occluded targets from aerial perspective. In this paper, we propose Multi-Scale Attention YOLO (MSA-YOLO) detection algorithm to address the above issues. MSA-YOLO includes a Squeeze, Excitation and Cross Stage Partial (SECSP) channel attention module for CNNs to extract richer pedestrian features with a small number of extra parameters. It also contains a multi-scale prediction module to capture the information among different pedestrian scales, which can recognize the small objects with higher accuracy and significantly reduce the missed detection. To sufficiently evaluate our proposed model, we manually collect and annotate a new benchmark dataset, Luoyang Pedestrian Dataset \footnote{The dataset can be downloaded through this anonymous link: \url{https://drive.google.com/drive/folders/13po1FX7Qk5RDgb60-dzOi74cq_kqDJtM?usp=sharing} }, which has much more sample annotations, features, scenes and image view angles than the existing benchmark datasets. In addition, the images in our dataset have higher resolution than most of benchmark pedestrian detection datasets, which can provide more detailed features of pedestrians and thus improve the model performance. When tested on Luoyang Pedestrian Dataset, our proposed MSA-YOLO algorithm significantly outperform the most commonly used baseline models with almost the same model size. This shows the efficiency of our proposed model. (The code and new dataset will be released to the public later.)

Deep learning methods have been widely used in PolSAR image classification. To learn the polarimetric information, many deep learning methods expect to learn high-level semantic features from original PolSAR data. However, only original data cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these shortages, we propose a double-channel CNN network combined with an edge-preserving MRF model(DCCNN-MRF) for PolSAR image classification. Firstly, to combine complex matrix data and multiple scattering features together, a double-channel convolution network(DCCNN) is developed, which consists of a Wishart-based complex matrix and multi-feature subnetworks. The Wishart-based complex matrix network can learn the statistical characteristics and channel correlation well, and the multi-feature network can learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of features to enhance advantageous features and reduce redundant ones. Finally, an edge preserving MRF model is designed to combine with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining adaptive weighted neighborhood for edge pixels. Experiments are conducted on four real PolSAR data sets with different sensors and bands. Experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.

Femur length (FL) is a biometric measurement of ultrasound images used to identify the growth patterns and abnormalities of the foetus. Automatic segmentation of FL can improve the efficiency and convenience of inexperienced users. The femur region in a low-cost ultrasound image is a small area with low contrast intensity compared with the non-femur region. This study proposed a fully automated framework for segmenting and measuring the FL in a portable ultrasound image. We utilized statistical modeling, employing Gaussian mixture functions for thresholding to extract the femur area from the background. We also used the localizing region-based active contour method to segment the femur region accurately. We also proposed a refinement step in this framework to obtain a more accurate femur area in the ultrasound image. Because the length and position of the femur are the main factors affecting foetal biometric measurement accuracy, we not only evaluated segmentation results using region-based methods, such as sensitivity, specificity, and dice similarity. We also applied the FL measurement approach to evaluate the angle and length accuracy relative to the ground truth. In terms of region-based segmentation performance, the proposed method provided the best average performance with a sensitivity of 0.78, specificity of 0.87, and dice similarity of 0.81. For FL measurement performance, the proposed framework achieved an average angle accuracy of 0.99, distance accuracy of 0.88, and length accuracy of 0.93.

This study aims to test a model linking destination image, perceived value, tourist satisfaction, and tourist loyalty. Based on a sample of 300 tourists travelling by car from the World Natural Heritage Site of Tianchi, China, a new model of destination image was explored and data were analysed using partial least squares structural equation modelling (PLS-SEM). The results show that perceived value and satisfaction are direct antecedents of destination loyalty. Above all, perceived value and tourist satisfaction mediate the relationship between destination image and loyalty. Finally, this study discusses the theoretical and management implications of the findings in order to boost the tourism industry in the context of car trips.

The present research endeavours to examine the impact of customers' perceptions regarding a firm's dedication to corporate social responsibility (CSR) on their allegiance to particular banking brands. The mediating factors of brand credibility and image help to facilitate the indirect relationship between corporate social responsibility (CSR) and brand equity, which is the focus of this study. The objective of the research is to investigate the plausible causal association among perceived corporate social responsibility, brand image, brand credibility, and brand equity. The study's data was obtained by conducting a survey among a sample of 320 banking customers in Ethiopia. In order to perform a thorough examination of the data, AMOS version 24.0 and structural equation modelling (SEM) methodologies were employed. The present research endeavours to broaden the conventional comprehension of the advantages that corporate social responsibility (CSR) offers to customers. It aims to address a void in the current literature by scrutinising the impacts of customers' perceptions of CSR, brand credibility, and brand image on their allegiance towards particular banking service brands. The findings of this study carry substantial implications for financial institutions, and the conclusions derived from the results are of considerable significance.

Every biological image contains quantitative data that can be used to test hypotheses about how patterns were formed, what entities are associated with one another, and whether standard mathematical methods inform our understanding of biological phenomena. In particular, spatial point distributions and polygonal tessellations are particularly amendable to analysis with a variety of graph theoretic, computational geometric, and spatial statistical tools such as: Voronoi Polygons; Delaunay Triangulations; Perpendicular Bisectors; Circumcenters; Convex Hulls; Minimal Spanning Trees; Ulam Trees; Pitteway Violations; Circularity; Clark-Evans spatial statistics; Variance to Mean Ratios; Gabriel Graphs; and, Minimal Spanning Trees. Furthermore, biologists have developed a number of empirically related correlations for polygonal tessellations such as: Lewis’s Law (the number of edges of convex polygons are positively correlated with the areas of these polygons): Desch’s Law (the number of edges of convex polygons are positively correlated with the perimeters of these polygons); and Errara’s Law (daughter cell areas should be roughly half that of their parent cells’ areas). We introduce a new Pitteway Law that the number of sides of the convex polygons in a Voronoi tessellation of biological epithelia is proportional to the minimal interior angle of the convex polygons as angles less than 90 degrees result in Pitteway violations of the Delaunay dual of the Voronoi tessellation.

The quantization error (QE) from Self-Organizing Map (SOM) output after learning is exploited in this studies. SOM learning is applied on time series of spatial contrast images with variable relative amount of white and dark pixel contents, as in monochromatic medical images or satellite images. It is proven that the QE from the SOM output after learning provides a reliable indicator of potentially critical changes in images across time. The QE increases linearly with the variability in spatial contrast contents of images across time when contrast intensity is kept constant. The hitherto unsuspected capacity of this metric to capture even the smallest changes in large bodies of image time series after using ultra-fast SOM learning is illustrated on examples from SOM learning studies on computer generated images, MRI image time series, and satellite image time series. Linear trend analysis of the changes in QE as a function of the time an image of a given series was taken gives proof of the statistical reliability of this metric as an indicator of local change. It is shown that the QE is correlated with significant clinical, demographic, and environmental data from the same reference time period during which test image series were recorded. The findings show that the QE from SOM, which is easily implemented and requires computation times no longer than a few minutes for a given image series of 20 to 25, is useful for a fast analysis of whole series of image data when the goal is to provide an instant statistical decision relative to change/no change between images.

When extract building from high resolution remote sensing image with meter/sub-meter accuracy, the shade of trees and interference of roads are the main factors of reducing the extraction accuracy. Proposed a Bayesian Convolutional Neural Networks(BCNET) model base on standard fully convolutional networks(FCN) to solve these problems. First take building with no shade or artificial removal of shade as Sample-A, woodland as Sample-B, road as Sample-C. Set up 3 sample libraries. Learn these sample libraries respectively, get their own set of feature vector; Mixture Gauss model these feature vector set, evaluate the conditional probability density function of mixture of noise object and roofs; Improve the standard FCN from the 2 aspect:(1) Introduce atrous convolution. (2) Take conditional probability density function as the activation function of the last convolution. Carry out experiment using unmanned aerial vehicle(UVA) image, the results show that BCNET model can effectively eliminate the influence of trees and roads, the building extraction accuracy can reach 97%.

Guided image filter implicitly balances noise and details based on local variance, achieving noise suppression while preserving prominent edges. However, we have observed limitations in using variance to distinguish between noise and image details, resulting in the suppression of fine structures alongside noise. Furthermore, the goal of enhancing image details, which is crucial in image filtering, has not been adequately addressed in edge-preserving filter design. In this paper, we approach image filtering as a problem of spectral energy reconfiguration, where the gain of each spectral band is adaptively regulated to achieve simultaneous noise suppression and detail enhancement. Instead of relying on variance, we employ a linear noise estimator to obtain the Signal-to-Noise Ratio (SNR) measurement necessary for dynamic gain regulation. Similar to the guided image filter, we determine the filter coefficients by solving the closed-form solution of the optimizer. We demonstrate that the proposed extended guided filter effectively integrates information from multiple spectral bands locally, allowing for the joint enhancement of meaningful details while simultaneously smoothing noise.

This study presents a method for the rapid and accurate generation of two-dimensional (2D) orthomosaic maps using selected image data collected by drone-captured video. The focus is on developing a real-time method capable of creating maps more quickly than image selection. The scale-invariant feature transform (SIFT) algorithm is applied to drone images to extract features in various scale regions. For feature point matching, a matching method based on the fast library for approximate nearest neighbors (FLANN) was adopted. A comparison of the computational speed of the FLANN with that of the k-nearest neighbors (KNN) and brute force matcher during the matching process revealed FLANN's superior capability for real-time data processing. The random sample consensus (RANSAC) algorithm was employed to enhance the accuracy of the matching by removing outliers, effectively identifying and eliminating mismatches, and reinforcing the reliability of feature point matching. The combination of SIFT, FLANN, and RANSAC algorithms demonstrates the capacity to process drone-captured image data in real time, facilitating the generation of precise 2D orthomosaic maps. The proposed method was assessed and validated using imagery obtained as the drone executed curvilinear and straight flight paths, confirming its accuracy and operational efficiency concurrently with the image capture process.

This study explores how the covid-19 pandemic affected some psychological factors in people who got tattoos during or after the lockdown, the psychological factors assessed were self-esteem, risk taking behaviour, body image and locus of control. The study used a quantitative, between-subjects design to investigate the experiences of participants who acquired tattoos during the pandemic compared to those who did not. The results showed that participants who got a tattoo during the pandemic reported higher levels of self-esteem and body image satisfaction compared to those who did not get a tattoo. Furthermore, the findings suggest that individuals with tattoos may have a more external locus of control. Participants with tattoos exhibited higher levels of risk-taking behaviour compared to those without tattoos, furthermore sex affected risk-taking behaviour in tattooed individuals, and females with tattoos displayed a higher risk taking tendency than their tattooed male counterparts. Further research needs to be done while acknowledging the limitations of this study. Overall, this study is pivotal in establishing how the pandemic may have affected the aforementioned psychological factors in people with tattoos. It also adds to the growing body of literature in body modification and psychology.

The study concentrates on researching possibilities of using computer image analysis and neural modeling in order to assess selected quality discriminants of spray-dried chokeberry powder. The aim of the paper is quality identification of chokeberry powders on account of their highest dying power, the highest bioactivity as well as technologically satisfying looseness of powder. The article presents neural models with vision technique backed up by devices such as digital camera as well as electron microscope. Reduction in size of input variables with PCA has influence on improving the processes of learning data sets, thus increasing effectiveness of identifying chokeberry fruit powders included in digital pictures, which is shown in the results of the conducted research. The effectiveness of image recognition are presented by classifying abilities as well as low Root Mean Square Error (RMSE), for which the best results are achieved with typology of network type Multi-Layer Perceptron (MLP). The selected networks type MLP are characterized by the highest degree of classification at 0.99 and RMSE at 0.11 at most at the same time.

Rapid and extensive urbanization has adversely impacted humans and ecological entities in the recent decades through a decrease in surface permeability and the emergence of urban heat islands (UHI). While detailed and continuous assessments of surface permeability and UHI are crucial for urban planning and management of landuse zones, they have mostly involved time consuming and expensive field studies, and single sensor derived large scale aerial and satellite imageries. We demonstrated the advantage of fusing imageries from multiple sensors for landuse and landcover (LULC) change assessments as well as for assessing surface permeability and UHI emergence in Tirunelveli, Tamilnadu, India. Cartosat-2 and Landsat-7 ETM+ imageries from 2007 and 2017 were fused and classified using a Rotation Forest (RF), while surface permeability and temperature were quantified using Soil-Adjusted Vegetation Index (SAVI) and Land Surface Temperature (LST) index, respectively. Fused images exhibited higher classification accuracies than non-fused images, i.e. overall kappa coefficient values 0.83 and 0.75, respectively. We observed an overall increase of 20 km2 (45%) in the coverage of urban (dry, real estate plots and built-up) areas, while a decrease of 27 km2 (37%) for vegetated (cropland and forest) areas in Tirunelveli between 2007 and 2017. The SAVI values indicated an extensive decrease in surface permeability for Tirunelveli overall (0.4) and also for almost all LULC zones. The LST values exhibited an associated overall increase (1.30C) of surface temperature in Tirunelveli with the highest increase (2.40C) for urban built-up areas between 2007 and 2017. The SAVI-LST combined metric depicted the Southeastern built-up areas in Tirunelveli as a potential UHI hotspot, while a caution for the Western riparian zone for UHI emergence in 2017. Our results provide important metrics for surface permeability and UHI monitoring, and inform urban and zonal planning authorities about the advantages of satellite image fusion.

The purpose of this paper is to explore the effect of corporate social responsibility (CSR) on brand image in the apparel industry in Jordan, using the moderating variable of customer consciousness. The current research uses a quantitative, descriptive, cause-effect, and cross-sectional approach, and also it uses a convenience sampling method. Data was collected from 440 respondents. Results indicate that Jordanian Apparel organizations have medium to highly implementing of all items and constructs of CSR, brand image items, and consciousness items. Moreover, there is a strong relationship between CSR dimensions, a medium relationship be-tween each CSR dimension and brand image, a medium relationship between each CSR dimension and consciousness, a medium relationship between total CSR and brand image, a medium relationship between total CSR and consciousness, and the medium relationship between brand image and consciousness. Results of the first model show that total CSR affects the brand image. Where social responsibility has the highest positive effect, followed by ethical responsibility, then economic responsibility, however, environmental responsibility negatively affects the brand image. The second model shows consciousness moderates the effect of CSR on the brand image. The study recommends longitudinal research on the Jordanian Apparel industry, especially to test the effect of environmental responsibility on the brand image. Moreover, the re-search uses customers’ consciousness as a moderating variable, which improves the effect of CSR on brand image. The Apparel industry organizations in Jordan should revise their daily practices particularly environmental responsibility and/or increase their customers’ awareness of their practices. Finally, the current research contributes to existing studies by using consciousness as a moderating variable.

Neutron computed tomography (nCT) has been established at many major neutron sources worldwide, using high-end equipment requiring major investment and development. Many older and smaller reactors would be capable of doing nCT as well, but cannot afford the investment before feasibility is proven. We have developed a compact low-cost but high-quality detection system using a new cooled CMOS camera that can either be fully integrated into a sophisticated setup, or used with a rudimentary CT control and motion system to quickly evaluate feasibility of neutron CT at a given beam line facility. Exchanging the scintillation screen makes it feasible for X-rays as well, even for visible light (and transparent samples) using a matte screen. The control system uses a hack to combine motion control with existing imaging software so it can be used to test several dozen different cameras without writing specific drivers. Freeware software can do reconstruction and 3D imaging.

Brain tissue segmentation is an important component of clinical diagnosis of brain diseases by means of multi-modal magnetic resonance imaging (MR). Brain tissue segmentation is developed by many unsupervised methods in literature. The most commonly used unsupervised methods are: K-Means, Expectation Maximization and Fuzzy Clustering. Fuzzy clustering methods offer considerable benefits compared with the aforementioned methods as they are capable of handling brain images which are complex, largely uncertain and imprecise in nature. However, this approach suffers from the intrinsic noise and intensity inhomogeneity (IIH) in the data resulted from the acquisition process. To resolve these issues, we propose a fuzzy consensus clustering algorithm that defines a membership function resulted from a voting schema to cluster the pixels. In particular, we first pre-process the MRI data and employ several segmentation techniques based on traditional fuzzy sets and intuitionistic sets. Then, we adopted a voting schema to fuse the results of the applied clustering methods. Finally, to evaluate the proposed method, we used the well-known performance measures (boundary measure, overlap measure and volume measure) on two publicly available datasets (OASIS and IBSR18). The experimental results show the superior performance of the proposed method in comparison with the recent state of the arts.

A method for generating fluoroscopic (time-varying) volumetric images using patient-specific motion models derived from 4-dimensional cone-beam CT (4D-CBCT) images is developed. 4D-CBCT images acquired immediately prior to treatment have the potential to accurately represent patient anatomy and respiration during treatment. Fluoroscopic 3D image estimation is done in two steps: 1) deriving motion models and 2) optimization. To derive motion models, every phase in a 4D-CBCT set is registered to a reference phase chosen from the same set using deformable image registration (DIR). Principal components analysis (PCA) is used to reduce the dimensionality of the displacement vector fields (DVFs) resulting from DIR into a few vectors representing organ motion found in the DVFs. The PCA motion models are optimized iteratively by comparing a cone-beam CT (CBCT) projection to a simulated projection computed from both the motion model and a reference 4D-CBCT phase, resulting in a sequence of fluoroscopic 3D images. Patient datasets were used to evaluate the method by estimating the tumor location in the generated images compared to manually defined ground truth positions. Experimental results showed that the average tumor mean absolute error (MAE) along the superior-inferior (SI) direction and the 95th percentile in two patient datasets were (2.29 mm and 5.79 mm) for patient 1 and (1.89 mm and 4.82 mm) for patient 2. This study has demonstrated the feasibility of deriving 4D-CBCT-based PCA motion models that have the potential to account for the 3D non-rigid patient motion and localize tumors and other patient anatomical structures on the day of treatment.

Background: MR image classification in datasets collected from multiple sources is complicated by inconsistent and missing DICOM metadata. Therefore, we aimed to establish a method for the efficient automatic classification of MR brain sequences. Methods: Deep convolutional neural networks (DCNN) were trained as one-vs-all classifiers to differentiate between six classes, T1 weighted (w), contrast-enhanced T1w, T2w, T2w-FLAIR, ADC, and SWI. Each classifier yields a probability, allowing threshold-based and relative probability assignment while excluding images with low probability (label: unknown, open-set recognition problem). Data from three high-grade glioma (HGG) cohorts was assessed; C1 (320 patients, 20101 MRI images) was used for training, while C2 (197, 11333) and C3 (256, 3522) were for testing. Two raters manually checked images through an interactive labeling tool. Finally, MR-Class' added value was evaluated via radiomics models' performance for progression-free survival (PFS) prediction in C2, utilizing the concordance index (C-I). Results: Approximately 10% of annotation errors were observed in each cohort between the DICOM series descriptions and the derived labels. MR-Class accuracy was 96.7% [95%-Cl: 95.8, 97.3] for C2 and 94.4% [93.6, 96.1] for C3. 620 images were misclassified; Manual assessment of those frequently showed motion artifacts or alterations of anatomy by large tumors. Implementation of MR-Class increased on average the PFS model C-I by 14.6% compared to a model trained without MR-Class. Conclusions: We provide a DCNN-based method for sequence classification of brain MR images and demonstrate its usability in two independent HGG datasets.

We propose a novel unsupervised semantic segmentation method for fast and accurate flood area detection utilizing color images acquired from Unmanned Aerial Vehicles (UAVs). To the best of our knowledge, this is the first fully unsupervised method for flood area segmentation in color images captured by UAVs, without the need of pre-disaster images. The proposed framework addresses the problem of flood segmentation based on parameter-free calculated masks and unsupervised image analysis techniques. First, a fully unsupervised algorithm gradually excludes areas classified as non-flood utilizing calculated masks over each component of the LAB colorspace, as well an RGB vegetation index and the detected edges of the original image. Unsupervised image analysis techniques, such as distance transform, are then applied, producing a probability map for the location of flooded areas. Finally, flood detection is obtained by applying the hysteresis thresholding segmentation. The proposed method is tested and compared with variations, and other supervised methods in two public datasets, consisting of 953 color images in total, yielding high-performance results, with 87.4% and 80.9% overall accuracy and F1-Score, respectively. The results and computational efficiency of the proposed method show that it is suitable for on board data execution and decision-making during UAVs flight.

Endoscopic medical images can suffer from uneven illumination, low contrast, and lack of texture information due to the use of point directional light sources and the presence of narrow tissue structures, posing diagnostic difficulties for physicians. In this paper, a deep learning-based su-pervised illumination enhancement network is designed for low-light endoscopic images, aiming to improve both global illumination and local details. Initially, a global illumination enhancement module is formulated utilizing a higher-order curve function to improve global illumination. Sec-ondly, a local feature extraction module incorporating dual attention is designed to capture local detailed features. Considering the significance of color fidelity in biomedical scenarios, the designed loss function prioritizes introducing color loss to alleviate image color distortion. Compared with seven state-of-the-art enhancement algorithms on Endo4IE endoscopic datasets, experimental re-sults show that the proposed method can better enhance low-light endoscopic images and avoid image color distortion. It provides an efficient method to enhance images captured by endoscopes which can effectively assist clinical diagnosis and treatment.

The shortage of physicians in rural communities contributes to increased mortality rates among Medicare beneficiaries. This increase in mortality risk is commonly due to diseases such as heart disease and cancer, including melanoma and non-melanoma skin cancer (NMSC). Mohs micrographic surgery (MMS) is considered the gold-standard treatment for NMSC tumors, however, due to a shortage of dermatologists and Mohs surgeons in rural areas, access to MMS is limited. In these areas, image guided superficial radiation therapy (IGSRT) serves as a viable option for the treatment of NMSC lesions, with fewer recurrences and 99% cure rates, which are comparable to MMS cure rates. IGSRT is performed in dermatology clinics with support from a multidisciplinary team, including radiation therapists, medical physicists, radiation oncologists, and dermatologists. As IGSRT is able to be performed by general dermatologists, Medicare beneficiaries in rural communities will have an increase in access to treatment options and a decrease in delayed skin cancer treatment.

Fractures of the talar neck and body are associated with spine fractures and scoliosis deformity, which affect cosmetic appearance and cause difficulty in ambulation. The implant design for talus surgery is thriving as a functional alternative in case of severe talar destruction, focusing on segmentation and reconstruction of the talus’s shape. However, manual segmentation of the talus is time-consuming and subjective. In this study we exploited the automatic segmentation framework to efficiently train a deep learning-based model to accurately segment the talus based on computed tomography imaging. We developed three model configurations with nnU-Net and investigated their Dice similarity coefficients (DSC) and 95% Hausdorff distances (HD95) for talus segmentation on a CT image dataset. The three configurations performed well (DSC > 0.95, HD95 < 0.6). When tested on the same samples, one of the configurations was more efficient while ensuring higher accuracy. We propose to focus on talus anatomic variations with increasing age based on this framework and apply it to clinical trials at the next stage.

Convolutional neural network architectures have become increasingly complex, which has improved the performance slowly on well-known benchmark datasets in the recent years. In this research, we have analyzed the true need for such complexity. We have introduced G-Net light, a lightweight modified GoogleNet with improved filter count per layer to reduce feature overlaps and complexity. Additionally, by limiting the amount of pooling layers in the proposed architecture, we have exploited the skip connections to minimize the spatial information loss. The investigations on the proposed architecture are evaluated on three retinal vessel segmentation publicly available datasets. The proposed G-Net light outperforms other vessel segmentation architectures by reducing the number of trainable parameters..

In high-traffic harbor waters, marine radar frequently encounters signal interference stemming from various obstructive elements, thereby presenting formidable obstacles in the precise identification of ships. To achieve precise pixel-level ship identification in the complex environments, a customized neural network-based ship segmentation algorithm named MrisNet is proposed. MrisNet employs a lightweight and efficient FasterYOLO network to extract features from radar images at different levels, capturing fine-grained edge information and deep semantic features of ship pixels. To address the limitation of deep features in the backbone network lacking detailed shape and structured information, an adaptive attention mechanism is introduced after the FasterYOLO network to enhance crucial ship features. To fully utilize the multi-dimensional feature outputs, MrisNet incorporates a Transformer structure to reconstruct the PANet feature fusion network, allowing for the fusion of contextual information and capturing more essential ship information and semantic correlations. In the prediction stage, MrisNet optimizes the target position loss using the EIoU function, enabling the algorithm to adapt to ship position deviations and size variations, thereby improving segmentation accuracy and convergence speed. Experimental results demonstrate that MrisNet achieves high recall and precision rates of 94.8% and 95.2%, respectively, in ship instance segmentation, outperforming various YOLO and other single-stage algorithms. Moreover, MrisNet has a model parameter size of 13.8M and real-time computational cost of 23.5G, demonstrating notable advantages in terms of convolutional efficiency. In conclusion, MrisNet accurately segments ships with different spot features and under diverse environmental conditions in marine radar images. It exhibits outstanding performance, particularly in extreme scenarios and challenging interference conditions, showcasing robustness and applicability.

Deep learning is widely used in image segmentation, effectively identifying crops and weeds and contributing to the reduction of herbicide use. Traditional methods of applying pesticides over large areas are inefficient in dealing with weeds as needed, leading to massive waste of pesticides, high-cost production, and serious environmental pollution. This affects crop yield and quality. Although weed recognition using conventional deep learning methods has evolved over time, there are still challenges in weed extraction, detection, and segmentation. Accurate recognition and detection of weeds are essential prerequisites for implementing variable spraying. This paper proposes a semantic segmentation method based on UNet++ for complex environments where accurate identification of plants and weeds is challenging, targeting weeds in sugar beets, peas, and rice. An attention module is integrated into the upsampling process of UNet++, and UNet++ is used as a backbone network to effectively integrate multi-scale information, efficiently suppressing external noise interference. The UNet++ model with an integrated attention mechanism module achieves higher IOU than the general UNet++ model used in medical image analysis. This method effectively detects crops and weeds in complex backgrounds, providing reference material for the accurate application of robotic herbicides.

Vision loss can be avoided if diabetic retinopathy (DR) is diagnosed and treated promptly. Following are the main 5 DR stages: none, moderate, mild, proliferate, and severe. In this study, a deep learning (DL) model is presented that diagnoses all 5 stages of DR with more accuracy than previous methods. The suggested method presents two scenarios: case 1 with image enhancement using contrast limited adaptive histogram equalization (CLAHE) filtering algorithm in conjunction with an Enhanced Super-resolution generative adversarial network (ESRGAN), and case 2 without image enhancement; augmentation techniques are then performed to generate a balanced dataset utilizing the same parameters for both cases. Using Inception-V3 applied to the Asia Pacific Tele-Ophthalmology Society (APTOS) datasets, the developed model achieved an accuracy of 98.7% for case 1 and 80.87% for case 2, which is greater than existing methods for detecting the five stages of DR. It was demonstrated that using CLAHE and ESRGAN improves a model's performance and learning ability.

The automatic diagnosis of cardiovascular diseases has received much attention in the deep learning field. In this context, the segmentation of the left ventricle endocardium constitutes a major task in diagnosing heart conditions such as health failure and hypertrophic cardiomyopathy. The objective of this paper is to propose a "deep convolution network" for segmenting the internal cavity of the left ventricle (endocardium) using MRI images. In particular, we design an improved UNET model which handles additional inception modules for efficiently segmenting the internal cavity of the left ventricle. Our approach has been validated on the Sunnybrook Cardiac Data (SCD) dataset and has showed promising results in terms of precision. More specifically, the improved UNET largely outperforms the baseline UNET model and many existing state-of-the-art methods.

Segmentation of brain tumor images is a major research topic in medical imaging to have a refined detection and understanding of abnormal masses in the brain. This paper proposes a new segmentation method, consisting of three main steps, to detect brain lesions using magnetic resonance imaging (MRI). In the first step, the parts of the image delineating the skull bone are removed to exclude insignificant data. In the second step, which is the main contribution of this study, the particle swarm optimization (PSO) technique is applied to detect the block that contains the brain lesions. The fitness function, used to determine the best block among all candidate blocks, is based on a two-way fixed-effects analysis of variance (ANOVA). In the last step of the algorithm, the K-means segmentation method is used in the lesion block to classify it as tumor or not. A thorough evaluation of the proposed algorithm is performed using the MRI database provided by the Kouba imaging center in Algiers, Algeria. Estimates of the selected fitness function are first compared to those based on the sum-of-absolute-differences (SAD) dissimilarity criterion and demonstrate the efficiency and robustness of the ANOVA. The performance of the optimized brain tumor segmentation algorithm is then compared to the results of several state-of-the-art techniques, including fuzzy C-means, K-means, Otsu thresholding, local thresholding, and watershed segmentation. The results obtained using Dice coefficient, Jaccard distance, correlation coefficient, and root mean square error (RMSE) measurements demonstrate the superiority of the proposed optimized segmentation algorithm over equivalent techniques.

Target detection and segmentation in synthetic aperture radar (SAR) images are vital steps for many remote sensing applications. In the era of data-driven deep learning, this task is extremely challenging due to the limited labeled data. Few-shot Learning has the ability to learn quickly from few samples with supervised information. Inspired by this, a few-shot learning framework named MSG-FN is proposed to solve the segmentation of ship targets in heterologous SAR images with few annotated samples. The proposed MSG-FN adopts a dual-branch network consisting of a support branch and a query branch. The support branch is used to extract features with an encoder, and the query branch uses a U-shaped encoder-decoder structure to segment the target in the query image. The encoder of each branch is composed of well-designed residual blocks combined with filter response normalization to capture robust and domain-independent features. A multi-scale similarity guidance module is proposed to improve the scale adaptability of detection by applying hand-on-hand guidance of support features to query features of various scales. In addition, a SAR dataset named SARShip-4i is built to evaluate the proposed MSG-FN and the experimental results show that the proposed method achieves superior segmentation results compared with the state-of-the-arts.

In this paper we propose a module that uses features learned by a deep convolutional neural network to infer areas of corrosion and segment pixels to corrosion areas of inspection interest. Our segmentation module is based on eigen tree decomposition and information based decision criteria. To interrogate performance we use several state-of-the-art deep learning architectures and compare to our approach. The results indicate that our method produces better results in terms of accuracy and precision, whilst maintaining good (f-score) significance over the entire dataset.

Background/Objectives: The aim of the project is a longitudinal assessment of body image and mental health in scoliosis females pre-, postoperatively and in a follow-up, and implementation (one group-CBT scoliosis sample, CBTSS) or not (second group-control scoliosis sample, CSS) of CBT interventions. A healthy female sample (HFS) was also selected for comparative purposes. Methods. 36 in total AIS patients participated in the 1st and 2nd study phases, whereas 23 were eligible in the follow-up. Regarding HFS, 18 participants were included in the study. The CBT intervention took place pre- and postoperatively, during the patients' stay in hospital. Participants completed the Spinal Appearance Questionnaire (SAQ), Body Esteem Scale (BES) and Strengths and Difficulties Questionnaire-25 (SDQ-25). Body image was also assessed using a virtual reality-based application “Avatar Scoliosis 3D”. Results: The difference between the desired and objective, actual body shape is significant preoperatively both in the CBTSS and CSS at p

In recent years, due to the advancement of machine learning, object detection has become a mainstream task in the computer vision domain. The first phase of object detection is to find the regions where objects can exist. With the improvement of deep learning, traditional approaches such as sliding windows and manual feature selection techniques have been replaced with deep learning techniques. However, object detection algorithms face a problem when performing in low light, challenging weather, and crowded scenes like any other task. Such an environment is termed a challenging environment. This paper exploits pixel-level information to improve detection under challenging situations. To this end, we exploit the recently proposed hybrid task cascade network. This network works collaboratively with detection and segmentation heads at different cascade levels. We evaluate the proposed methods on three complex datasets of ExDark, CURE-TSD, and RESIDE and achieve an mAP of 0.71, 0.52, and 0.43, respectively. Our experimental results assert the efficacy of the proposed approach.

This paper presents a novel approach for semantic segmentation of building roof in dense urban environment with Deep Convolution Neural Network (DCNN) using imagery acquired by a Chinese Very High Resolution (VHR) satellite mission, i.e. GaoFen-2 (GF-2). To provide an operational end-to-end work flow for accurate build roof mapping with feature extraction as well as image segmentation, a fully convolutional DCNN with both convolutional and deconvolutional layers is designed to perform the VHR image analysis for labeling pixels. Since the diverse urban patterns and building styles in large areas, sample image data sets of building roof and non-building roof are collected over different metropolitan regions in China. We selected typical cities with dense urban environment in each metropolitan region as study areas for collecting training and test samples. High performance cluster with GPU-mounted workstations is employed to perform the model training and optimization. With the building roof samples collected over different cities, the predictive model with multiple NN layers is developed for building roof labeling. The validation of the building roof map shows that the overall accuracy(OA) and the mean Intersection Over Union( mIOU) of DCNN based segmentation are 94.67%, 0.85 respectively, while CRF-refined segmentation achieved OA of 94.69% and mIOU of 0.83. The results suggest that the proposed approach is a promising solution for building roof mapping with VHR images over large areas across different urban and building patterns. With the operational acquisition of GF2 VHR imagery, it is expected to develop an automated pipeline for operational built-up area monitoring and timely update of building roof map over large areas.

The semantic segmentation of high-resolution remote sensing images (HR-RSI) is crucial for a wide range of applications, such as precision agriculture, urban planning, natural resource assessment, and ecological monitoring. However, accurately classifying pixels in HR-RSI faces challenges due to densely distributed small objects and scale variations. Existing techniques, including Convolutional Neural Networks (CNNs) and other methods for hierarchical feature extraction and fusion of remote sensing image, often do not achieve the desired accuracy. In this paper, we propose a novel approach called the Hierarchical Rich-scale Fusion Network (HRFNet) to address these challenges. HRFNet utilizes advanced information rating and image partition techniques to extract rich-scale features within image layers. This allows for the adaptive exploration of both local and global contextual information. Moreover, we introduce a structured intra-layer to inter-layer feature aggregation module, which enables the adaptive extraction of fine-grained details and high-level semantic information from multi-layer feature maps in a highly flexible manner. Extensive experimentation has been conducted to validate the effectiveness of our proposed method. Our results demonstrate that HRFNet outperforms existing techniques, achieving state-of-the-art (SOTA) results on benchmark datasets, specifically the ISPRS Potsdam and Vaihingen datasets.

Semantic image segmentation has recently witnessed considerable progress by training deep convolutional neural networks (CNNs). The core issue of this technique is the limited capacity of CNNs to depict visual objects. Existing approaches tend to utilize approximate inference in a discrete domain or additional aides and do not have a global optimum guarantee. We propose the use of the multi-label manifold ranking (MR) method in solving the linear objective energy function in a continuous domain to delineate visual objects and solve these problems. We present a novel embedded single stream optimization method based on the manifold ranking (MR) model to avoid approximations without sacrificing expressive power. In addition, we propose a novel network, which we refer to as dual multi-scale manifold ranking (\textbf{DMSMR}) network, that combines the dilated, multi-scale strategies with the single stream MR optimization method in the deep learning architecture to further improve the performance. Experiments on high resolution images, including close-range and remote sensing datasets, demonstrate that the proposed approach can achieve competitive accuracy without additional aides in an end-to-end manner.

The objectives of this paper are to investigate the tradeoffs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image, modern high-resolution satellite image data sets (Maxar WorldView data) and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100-200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.

This paper considered the issue of agricultural fields boundary recognition in satellite images. A novel algorithm based on the aggregated history of vegetation index data obtained via open satellite data, Sentinel-2, was proposed. The proposed algorithm included several basic steps, namely the detection of parcel regions on aggregated index data; the calculation of aggregated edge maps; the segmentation of parcel regions using the edges obtained; the computation of connected components and their contour extraction. In this paper, we showed that the use of aggregated vegetation index data and boundary maps allow for much more accurate agricultural field segmentation compared to the instant vegetation index approach. The quality of segmentation within regions of Russia and the Ukraine was estimated. The dataset that was used and Python implementation of the proposed algorithm were provided.

(1) Background: OCT imaging has been used to assess enamel demineralization in dental research but is not yet developed enough to qualify as a diagnostic technique in clinics. The current capabilities of most commercial acquisition software allow for visual and qualitative assessment. There is a need for a fast and verified batch-processing algorithm for segmenting and analyzing the de-mineralized enamel. This study suggests a GUI MATLAB algorithm for processing and quantitative analysis of the demineralized enamel. (2) Methods: A group of artificially demineralized human enamels was in vitro scanned under the OCT, and ROI frames were extracted. By using a selected intensity threshold colormap, inter- (Ie) and intra- (Ia) prismatic demineralization can be segmented. A set of quantitative measurements for average demineralized depth, average line profile, and integrated reflectivity can be obtained for an accurate assessment. Real and simulated OCT frames were used for algorithm verification. (3) Results: A strong correlation between automated and known Excel measurements for the average demineralization depth was found (R² > 0.97). (4) Conclusions: OCT image segmentation and quantification of the enamel demoralization zones are possible. The algorithm can assess the future development of a real-time assessment of dental diagnostics using an oral probe OCT.

Degradation of environment quality is currently the prime cause of the recent occurrence of natural disasters; it also contributes in the increase of the area that is prone to natural disasters. This research is aimed to map the potential of areas around Pesanggrahan river in DKI Jakarta by segmenting the Digital Elevation Model derived from LIDAR data. The objective of this segmentation is to find the watershed lines of the DEM image. Data processing in this research is using LIDAR data which take the ground surface data, which is overlaid with Jakarta river map and subsequently, the data is then segmented the image. The expected result of the research is the flood potential area information, especially along the Pesanggrahan river in South Jakarta.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions.

The Coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared as a global pandemic. Due to its infection rate and severity, it has emerged as one of the major global threats of the current generation. To support the current combat against the disease, this research aims to propose a Machine Learning based pipeline to detect the COVID-19 infection using the lung Computed Tomography scan images (CTI). This implemented pipeline consists of a number of sub-procedures ranging from segmenting the COVID-19 infection to classifying the segmented regions. The initial part of the pipeline implements the segmentation of the COVID-19 affected CTI using Social-Group-Optimization and Kapur’s Entropy thresholding, followed by k-means clustering and morphology-based segmentation. The next part of the pipeline implements feature extraction, selection and fusion to classify the infection. PCA based serial fusion technique is used in fusing the features and the fused feature vector is then employed to train, test and validate four different classifiers namely Random Forest, k-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, and Decision Tree. Experimental results using benchmark datasets show a high accuracy (> 91%) for the morphology-based segmentation task and for the classification task the KNN offers the highest accuracy among the compared classifiers (> 87%). However, this should be noted that this method still awaits clinical validation, and therefore should not be used to clinically diagnose the ongoing COVID-19 infection.

The move from paper to online is not only necessary for remote working, it is also significantly more sustainable. This trend has seen a rising need for high-quality digitization of content from pages and whiteboards to sharable online material. But capturing this information is not always easy, nor are the results always satisfactory. Available scanning apps vary in their usability and do not always produce clean results, retaining surface imperfections from the page or whiteboard in their output images. CleanPage, a novel smartphone-based document and whiteboard scanning system, is presented. CleanPage requires one button-tap to capture, identify, crop and clean an image of a page or whiteboard. Unlike equivalent systems, no user intervention is required during processing and the result is a high-contrast, low-noise image with a clean homogenous background. Results are presented for a selection of scenarios showing the versatility of the design. CleanPage is compared with two market leader scanning apps using two testing approaches: real paper scans and ground-truth comparisons. These comparisons are achieved by a new testing methodology that allows scans to be compared to unscanned counterparts, by using synthesized images. Real paper scans are tested using image quality measures. An evaluation of standard image quality assessments is included in this work and a novel quality measure for scanned images is proposed and validated. The user experience for each scanning app is assessed, showing CleanPage to be fast and easier to use.

Particle Image Velocimetry (PIV) is a widely used experimental technique for measuring flow. In recent years, open-source PIV software has become more popular as it offers researchers and practitioners enhanced computational capabilities. Software development for graphical processing unit (GPU) architectures requires careful algorithm design and data structure selection for optimal performance. PIV software, optimized for central processing units (CPUs), offer an alternative to specialized GPU software. In the present work, an improved algorithm for the OpenPIV-Python software is presented and implemented under a traditional CPU framework. The Python language was selected due to its versatility and widespread adoption. The algorithm was also tested on a supercomputing cluster, a workstation, and Google Colaboratory during the development phase. Using a known velocity field, the algorithm precisely captured the time-average flow, monetary velocity fields, and vortices.

CT scans are currently the most common imaging modality used for suspected stroke patients due to their short acquisition time and wide availability. However, MRI offers superior tissue contrast and image quality. In this study, eight deep learning models are developed, trained, and tested using a dataset of 181 CT/MR pairs from stroke patients. The resultant synthetic MRIs generated by these models are compared through a variety of qualitative and quantitative methods. The synthetic MRIs generated by a 3D UNet model consistently demonstrated superior performance across all methods of evaluation. Overall, the generation of synthetic MRIs from CT scans using the methods described in this paper produces realistic MRIs that can guide the registration of CT scans to MRI atlases. The synthetic MRIs enable the segmentation of white matter, gray matter, and cerebrospinal fluid using algorithms designed for MRIs, exhibiting a high degree of similarity to true MRIs.

An algorithm for the treatment of images affected by both blurring and salt&pepper noise is proposed with a cost only proportional to the number of pixels. The methodology uses a discretization scheme for the Laplace operator multiplied by a suitable nonlinear term depending on the gradient. Even if this approach resembles a diffusion type algorithm, only one step of the procedure is applied, leading to significant time savings. The procedure is successfully tested on some standard black&white natural images.

Abstract: Imaging devices of less than 300,000 pixels are mostly used for sewage conduit exploration due to the petty nature of the survey industry in Korea. P articular ly , devices of less than 100,000 pixels are still widely used, and the environment for image processing is very bitter . Since the sewage conduit image s covered in this study ha ve a very low resolution (240 × 320 = 76,800 pixels), it is very difficult to detect cracks. Because most of the resolution of the sewe r conduit images are very low in Korea, this problem of low resolution was selected as the subject of study. Cracks were detected through a total of six steps of improving the crack in Step 2, finding the optimal threshold value in Step 3, and applying an algorithm to detect cracks in Step 5. Cracks were effectively detected by the optimal parameters in Steps 2 and 3 and the user algorithm in Step 5. Desp ite the very low resolution, the cracked image s showed 96.4% accuracy of detection, and the non cracked image s showed 94.5% accuracy . Moreover, the analysis was excellent in quality , also . It is believed that the findings of this study can be effectively u sed for crack detection with low resolution images.

It is one of very important and basic problem in compute vision field that recovering depth information of objects from two-dimensional images. In view of the shortcomings of existing methods of depth estimation, a novel approach based on SIFT (the Scale Invariant Feature Transform) is presented in this paper. The approach can estimate the depths of objects in two images which are captured by an un-calibrated ordinary monocular camera. In this approach, above all, the first image is captured. All of the camera parameters remain unchanged, and the second image is acquired after moving the camera a distance d along the optical axis. Then image segmentation and SIFT feature extraction are implemented on the two images separately, and objects in the images are matched. Lastly, an object depth can be computed by the lengths of a pair of straight line segments. In order to ensure that the best appropriate a pair of straight line segments are chose and reduce the computation, the theory of convex hull and the knowledge of triangle similarity are employed. The experimental results show our approach is effective and practical.

The article describes a classification solution for amber stones. The problem of classifying amber is known for a long time among jewelers and artisans of amber art. Existing solutions can classify amber pieces according to color, but a need to classify by shape and texture is not satisfied up to now. The proposed solution is capable of classifying the gemstones according to a shape. Amber can be considered as a specific object since the form is difficult to define unambiguously. Data for amber experiments was gathered from amber art craftsmen. In the proposed solution amber form can be classified into 10 different classes (7 classes chosen during the experiment).

Speckle noise is one of the most difficult noises to remove especially in medical applications. It is a nuisance in ultrasound imaging systems which is used in about half of all medical screening systems. Thus, noise removal is an important step in these systems, thereby creating reliable, automated, and potentially low cost systems. Herein, a generalized approach MFNR (Multi-Frame Noise Removal) is used, which is a complete Noise Removal system using KDE (Kernal Density Estimation). Any given type of noise can be removed if its probability density function (PDF) is known. Herein, we extracted the PDF parameters using KDE. Noise removal and detail preservation are not contrary to each other as the case in single-frame noise removal methods. Our results showed practically complete noise removal using MFNR algorithm compared to standard noise removal tools. The Peak Signal to Noise Ratio (PSNR) performance was used as a comparison metric. This paper is an extension to our previous paper where MFNR Algorithm was showed as a general purpose complete noise removal tool for all types of noises

Document deskewing is a fundamental problem in document image processing. While existing methods have limitations, such as Hough Line Transformation that can deskew images upside down, and Deep Learning models that require huge amounts of human labour and computational resources and still fail to deskew while taking care of orientation, OCR-based methods also struggle to read text when it is tilted. In this paper, we propose a novel, simple, cost-effective deep learning method for fixing the skew and orientation of documents. Our approach reduces the search space for the machine learning model to predict whether an image is upside down or not, avoiding the huge search space of predicting an angle between 0 and 360. We finetuned a MobileNetV2 model, which was pre-trained on imagenet, using only 200 images and achieve good results. This method is useful for automation-based tasks, such as data extraction using OCR technology, and can greatly reduce manual labour.

Recent advancements in computer vision, especially deep learning models, have shown considerable promise in tasks related to plant image object detection. However, the efficiency of these deep learning models heavily relies on input image quality, with low-resolution images significantly hindering model performance. Therefore, reconstructing high-quality images through specific techniques will help extract features from plant images, thus improve model performance. In this study, we explored the value of super-resolution technology for improving object detection model performance on plant images. Firstly, we built a comprehensive dataset comprising 1030 high-resolution plant images, named the PlantSR dataset. Subsequently, we developed a super-resolution model using the PlantSR dataset and benchmarked it against several state-or-the-art models designed for general image super-resolution tasks. Our proposed model demonstrated superior performance on the PlantSR dataset, indicating its efficacy in enhancing the super-resolution of plant images. Furthermore, we explored the effect of super-resolution on two specific object detection tasks: apple counting and soybean seed counting. By incorporating super-resolution as a pre-processing step, we observed a significant reduction in mean absolute error. Specifically, on the YOLOv7 model employed for apple counting, the mean absolute error decreased from 13.085 to 5.71. Similarly, on the P2PNet-Soy model utilized for soybean seed counting, the mean absolute error decreased from 19.159 to 15.085. These findings underscore the substantial potential of super-resolution technology in improving the performance of object detection models for accurately detecting and counting specific plants from images. The source codes and associated datasets are available at https://github.com/SkyCol/PlantSR.

In the age of social media, images come from unreliable sources that may change their content to fit a narrative. Automated detection of forged images is a complex task, especially considering recent technological advances in image manipulation software. However, in the existing literature, it is possible to identify two general approaches adopted by detection methods, active and passive. Active techniques preemptively act on an image by inserting structures before any manipulation is made that can verify its authenticity. In contrast, passive methods analyze the content of an image in search of traces of manipulation. In this way, this research proposes a novel approach to image manipulation detection, combining two passive methods through neural networks, creating a generalist approach capable of detecting with greater accuracy than the methods that compose it. Furthermore, this work used a combination of four datasets available in the literature for training and evaluation. After training, the merged approach obtained an accuracy of 89.59% in the set of validation images, significantly higher than the model trained with only unaltered images, which obtained 78.64%, and the two other models trained using images with a feature selection method applied to enhance inconsistencies that obtained 68.02% for Error-Level Analysis images and 50.70% for the method using Discrete Wavelet Transform. In addition to the performance improvement, the proposed approach’s accuracy variation was lower than the other models.

During the few years, various algorithms have been developed to extract features from high-resolution satellite imagery. For the classification of these extracted features, several complex algorithms have been developed. But these algorithms do not possess critical refining stages of processing the data at the preliminary phase. Various satellite sensors have been launched such as LISS3, IKONOS, QUICKBIRD, and WORLDVIEW etc. Before classification and extraction of semantic data, imagery of the high resolution must be refined. The whole refinement process involves several steps of interaction with the data. These steps are pre-processing algorithms that are presented in this paper. Pre-processing steps involves Geometric correction, radiometric correction, Noise removal, Image enhancement etc. Due to these pre-processing algorithms, the accuracy of the data is increased. Various applications of these pre-processing of the data are in meteorology, hydrology, soil science, forest, physical planning etc. This paper also provides a brief description of the local maximum likelihood method, fuzzy method, stretch method and pre-processing methods, which are used before classifying and extracting features from the image.

Industrial nameplates serve as a means of conveying critical information and parameters. In this work, we propose a novel approach for rectifying industrial nameplate pictures utilizing a probabilistic Hough transform. Our method effectively corrects for distortions and clipping, and features a collection of challenging nameplate pictures for analysis. To determine the corners of the nameplate, we employ a progressive probability Hough transform, which not only enhances detection accuracy but also possesses the ability to handle complex industrial scenarios. The results of our approach are clear and readable nameplate text, as demonstrated through experiments that show improved accuracy in model identification compared to other methods.

Video lectures are becoming more popular and in demand as online classroom teaching is becoming more prevalent. Massive Open Online Courses (MOOCs), such as NPTEL, have been creating high-quality educational content that is freely accessible to students online. A large number of colleges across the country are now using NPTEL videos in their classrooms. So more video lectures are being recorded, maintained, and uploaded. These videos generally contain information about that video before the lecture begins. We generally observe that these educational videos have metadata containing five to six attributes: Institute Name, Publisher Name, Department Name, Professor Name, Subject Name, and Topic Name. It would be easy to maintain these videos if we could organize them according to their categories. The indexing of these videos based on this information is beneficial for students all around the world to efficiently utilise these videos. In this project, we are trying to get the metadata information mentioned above from the video lectures.

Neural networks were treated as black boxes for a long time. Previous works have unearthed what aspects of an image were important for convolutional layers at different positions in the network. This was done using deconvolutional networks. In this paper, we examine how well a convolutional neural network performs when those convolutional layers which are relatively unimportant for a particular image (i.e., the image does not produce one of the strongest activations) are skipped in the training, validating, and testing process.

This paper presented a feature vector using a different statistical texture analysis of brain tumor from MRI image. The statistical feature texture is computed using GLCM (Gray Level Co-occurrence Matrices) of Brain Nodule structure. For this paper, the brain nodule segmented using strips method to implemented marker watershed image segmentation based on PSO (Particle Swarm Optimization) and Fuzzy C-means clustering (FCM). Furthermore, the four angles 0^o, 45^o, 90^o and 135^o are calculated the segmented brain image in GLCM. The four angular directions are calculated using texture features are correlation, energy, contrast and homogeneity. The texture analysis is performed a different types of images using past years. So the algorithm proposed statistical texture features are calculated for iterative image segmentation. These results show that MRI image can be implemented in a system of brain cancer detection.

During the high-speed flight of a vehicle in the atmosphere, surface friction with the air generates aerodynamic heating. The aerodynamic heating phenomenon can create extremely high temperatures near the surface. These high temperatures impact material properties and the structure of the aircraft, so thermal deformation measurement is essential in aerospace engineering. This paper revisits high-temperature deformation measurement using the digital image correlation (DIC) technique under high-intensity blackbody radiation with a precise speckle pattern fabrication and a heat haze reduction method. The effect of speckle pattern on the DIC measurement has been thoroughly studied at room temperature, but high-temperature measurement studies have not reported such effects so far. We found that the commonly used methods to reduce the heat haze effect could produce incorrect results. Hence, we propose a new method to mitigate heat haze effects. An infrared radiation heater was employed to make an experimental setup that could heat a specimen up to 950 ℃. First, we mitigated image saturation using a short-wavelength bandpass filter with blue light illumination, a standard procedure for high-temperature DIC deformation measurement. Second, we studied how to determine the proper size of the speckle pattern under a high-temperature environment. Third, we devised a reduction method for the heat haze effect. As proof of the effectiveness of our developed experimental method, we successfully measured the deformation of stainless steel 304 specimens from 25 ℃ to 800 ℃. The results confirmed that this method can be applied to the research and development of thermal protection systems in the aerospace field.

Artistic image completion is fundamental for the preservation and restoration of invaluable art paintings and it has experienced significant progress through the implementation of deep learning methodologies. Despite these advancements, challenges persist, even with sophisticated approaches like Generative Adversarial Networks (GANs), particularly in achieving optimal results for high-resolution paintings. Small-scale texture synthesis and the inference of missing information from distant contexts present persistent issues, leading to distortions in lines and unnatural colors, especially in art paintings with complicated structures and textures. Concurrently, patch-based image synthesis has evolved by incorporating global optimization on the image pyramid to enhance structural coherence and details. However, methods relying on gradient-based synthesis encounter obstacles related to directionality, inconsistency, and the heavy computational burdens associated with solving the Poisson equation in non-integrable gradient fields. This paper introduces a groundbreaking approach, integrating Weighted Similarity-Confidence Laplacian Synthesis, to comprehensively address these challenges and advance the field of artistic image completion. This proposal addresses challenges not only in high-resolution artistic image completion but also makes a significant contribution to the broader field of patch-based synthesis by utilizing the Laplacian pyramid for enhanced edge-aware correspondence search. Experimental result confirms the effectiveness of our approach, offering promising outcomes for the preservation and restoration of art paintings with complicated details and irregular missing regions.

A topic of growing interest in urban remote sensing is the automated extraction of geometrical building information for 3D city modeling. Roof geometry information is useful for applications such as urban planning, solar potential estimation and telecommunication installation planning, and wind flow simulations for pollutant diffusion analysis. Recent research has proven that the advance in remote sensing technologies and deep learning methods offer the prospects of deriving the roof structure information accurately and efficiently. In this study, we propose a Vectorized Roof Extractor- method based on Fully Convolutional Networks (FCNs) and advanced polygonization method to extract roof structure from aerial imagery and a normalized Digital Surface Models (nDSM) in a regularized vector format. The roof structure consists of building outlines, external edges of the building roof, inner rooflines, internal intersections of the main roof planes. The methodology is comprised of segmentation, vectorization and post-processing for outer rooflines, external edges of the building roof, and inner rooflines, and internal intersections of the main roof planes. For the comparison, we adapt the Frame field Learning (FFL) method originally designed to extract building polygons [1]. Our experiments are conducted on a custom data set derived for the city of Enschede, The Netherlands, using aerial imagery, nDSM and manually digitized training polygons. The results show that the proposed Vectorized Roof Extractor outperformed adapted FFL on PoLiS distance with values of 3.5 m and 1.2 m for outlines and inner rooflines, respectively. Furthermore, the model surpassed the adapted FFL on PoLiS-thresholded F-score for outlines and inner rooflines, with 0.31 and 0.57, respectively. The Vectorized Roof Extractor produced adequate visual results, with straighter walls and fewer missed inner roofline detections. It can predict buildings with common walls thanks to skeleton graph computation. To summarize, the proposed method is suitable for urban applications and has the potential to be improved further.

This paper presents the latest developments in microCT, both globally and locally, for supporting the additive manufacturing industry. There are a number of recently developed capabilities which are especially relevant to the non-destructive quality inspection of additive manufactured parts; and also for advanced process optimization. These new capabilities are all locally available but not yet utilized to their full potential, most likely due to a lack of knowledge of these capabilities. The aim of this paper is therefore to fill this gap and provide an overview of these latest capabilities, showcasing numerous local examples.

With an increased interest in applications that require a clean background image, such as video surveillance, object tracking, street view imaging and location-based services on web-based maps, multiple algorithms have been developed to reconstruct a background image from cluttered scenes. Traditionally, statistical measures and existing image quality techniques have been applied for evaluating the quality of the reconstructed background images. Though these quality assessment methods have been widely used in the past, their performance in evaluating the perceived quality of the reconstructed background image has not been verified. In this work, we discuss the shortcomings in existing metrics and propose a full reference Reconstructed Background image Quality Index (RBQI) that combines color and structural information at multiple scales using a probability summation model to predict the perceived quality in the reconstructed background image given a reference image. To compare the performance of the proposed quality index with existing image quality assessment measures, we construct two different datasets consisting of reconstructed background images and corresponding subjective scores. The quality assessment measures are evaluated by correlating their objective scores with human subjective ratings. The correlation results show that the proposed RBQI outperforms all the existing approaches. Additionally, the constructed datasets and the corresponding subjective scores provide a benchmark to evaluate the performance of future metrics that are developed to evaluate the perceived quality of reconstructed background images.

Hyperspectral (HS) imaging plays a pivotal role in various fields, including medical diagnostics, where precise human vein detection is crucial. Hyperspectral image data are very large and can cause computational complexities. Dimensionality reduction techniques are often employed to streamline HS image data processing. This paper investigates the effectiveness of three dimensionality reduction techniques, namely: Principal Component Analysis (PCA), Folded PCA (FPCA), and Ward’s Linkage Strategy using Mutual Information (WaLuMI) for vein detection using HS images. A HS image dataset, encompassing left and right-hand images captured from 100 subjects with varying skin tones was created and annotated using anatomical data to represent vein and non-vein areas within the images. To generate experimental results, the HS image dataset was divided into train and test datasets. Optimum performing parameters for each of the dimensionality reduction techniques in conjunction with The Support Vector Machine binary classification were determined using the Training dataset. The performance of the three dimensionality reduction based vein detection methods was then assessed and compared using the test image dataset. Results show that the FPCA-based method outperforms the other two methods in terms of accuracy. For visualization purposes, the classification prediction image for each technique is post-processed using morphological operators, and results show the significant potential of HS imaging in vein detection.

Fatigue fractures in materials are the main cause of approximately 80% of all material failures, and it is believed that such failures can be predicted and mathematically calculated in a reliable manner. It is possible to establish prediction modalities in cases of fatigue fracture, according to three fundamental variables in fatigue, such as volume, number of fracture cycles, as well as applied stress, with the integration of Weibull constants (length characteristic). This investigation was carried out mechanical fatigue tests on specimens smaller than 4 mm2 in section of different industrial materials for their subsequent analysis through precision computed tomography in search of microfractures. The measurement of these microfractures, along with their metrics and classifications, was recorded. A convolutional neural network trained with deep learning was used to achieve the detection of microfractures in image processing. The detection of microfractures in images with 480x854 or 960x960 pixels is the primary objective of this network, and its accuracy is above 95%. Images that have microfractures and those that do not are classified by the network. Subsequently, by means of image processing, the microfracture is isolated. Finally, the images that do contain this feature are interpreted by image processing to obtain their area, perimeter, characteristic length, circularity, orientation, and type microfracture metrics. All values will be obtained in pixels and converted to metric units (μm) through a conversion factor based on image resolution.

The development of unmanned satellite space technology is increasingly willing, the emergence of medium resolution satellites with sensitivity and spectral variants such as Landsat is very effective in observing environmental changes, while the purpose of this study is to monitor the development of built-in land using image transformation techniques, estimating built-in land changes. The research method uses the NDVI image transformation technique, NDBI and Built Up Index, with Landsat satellite image data obtained from USGS. Accuracy sampling is done by purposive sampling with confusion matrix accuracy test technique. The research results were found. developed land for the period 2004 - 2010 with a percentage of 19.25%, for stages 2010 - 2018 with a percentage of 30.25%. The land development was built based on the area of ​​the highest sub-district in the Kubung area in the early period with a percentage of 7.20% then in the second period with a percentage of 32.23%. The quality of the accuracy of the results of image analysis using confusion matrix technique with an image accuracy level in a field sample of 185 with an image accuracy of 86.04%.

In this paper, a technique of image watermarking using multiple images as watermarks is presented. The technique is based on transform domain functions including discrete wavelet transform (DWT), discrete cosine transform (DCT) and singular value decomposition (SVD) with an image as the host signal i.e. the watermarks will be used as proofs of the authenticity of the host image. The technique is executed by performing multilevel DWT followed by applying DCT and SVD to both the host and watermark. Multiple watermarks are used for the insurance of better security level. The scheme is immune to common image processing operations & some attacks and exhibits PSNR of 108.3781dB, normalized cross correlation (NCC) over 0.99 and normalized correlation (NC) over 0.99.

The aim of the research was getting to know the risk of dependency on physical exercising in individual sportspeople and the relationship with body dissatisfaction and motivation. 225 triathletes, swimmers, cyclists and athletes- with ages going from 18 to 63 years old took part in the research, of which 145 were men (M = 35.57 ±10.46 years) and 80 women (M = 32.83 ±10.31 years). The EDS-R was used to study the dependency on exercising, BSQ to study body dissatisfaction, BREQ-3 to know the motivation of participants and BIAQ to analyse conducts of avoidance to body image. The obtained results show that 8.5% of the subjects had risk of dependency on exercising and that 18.2% tend to have corporal dissatisfaction, without meaningful differences in the kind of sport they practiced. However, there were important differences concerning the dependency on physical exercise (15% vs 4.8%) and body dissatisfaction (31.1% vs 11%) in relation to sex, being the higher percentage referring to women. The introjected regulation and the conduct of food restriction were the predictor variables of the dependency on exercising and corporal dissatisfaction.

Much has been learned about the interaction between myosin and actin through biochemistry, in vitro motility assays and cryo-electron microscopy of F-actin decorated with myosin heads. Comparatively less is known about actin-myosin interactions within the filament lattice of muscle, where myosin heads function as independent force generators and thus most measurements report an average signal from multiple biochemical and mechanical states. All of the 3-D imaging by electron microscopy that has revealed the interplay of the regular array of actin subunits and myosin heads within the filament lattice has been accomplished using the flight muscle of the large waterbug Lethocerus sp. Lethocerus flight muscle possesses a particularly favorable filament arrangement that enables all the myosin cross-bridges contacting the actin filament to be visualized in a thin section. This review covers the history of this effort and the progress toward visualizing the complex set of conformational changes that myosin heads make when binding to actin in several static states as well as fast frozen actively contracting muscle. The efforts have revealed a consistent pattern of changes to the myosin head structures determined by X-ray crystallography needed to explain the structure of the different acto-myosin interactions observed in situ.

At present, business strategies in SMEs (Small and medium enterprises) are crucial for consolidation in highly competitive markets, in achieving a better image and in business profitability. One of the strategies that have the most success and business success are sustainable practices and social responsibility such as: ISO 14001 and ISO 26001. The literature related to sustainable business is based mainly on the theory of resources and capabilities, and in theory based on Stakeholders. These currents state that companies should focus on profitable strategies to ensure significant and long-term results, in order to achieve organizational and financial results for stakeholders. In this work, the sample consists of 215 companies from the commerce, services and industry sectors, located in the southern region of the State of Sonora in Mexico. The objective of the work is to analyze the influence of ISO 14001 and 26001 standards on the image and profitability of SMEs. The statistical analysis of the data has been carried out through the linear regression technique by OLS (Ordinary Least Squares). The findings prove that the ISO 14001 standard is the one that most influences the improvement of the business image and the level of profitability of the SME. In addition, we discovered that ISO 26001 has a partial influence on the image and profitability of the SME.

Detector-based spectral CT offers the possibility of obtaining spectral information from which discrete acquisitions at different energy levels can be derived, yielding so-called virtual monoenergetic images (VMI). In this study, we aimed to develop a jointly optimized deep learning framework based on dual-energy CT pulmonary angiography (DE-CTPA) data to generate synthetic monoenergetic images (SMI) for improving automatic pulmonary embolism (PE) detection in single-energy CTPA scans. For this purpose, we used two data sets: our institutional DE-CTPA data set D1 comprising polyenergetic arterial series and the corresponding VMI at low-energy levels (40 keV) with 7,892 image pairs, and a 10% subset of the 2020 RSNA Pulmonary Embolism Detection Challenge data set D2, which consisted of 161,253 polyenergetic images with dichotomous slice-wise annotations (PE/no PE). We trained a fully convolutional encoder-decoder on D1 to generate SMI from single-energy CTPA scans of D2, which were then fed into a ResNet50 network for training of the downstream PE classification task. The quantitative results on the reconstruction ability of our framework revealed high-quality visual SMI predictions with reconstruction results of 0.984 ± 0.002 (structural similarity) and 41.706 ± 0.547 dB (peak-signal-to-noise ratio). PE classification resulted in an AUC of 0.84 for our model, which achieved improved performance compared to other naive approaches with AUCs up to 0.81. Our study stresses the role of using joint optimization strategies for deep learning algorithms to improve automatic PE detection. The proposed pipeline may prove to be beneficial for computer-aided detection systems and could help rescue CTPA studies with suboptimal opacification of the pulmonary arteries from single-energy CT scanners.

Advancements in deep learning and availability of medical imaging data have led to use of CNN based architectures in disease diagnostic assisted systems. In spite of the abundant use of reverse transcription-polymerase chain reaction (RT-PCR) based tests in COVID-19 diagnosis, CT images offer an applicable supplement with its high sensitivity rates. Here, we study classification of COVID-19 pneumonia (CP) and non-COVID-19 pneumonia (NCP) in chest CT scans using efficient deep learning methods to be readily implemented by any hospital. We report our deep network framework design that encompasses Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory (biLSTM) architectures. Our study achieved high specificity (CP: 98.3%, NCP: 96.2% Healthy: 89.3%) and high sensitivity (CP: 84.0%, NCP: 93.9% Healthy: 94.9%) in classifying COVID-19 pneumonia, non-COVID-19 pneumonia and healthy patients. Next, we provide visual explanations for the CNN predictions with gradient-weighted class activation mapping (Grad-CAM). The results provided a model explainability by showing that Ground Glass Opacities (GGO), indicators of COVID-19 pneumonia disease, were captured by our CNN network. Finally, we have implemented our approach in three hospitals proving its compatibility and efficiency.

Speckle noise reduction is an important area of research in the field of ultrasound image processing. Several algorithms for speckle noise characterization and analysis have been recently proposed in the area. Synthetic ultrasound images can play a key role in noise evaluation methods as they can be used to generate a variety of speckle noise models under different interpolation and sampling schemes, and can also provide valuable ground truth data for estimating the accuracy of the chosen methods. However, not much work has been done in the area of modelling synthetic ultrasound images, and in simulating speckle noise generation to get images that are as close as possible to real ultrasound images. An important aspect of simulated synthetic ultrasound images is the requirement for extensive quality assessment for ensuring that they have the texture characteristics and gray-tone features of real images. This paper presents texture feature analysis of synthetic ultrasound images using local binary patterns (LBP) and demonstrates the usefulness of a set of LBP features for image quality assessment. Experimental results presented in the paper clearly show how these features could provide an accurate quality metric that correlates very well with subjective evaluations performed by clinical experts.

Radiotherapy commonly utilizes CBCT for patient positioning and treatment monitoring. CBCT is deemed to be secure for patients, making it suitable for the delivery of fractional doses. However, limitations such as a narrow field of view, beam hardening, scattered radiation artifacts, and variability in pixel intensity hinder the direct use of raw CBCT for dose recalculation during treatment. To address this issue, reliable correction techniques are necessary to remove artifacts and remap pixel intensity into HU values. This study proposes a deep-learning framework for calibrating CBCT images acquired with narrow FOV systems and demonstrates its potential use in proton treatment planning updates. Cycle-consistent GAN processes raw CBCT to reduce scatter and remap HU. Monte Carlo simulation is used to generate CBCT scans, enabling the possibility to focus solely on the algorithm’s ability to reduce artifacts and cupping effects without considering intra-patient longitudinal variability and producing a fair comparison between planning CT and calibrated CBCT dosimetry. To showcase the viability of the approach using real-world data, experiments were also conducted using real CBCT. Tests were performed on a publicly available dataset of 40 patients who received ablative radiation therapy for pancreatic cancer. The simulated CBCT calibration led to a difference in proton dosimetry of less than 2%, compared to the planning CT. The potential toxicity effect on the organs at risk decreased from about 50% (uncalibrated) up the 2% (calibrated). The gamma pass rate at 3%/2mm produced an improvement of about 37% in replicating the prescribed dose before and after calibration (53.78% vs 90.26%). Real data also confirmed this with slightly inferior performances for the same criteria (65.36% vs 87.20%). These results may confirm that generative artificial intelligence brings the use of narrow FOV CBCT scans incrementally closer to clinical translation in proton therapy planning updates.

Skin image analysis using artificial intelligence (AI) has recently attracted significant research interest, particularly for analyzing skin images captured by mobile devices. Acne is one of the most common skin conditions with profound effects in severe cases. In this study, we developed an AI system called AcneDet for automatic acne object detection and acne severity grading using facial images captured by smartphones. AcneDet includes two models for conducting two tasks: (1) a Faster R-CNN-based deep learning model for the detection of acne lesion objects of four types including blackheads/whiteheads, papules/pustules, nodules/cysts, and acne scars; and (2) a LightGBM machine learning model for grading acne severity using the Investigator’s Global Assessment (IGA) scale. The output of the Faster R-CNN model, i.e., the counts of each acne type, were used as input for the LightGBM model for acne severity grading. A dataset consisting of 1,572 labeled facial images captured by both iOS and Android smartphones was used for training. The results show that the Faster R-CNN model achieves a mAP of 0.54 for acne object detection. The mean accuracy of acne severity grading by the LightGBM model is 0.85. With this study, we hope to contribute to the development of artificial intelligent systems that are able to help acne patients understand more about their conditions and support doctors in acne diagnosis.

The key to simulating soil erosion is to calculate the vegetation cover (C) factor. Methods that apply remote sensing to calculate C factor at regional scale cannot directly use the C factor formula. That is because the C factor formula is obtained by experiment, and needs the coverage ratio data of croplands, woodlands and grasslands at standard plot scale. In this paper, we present a C factor conversion method from a standard plot to a km-sized grid based on large sample theory and multi-scale remote sensing. Results show that: 1) Compared with the existing C factor formula, our method is based on the coverage ratio of croplands, woodlands and grasslands on a km-sized grid, takes the C factor formula obtained from the standard plot experiment and applies it to regional scale. This method improves the applicability of the C factor formula, and can satisfy the need to simulate soil erosion in large areas. 2) The vegetation coverage obtained by remote sensing interpretation is significantly consistent (paired samples t-test, t = −0.03, df = 0.12, 2-tail significance p < 0.05) and significantly correlated with the measured vegetation coverage. 3) The C factor of the study area is smaller in the middle, southern and northern regions, and larger in the eastern and western regions. The main reason for that is the distribution of woodlands, the Hunshandake and Horqin sandy lands and the valleys affected by human activities. 4) The method presented in this paper is more meticulous than the C factor method based on the vegetation index, improves the applicability of the C factor formula, and can be used to simulate soil erosion on large scale and provide strong support for regional soil and water conservation planning.

A free-fall baited camera lander was launched for the first time on the Cosmonaut Sea shelf of East Antarctica at the depth of 694 m during the 38th Chinese National Antarctic Research Expedition (CHINARE) in 2022. We identified 31 unique taxa (23 of invertebrates and 8 of fishes) belonging to 8 phyla from 2403 pictures and 40 videos. The Antarctic jonasfish (Notolepis coatsi) was the most frequently observed fish taxa. Ten species of vulnerable marine ecosystem (VME) taxa were observed, accounting for 32% of all species. The maximum number (MaxN) of Natatolana meridionalis individuals per image frame was ten, and they were attracted to the bait. The macrobenthic community type was sessile suspension feeders with associated fauna (SSFA), which was shaped by the muddy substrata with scattered rocks. Rocks served as the best habitats for sessile fauna. The study reveals the megafauna community and their habitat by image survey in the Cosmonaut Sea for the first time. It helped us obtain Antarctic biodiversity baselines and monitoring data for future’s ecosystem health assessment and better protection.

Olive fruits at different ripening stages give rise to various table olive products and oil qualities. Therefore, developing an efficient method for recognizing and sorting olive fruits based on their ripening stages can greatly facilitate postharvest processing. This study introduces an automatic computer vision system that utilizes deep learning technology to classify the `Roghani` Iranian olive cultivar into five ripening stages using color images. The developed model employs convolutional neural networks (CNN) and transfer learning based on the Xception architecture and ImageNet weights as the base network. The model was fine-tuned by testing multiple configurations of well-known CNN layers. To minimize overfitting and enhance model generality, data augmentation techniques were employed. By considering different optimizers and two image sizes, four final candidate models were generated. These models were then compared in terms of loss and accuracy on the test dataset, classification performance (classification report and confusion matrix), and generality. All four candidates exhibited high accuracies ranging from 86.93% to 93.46% and comparable classification performance. In all models, at least one class was recognized with 100% accuracy. However, by taking into account the risk of overfitting, two models were discarded. Finally, a model with an image size of 224 × 224 and an SGD optimizer, which had a loss of 1.23 and an accuracy of 86.93%, was selected as the preferred option. The results of this study offer robust tools for automatic olive sorting systems, simplifying the differentiation of olives at various ripening levels for different post-harvest products.