Human beatboxing is a vocal art making use of speech organs to produce vocal drum sounds and imitate musical instruments. Beatbox sound classification is a current challenge that can be used for automatic database annotation and music-information retrieval. In this study, a large-vocabulary humanbeatbox sound recognition system was developed with an adaptation of Kaldi toolbox, a widely-used tool for automatic speech recognition. The corpus consisted of eighty boxemes, which were recorded repeatedly by two beatboxers. The sounds were annotated and transcribed to the system by means of a beatbox specific morphographic writing system (Vocal Grammatics). The image processing techniques plays vital role on image Acquisition, image pre-processing, Clustering, Segmentation and Classification techniques with different kind of images such as Fruits, Medical, Vehicle and Digital text images etc. In this study the various images to remove unwanted noise and performs enhancement techniques such as contrast limited adaptive histogram equalization, Laplacian and Harr filtering, unsharp masking, sharpening, high boost filtering and color models then the Clustering algorithms are useful for data logically and extract pattern analysis, grouping, decision-making, and machine-learning techniques and Segment the regions using binary, K-means and OTSU segmentation algorithm. It Classifying the images with the help of SVM and K-Nearest Neighbour(KNN) Classifier to produce good results for those images.

The popularity of handheld devices for point-of-care ultrasound (POCUS) has increased in recent years due to their portability and cost-effectiveness. However, POCUS has the drawback of lower imaging quality compared to conventional ultrasound, because of hardware limitations. Improving the quality of POCUS through post-image processing would therefore be beneficial, with deep learning approaches showing promise in this regard. This review investigates the state-of-the-art progress of image enhancement using deep learning suitable for POCUS applications. A systematic search was conducted from January 2024 to February 2024 on PubMed and Scopus. From the 457 articles that were found, the full text was retrieved for 69 articles. From this selection, 15 articles were identified addressing multiple quality enhancement aspects. A disparity in the baseline performance of the low-quality input images was seen across these studies, ranging between 8.65–29.24 dB for the Peak Signal-to-Noise Ratio (PSNR) and 0.03-0.71 for the Structural Similarity Index Measure (SSIM). In six studies, where both PSNR and the SSIM metrics were reported for the baseline and the generated images a mean difference of 6.60 (SD ± 2.99) and 0.28 (SD ± 0.15) was observed for the PSNR and SSIM, respectively. The reported performances demonstrate the potential of deep-learning-based image enhancement for POCUS. However, variability in the extent of performance gain across datasets and articles was notable, and the heterogeneity across articles makes quantifying the exact improvements challenging.

Medical image segmentation is a critical step in various healthcare applications, aiding in diagnosis, treatment planning, and disease monitoring. In this study, we investigate the efficacy of a segmentation approach based on the 2D wavelet transform. Leveraging a dataset comprising 10 diverse medical images, we evaluate the performance of our segmentation method using three key metrics: accuracy, precision, and recall. Our findings demonstrate that the proposed approach enhances segmentation accuracy, offering promising results compared to existing methods. By harnessing the multi-resolution feature extraction capabilities of the 2D wavelet transform, our method achieves improved delineation of medical image structures, paving the way for more accurate and efficient healthcare interventions.

Accurate medical image segmentation is paramount for precise diagnosis and treatment in modern healthcare. This research presents a comprehensive study on the efficacy of Particle Swarm Optimization (PSO) combined with Histogram Equalization (HE) preprocessing for medical image segmentation, focusing on Lung CT-Scan and Chest X-ray datasets. Best Cost values reveal the PSO algorithm’s performance, with HE preprocessing demonstrating significant stabilization and enhanced convergence, particularly in complex Lung CT-Scan images. Evaluation metrics, including Accuracy, Precision, Recall, F-Score, Specificity, Dice, and Jaccard, show substantial improvements with HE preprocessing, emphasizing its impact on segmentation accuracy. Comparative analyses against alternative methods, such as Otsu, Watershed, and K-means, confirm the competitiveness of the PSO-HE approach, especially in Chest X-ray images. The study also underscores the positive influence of preprocessing on image clarity and precision. These findings highlight the promise of the PSO-HE approach in advancing the accuracy and reliability of medical image segmentation, paving the way for further research and method integration to enhance this critical healthcare application.

This review provides an overview of eXplainable AI (XAI) methods for oncological ultrasound image analysis and compares their performance evaluations. A systematic search of Medline Embase and Scopus between March 25 and April 14 2024 identified 17 studies describing 14 XAI methods, including visualization, semantics, example-based, and hybrid functions. These methods primarily provided specific, local, and post-hoc explanations. Performance evaluations focused on AI model performance, with limited assessment of explainability impact. Standardized evaluations incorporating clinical end-users are generally lacking. Enhanced XAI transparency may facilitate AI integration into clinical workflows. Future research should develop real-time methodologies and standardized quantitative evaluative metrics.

Capsule endoscopy, which uses a wireless camera to take images of the digestive tract, is emerging as an alternative to traditional colonoscopy. The diagnostic values of these images depend on the quality of revealed underlying tissue surfaces. In this paper, we consider the problem of enhancing the visibility of detail and shadowed tissue surfaces for capsule endoscopy images. Using concentric circles at each pixel for random walks combined with stochastic sampling, the proposed method enhances the details of vessel and tissue surfaces. The framework decomposes the image into two detail layers that contain shadowed tissue surfaces and detail features. The target pixel value is recalculated for the smooth layer using similarity of the target pixel to neighboring pixels by weighting against the total gradient variation and intensity differences. In order to evaluate the diagnostic image quality of the proposed method, we used clinical subjective evaluation with a rank order on selected KID image database and compared to state of the art enhancement methods. The result showed that the proposed method provides a better result in terms of diagnostic image quality and objective quality contrast metrics and structural similarity index.

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: describe briefly 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, it must not contain results which are not presented and substantiated in the main text and should not exaggerate the main conclusions.

This paper develops a detail image signal enhancement that makes images perceived as clearer and more resolved and so is more effective for higher resolution displays. We observe that the local variant signal enhancement makes images more vivid, and the more revealed granular signals harmonically embedded on the local variant signals make images more resolved. Based on this observation, we develop a method that not only emphasizes the local variant signals by scaling up the frequency energy in accordance with human visual perception, but also strengths up the granular signals by embedding the alpha-rooting enhanced frequency components. The proposed energy scaling method emphasizes the detail signals in texture images and rarely boosts noisy signals in plain images. In addition, to avoid the local ringing artifact, the proposed method adjusts the enhancement direction to be parallel to the underlying image signal direction. It was verified through the subjective and objective quality evaluations that the developed method makes images perceived as clearer and highly resolved.

This article presents a method of segmenting images with gray levels that uses Onicescu's information energy calculated in the context of the neutrosophic theory. Starting from the information energy calculation for complete neutrosophic information, it is shown how to extend its calculation for incomplete and inconsistent neutrosophic information. The segmentation method is based on calculation of thresholds for separating the gray levels using the local maximum points of the Onicescu information energy.

Infrared and visible light image fusion technology integrates image feature information from two different modalities to generate an image that integrates complementary information from the source images. However, in low-light scenarios, the degradation of lighting in visible light images leads to existing fusion methods being unable to effectively extract texture detail information from the scene. At this time, the target prominence information provided by infrared images alone is far from sufficient. To address this challenge, this paper proposes a lightweight infrared and visible light image fusion method based on low-light enhancement, named LLE-Fuse. Firstly, the method improves the MobileOne Block by embedding the Sobel operator in the Edge-MobileOne Block to perform feature extraction and downsampling on the source images. Then, intermediate features of different scales are obtained and fused through a cross-modal attention fusion module, followed by image reconstruction using a decoder with upsampling. Next, the CLAHE algorithm is used for image enhancement of infrared and visible light images, and the enhanced loss guides the network model to learn the capability of low-light enhancement. Finally, upon completion of the network training, the method optimizes the Edge-MobileOne Block into the direct connection structure of MobileNetV1 through structural re-parameterization, effectively reducing the computational resource consumption of the model network. Through extensive experimental comparisons, this paper's method demonstrates excellent performance in both visual appeal and evaluation metrics, providing satisfactory fusion results even in low-light scenarios.

In order to improve contrast and restore color for underwater image captured by camera sensors without suffering from insufficient details and color cast, a fusion algorithm for image enhancement in different color spaces based on contrast limited adaptive histogram equalization (CLAHE) is proposed in this article. The original color image is first converted from RGB color space to two different special color spaces: YIQ and HSI. The color space conversion from RGB to YIQ is a linear transformation, while the RGB to HSI conversion is nonlinear. Then, the algorithm separately operates CLAHE in YIQ and HSI color spaces to obtain two different enhancement images. The luminance component (Y) in the YIQ color space and the intensity component (I) in the HSI color space are enhanced with CLAHE algorithm. The CLAHE has two key parameters: Block Size and Clip Limit, which mainly control the quality of CLAHE enhancement image. After that, the YIQ and HSI enhancement images are respectively converted backward to RGB color. When the three components of red, green, and blue are not coherent in the YIQ-RGB or HSI-RGB images, the three components will have to be harmonized with the CLAHE algorithm in RGB space. Finally, with 4 direction Sobel edge detector in the bounded general logarithm ratio operation, a self-adaptive weight selection nonlinear image enhancement is carried out to fuse YIQ-RGB and HSI-RGB images together to achieve the final fused image. The enhancement fusion algorithm has two key factors: average of Sobel edge detector and fusion coefficient, and these two factors determine the effects of enhancement fusion algorithm. A series of evaluate metrics such as mean, contrast, entropy, colorfulness metric (CM), mean square error (MSE) and peak signal to noise ratio (PSNR) are used to assess the proposed enhancement algorithm. The experiments results showed that the proposed algorithm provides more detail enhancement and higher values of colorfulness restoration as compared to other existing image enhancement algorithms. The proposed algorithm can suppress effectively noise interference, improve the image quality for underwater image availably.

Thresholding is considered as a statistical-decision making theory which can lessen the average error incurred in allocating pixels to two or more groups. The traditional Bayes decision rule can be applied with the prior knowledge of the Probability Density Function (PDF) of each class. It is surmised that a threshold resulting in the best class separation is the optimal one. In this paper, Otsu’s thresholding for image segmentation has been implemented. The well-known Otsu’s method is to learn a threshold that can maximize the between-class variance or equivalently make light of the within-class variance of the entire image. At first, a color image of a tree is taken. After that, the image is transformed into a grayscale image. Then in the first part, two-level thresholding is conducted, and later on, three-level thresholding is also applied. Again, two-level thresholding, as well as three level thresholding, are also applied to some other images. Finally, the comparison is made between two level thresholding and three level thresholding

Abstract: Image aesthetic assessment (IAA) with neural attention has made significant progress due to its effectiveness in object recognition. Current studies have shown that the features learned by convolutional neural networks (CNN) at different learning stages indicate meaningful information. The shallow feature contains the low-level information of images and the deep feature perceives the image semantics and themes. Inspired by this, we propose a visual enhancement network with feature fusion (FF-VEN). It consists of two sub-modules, the visual enhancement module (VE module) and the shallow and deep feature fusion module (SDFF module). The former uses an adaptive filter in the spatial domain to simulate human eyes according to the region of interest (ROI) extracted by neural feedback. The latter not only takes out the shallow feature and the deep feature by transverse connection, but also uses a feature fusion unit (FFU) to fuse the pooled features together with the aim of information contribution maximization. Experiments on standard AVA dataset and Photo.net dataset show the effectiveness of FF-VEN.

The notion of enhancement of the image is to ameliorate the perceptibility of information contained in an image. In the present research, a novel technique for the enhancement of image quality is propounded using fuzzy logic technique with a cuckoo optimization algorithm. Generally, the image is transformed from RGB domain to HSV domain keeping the color information intact within the image. The image has been categorized into three regions: underexposed, overexposed and mixed region on the basis of two threshold values. For the fuzzification of under and overexposed area the degree of membership is defined by the Gaussian membership, while the mixed area is fuzzified by parametric sigmoid function. The key parameters like visual factors and fuzzy contrast provide the quantitative analysis of an image. An objective function is framed which involves entropy and visual factor has been optimized by a new evolutionary cuckoo optimization algorithm. The results procured after simulation by the cuckoo optimization algorithm are compared with Bacterial foraging algorithm and ant colony optimization based image enhancement and this approach is found to be improved.

This paper has two major parts. In the first part histogram equalization for the image enhancement was implemented without using the built-in function in MATLAB. Here, at first, a color image of a rat was chosen and the image was transformed into a grayscale image. After this conversion, histogram equalization was implemented on the grayscale image. Later on, in the same image for each RGB channel, histogram equalization was implemented to observe the effect of histogram equalization on each channel. In the end, the histogram equalization was implemented to this specific color image of a rat. In the second part, for the grayscale image in part 1, the desired histogram of another colored image of a rat was introduced and histogram specification was implemented on the original colored image.

This paper has two major parts. In the first part histogram equalization for the image enhancement was implemented without using the built-in function in MATLAB. Here, at first, a color image of a rat was chosen and the image was transformed into a grayscale image. After this conversion, histogram equalization was implemented on the grayscale image. Later on, in the same image for each RGB channel, histogram equalization was implemented to observe the effect of histogram equalization on each channel. In the end, the histogram equalization was implemented to this specific color image of a rat. In the second part, for the grayscale image in part 1, the desired histogram of another colored image of a rat was introduced and histogram specification was implemented on the original colored image.

Open-vocabulary learning has recently gained prominence as a means to enable image segmentation for arbitrary categories based on textual descriptions. This advancement has extended the applicability of segmentation systems to a broader range of generally purpose scenarios. However, current methods often revolve around specialized architectures and parameters tailored to specific segmentation tasks, resulting in a fragmented landscape of segmentation models. In response to these challenges, we introduce OVAMTSeg, a versatile framework designed for Open-Vocabulary and Multitask Image Segmentation. OVAMTSeg harnesses adaptive prompt learning to empower the model to capture category-sensitive concepts, enhancing its robustness across diverse multi-task and scenario contexts. Text prompts are employed to effectively capture semantic and contextual features of the text, while cross-attention and cross-modal interactions enable the fusion of image and text features. Furthermore, a transformer-based decoder is incorporated for dense prediction. Extensive experimental results underscore the effectiveness of OVAMTSeg, showcasing its state-of-the-art performance and superior generalization capabilities across three segmentation tasks. Notable achievements include a 47.5 mIoU in referring expression segmentation, 51.6 mIoU on Pascal-VOC with four unseen classes, 46.6 mIoU on Pascal-Context in zero-shot segmentation, 65.9 mIoU on Pascal-5i, and 35.7 mIoU on COCO-20i datasets for one-shot segmentation.

Breast cancer is a leading cause of death among women. Conventional screening methods, such as mammography, and ultrasound diagnosis are expensive and have significant limitations. Digital Image Elasto Tomography (DIET) is a new noninvasive breast cancer screening system that has a potential to be a low cost and reliable breast cancer screening tool. It is based on modal analysis of the breast mass, and stereographic 3D image analysis to detect the stiffer abnormal tissues. However, camera sensor noise, especially Gaussian noise is a major source of Optical Flow (OF) error in this approach to tumor detection. This work studies the performance of different conventional filters, including the standard Gaussian filter tool to remove this noise and produce more robust screening results. A radical approach, Multiple Frame Noise Removal (MFNR) is proposed, for use in this type of medical image processing instead of a Gaussian filter or other typical image noise removal tools. Its a multiple frame noise removal method where Probability Density Function (PDF) of noise is extracted from the multiple images by characterizing the same pixel positions in multiple images. The noise becomes deterministic, and hence easily removed. The proposed algorithm was applied to a data set from 10 phantom breast tests with a prototype DIET system, and 10 in-vivo samples from healthy women. Comparisons were made to an optimal Gaussian filter form that is commonly used. Reductions in OF error using these digitally imaged data sets was used to compare performance. Refinement of the images for medical applications requires higher PSNR, which was successfully achieved by using MFNR algorithm. In this study, the algorithm was used to improve the imaging results of a DIET system. The conventional wisdom that states that noise removal and detail preservation are contrasting effects is

In recent years, underwater exploration for deep-sea resource utilization and development has a considerable interest. In an underwater environment, the obtained images and videos undergo several types of quality degradation resulting from light absorption and scattering, low contrast, color deviation, blurred details, and nonuniform illumination. Therefore, the restoration and enhancement of degraded images and videos are critical. Numerous techniques of image processing, pattern recognition and computer vision have been proposed for image restoration and enhancement, but many challenges remain. This survey presents a comparison of the most prominent approaches in underwater image processing and analysis. It also discusses an overview of the underwater environment with a broad classification into enhancement and restoration techniques and introduces the main underwater image degradation reasons in addition to the underwater image model. The existing underwater image analysis techniques, methods, datasets, and evaluation metrics are presented in detail. Furthermore, the existing limitations are analyzed, which are classified into image-related and environment-related categories. In addition, the performance is validated on images from the UIEB dataset for qualitative, quantitative, and computational time assessment. Areas in which underwater images have recently been applied are briefly discussed. Finally, recommendations for future research are provided and the conclusion is presented.

Problem. Image biomarker analysis, also known as radiomics, is a tool for tissue characterization and treatment prognosis that relies on routinely acquired clinical images and delineations. Due to the uncertainty in image acquisition, processing, and segmentation (delineation) protocols, radiomics often lacks reproducibility. Radiomics harmonization techniques have been proposed as a solution to reduce these sources of uncertainty and/or their influence on the prognostic model performance. A relevant question is how to estimate the protocol-induced uncertainty of a specific image biomarker, what the effect is on the model performance, and how to optimize the model given the uncertainty. In this manuscript, we show how protocol uncertainty can drastically reduce prognostic model performance. We introduce an effect-size measure η that assesses the protocol-induced uncertainty versus the measurable effect. Methods. Two non-small cell lung cancer (NSCLC) cohorts, composed of 421 and 240 patients respectively, were used for training and testing. Per patient, a Monte Carlo algorithm was used to generate three hundred synthetic contours with a surface dice tolerance measure less than 1.18 mm with respect to the original GTV. These contours were subsequently used to derive 104 radiomic features, which were ranked on their relative sensitivity to contour perturbation, expressed in the parameter η. The top four (low η) and the bottom four (high η) features were selected for two models based on Cox proportional hazards model. To investigate the influence of segmentation uncertainty on the prognostic model, we trained and tested the setup in 5000 augmented realizations (using a Monte Carlo sampling method); the log-rank test was used to assess the stratification performance and stability to segmentation uncertainty. Results. Although both low and high η setup showed significant testing set log-rank p-values (p=0.01) in the original GTV delineations (without segmentation uncertainty introduced), in the model with high uncertainty to effect ratio only around 30% of the augmented realizations resulted in model performance with p < 0.05 in the test set. In contrast, the low η setup performed with log-rank p < 0.05 in 90% of the augmented realizations. Moreover, the high η setup classification was uncertain for 50% of the subjects in the testing set (for 80% agreement rate), whereas the low η setup was uncertain only in 10% of the cases. The code and part of the data are available at https://github.com/Maastro-CDS-Imaging-Group/sure. Discussion. Estimating image biomarker model performance based only on the original GTV segmentation without considering segmentation uncertainty may be deceiving. The model might result in a significant stratification performance, but can be unstable for delineation variations, which are inherent to manual segmentation. Simulating segmentation uncertainty using the method described allows for more stable image biomarker estimation, selection, and model development. The segmentation uncertainty estimation method described here is universal and can be extended to estimate other protocol uncertainties (such as image acquisition and pre-processing).

In this paper, we use a machine learning method, known as Nonnegative Matrix Factorization, to extract from a given image some new information obtained from a number of color space representations. Such kind of information, termed ``metacolor'', can be considered as a particular color space representation of the image, which can be used to obtain a binary segmentation of the investigated image by distinguishing foreground and background pixels. Some numerical experiments prove that the proposed method shows improved results when compared with common simpler thresholding algorithms.

Remote sensing image registration plays an important role in military and civilian fields, such as natural disaster damage assessment, military damage assessment and ground targets identification, etc. However, due to the ground relief variations and imaging viewpoint changes, non-rigid geometric distortion occurs between remote sensing images with different viewpoint, which further increases the difficulty of remote sensing image registration. To address the problem, we propose a multi-viewpoint remote sensing image registration method which contains the following contributions. (i) A multiple features based finite mixture model is constructed for dealing with different types of image features. (ii) Three features are combined and substituted into the mixture model to form a feature complementation, i.e., the Euclidean distance and shape context are used to measure the similarity of geometric structure, and the SIFT (scale-invariant feature transform) distance which is endowed with the intensity information is used to measure the scale space extrema. (iii) To prevent the ill-posed problem, a geometric constraint term is introduced into the L2E-based energy function for better behaving the non-rigid transformation. We evaluated the performances of the proposed method by three series of remote sensing images obtained from the unmanned aerial vehicle (UAV) and Google Earth, and compared with five state-of-the-art methods where our method shows the best alignments in most cases.

It is very difficult to accurately divide farmland and woodland in Gaofen 2 (GF-2) remote sensing image, because their single plant coverage is very small, and their spectra are very similar. The ratio of spatial resolution and one plant’s coverage area must be fully taken into account when designing the Convolutional Neural Network structure for extracting them from GF-2 image. We establish a Convolutional Encode Neural Networks model (CENN), The first layer has two sets of convolution kernels to learn the characteristics of farmland and woodland respectively, while the second layer is the encoder to encode the characteristics by transfer function, which can map the results to the corresponding category number. In the training stage, samples of farmland, woodland, and other categories are categorically used to train CENN, as soon as training is accomplished, CENN would acquire enough ability to accurately extract farmland and woodland from remote sensing images. The final extraction result is obtained by implementing per-pixel segmentation of images used to train the CENN. CENN is compared and analyzed with others such as Deep Belief Network (DBN), Full Convolutional Network (FCN), Deeplab Model. The results of experiments show that CENN can more accurately mine the characteristics of farmland and woodland, and it achieves its goal of extracting farmland and woodland with high precision from GF-2 images.

This paper describes an image processing method that makes use of image parts instead of neural parts. Neural networks excel at image or pattern recognition and they do this by constructing complex networks of weighted values that can cover the complexity of the pattern data. These features however are integrated holistically into the network, which means that they can be difficult to use in an individual sense. A different method might scan individual images and use a more local method to try to recognise the features in it. This paper suggests such a method, where a trick during the scan process can not only recognise separate image parts, as features, but it can also produce an overlap between the parts. It is therefore able to produce image parts with real meaning and also place them into a positional context. Tests show that it can be quite accurate, on some handwritten digit datasets, but not as accurate as a neural network, for example. The fact that it offers an explainable interface could make it interesting however. It also fits well with an earlier cognitive model, and an ensemble-hierarchy structure in particular.

With the advent of deep learning, significant progress has been made in low-light image enhancement methods. However, deep learning requires enormous paired training data, which is challenging to capture in real-world scenarios.To address this limitation, this paper presents a novel unsupervised low-light image enhancement method, which first introduces the frequency domain features of images in low-light image enhancement tasks. Our work is inspired by imagining a digital image as a spatially varying metaphoric “field of light”, then subjecting the influence of physical processes such as diffraction and coherent detection back onto the original image space via a frequency-domain to spatial-domain transformation (inverse Fourier transform). However, the mathematical model created by this physical process still requires complex manual tuning of the parameters for different scene conditions to achieve the best adjustment. Therefore, we proposed a dual-branch convolution network to estimate pixel-wise and high-order spatial interactions for dynamic range adjustment of the frequency feature of the given low-light image. Guided by the frequency feature from the “field of light” and parameter estimation networks, our method enables dynamic enhancement of low-light images. Extensive experiments have shown that our method performs well compared to state-of-the-art unsupervised, and its performance approximates the level of the state-of-the-art supervised methods qualitatively and quantitatively. At the same time, the light network structure design allows the proposed method to have an extremely fast inference speed(nearly 150 FPS on an NVIDIA 3090 Ti GPU for an image of size 600×400×3 ). Furthermore, the potential benefits of our method to object detection in the dark are discussed.

Recently, Artificial Intelligence (AI)-based algorithms have revolutionized the medical image segmentation processes. Thus, the precise segmentation of organs and their lesions may contribute to an efficient diagnostics process and a more effective selection of targeted therapies as well as increasing the effectiveness of the training process. Thus, AI may contribute to the automatization of the image scan segmentation process and increase the quality of the resulting 3D objects, which may lead to the generation of more realistic virtual objects. In this paper, we focus on the AI-based solutions applied in the medical image scan segmentation, and intelligent visual-content generation, i.e. computer-generated three-dimensional (3D) images in the context of Extended Reality (XR). We consider different types of neural networks used with a special emphasis on the learning rules applied, taking into account algorithm accuracy and performance, as well as open data availability. This paper also attempts to summarize the current development of AI-based segmentation methods in medical imaging and intelligent visual content generation that are applied in XR. Finally, this paper concludes with possible developments and open challenges in AI application in Extended Reality-based solutions. Finally, the future lines of research and development directions of Artificial Intelligence applications both in medical image segmentation and Extended reality-based medical solutions are discussed.

Multi-threshold image segmentation is a relevant research field in further higher-level image preprocessing and computer vision. This paper adopts the Bayesian Forecasting Evolutionary Algorithm (BFEA) for natural scenery image segmentation using multilevel thresholding. An update method for the prediction vector is designed for image segmentation. The design idea of the BFEA algorithm for multilevel thresholding is based on the basic principle of Evolutionary Computation, the probability distribution of promising solutions, and the Bayesian theorem. BFEA could effectively solve the curse of dimensionality. Extensive experiments have demonstrated that the proposed algorithm dominated the state-of-the-art population-based thresholding method in term of the quality of image, function fitness value, optimal threshold value, SSIM value, PSNR value, computation time, dimensionality issue and convergence rate. The proposed method is very effective for color image segmentation.

The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2)—a successor with enhanced architecture and a larger training corpus—we reassess these challenges. This paper introduces SAM2-Adapter, the first adapter designed to overcome the persistent limitations observed in SAM2 and achieve new state-of-the-art (SOTA) results in specific downstream tasks including medical image segmentation, camouflaged (concealed) object detection, and shadow detection. SAM2-Adapter builds on the SAM-Adapter's strengths, offering enhanced generalizability and composability for diverse applications. We present extensive experimental results demonstrating SAM2-Adapter's effectiveness. We show the potential and encourage the research community to leverage the SAM2 model with our SAM2-Adapter for achieving superior segmentation outcomes. Code, pre-trained models, and data processing protocols are available at http://tianrun-chen.github.io/SAM-Adaptor/.

Enhancing underwater images in epicontinental sea is a challenging problem owing to the influence of ocean currents, the refraction, absorption and scattering of light by suspended particles, and the weak illumination intensity. Recently, different methods have relied on the underwater image formation model and deep learning techniques to restore the underwater image, but they tend to degrade underwater image, interference of background clutter and miss boundary details of blue regions. Improved image fusion and enhancement algorithm based on a priori dark channel is proposed in this paper. Image edge features sharpening and dark detail enhancement by homomorphism filtering in CIELab color space is realized. In RGB color space, the multi-scale retinal with color restoration (MSRCR) algorithm is used to improve color deviation and enhance color saturation, and the contrast-limited adaptive histogram equalization (CLAHE) algorithm is used to de fog and enhance image contrast. Finally, according to the dark channel images of the three processing results, the final enhanced image is obtained by linear fusion of multiple images and multiple channels. Experimental results demonstrate the effectiveness and practicality of the proposed method on various datasets.

When the image quality is evaluated, the human visual system (HVS) infers the details in the image through its internal generative mechanism. In this process, the HVS integrates both local and global information of the image, utilizes contextual information to restore the original image information, and compares it with the distorted image information for image quality evaluation. Inspired by this mechanism, a no-reference image quality assessment method is proposed based on a multitask image restoration network. The multitask image restoration network generates a pseudo-reference image as the main task and produces structural similarity index measure map as an auxiliary task. By mutually promoting the two tasks, a higher quality pseudo-reference image is generated. In addition, when predicting the image quality score, both the quality restoration features and the difference features between the distorted and reference images are used, thereby fully utilizing the information from the pseudo-reference image. To enable the model to focus on both global and local features, a multi-scale feature fusion module is proposed. Experimental results demonstrate that the proposed method achieves excellent performance on both synthetically and authentically distorted databases.

Automatic target detection of remote sensing images (RSI) plays an important role in military reconnaissance, disaster monitoring, and target rescue. The core task of remote sensing target detection is to judge the target categories and complete precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for remote sensing images with complex backgrounds. To achieve accurate detection of different categories targets in remote sensing images, this study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information, and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The advantage of FESSD over other state-of-the-art target detection methods is validated by experiments on the presented seven-class target detection dataset (SD-RSI) and the public DIOR dataset.

Image denoising has been one of the important problems in the field of computer vision, and it has a wide range of practical value in many applications, such as medical image processing, image enhancement, and computational photography. Traditional image denoising methods are usually based on hand-designed features and filters, but these methods perform poorly under complex noise and image structures. In recent years, the rapid development of neural network technology has revolutionized the image-denoising task. This paper introduces the knowledge about neural networks and image denoising, explores the impact of neural networks on image denoising, and how is it possible to denoise images by neural networks. It also summarises other image-denoising methods and finally points out the challenges and problems faced by image-denoising at present. Some possible new development directions are proposed to provide new solutions for image-denoising researchers and to promote the development of the field.

The use of unmanned aerial vehicle (UAV) during emergency response of a disaster has been widespread in recent years and the terrain images captured by the cameras on board these vehicles are significant sources of information for such disaster monitoring operations. Thus, analyzing such images are important for assessing the terrain of interest during such emergency response operations. Further, these UAVs are mainly used in disaster monitoring systems for the automated deployment of sensor nodes in real time. Therefore, deploying and localizing the wireless sensor nodes optimally, only in the regions of interest that are identified by segmenting the images captured by UAVs, hold paramount significance thereby effecting their performance. In this paper, the highly effective nature-inspired Plant Growth Simulation Algorithm (PGSA) has been applied for the segmentation of such terrestrial images and also for the localization of the deployed sensor nodes. The problem is formulated as a multi-dimensional optimization problem and PGSA has been used to solve it. Furthermore, the proposed method has been compared to other existing evolutionary methods and simulation results show that PGSA gives better performance with respect to both speed and accuracy unlike other techniques in literature.

Objective Image Quality Assessment (IQA) measures are playing an increasingly important role in the evaluation of digital image quality. New IQA indices are expected to be strongly correlated with subjective observer evaluations expressed by MOS/DMOS scores. One such recently proposed index is the SuperPixel-based SIMilarity (SPSIM) index, which uses superpixel patches instead of the rectangular pixel grid.The authors in this paper have been proposed three modifications of SPSIM index. For this purpose, the color space used by SPSIM was changed and the way SPSIM determines similarity maps was modified using methods derived from the algorithm for computing the MDSI index. The third modification was a combination of the first two. These three new quality indices were used in the assessment process. The experimental results obtained on many color images from five image databases demonstrated the advantages of the proposed SPSIM modifications.

Multispectral image (MSI) and hyperspectral image (HSI) fusion (MHIF) aims to address the challenge of acquiring high-resolution (HR) HSI images. This field combines a low-resolution (LR) HSI with an HR-MSI to reconstruct HR-HSI. Existing methods directly utilize transformers to perform feature extraction and fusion. Despite the demonstrated success, there exist two limitations: 1) Employing the entire transformer model for feature extraction and fusion fails to fully harness the transformer’s potential in integrating the spectral of the HSI and spatial information of the MSI. 2) HSI has a strong spectral correlation and exhibits sparsity in the spatial domain. Existing transformer-based models do not optimize this physical property, which makes their methods prone to spectral distortion. To accomplish these issues, this paper introduces a novel framework for MHIF called Sparse Mix-Attention Transformer (SAMformer). Specifically, to fully harness the advantages of the Transformer architecture, we propose a Spectral Mix Attention Block (SMAB), which concatenates the keys and values extracted from LR-HSI and HR-MSI to create a new multi-head attention module. This design facilitates the extraction of detailed long-range information across spatial and spectral dimensions. Besides, to address the spatial sparsity inherent in HSI, we incorporated a sparse mechanism within the core of SMAB called Sparse Spectral Mix Attention Block (SSMAB). In the SSMAB, we compute attention maps from queries and keys and select the K highly correlated values as the sparse attention map. This approach enables us to achieve a sparse representation of spatial information while eliminating spatially disruptive noise. Extensive experiments conducted on three benchmark datasets, namely Cave, Harvard, and Pavia Center, demonstrate the SMAformer method outperforms state-of-the-art methods.

Visible light photography diagnostic images are coloured ex vivo medical images popularly used in Dermatology and Endoscopy for diagnosis and monitoring. The need to protect the integrity of these images as well as associated patient data calls for techniques such as image steganography and watermarking. This research explores and compares the effect of watermarking on the YIQ and YCbCr colour transforms used in processing digital coloured images and video in recent times. Using a new spread spectrum watermarking algorithm, it was found that YIQ has better distortion performance than YCbCr in the order of 3dB while YCbCr had lower BER for accurate watermark retrieval and tamper detection in the order of 1.3 x 10-3.

In this paper, the filtering method of biomedical image denoising is described comprehensively. Firstly, it introduces the biomedical image denoising, describes the relationship between biomedical image denoising and medical care, introduces the filtering methods, the filtering methods of biomedical image denoising, the challenges encountered by the current filtering methods, and other application fields of filtering methods. Firstly, the background of biomedical image denoising is introduced. Biomedical image denoising is a challenge. Different imaging modes have different noise characteristics, and noise levels can vary greatly depending on the specific application. Secondly, it describes that biomedical image denoising plays an important role in medical care, and the biomedical image directly affects the patient's diagnosis, treatment plan and the overall quality of medical care service. Then the filtering method is introduced in detail, describing the core concepts and related features of linear filtering, nonlinear filtering and frequency domain filtering, and then focusing on the adaptive filtering method, describing the characteristics, conditions of use, common algorithms and advantages of adaptive filtering method. Then the filter methods of biomedical image denoising are introduced, and the core concepts of Gaussian filter, median filter, total variation denoising and Wiener filter are introduced respectively. Then, the challenges encountered by filtering methods are described, such as the accurate selection of filters, the balance between noise reduction and image detail preservation are introduced. Finally, the application of filtering method in other fields is mentioned, such as audio processing, speech recognition and so on. In summary, this paper comprehensively expounds the denoising and filtering methods of biomedical images, the filtering methods of medical image denoising, the relationship between medical image denoising and medical care, and the challenges encountered by filtering methods.

Digital images have become an important carrier for people to access information in the information age. However, with the development of the technology, digital images are vulnerable to illegal access and tampering, to the extent that they pose a serious threat to personal privacy, social order and national security. Therefore, image forensic techniques have become an important research topic in the field of multimedia information security. In recent years, deep learning technology has been widely applied in the field of image forensics and the performance achieved has significantly exceeded the conventional forensic algorithms. This survey compares the state-of-the-art image forensic techniques based on deep learning in recent years. The image forensic techniques are divided into passive and active forensics. In passive forensics, forgery detection techniques are reviewed, and the basic framework, evaluation metrics and commonly used datasets for forgery detection are presented. The performance, advantages and disadvantages of existing methods are also compared and analyzed according to different types of detection. In active forensics, robust image watermarking techniques are overviewed, the evaluation metrics and basic framework of robust watermarking techniques are presented. The technical characteristics and performance of existing methods are analyzed based on the different types of attacks on images. Finally, future research directions and conclusions are given to provide useful suggestions for people in image forensics and related research fields.

The fusion of global contextual information with local cropped block details is crucial for segmenting ultra-high resolution images. In this study, we introduce a novel fusion mechanism termed Global-Local Deep Fusion (GL-Deep Fusion) based on an enhanced transformer architecture, which efficiently integrates global contextual information and local details. Specifically, we propose the Global-Local Synthesis Networks (GLSNet), a dual-branch network where one branch processes the entire original image, while the other branch handles cropped local patches as input. The feature fusion of different branches in GLSNet is achieved through GL-Deep Fusion, significantly enhancing the accuracy of ultra-high resolution image segmentation. Particularly effective is GLSNet in identifying tiny overlapping items. To optimize GPU memory utilization, we meticulously design a dual-branch architecture that proficiently leverages the features it extracts, seamlessly integrating them into the enhanced transformer framework of GL-Deep Fusion. Extensive experiments conducted on challenging benchmarks, including DeepGlobe and Vaihingen datasets, demonstrate that GLSNet achieves a new state-of-the-art performance in terms of GPU memory utilization and segmentation accuracy tradeoff.

Image generation optimization is an important research direction in the field of deep learning, which aims to improve the performance of image generation models and the quality of generated images. In recent years, researchers have made significant progress in image generation optimization with the development of deep generative models such as generative adversarial networks (GANs) and variational autoencoders (VAEs). These models are able to generate high-quality, realistic images by learning the distribution of image data. In this study, a deep learning-based image generation optimization model was adopted, which combined the advantages of GAN and VAE. The model architecture consists of a generator and a discriminator, where the generator is responsible for generating the image and the discriminator is used to judge the authenticity of the image. In addition, the model also introduces attention mechanism and self-supervised learning strategy to further improve the quality and diversity of generated images. In the training process, a large-scale image dataset is used, and a variety of optimization algorithms are used to improve the stability and efficiency of the model. By evaluating various indicators of the generative model, including image quality, generation speed and model convergence, it was found that the introduced attention mechanism and self-supervised learning strategy significantly improved the performance of the model.

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

This paper develops a multi-task learning framework that attempts to incorporate the image structure knowledge to assist image inpainting, which is not well explored in previous works. The primary idea is to train a shared generator to simultaneously complete the corrupted image and corresponding structures --- edge and gradient, thus implicitly encouraging the generator to exploit relevant structure knowledge while inpainting. In the meantime, we also introduce a structure embedding scheme to explicitly embed the learned structure features into the inpainting process, thus to provide possible preconditions for image completion. Specifically, a novel pyramid structure loss is proposed to supervise structure learning and embedding. Moreover, an attention mechanism is developed to further exploit the recurrent structures and patterns in the image to refine the generated structures and contents. Through multi-task learning, structure embedding besides with attention, our framework takes advantage of the structure knowledge and outperforms several state-of-the-art methods on benchmark datasets quantitatively and qualitatively.

This article presents a new method of segmenting grayscale images by minimizing Shannon's neutrosophic entropy. For the proposed segmentation method, the neutrosophic information components, i.e., the degree of truth, the degree of neutrality and the degree of falsity are defined taking into account the belonging to the segmented regions and at the same time to the separation threshold area. The principle of the method is simple and easy to understand and can lead to multiple thresholds. The efficacy of the method is illustrated using some test gray level images. The experimental results show that the proposed method has good performance for segmentation with optimal gray level thresholds.

The landscape image is the bridge of communication between people and forests, and the cut point of the supply-side reform of forest tourism products. The research collected 140 copies in total of forest landscape image drawings from non-art-major graduate students by randomly sampling during April and May, 2018, and constructed the landscape image conceptual model of forest by utilizing the landscape image sketching technique. The results showed that (1) In regard to linguistic knowledge, the natural landscape elements for instance, herbaceous plants, terrains, creatures, water and sky, and the broad-leaf forest objectively reflected not only the real forest landscape and the local native vegetation, but the variation of forest species with little attention. (2) On the perspective of spatial view, the sideways view indicated that graduate students preferred to watch forests at a moderate distance externally and few looked at forests internally. (3) In the view of self-orientation, the objective landscape indicated that graduate students preferred to demonstrate forest landscapes, they did not realize to interact with the environment. (4) On the aspect of social meaning, the scenic view and forest structure stated that graduate students preferred rural forest landscapes, not significantly for other special interests for forest. In conclusions, (1) the forest is thought to be a feature of people's life world and of rural scenes around homes, not an objective perception of the forest. (2) The forest is regarded as an important habitat for animals and a limited resource for people's life, production and recreation needs, into which people will go only to meet such needs. (3) The natural values of forests, like the ecology and aesthetics, etc. get more attention, while the social values of forests, like the life, production and culture receives rather low attention.

(1) In order to study the influence of chaotic system on wheat image encryption, a method to find the optimal chaotic system encryption based on wheat image is proposed. (2) 10 different chaotic system schemes are combined to encrypt wheat images by 13 common chaotic maps, respectively. The best chaotic system scheme is obtained by considering the anti-attack capability of these encryption schemes, which analyzes 8 commonly used image encryption performance evaluation indexes. (3) The experimental results show that the new four-dimensional chaotic system has the best encryption effect, which is suitable for wheat image encryption. (4) The proposed scheme of wheat image encryption based on chaotic system provides a reference for other crop image encryption.

With the development of deep learning, the Super-Resolution (SR) reconstruction of microscopic images has improved significantly. However, the scarcity of microscopic images for training, the underutilization of hierarchical features in original Low Resolution (LR) images, and the high-frequency noise unrelated with the image structure generated during reconstruction process are still challenges in the Single Image Super-Resolution (SISR) field. Faced with these issues, we first collected sufficient microscopic images through Motic, a company engaged in the design and production of optical and digital microscopes, to establish a dataset. Secondly, we proposed a Residual Dense Attention Generative Adversarial Network (RDAGAN). The network comprises a generator, an image discriminator, and a feature discriminator. The generator includes a Residual Dense Block (RDB) and a Convolutional Block Attention Module (CBAM), focusing on extracting the hierarchical features of the original LR image. Simultaneously, the added feature discriminator enables the network to generate high-frequency features pertinent to the image’s structure. Finally, we conducted experimental analysis and compared our model with six classic models. Compared with the best model, our model improved PSNR and SSIM by about 1.5dB and 0.2, respectively.

Underwater imaging presents unique challenges, notably color distortions and reduced contrast due to light attenuation and scattering. Most underwater image enhancement methods, first use linear transformations for color compensation and then enhance the image. We observed that linear transformation for color compensation is not suitable for certain images. For such images, a non-linear mapping is a better choice. Our paper introduces a unique underwater image restoration approach leveraging a streamlined convolutional neural network (CNN) for dynamic weight learning for linear and non-linear mapping. In the first phase, a classifier is applied that classifies the input images into Type-I or Type-II. In the second phase, depending on the classification, the Deep Line Model (DLM) for Type-I images or the Deep Curve Model (DCM) for Type-II images. For mapping an input image to an output image, DML creatively combines color compensation and contrast adjustment in a single step and uses deep lines for transformation, whereas DCM employs higher-order curves. Both models utilize lightweight neural networks that learn per-pixel dynamic weights based on the input image’s characteristics. Comprehensive evaluations on benchmark datasets using metrics like peak signal-to-noise ratio(PSNR) and root mean squares error (RMSE) affirm our method’s effectiveness in accurately restoring underwater images, outperforming existing techniques.

In recent years, significant advancements in the field of machine learning have influenced the domain of image restoration. While these technological advancements present prospects for improving the quality of images, they also present difficulties, particularly the proliferation of manipulated or counterfeit multimedia information on the internet. The objective of this paper is to provide a comprehensive review of existing inpainting algorithms and forgery detections, with a specific emphasis on techniques that are designed for the purpose of removing objects from digital images. In this study, we will examine various techniques encompassing conventional texture synthesis methods, as well as those based on neural networks. Furthermore, we will explore the artifacts associated with the identification of modified photos and present the artifacts frequently introduced by the inpainting procedure and assess the state-of-the-art technology for detecting such modifications. Lastly, we shall look at the available datasets and how the methods compare with each other. Having covered all of the above, the final outcome of this study is to provide a comprehensive perspective on the abilities and constraints to detect images for which an inpainting object removal method was applied.

In recent years, the High Dynamic Range (HDR) image has gained widespread popularity 1 across various domains such as security, multimedia, and biomedical fields, owing to its ability 2 to deliver an authentic visual experience. However, the extensive dynamic range and rich detail 3 in HDR images present challenges in assessing their quality. Therefore, current efforts involve 4 constructing subjective databases and proposing objective quality assessment metrics to achieve 5 efficient HDR Image Quality Assessment (IQA). Recognizing the absence of a systematic overview 6 of these approaches, this paper provides a comprehensive survey of existing HDR IQA methods. 7 Furthermore, this paper aims to serve as a valuable resource for researchers by discussing the 8 limitations of current methodologies and potential research directions in the future.

Thermal infrared imagery provides temperature information on target objects, and has been widely applied in non-destructive testing. However, thermal infrared imagery is not always able to display detailed textures of inspected objects, which hampers the understanding of geometric entities consisting of temperature information. Although some commercial software has been developed for 3D thermal model displays, the software requires the use of expensive specific thermal infrared sensors. This study proposes a cost-effective method for 3D thermal model reconstruction based on image-based modeling. Two smart phones and a low-cost thermal infrared camera are employed to acquire visible images and thermal images, respectively, that are fused for 3D thermal model reconstruction. The experiment results demonstrate that the proposed method is able to effectively reconstruct a 3D thermal model which extremely approximates its corresponding entity. The total computation time for the 3D thermal model reconstruction is intensive while generating dense points required for the creation of a geometric entity. Future work will improve the efficiency of the proposed method in order to expand its potential applications to in-time monitoring.

Saliency detection in synthetic aperture radar (SAR) image is a difficult problem. This paper proposed a multitask saliency detection (MSD) model for the saliency detection task of SAR image. Firstly, we extract four features of SAR image as the input of the MSD model, which include the intensity, orientation, uniqueness and global contrast. Then, the saliency map is generated by the multitask sparsity pursuit (MTSP) which integrates the multiple features collaboratively. Subjective and objective evaluation of the MSD model verifies its effectiveness. Based on the saliency maps of the source images, an image fusion method is proposed for the SAR and color optical image fusion. The experimental results of real data show the proposed image fusion method is superior to the presenting methods in terms of several universal quality evaluation indexes, as well as in the visual quality. The salient areas in the SAR image can be highlighted and the spatial and spectral details of color optical image can also be preserved in the fusion result.

Popular geo-computer vision works make use of aerial imager with sizes ranging from 64 × 64 to 1024 × 1024 pixels without any overlap, although the learning process of deep learning models can be affected by the reduced semantic context or the lack of information near image boundaries. In this work, the impact of three image sizes (256 × 256, 512 × 512, and 1024 × 1024 pixels) and two image overlap levels (no overlap and 12.5% overlap) on the performance of road classification models was statistically evaluated. For this, two convolutional neural networks used in various tasks of geospatial object extraction were trained (using the same hyperparameters) on a large dataset (containing aerial image data covering 8650 km² of the Spanish territory that was labelled with binary road information) under twelve different scenarios, each scenario featuring a different combination of tile size and overlap. To assess their generalisation capacity, the performance of all resulting models was evaluated on a data from novel areas covering approximately 825 km². The performance metrics obtained were analysed using appropriate descriptive and inferential statistical techniques to evaluate the impact of the performance at distinct levels of the fixed factors (tile size, tile overlap, neural network architecture). Statistical tests were applied to study the main and interaction effects of the fixed factors on the performance. A significance level of 0.05 was applied to all the null hypothesis tests. The results were highly significant for the main effects (p-values lower than 0.001), while the two-way and three-way interaction effects among them had different levels of significance. The results indicate that the training of road classification models on images with a higher tile size (more semantic context) and tile overlap (additional border context and continuity) significantly impacts their performance. The best model was trained on a dataset featuring tiles with a size of 1024 × 1024 pixels and a 12.5% overlap and achieved a loss value of 0.0984, an F1 score of 0.8728, and an ROC-AUC score of 0.9766, together with an error rate of 3.5% on the test set.

Self-supervised learning is a method that learns general representation from unlabeled data. Masked image modeling (MIM), one of the generative self-supervised learning methods, has drawn attention showing state-of-the-art performance on various downstream tasks, though showing poor linear separability resulting from the token-level approach. In this paper, we propose a contrastive learning-based multi-view masked autoencoder for MIM, exploiting an image-level approach by learning common features from two different augmented views. We strengthen MIM by learning long-range global patterns from contrastive loss. Our framework adopts simple encoder-decoder architecture, learning rich and general representation by following a simple process: 1) two different views are generated from an input image with random masking and by contrastive loss, we can learn semantic distance of the representations generated by an encoder. By applying a high mask ratio, 80%, it works as strong augmentation and alleviates the representation collapse problem. 2) With reconstruction loss, decoder learns to reconstruct an original image from the masked image. We assess our framework by several experiments on benchmark datasets of image classification, object detection, and semantic segmentation. We achieve 84.3% fine-tuning accuracy on ImageNet-1K classification and 76.7% in linear probing, exceeding previous studies and show promising results on other downstream tasks. Experimental results demonstrate that our work can learn rich and general image representation by applying contrastive loss to masked image modeling.

Many dedicated designs for real-time operations provide functionality on fixed-sized operators, but where speed, scalability, and flexibility are required, extensive research is demanded. Dedicated designs can provide real-time processing for many applications. This paper presents an FPGA-based design of a general image processor. The proposed design is based on a fixed-point representation of binary numbers. The proposed design provides a mechanism to manage matrices on-chip along with matrix arithmetic. The matrices are represented with simple identifiers and microinstruction that assist in the computation of many operations which are useful for solving complex problems. The design was successfully implemented and tested using VHDL language. The proposed design is an efficient architecture as a standalone processor with all embedding computational resources necessary for an embedded image processing application.

Real-time image processing is crucial in applications such as video surveillance, diagnostic medicine, and autonomous vehicle systems. Parallel computing is essential to address the demands of real-time processing, but challenges persist in its practical implementation. This review analyzes parallel computing techniques applied to real-time image processing, examining parallel architectures and algorithms, identifying effective applications, and evaluating challenges and limitations. The results of this study will contribute to the development of more efficient solutions for real-time image processing. Keywords: Parallel computing, real-time image processing, video surveillance, diagnostic medicine, autonomous vehicle systems.

Image registration (IR) is a process that deforms images to align them with respect to a reference space, making it easier for medical practitioners to examine various medical images in a standardized reference frame, such as having the same rotation and scale. This document introduces image registration using a simple numeric example. It provides a definition of image registration along with a space-oriented symbolic representation. This review covers various aspects of image transformations, including affine, deformable, invertible, and bidirectional transformations, as well as medical image registration algorithms such as Voxelmorph, Demons, SyN, Iterative Closest Point, and SynthMorph. It also explores atlas-based registration and multistage image registration techniques, including coarse-fine and pyramid approaches. Furthermore, this survey paper discusses medical image registration taxonomies, datasets, evaluation measures, such as correlation-based metrics, segmentation-based metrics, processing time, and model size. It also explores applications in image-guided surgery, motion tracking, and tumor diagnosis. Finally, the document addresses future research directions, including the further development of transformers.

Large structures such as wind turbines are subject to environmental factors and varying operational loads which may result in structural damage, making components of these large structures prone to performance and mechanical degradation. The use of high-definition optical vision sensors in digital image correlation (DIC) allow for the application of a non-destructive image registration technique in which it measures finite three-dimensional deformations on surfaces through correlations of a unique pattern or set of unique localized patterns. However, the physical placement of an artificial marker such as a unique speckled pattern on the surface of the structure is time-consuming and often impractical for large structures. Therefore, we propose a novel auto-mated methodology that searches and segments salient and unique regions of an image as well as for all subsequent images to assist in performing efficient displacement measurements for vibrational study and structural health monitoring purposes. Our algorithm is validated on a con-trolled set of images, as well as on a small structure and large real-world wind turbine, which suggests the algorithm’s efficacy without the use of artificial markers for large structural health monitoring.

Recent studies on the image of the Turin Shroud (TS) lead to think it could have been formed through a not well-identified mechanism of energy radiation. In order to remove some lacunas about this imaging process, a reverse engineering method has been applied to it, arriving to exclude some possible mechanisms. The image formation of a human face wrapped on a cloth by using an ad-hoc developed software has been simulated. The results of different kinds of the radiation depending from different parameters have been simulated, each one connected with accredited hypotheses. On the basis of the comparison among the different images produced by the software and the TS Face, some useful information both about the kind of radiation and the cloth wrapping conditions have been obtained. The effect of image distortion of a cloth wrapped around a face has been discussed too by defining the best laws of radiation and of their attenuation with distance. A Lambertian law is not compatible with the TS image. A vertical radiation shows a problem in reproducing the requested resolution. A radiation perpendicular to the emitting surface, like that produced by an electric field appears promising to explain the TS Face.

This paper proposes a new approach for multi-focus images fusion based on Region Mosaicing on Contrast Pyramids (REMCP). A density-based region growing method is developed to construct a focused region mask for multi-focus images. The segmented focused region mask is decomposed into a mask pyramid, which is then used for supervised region mosaicking on a contrast pyramid. In this way, the focus measurement and the continuity of focused regions are incorporated and the pixel level pyramid fusion is improved at the region level. Objective and subjective experiments show that the proposed REMCP is more robust to noise than compared algorithms and can fully preserves the focus information of the multi-focus images meanwhile reducing distortions of the fused images.

Aiming at the problems that are poor generalization performance, low retrieval accuracy and large time consumption of existing content-based image retrieval system, the hierarchical image retrieval method based on multi feature fusion is proposed in this paper. The retrieval accuracy rates on Corel5K, UKbeach and Holidays are 68.23(Top 1), 3.73(N-S) and 88.20(mAp), respectively. The experimental results show that the method proposed in this paper can effectively improve the deficiency of single feature retrieval and save time significantly in the premise of a small amount of loss of accuracy.

Accuracy and computational cost are the main challenges of deep neural networks in image recognition. This paper proposes an efficient ranking reduction to binary classification approach using a new feed-forward network and feature selection based on ranking the image pixels. Preference net (PN) is a novel deep ranking learning approach based on Preference Neural Network (PNN), which uses new ranking objective function and positive smooth staircase (PSS) activation function to accelerate the image pixels’ ranking. PN has a new type of weighted kernel based on spearman ranking correlation instead of convolution to build the features matrix. The PN employs multiple kernels that have different sizes to partial rank image pixels’ in order to find the best features sequence. PN consists of multiple PNNs’ have shared output layer. Each ranker kernel has a separate PNN. The output results are converted to classification accuracy using the score function. PN has promising results comparing to the latest deep learning (DL) networks using the weighted average ensemble of each PN models for each kernel on CFAR-10 and Mnist-Fashion datasets in terms of accuracy and less computational cost.

Image captioning aims at generating meaningful verbal descriptions of a digital image. Our paper focuses on the classic encoder-decoder deep learning model that consists of several components – sub-networks, each performing a separate task that, combined, form an effective caption generator. We investigate image feature extractors, recurrent neural networks, word embedding models, and word generation layers and discuss how each component influences the captioning model’s overall performance. Our experiments are performed on the MS COCO 2014 dataset. The results help design efficient models with optimal combinations of their components.

Deep neural networks with powerful auto-optimization tools have been widely applied in various research fields, e.g., NLP and computer vision. However, existing neural network architectures typically are constructed using different inductive biases, e.g., preconceptions, expecting to decrease parameter search space during training, reduce computational cost or introduce expert knowledge in the neural network design. As an alternative, Multilayer Perceptron (MLP) provides much better freedom for exploration, has a lower inductive bias than convolutional neural networks (CNNs), and offers good flexibility in learning complex patterns. Even though, such neural architectures are commonly built in a flat Euclidean space, which is not necessarily the optimal space for any data, and is especially not good for modeling hierarchical correlations. Hyperbolic neural networks (HNNs) have gained attention for their ability to capture hierarchical structures present in complex data types like graphs. Recently, there has been an increasing interest to extend HNNs to computer vision tasks, motivated by the observations that images possess rich hierarchical relations. However, this is generally applied by employing a Euclidean backbone for learning higher-level semantic representations and only incorporating a hyperbolic classifier for classification, which, we argue, does not make full use of the advantage of hyperbolic space. Considering the recovery of the attention-free Multilayer Perceptron(MLP), in this paper, we extend it to non-Euclidean space and propose a novel architecture, named Hyperbolic Res-MLP (HR-MLP), that leverages fully hyperbolic layers to learn feature embeddings and perform image classification in an end-to-end fashion. With the help of the proposed Lorentz cross-patch and cross-channel layers, we can directly perform operations in the hyperbolic domain with fewer parameters, making it faster to train and providing comparatively better performance than its Euclidean counterpart. Experiments on CIFAR10, CIFAR100, and MiniImageNet demonstrate a comparable and superior performance when compared to Euclidean baselines. Our code is available at (https://github.com/Ahmad-Omar-Ahsan/HR-MLP)

Image processing is a computationally intensive task that can benefit significantly from parallel techniques. In this study, we evaluate the efficiency of image processing using parallel techniques compared to sequential techniques. We use Dask to parallelize the loading and processing of images and compare the execution times for various image processing techniques, including smoothing, edge detection, rotation, and thresholding. The results show that parallel processing significantly reduces execution time compared to sequential processing.

Medical image analysis is an important branch in the field of medicine, which mainly uses image processing and analysis techniques to interpret and diagnose medical image data. Medical image data helps doctors to effectively observe and diagnose patients' body structures, tissues and lesions. Medical image analysis has been an important research area in the medical field, and it is important for disease diagnosis, treatment planning, and condition monitoring. In recent years, the rapid development of deep learning and computer vision technologies has contributed greatly to the automation, multimodal data fusion, real-time application, and accuracy improvement of medical image analysis. In addition, the development of deep learning has given rise to some new research areas in medical image analysis, such as Generative Adversarial Networks (GANs) for synthetic medical images, self-supervised learning for unsupervised feature learning, and neural network interpretability. In this paper, we will introduce some optimisation methods for medical images which are effective in improving the accuracy, efficiency and reliability of medical image analysis.

Gradient-domain image processing is a technique where, instead of operating directly on the image pixel values, the gradient of the image is computed and processed. The resulting image is obtained by reintegrating the processed gradient. This is normally done by solving the Poisson equation, most oftenly by means of a finite difference implementation of the gradient descent method. However, this technique in some cases lead to severe haloing artefacts in the resulting image. To deal with this, local or anisotropic diffusion has been added as an ad-hoc modification of the Poisson equation. In this paper, we show that a version of anisotropic gradient-domain image processing can result from a more general variational formulation through the minimisation of a functional formulated in terms of the eigenvalues of the structure tensor of the differences between the processed gradient and the gradient of the original image. Example applications of linear and non-linear local contrast enhancement and colour image daltonisation illustrate the behaviour of the method.

This article presents a new method of segmenting images with gray levels. The method is based on determining several thresholds for separation of gray levels. The determination of these thresholds is done using the certainty of the neutrosophic information. The concept of this method can be stated simply: to choose the local maximums for the neutrosophic certainty.

The latest methods based on deep learning have achieved amazing results regarding the complex work of inpainting large missing areas in an image. This type of method generally attempts to generate one single "optimal" inpainting result, ignoring many other plausible results. However, considering the uncertainty of the inpainting task, one sole result can hardly be regarded as a desired regeneration of the missing area. In view of this weakness, which is related to the design of the previous algorithms, we propose a novel deep generative model equipped with a brand new style extractor which can extract the style noise (a latent vector) from the ground truth image. Once obtained, the extracted style noise and the ground truth image are both input into the generator. We also craft a consistency loss that guides the generated image to approximate the ground truth. Meanwhile, the same extractor captures the style noise from the generated image, which is forced to approach the input noise according to the consistency loss. After iterations, our generator is able to learn the styles corresponding to multiple sets of noise. The proposed model can generate a (sufficiently large) number of inpainting results consistent with the context semantics of the image. Moreover, we check the effectiveness of our model on three databases, i.e., CelebA, Agricultural Disease, and MauFlex. Compared to state-of-the-art inpainting methods, this model is able to offer desirable inpainting results with both a better quality and higher diversity. The code and model will be made available on https://github.com/vivitsai/SEGAN.

Identifying the total number of fruits on trees has long been of interest in agricultural crop estimation work. Yield prediction of fruits in practical environment is one of the hard and significant tasks to obtain better results in crop management system to achieve more productivity with regard to moderate cost. Utilized color vision in machine vision system to identify citrus fruits, and estimated yield information of the citrus grove in-real time. Fruit recognition algorithms based on color features to estimate the number of fruit. In the current research work, some low complexity and efficient image analysis approach was proposed to count yield fruits image in the natural scene. Semi automatic segmentation and yield calculation of fruit based on shape analysis is presented. Color and shape analysis was utilized to segment the images of different fruits like apple, pomegranate obtained under different lighting conditions. First the input sectional tree image was converted from RGB colour space into the colour space transform (i.e., YUV, YIQ, or YCbCr). The resultant image was then applied to the algorithm for fruit segmentation. After it is applied Morphological Operations which is enhanced image then execute Blob counting method which identify the object and count the number of it. Accuracy of this algorithm used in this thesis is 82.21% for images that have been scanned.

The theory of fractional calculus extends the order of classical integer calculus from integer to non-integer. As a new engineering application tool, it has made many important research achievements in many fields, including image processing. This paper mainly studies the application of fractional calculus theory in image enhancement and denoising, including the basic theory of fractional calculus and its amplitude frequency characteristics, the application of fractional differential operator in image enhancement, and the application of fractional integral operator in image denoising. The experimental results show that the fractional calculus theory has more special advantages in image enhancement and denoising. Compared with the existing integer order image enhancement operators, the fractional differential operator can more effectively enhance the "weak edge" and "strong texture" details of the image. The fractional order integral image denoising operator can not only improve the signal-to-noise ratio of the image compared to traditional denoising methods, but also better preserve detailed information such as edges and textures of the image.

In rye, there is a considerable variety of grain color which is determined by the diversity of compounds localized in different parts of the grain (caryopsis) - pericarp, testa, and aleurone. The localization of anthocyanins and proanthocyanidins was analyzed in 26 rye samples with identified anthocyanin genes, along with the analysis of CIE color coordinates. The Grain Scan program [1] was used to analyze images of individual grains. The localization of anthocyanins and proanthocyanidins was studied on longitudinal and cross sections of grains using light microscopy and MALDI-imaging. The violet-grained samples contain anthocyanins in the pericarp, and the green-grained samples contain anthocyanins in the aleurone layer. The green, violet and yellow-grained rye, with the exception of two anthocyaninless mutants vi3 and vi6, shows the presence of proanthocyanidins in the brown-colored testa. Four main color groups of the rye grains (yellow, green, brown, violet) could be differentiated using the color coordinate h° (hue angle). Interspecies and intraspecies variability for the localization of colored flavonoids in cereal grains is discussed.

Single image deraining (SID) has shown its importance in many advanced computer vision tasks. Though many CNN based image deraining methods have been proposed, how to effectively remove raindrops while maintaining background structure remains a challenge that needs to be overcome. Most of the deraining work focuses on removing rain streaks, but in heavy rain images, the dense accumulation of rainwater or the rain curtain effect significantly interferes with the effective removal of rain streaks, and often introduces some artifacts that make the scene more blurry. In this paper, we propose a new network structure R-PReNet for single image deraining with good background structure maintaining. This framework fully utilizes the cyclic recursive structure of PReNet. Moreover, we introduce residual channel prior (RCP) and feature fusion modules for better deraining performance by focusing on background feature information. Compared with the previous methods, our method has significantly improvement effect on the rainstorm image with the artifacts removing and good visual detail restoring.

Recent advances in microscopy imaging and image analysis motivate more and more institutes world-wide to establish dedicated core-facilities for bio-image analysis. To maximize the benefits research groups at these institutes gain from their core-facilities, they should be established to fit well into their respective environment. In this article, we introduce common collaborator requests and corresponding potential services core-facilities can offer. We also discuss potential conflicts of interests between the targeted missions and implementations of services to guide decision makers and core-facility founders to circumvent common pitfalls.

Image fusion is a useful tool for producing a high-resolution multispectral image to be used for land use and land cover mapping. In this study, we use nine pansharpening algorithms namely Color Normalized (CN), Gram-Schmidt (GS), Hyperspherical Color Space (HCS), High Pass Filter (HPF), Nearest-Neighbor Diffusion (NND), Principal Component Analysis (PCA), Resolution Merge (RM), Stationary Wavelet Transform (SWT), and Wavelet Resolution Merge (WRM) to fusion Worldview-3 multispectral Bands and panchromatic band. In spectral and spatial fidelity, several image quality metrics are used to evaluate the performance of pansharpening algorithms. The SWT and PCA algorithms showed better results compared to other pansharpening algorithms while GS and CN algorithms showed the worst results for the original image fusion. The effect of fusion on each band was separately investigated and according to the calculations, we found that the CoastalBlue band and the Blue band showed the best result and the NIR-1 band and NIR-2 band show the worst result for the original image fusion. In the end, we conclude that the choice of fusion method depends on the requirement of remote sensing application.

In this paper, at first, a color image of a car is taken. Then the image is transformed into a grayscale image. After that, the motion blurring effect is applied to that image according to the image degradation model described in equation 3. The blurring effect can be controlled by a and b components of the model. Then random noise is added in the image via Matlab programming. Many methods can restore the noisy and motion blurred image; particularly in this paper Inverse filtering as well as Wiener filtering are implemented for the restoration purpose. Consequently, both motion blurred and noisy motion blurred images are restored via Inverse filtering as well as Wiener filtering techniques and the comparison is made among them.

Numerous image processing techniques (IPTs) have been employed to detect crack defects, offering an alternative to human-conducted onsite inspections. These IPTs manipulate images to extract defect features, particularly cracks in surfaces produced through Additive Manufacturing (AM). This article presents a vision-based approach that utilizes deep convolutional neural networks (CNNs) for crack detection in AM surfaces. Traditional image processing techniques face challenges with diverse real-world scenarios and varying crack types. To overcome these challenges, our proposed method leverages CNNs, eliminating the need for extensive feature extraction. Annotation for CNN training is facilitated by LabelImg without the requirement for additional IPTs. The trained CNN, enhanced by OpenCV preprocessing techniques, achieves an outstanding 99.54% accuracy on a dataset of 14,982 annotated images with resolutions of 1536 × 1103 pixels. Evaluation metrics exceeding 96% precision, 98% recall, and a 97% F1-score highlight the precision and effectiveness of the entire process.

Abstract: The two-dimensional Fuzzy Transform was applied in image compression. The quality of the image compressed with this methodis better than that obtained using methods based on fuzzy relation equations and comparable with that of the JPEG method, with better compression execution times. In this paper we propose a variation of the method based on the two-dimensional Fuzzy Transform of image compression, in which the image is first partitioned into blocks and then each block is compressed with the higher compression rate. The advantage of this method consistsinto a greater compression of the image, guaranteeing a high quality of the reconstructed image.The results show that our method is better than the Fuzzy Transform method improving also the quality of the reconstructed image.

Neural-objective and image optimization approaches for drilling fluid rheology automation are crucial for drilling engineering optimization. A myriad of intelligent computational models are employed to predict and monitor the parameters of mud rheology and filter cake permeability posture using an artificial neural network feedforward (ANN-FF) function, a non-ANN-FF function, an image processing tool, and a model optimization tool. 498 datasets of synthetic-based mud (SBM) flat rheology from a drilling mud laboratory at Nazarbayev University were imported into a user-friendly MATLAB application using image processing and nftool. Apart from the Google TensorFlow Sequential API DNN architecture used, a Levenberg-Marquardt training algorithm with input sigmoid hidden neurons 10, 12, and 18 coupled with a linear output layer was also used to predict the SBM flow index. OBM and SBM filter cakes were processed for void spaces; however, a model study was extrapolated to maximize filtration volume Vf. The study’s findings show that the ANN-FF model employed for rheological property monitoring and prediction had higher steady and exponential levels of accuracy and a correlation coefficient of 0.96-0.99. More so, SBM and OBM image processing presented an area of void spaces of 1790M2 and 1739M2, respectively. The porosity and permeability postures of both SBM and OBM resulted in a significant void space capable of maximizing the flow index. In addition, the single-objective modelling based on a genetic algorithm did validate the experimental rheological data for flow index or filtration volume Vf optimization; the study resulted in the finding that the constrained physics-informed objective function hindered maximizing oil recovery and instead predicted possible formation damage. It is empirical to note that automating flow predictions with neural, objective, and image functions has presented an alternative novel method for non-programmers using MATLAB and Google Colabs that is capable of enhancing mud rheological parameters, drilling efficiency, and hydrocarbon recovery.

The widespread availability of digital image processing softwares has given rise to various forms of image manipulation and forgery which can pose a significant challenge in different fields such as law enforcement, journalism etc,. it can also lead a privacy concern. We are proposing a privacy-preserving framework to encrypt images before processing them is vital to maintain the privacy and confidentiality of sensitive images, especially those used for purpose of Investigation. To address these challenges, we propose a novel solution that detects image forgeries while preserving the privacy of the images. Our method proposes a privacy-preserving framework that encrypts the images before processing them, making it difficult for unauthorized individuals to access them. The proposed method utilizes a compression quality analysis in the encrypted domain to detect the presence of forgeries in images if the forged portion (dummy image) has a compression quality different from the original image (featured image) in the encrypted domain. This approach effectively localizes the tampered portions of the image, even for small pixel blocks of size 10x10 in the encrypted domain. Furthermore, the method identifies the featured image's JPEG quality using the first minima in the energy graph.

Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, we present a comprehensive approach utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets are based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH Dataset, we deployed an ensemble strategy incorporating VGG16 and ResNet50 architec-tures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique, to preprocess a high-resolution image, which facilitates focused analysis of localized regions of interest. The annotated BACH dataset encompasses 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, we employed the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify mi-croscopic images into eight distinct categories (four benign and four malignant). For both models we leveraged a five-fold cross-validation approach for rigorous training and testing. Preliminary ex-perimental results indicate a Patch classification accuracy of 95.31% (on BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to on-going endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens.

Recently, the mapping industry has been focusing on the possibility of large-scale mapping from unmanned aerial vehicles (UAVs) owing to advantages such as easy operation and cost reduction. In order to produce large-scale maps from UAV images, it is important to obtain precise orientation parameters. For this, various techniques have been developed and are included in most of the commercial UAV image processing software. For mapping, it is equally important to select images that can cover a region of interest (ROI) with the fewest possible images. Otherwise, to map the ROI, one may have to handle too many images, and commercial software does not provide information needed to select images, nor does it explicitly explain how to select images for mapping. For these reasons, stereo mapping of UAV images in particular is time consuming and costly. In order to solve these problems, this study proposes a method to select images intelligently. We can select a minimum number of image pairs to cover the ROI with the fewest possible images. We can also select optimal image pairs to cover the ROI with the most accurate stereo pairs. We group images by strips, and generate the initial image pairs. We then apply an intelligent scheme to iteratively select optimal image pairs from the start to the end of an image strip. According to the results of the experiment, the number of images selected is greatly reduced by applying the proposed optimal image–composition algorithm. The selected image pairs produce a dense 3D point cloud over the ROI without any holes. For stereoscopic plotting, the selected image pairs were map the ROI successfully on a digital photogrammetric workstation (DPW), and a digital map covering the ROI is generated. The proposed method should contribute to time and cost reductions in UAV mapping.

In many image processing and computer vision applications, the main aim is to describe image contents. So, different visual properties such as color, texture and shape are extracted to make aim. In this respect, texture information play important role in image description and visual pattern classification. Texture is referred to a specific local distribution of intensities that is repeated throughout the image. Since now different operations or descriptors have been proposed to analysis texture characteristics. In the multi object images specific texture operators usually doesn’t provide accurate results. So, in many cases, combination of texture operators are used to achieve more discriminant features. In this paper, some combination methods are survived to analysis effect of combinational texture features in image content description. Also, in the result part, different related methods are compared in terms of accuracy and computational complexity.

X-ray tomography is an effective non-destructive testing method for industrial quality control. Limited angle tomography can be used to reduce the amount of data that needs to be acquired and thus speed up the process. In some industrial applications, however, objects are flat and layered, and laminography is preferred. It can deliver 2D images of the structure of a layered object at a particular depth from very limited data. An image at a particular depth is obtained by summing those parts of the data that contribute to that slice. This produces a sharp image of that slice while superimposing a blurred version of structures present at other depths. In this paper, we investigate an optimal experimental design (OED) problem for laminography that aims to determine the optimal source positions. Not only can this be used to mitigate imaging artifacts, it can also speed up the acquisition process in case where moving the source and detector is time consuming (e.g., in robotic arm imaging systems). We investigate the imaging artifacts in detail through a modified Fourier Slice Theorem. We address the experimental design problem within the Bayesian risk framework using empirical Bayes risk minimization. Finally, we present numerical experiments on simulated data.

Autonomous image recognition has numerous potential applications in the field of planetary science and geology. For instance, having the ability to classify images of rocks would allow geologists to have immediate feedback without having to bring back samples to the laboratory. Also, planetary rovers could classify rocks in remote places and even in other planets without needing human intervention. Shu et al. classified 9 different types of rock images using a Support Vector Machine (SVM) with the image features extracted autonomously. Through this method, the authors achieved a test accuracy of 96.71%. In this research, Convolutional Neural Networks(CNN) have been used to classify the same set of rock images. Results show that a 3-layer network obtains an average accuracy of 99.60% across 10 trials on the test set. A version of Self-taught Learning was also implemented to prove the generalizability of the features extracted by the CNN. Finally, one model has been chosen to be deployed on a mobile device to demonstrate practicality and portability. The deployed model achieves a perfect classification accuracy on the test set, while taking only 0.068 seconds to make a prediction, equivalent to about 14 frames per second.

An effective on-board cloud detection method in small satellites would greatly improve the downlink data transmission efficiency and reduce the memory cost. In this paper, an ensemble method combining a lightweight U-Net with wavelet image compression is proposed and evaluated. The red, green, blue and infrared waveband images from Landsat-8 dataset are trained and tested to estimate the performance of proposed method. The LeGall-5/3 wavelet transform is applied on the dataset to accelerate the neural network and improve the feasibility of on-board implement. The experiment results illustrate that the overall accuracy of the proposed model achieves 97.45% by utilizing only four bands. Tests on low coefficients of compressed dataset have shown that the overall accuracy of the proposed method is still higher than 95%, while its inference speed is accelerated to 0.055 second per million pixels and maximum memory cost reduces to 2Mb. By taking advantage of mature image compression system in small satellites, the proposed method provides a good possibility of on-board cloud detection based on deep learning.

This paper investigates the adaptability of four state-of-the-art Artificial Intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n=856 cancer cases and n=856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish image subsets. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&amp;H and End2End AI models, both in the pre-trained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by GLAM model (0.909), I&amp;H (0.893) and End2End (0.875). There were significant differences (P&lt;0.05) in the performances of the four AI models between high-concordance subset and entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with strong concordance of radiologists’ annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.

The paper describes the new method for image compression based on coordinated group signal transformation. The algorithm is a type of difference coding. Coordinated processing significantly simplifies the difference signal conversion scheme using a single group codec for all signals. The described method considers color channels as correlated signals of a multi-channel communication system. The specifics of the processed data required modification of the coordinated group processing algorithm. First, we changed how to calculate the difference signals to prevent data loss. Secondly, the group codec was supplemented with a neural network to improve the quality of reconstructed images. We considered the following types of neural networks: fully connected, recurrent, convolution, and convolution in the Fourier space. Based on the simulation results, it is best to use fully connected neural networks if the goal is to minimize processing delay time. These networks have a response time of 13 ms. On the other hand, if the priority is to improve quality in cases where delays are not critical, then convolution neural networks in the Fourier space should be used. These networks have a response time of 140 ms and are of significant interest.

Advanced image processing will be crucial for emerging technologies such as autonomous driving, where the requirement to quickly recognize and classify objects under rapidly changing, poor visibility environments in real time will be needed. Photonic technologies will be key for next-generation signal and information processing, due to their wide bandwidths of 10’s of Terahertz and versatility. Here, we demonstrate broadband real time analog image and video processing with an ultrahigh bandwidth photonic processor that is highly versatile and reconfigurable. It is capable of massively parallel processing over 10,000 video signals simultaneously in real time, performing key functions needed for object recognition, such as edge enhancement and detection. Our system, based on a soliton crystal Kerr optical micro-comb with a 49GHz spacing with >90 wavelengths in the C-band, is highly versatile, performing different functions without changing the physical hardware. These results highlight the potential for photonic processing based on Kerr microcombs for chip-scale fully programmable high-speed real time video processing for next generation technologies.

Recent advancements in cognitive neuroscience, particularly in Electroencephalogram (EEG) signal processing, image generation, and brain-computer interfaces (BCI), have opened up new avenues for research. This study introduces a novel framework, Bridging Artificial Intelligence and Neurological Signals (BRAINS), which leverages the power of AI to extract meaningful information from EEG signals and generate images. The BRAINS framework addresses the limitations of traditional EEG analysis techniques, which struggle with nonstationary signals, spectral estimation, and noise sensitivity. Instead, BRAINS employs Long Short-Term Memory (LSTM) networks and contrastive learning, which effectively handle time-series EEG data and recognize intrinsic connections and patterns. The study utilizes the MNIST dataset of handwritten digits as stimuli in EEG experiments, allowing for diverse yet controlled stimuli. The data collected is then processed through an LSTM-based network employing contrastive learning and extracting complex features from EEG data. These features are fed into an image generator model, producing images as close to the original stimuli as possible. This study demonstrates the potential of integrating AI and EEG technology, offering promising implications for the future of brain-computer interfaces.

Traditional image steganography conceals secret messages into unprocessed natural images by modifying the pixel value, causing the obtained stego different from the original image in terms of statistical distribution, thereby could be detected by a well-trained classifier for steganalysis. To ensure the steganography is imperceptible and in line with the trend of art images produced by Artificial Intelligence Generated Content (AIGC) becoming popular in social networks, this paper proposes to embed hidden information throughout the process of the generation of an art-style image by designing an image style transformation neural network with steganography function. The proposed scheme takes a content image, an art-style image, and messages to be embedded as inputs, processing them with an encoder-decoder model, and finally generates a styled image containing the secret messages at the same time. An adversarial training technique is applied to enhance the imperceptibility of the generated art-styled stego image with from plain style-transferred images. The lack of the original cover image makes it difficult for the opponent learning a steganalyzer to identify the stego. The recommended approach can successfully withstand existing steganalysis techniques and attain the embedding capacity of 3 bits per pixel for a color image, according to experimental results.

Cervical cancer remains a major public health problem. Despite the screening programs, cervical cancer is the second most commonly diagnosed cancer. Most of the cases occur in less developed countries, and it is the third leading cause of cancer death among females. In 2000–2007, the five-year relative survival rate for European women diagnosed with cervical cancer was 62%.[1] Standard treatment for locally advanced cervical cancer reveals external beam radiotherapy (EBRT) with concurrent chemotherapy followed by image-guided adaptive brachytherapy (IGABT) boost [2, 3]. In the last years, the Gynaecological (GYN) working group composed of Group Européen de Curiethérapie-European Society for Therapeutic Radiology and Oncology (GEC-ESTRO) has developed new recommendations for the treatment of cervical cancer based on IGABT. The treatment plan includes 3-dimensional (3D) imaging based on magnetic resonance imaging (MRI) or computed tomography (CT), adaptive to the target volume and organ at risk [4–6]. The brachytherapy insertion is made under anaesthesia. At the time of the application insertion, the ultrasound is used to guide the dilatation of the uterine canal and assess the depth of the uterine cavity. In this paper, we review the data available in international literature about the use of ultrasound (US) in brachytherapy treatment of cervical cancer.

Image encryption based on chaotic maps is an important way to ensure the secure communication of digital multimedia on the Internet. To improve the encryption performance and security of image encryption systems, a new image encryption algorithm is proposed by employing a compound chaotic map and random cyclic shift. Firstly, an improved Hybrid chaotic system is designed by coupling Logistic, ICMIC, Tent, and Chebyshev maps (HLITC). Comparison tests with previous chaotic maps in terms of chaotic trajectory, Lyapunov exponent, and Kolmogorov entropy illustrate the new hybrid chaotic map has better chaotic performance. Then the proposed HLITC chaotic system is used to develop a new chaotic image encryption scheme with the double cyclic shift. The improved HLITC chaotic system is performed to generate key sequences used in the image scrambling and diffusion stage. The spiral transformation controlled by chaotic sequence is used to scramble the pixels of the plaintext image, while the XOR operation based on a chaotic map is used for pixel diffusion. Extensive experiments of statistical analysis, key sensitivity, and keyspace analysis are conducted. Experimental results show the proposed encryption scheme has good robustness against brute force attacks, statistical attacks, and differential attacks, and is more effective than many existing chaotic image encryption algorithms.

This work tackles the problem of image restoration, a crucial task in many fields of applied sciences, focusing on removing degradation caused by blur and noise during the acquisition process. Drawing inspiration from the multi-penalty approach based on the Uniform Penalty principle introduced in [Bortolotti et al. arXiv.math.NA/2309.14163], we develop here a new image restoration model and an iterative algorithm for its effective solution. The model incorporates pixel-wise regularization terms and establishes a rule for parameters selection, aiming to restore images through the solution of a sequence of constrained optimization problems. To achieve this, we present a modified version of the Newton Projection method, adapted to multi-penalty scenarios, and prove its convergence. Numerical experiments demonstrate the efficacy of the method in eliminating noise and blur while preserving the image edges.

This study proposes a method for image matching between infrared(IR)-RGB images using a deep learning network to estimate the deformation field. We propose a deformation field generator (DFG) that estimates the deformation field of the transformation matrix to match each pixel or IR image to the RGB image. DFG is a network that receives IR and RGB images as input; the output size is two channels and has the sample resolution as the input image. By warping the IR image through a grid-sampler that warps the image according to the value of the deformation field, we can obtain a warped IR image that matches the RGB image. Additionally, to check whether the warped IR image matched the RGB image, the masking images detecting the segmentation of objects were photographed in two images. Without directly comparing IR and RGB images, we proposed mask loss that warps the IR mask image through the deformation field and grid sampler and then compares the warped IR mask image with the RGB mask image. Mask loss solves the spatial similarity comparison problem with multi-modality images, such as IR and RGB images, by comparing the mask image with the same modality image as the mask image.

The Double Random Phase Encoding (DRPE) image encryption method has garnered significant attention in color image processing and optical encryption, thanks to its parallel encryption of R, G, B. However, DRPE-based color image encryption faces two challenges. Firstly, it disregards the correlation of R, G, and B, compromising the encrypted image's robustness. Secondly, DRPE schemes relying on Discrete Fourier Transform (DFT) and Discrete Fractional Fourier Transform (DFRFT) are vulnerable to linear attacks, such as Known Plaintext Attack (KPA) and Chosen Plaintext Attack (CPA). Quantum walk stands out as a remarkable tool for designing modern cryptographic mechanisms, offering resistance to potential attacks from both classical and quantum computers.Therefore, this study presents an optical color image encryption algorithm that combines two-dimensional quantum walk with 24-bit plane permutation, dubbed OCT. This approach employs pseudo-random numbers generated by Two-Dimensional Quantum Walking (TDQW) for phase modulation in DRPE and scrambles the encrypted image's real and imaginary parts using the Generalized Arnold Transform. The 24-bit plane permutation helps reduce correlation of the R, G, B, while the Generalized Arnold Transform bolsters DRPE's resistance to linear attacks. By incorporating TDQW, the key space is significantly expanded. Experimental results validate the effectiveness and security of proposed method.

Color image binarization plays a pivotal role in image preprocessing work, significantly impacting subsequent tasks, particularly in text recognition. This paper concentrates on Document Image Binarization (DIB), aiming to separate a image into foreground (text) and background (non-text content). Through a thorough analysis of conventional and deep learning-based approaches, we conclude that prevailing DIB methods leverage deep learning technology. Furthermore, we explore the receptive fields pre- and post-network training to underscore the Transformer model's advantages. Subsequently, we introduce a lightweight model based on the U-Net structure, enhanced with the Mobile ViT module to better capture global information features in document images. Given its adeptness at learning both local and global features, our proposed model exhibits superior performance on two standard datasets (DIBCO2012 and DIBCO2017) compared to state-of-the-art methods. Notably, our proposed DIB method presents a straightforward end-to-end model devoid of additional image preprocessing or post-processing. Moreover, its parameter count is less than a quarter of the HIP'23 model, which achives best results on three datasets(DIBCO2012, DIBCO2017 and DIBCO2018). Finally, two sets of ablation experiments were conducted to verify the effectiveness of the proposed binarization model.

Deep Learning is a recent and important addition to the computational toolbox available for image reconstruction in fluorescence microscopy. We review state-of-the-art applications such as image restoration, super-resolution, and light-field imaging, and discuss how the latest Deep Learning research can be applied to other image reconstruction tasks such as structured illumination, spectral deconvolution, and sample stabilisation. Despite its successes, Deep Learning also poses significant challenges, has often misunderstood capabilities, and overlooked limits. We will address key questions, such as: What are the challenges in obtaining training data? Can we discover structures not present in the training data? And, what is the danger of inferring unsubstantiated image details?

An important aspect of PET imaging in clinical application is the localization and detection of tumors and lesions by administering a predetermined amount of radiotracer. This allows for example, a detailed view of what is going inside the patient body in cellular level. The quality of PET image is strongly dependent on the amount of administrated radiotracer and the patient’s body parameters. As the amount of injection radiotracer increases, the quality of resulting image increases and the lesion detection efficiency increases. The PET examiner society recognizes that any dose of radiotracer is associated with some possible radiation risks. It can harmful to the patient if essential PET imaging session is not made due to fear of radiation risk. In order to ensure the highest quality diagnosis and the smallest radiation risk, the patient should receive the smallest amount of radiotracer that provide image with sufficient quality. Our study is focused on proposing an efficient PET simulation tool that predict the smallest possible amount of administrated radiotracer to provides the appropriate diagnostic information based on significant patient’s body parameters (weight, age) at fixed scanning to improve the clinical diagnostic process in term of tumor detecting and localization. We have built a model of particular PET scanner and model of patient based on real MRI image and digital anthropomorphic phantom of our region of interest (brain). We have performed Monte Carlo simulation for whole PET procedure with special parameter In evaluating stage, a dataset of 60 patient is used and 11 independent dose prediction simulation for each patient are performed. We conclude that our simulator perform a desirable and efficient prediction of injection radiotracer amount that optimizes the current clinical amount up to 28%. In addition, we found that the total injected radiotracer dosage for adult patients are mostly affected when considering patient weight rather than patient age.

Parallax processing and structure preservation has long been important and challenging tasks in image stitching. In this paper, an image stitching method based on sliding camera to eliminate perspective deformation and asymmetric optical flow to solve parallax is proposed. By maintaining the viewpoint of two input images in the mosaic non-overlapping area and creating a virtual camera by interpolation in the overlapping area, the viewpoint is gradually transformed from one to another image view-point so as to complete the smooth transition of the two image viewpoints and reduce perspective deformation. Two coarsely aligned warped images are generated with the help of a global projection plane. After that, the optical flow propagation and gradient descent method are used to quickly calculate the bidirectional asymmetric optical flow between the two warped images, and the optical flow-based method is used to further align the two warped images to reduce parallax. In the image blending, the softmax function and registration error are used to adjust the width of the blending area, further eliminating ghosting and reduce parallax. Finally, the comparative experiments show that our method can effectively eliminate perspective deformation, reduce misalignment, and save running time.

This paper describes the first results of an Image Recognition Based Location (IRBL) for mobile application focusing on the procedure to generate a Database of range images (RGB-D). In an indoor environment, to estimate the camera position and orientation, a prior spatial knowledge of the surrounding is needed. In order to achieve this objective a complete 3D survey of two different environment (Bangbae metro station of Seoul and E.T.R.I. building in Daejeon – Republic of Korea) was performed using LiDAR (Light Detection And Ranging) instrument and the obtained scans were processed in order to obtain a spatial model of the environments. From this, two databases of reference images were generated using a specific software realized by the Geomatics group of Politecnico di Torino (ScanToRGBDImage). This tool allow to generate synthetically different RGB-D images) centered in the each scan position in the environment. Later, the external parameters (X, Y, Z, ω, φ, κ) and the range information extracted from the DB images retrieved, are used as reference information for pose estimation of a set of acquired mobile pictures in the IRBL procedure. In this paper the survey operations, the approach for generating the RGB-D images and the IRB strategy are reported. Finally the analysis of the results and the validation test are described.