Skin cancer is one of the widespread diseases that typically develop on the skin due to continuous exposure to sunlight. Although cancer can appear on any part of the human body, skin cancer reports account for over half of all cancer occurrences worldwide. There are substantial obstacles to the precise diagnosis and classification of skin lesions because of the morphological variety and indistinguishable characteristics across skin malignancies. Recently, Deep Learning models have been used in the field of image-based lesion diagnosis, and it has demonstrated diagnostic efficiency on par with that of dermatologists. To increase classification efficiency and accuracy for skin lesions, a cutting-edge multi-layer deep Convolutional Neural Network (CNN) termed SkinLesNet has been built in this study. The ResNetV50 and VGG16 models have been carefully compared to review the performance of the proposed model. The dataset used in this study, PAD-UFES-20, contains 1314 samples in total and includes three common forms of skin lesions. The proposed approach, SkinLesNet, significantly outperforms the well-known compared models in the given conditions

In autonomous driving systems, high-speed and real-time image processing, along with object recognition, are crucial technologies. This paper builds upon the research achievements in in-dustrial item sorting systems and proposes an object recognition and sorting system for auton-omous driving. In industrial sorting lines, goods sorting robots often need to work at high speeds to efficiently sort large volumes of items. This poses a challenge to the robot's real-time vision and sorting capabilities, making it both practical and economically viable to implement a real-time and low-cost sorting system in a real-world industrial sorting line. Existing sorting systems have limitations such as high cost, high computing resource consumption, and high power consump-tion. These issues lead to the fact that existing sorting systems are typically used only in large industrial plants. In this paper, we design a high-speed, low-cost, low-resource-consumption FPGA (Field-Programmable Gate Array) based item sorting system that achieves similar perfor-mance to current mainstream sorting systems at a lower cost and consumption than existing sorting systems. The recognition part employs a morphological recognition method, which segments the image using a frame difference algorithm and then extracts the color and shape features of the items. To handle sorting, a six-degree-of-freedom robotic arm is introduced in the sorting segment. The improved cubic B-spline interpolation algorithm is employed to plan the motion trajectory and consequently control the robotic arm to execute the corresponding actions. Through a series of experiments, this system achieves an average recognition delay of 25.26ms, ensures smooth operation of the gripping motion trajectory, minimizes resource consumption, and reduces implementation costs.

Deepfakes are manipulated or altered images, or video, that are created using deep learning models with high levels of photorealism. The two popular methods of producing a deepfake are based on either convolutional neural networks (CNN), or autoencoders. Deepfakes created using CNN comparatively show higher qualities of realism, yet oftentimes leave artifacts and distortions in the generated media that can be detected using machine learning and deep learning algorithms. In recent years, there has been an influx of periocular image and video data because of the increase usage of face masks. By wearing masks, much of what is used for facial recognition is hidden, leaving only the periocular region visible to an observer. This loss of vital information leads to easier misidentification of media, allowing deepfakes to less likely be identified as fake. In this work, feature extraction methods, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradients (HOG), and CNN, are used to train an ensemble deep learning model to detect deepfakes in videos on a frame-by-frame level based on the periocular region. Our proposed model is able to distinguish original and manipulated images with accuracies around 98.9 percent, which is an improvement to previous works by combining SIFT and HOG for deepfake detection in convolutional neural networks.

Maze navigation using one or more robots has become a recurring challenge in scientific literature and real life practice, with fleets having to find faster and better ways to navigate environments such as a travel hub (e.g. airports) or to evacuate a disaster zone. Many methods have been used to solve this issue, including the implementation of a variety of sensors and other signal receiving systems. Most interestingly, camera-based techniques have increasingly become more popular in this kind of applications, given their robustness and scalability. In this paper, we have implemented an end-to-end strategy to address this scenario, allowing a robot to solve a maze in an autonomous way, by using computer vision and path planning. In addition, this robot shares the generated knowledge to another by means of communication protocols, having to adapt its mechanical characteristics to be able to solve the same challenge. The paper presents experimental validation of the four components of this solution, namely camera calibration, maze mapping, path planning and robot communication. Finally, we present the integration and functionality of these methods applied in a pair of NAO robots.

To build a representation of what we see, the human brain recruits regions throughout the visual cortex in cascading sequence. Recently, an approach was proposed to evaluate the dynamics of visual perception in high spatiotemporal resolution at the scale of the whole brain. This method combined functional magnetic resonance imaging (fMRI) data with magnetoencephalography (MEG) data using representational similarity analysis and revealed a hierarchical progression from primary visual cortex through the dorsal and ventral streams. To assess the replicability of this method, here we present results of a visual recognition neuro-imaging fusion experiment, and compare them within and across experimental settings. We evaluated the reliability of this method by assessing the consistency of the results under similar test conditions, showing high agreement within participants. We then generalized these results to a separate group of individuals and visual input by comparing them to the fMRI-MEG fusion data of Cichy et al. (2016), revealing a highly similar temporal progression recruiting both the dorsal and ventral streams. Together these results are a testament to the reproducibility of the fMRI-MEG fusion approach and allows for the interpretation of these spatiotemporal dynamic in a broader context.

Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot-spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point clouds by projecting them into 2D images and evaluating consistency with textual prompts. These methods benefit from the robust open-world understanding capabilities of visual-language pre-trained models and require no additional training. However, they face several challenges summarized as prompt ambiguity, image domain gap, view weights confusion, and feature deviation. In response to these challenges, we propose PointBLIP, a zero-training point cloud classification network based on the recently introduced BLIP-2 visual-language model. PointBLIP is adept at processing similarities between multi-images and multi-prompts. We separately introduce a novel method for point cloud zero-shot and few-shot classification, which involves comparing multiple features to achieve effective classification. Simultaneously, we enhance the input data quality for both the image and text sides of PointBLIP. In point cloud zero-shot classification tasks, we outperform state-of-the-art methods on three benchmark datasets. For few-shot classification tasks, to the best of our knowledge, we present the first zero-training few-shot point cloud method, surpassing previous works under the same conditions and showcasing comparable performance to full-training methods.

Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is a challenging problem. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Identifying objects in floor plan images is also challenging due to the variety of floor plans and different objects. We faced a problem in training our network because of the lack of publicly available datasets. Currently, available public datasets do not have enough images to train deep neural networks efficiently. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10000 images to address this issue. Our proposed method conveniently surpasses the previous state-of-the-art results on the SESYD dataset and sets impressive baseline results on the proposed SFPI dataset. The dataset can be downloaded from SFPI Dataset Link. We believe that the novel dataset enables the researcher to enhance the research in this domain further.

Color can direct visual attention to specific locations through bottom-up and top-down mechanisms. Using Continuous Flash Suppression (CFS) as way to investigate the factors that gate access to consciousness, the current study investigated whether color also directly affected the timing of conscious perception. Low or high spatial frequency (SF) gratings with different orientations were shown as targets to the non-dominant eye of human participants. CFS patterns were presented at a rate of 10Hz to the dominant eye to delay conscious perception of the targets, and participants had the task to report the target’s orientation as soon as they could see it. With low-SF targets, two types of color-based effects became evident. First, when the targets and the CFS patterns had different colors, the targets entered consciousness faster than in trials where the targets and CFS patterns had the same color. Second, when participants searched for a specific target color, targets that matched these search settings entered consciousness faster compared to conditions where the target color was irrelevant and could vary from trial to trial. Thus, the current study demonstrates that color is a central feature of human perception and leads to faster conscious perception of visual stimuli through bottom-up and top-down attentional mechanisms.

Until the 1950s, developmental dyslexia was defined as a hereditary visual disability, selectively affecting reading without compromising oral or non-verbal reasoning skills. This changed radically after the development of the phonological theory of dyslexia; this not only ruled out any role for visual processing in its aetiology, but also cast doubt on the use of discrepancy between reading and reasoning skills as a criterion for diagnosing it. Here I argue that this theory is set at too high a cognitive level to be explanatory; we need to understand the pathophysiological visual and auditory mechanisms that cause children’s phonological problems. I discuss how the ‘magnocellular theory’ attempts to do this in terms of slowed and error prone temporal processing which leads to dyslexics’ defective visual and auditory sequencing when attempting to read. I attempt to deal with the criticisms of this theory and show how it leads to a number of successful ways of helping dyslexic children to overcome their reading difficulties.

The European Space Agency (ESA) defines as Earth observation (EO) Level 2 information product a single-date multi-spectral (MS) image corrected for atmospheric, adjacency and topographic effects, stacked with its data-derived scene classification map (SCM), whose thematic map legend includes quality layers cloud and cloud-shadow. ESA EO Level 2 product generation is an inherently ill-posed computer vision (CV) problem never accomplished to date in operating mode by any EO data provider at the ground segment. Herein, it is considered: (I) necessary not sufficient pre-condition for the yet-unaccomplished dependent problems of semantic content-based image retrieval (SCBIR) and semantics-enabled information/knowledge discovery (SEIKD) in multi-source EO big data cubes. (II) Synonym of EO Analysis Ready Data (ARD) format. (III) Equivalent to a horizontal policy for background developments in Space Economy 4.0. In compliance with the GEO-CEOS Quality Assurance Framework for EO Calibration/Validation guidelines, to contribute toward filling an analytic and pragmatic information gap from multi-sensor EO big data to timely, comprehensive and operational EO value-adding information products and services, this work presents an innovative AutoCloud+ CV software toolbox for cloud and cloud-shadow quality layer detection in ESA EO Level 2 product. In vision, spatial information dominates color information. Inspired by this true-fact, the inherently ill-posed AutoCloud+ CV software was conditioned, designed and implemented to be “universal”, meaning fully automated (no human-machine interaction is required), near real-time, robust to changes in input data and scalable to changes in MS imaging sensor’s spatial and spectral resolution specifications.

This study advances the field of solar irradiance nowcasting by introducing a discrete-level classification approach, diverging from traditional continuous measurement methods. Grounded in a need for cost-effective and modular solutions, the research employs high-resolution computer vision coupled with a deep learning framework to predict Direct Normal Irradiance (DNI). By harnessing the capabilities of a Logitech C900 1080p HD camera and an NVIDIA Jetson module, the study achieves real-time data processing, pivotal for CSP systems' operational efficiency. The core of the methodology is the ResNet-50 convolutional neural network, refined via transfer learning on a bespoke dataset, culminating in a predictive accuracy of 85.78%. This discrete classification model contrasts with conventional, costly instruments like the MS-57, offering a novel and accessible alternative for DNI estimation. Such innovation not only demonstrates high predictive accuracy but also signifies a shift towards less resource-intensive and more adaptable solar energy forecasting tools, contributing a significant leap towards optimizing renewable energy systems.

Simultaneous Localization and Mapping (SLAM) is a crucial function for most autonomous systems, allowing them to both navigate through and create maps of unfamiliar surroundings. Traditional Visual SLAM, also commonly known as VSLAM, relies on frame-based cameras and structured processing pipelines, which face challenges in dynamic or low-light environments. However, recent advancements in event camera technology and neuromorphic processing offer promising opportunities to overcome these limitations. Event cameras inspired by biological vision systems capture the scenes asynchronously consuming minimal power but with higher temporal resolution. Neuromorphic processors, which are designed to mimic the parallel processing capabilities of the human brain, offer efficient computation for real-time data processing of event-based data streams. This paper provides a comprehensive overview of recent research efforts in integrating event cameras and neuromorphic processors into VSLAM systems. It discusses the principles behind event cameras and neuromorphic processors, highlighting their advantages over traditional sensing and processing methods. Furthermore, an in-depth survey was conducted on state-of-the-art approaches in event-based SLAM, including feature extraction, motion estimation, and map reconstruction techniques. Additionally, the integration of event cameras with neuromorphic processors, focusing on their synergistic benefits in terms of energy efficiency, robustness, and real-time performance was explored. The paper also discusses the challenges and open research questions in this emerging field, such as sensor calibration, data fusion, and algorithmic development. Finally, the potential applications and future directions for event-based SLAM systems are outlined, ranging from robotics and autonomous vehicles to augmented reality.

Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

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

A machine learning method for classifying Lung UltraSound is here proposed to pro- vide a point of care tool for supporting a safe, fast and accurate diagnosis, that can also be useful during a pandemic like as SARS-CoV-2. Given the advantages (e.g. safety, rapidity, portability, cost-effectiveness) provided by the ultrasound technology over other methods (e.g. X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest LUS public dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art. The complexity of this solution keeps the number of parameters in the same order as an EfficientNet-b0 by adopting specific design choices that are adaptive ensembling with a combination layer, ensembling performed on the deep features, minimal ensemble only two weak models. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where the focus is on an inaccurate weak model versus an accurate model.

AI is leveraging all aspects of life. Medical services are not untouched. Especially in the field of medical image processing and diagnosis. Big IT and Biotechnology companies are investing millions of dollars in medical and AI research. The recent outbreak of SARS COV-2 gave us a unique opportunity to study for a non interventional and sustainable AI solution. Lung disease remains a major healthcare challenge with high morbidity and mortality worldwide. The predominant lung disease was lung cancer. Until recently, the world has witnessed the global pandemic of COVID19, the Novel coronavirus outbreak. We have experienced how viral infection of lung and heart claimed thousands of lives worldwide. With the unprecedented advancement of Artificial Intelligence in recent years, Machine learning can be used to easily detect and classify medical imagery. It is much faster and most of the time more accurate than human radiologists. Once implemented, it is more cost-effective and time-saving. In our study, we evaluated the efficacy of Microsoft Cognitive Service to detect and classify COVID19 induced pneumonia from other Viral/Bacterial pneumonia based on X-Ray and CT images. We wanted to assess the implication and accuracy of the Automated ML-based Rapid Application Development (RAD) environment in the field of Medical Image diagnosis. This study will better equip us to respond with an ML-based diagnostic Decision Support System(DSS) for a Pandemic situation like COVID19. After optimization, the trained network achieved 96.8% Average Precision which was implemented as a Web Application for consumption. However, the same trained network did not perform like Web Application when ported to Smartphone for Real-time inference, which was our main interest of study. The authors believe, there is scope for further study on this issue. One of the main goals of this study was to develop and evaluate the performance of AI-powered Smartphone-based Real-time Applications. Facilitating primary diagnostic services in less equipped and understaffed rural healthcare centers of the world with unreliable internet service.

The ever-evolving ways attacker continues to im prove their phishing techniques to bypass existing state-of-the-art phishing detection methods pose a mountain of challenges to researchers in both industry and academia research due to the inability of current approaches to detect complex phishing attack. Thus, current anti-phishing methods remain vulnerable to complex phishing because of the increasingly sophistication tactics adopted by attacker coupled with the rate at which new tactics are being developed to evade detection. In this research, we proposed an adaptable framework that combines Deep learning and Randon Forest to read images, synthesize speech from deep-fake videos, and natural language processing at various predictions layered to significantly increase the performance of machine learning models for phishing attack detection.

Amidst the burgeoning global concerns surrounding skin cancer, the quest for precise and efficient diagnostic methodologies has intensified. Conventional diagnostic approaches relying on subjective visual inspection by dermatologists often grapple with subjectivity and resource constraints. This predicament underscores the critical role of Artificial Intelligence (AI) in revolutionizing diagnostic paradigms by significantly enhancing accuracy and accessibility. This study embarks on an extensive exploration of skin cancer classification, specifically targeting the intricate task of 8-class skin cancer classification. Employing cutting-edge deep learning models on the ISIC2019 dataset, a comprehensive analysis was conducted utilizing a diverse array of pre-trained ImageNet architectures and Vision Transformer models. To counteract the inherent class imbalance in skin cancer datasets, a pioneering "Naturalize" augmentation technique was introduced, leading to the creation of indispensable tools—the Naturalized 2.4K ISIC2019 and groundbreaking Naturalized 7.2K ISIC2019 datasets—catalyzing advancements in classification accuracy. The pivotal role of AI in mitigating the risks of misdiagnosis and under-diagnosis in skin cancer becomes evident through this research. AI’s proficiency in analyzing vast datasets and discerning subtle patterns augments the diagnostic prowess of dermatologists significantly. Integration of AI-powered systems in skin cancer diagnosis holds immense promise in facilitating early detection and substantially improving patient outcomes. The meticulous evaluation employed quantitative measures such as confusion matrices, classification reports, and visual analyses using Score-CAM across diverse dataset variations. Astonishingly, the culmination of these endeavors culminated in an unprecedented achievement—100% average accuracy, precision, recall, and F1-Score—within the groundbreaking Naturalized 7.2K ISIC2019 dataset. This remarkable feat underscores the transformative potential of AI-driven methodologies, exemplifying their prowess in redefining the landscape of skin cancer diagnosis and management. In summary, this research represents a pivotal stride towards redefining dermatological diagnosis, showcasing the remarkable impact of AI-powered solutions in surmounting the challenges inherent in skin cancer diagnosis. The attainment of 100% across crucial metrics within the Naturalized 7.2K ISIC2019 dataset serves as a testament to the transformative capabilities of AI-driven approaches in reshaping the trajectory of skin cancer diagnosis and patient care.

Recent progress in deep learning has led to accurate and efficient generic object detection networks. Training of highly reliable models depends on large datasets with highly textured and rich images. However, in real-world scenarios, the performance of the generic object detection system decreases when (i) occlusions hide the objects, (ii) objects are present in low-light images, or (iii) they are merged with background information. In this paper, we refer to all these situations as challenging environments. With the recent rapid development in generic object detection algorithms, notable progress has been observed in the field of object detection in challenging environments. However, there is no consolidated reference to cover state-of-the-art in this domain. To the best of our knowledge, this paper presents the first comprehensive overview, covering recent approaches that have tackled the problem of object detection in challenging environments. Furthermore, we present the quantitative and qualitative performance analysis of these approaches and discuss the currently available challenging datasets. Moreover, this paper investigates the performance of current state-of-the-art generic object detection algorithms by benchmarking results on the three well-known challenging datasets. Finally, we highlight several current shortcomings and outline future directions.

Loss of photoreceptors in retinal degenerative diseases also impacts the inner retina: bipolar cell dendrites retract, neurons rewire and protein expression changes. ON-bipolar cells represent an attractive target for optogenetic vision restoration. However, above-described maladaptations may negatively impact the quality of restored vision. To investigate this question, we employed human post-mortem retinas and transgenic rd1_Opto-mGluR6 mice expressing the optogenetic construct Opto-mGluR6 in ON-bipolar cells and carrying the retinal degeneration rd1 mutation. We found significant changes in delayed rectifier potassium channel expression in ON-bipolar cells of degenerative retinas. In particular, we found an increase in Kv1.3 expression already in early stages of degeneration. Immunohistochemistry localized Kv1.3 channels specifically to OBC axons. In whole-cell patch-clamp experiments, ON-bipolar cells in the degenerated murine retina were less responsive, which could be reversed by application of the specific Kv1.3 antagonist Psora-4. Notably, Kv1.3 block significantly increased the amplitude and kinetics of Opto-mGluR6-mediated light responses in ON-bipolar cells of the blind retina and increased the signal-to-noise ratio of light-triggered responses in retinal ganglion cells. We propose that reduction of Kv1.3 activity in the degenerated retina, either by pharmacological block or by KCNA3 gene silencing, could improve the quality of restored vision.

This paper presents a methodology to detect the erosion and progradation effects in the Atrato river delta, located in the Gulf of Urabá in Colombia using SAR (Synthetic Aperture Radar) data. Other authors have studied this area by using optical images, encountering difficulties given the persistent presence of clouds in this region. SAR imagery is rescaled, despeckled, composed, classified, registered and processed to obtain a heatmap that shows the overall changes during eight years (2016–2023) in one single image. Since this technology uses microwave active signals, the presence of clouds and other environmental phenomena was not a problem, and all the images from the selected dates could be processed and analyzed. Also, detection of the dynamic processes was obtained for every period considered in this study with respect to the previous one in time, calculating areas and detecting the regions subject to the erosion and progradation processes. The multitemporal analysis performed found that the newly created mouth is the most active area for these processes, coinciding with other studies. A comparison of these findings with the Oceanic Niño Index (ONI) showed a relative delayed coupling to the erosion process and a coupling of progradation with dry and wet seasons.

Tables in the document image are one of the most important entities since they contain crucial information. Therefore, accurate table detection can significantly improve information extraction from tables. In this work, we present a novel end-to-end trainable pipeline, HybridTabNet, for table detection in scanned document images. Our two-stage table detector uses the ResNeXt-101 backbone for feature extraction and Hybrid Task Cascade (HTC) to localize the tables in scanned document images. Moreover, we replace conventional convolutions with deformable convolutions in the backbone network. This enables our network to detect tables of arbitrary layouts precisely. We evaluate our approach comprehensively on ICDAR-13, ICDAR-17 POD, ICDAR-19, TableBank, Marmot, and UNLV. Apart from the ICDAR-17 POD dataset, our proposed HybridTabNet outperforms earlier state-of-the-art results without depending on pre and post-processing steps. Furthermore, to investigate how the proposed method generalizes unseen data, we conduct an exhaustive leave-one-out-evaluation. In comparison to prior state-of-the-art results, our method reduces the relative error by 27.57% on ICDAR-2019-TrackA-Modern, 42.64% on TableBank (Latex), 41.33% on TableBank (Word), 55.73% on TableBank (Latex + Word), 10% on Marmot, and 9.67% on UNLV dataset. The achieved results reflect the superior performance of the proposed method.

Visual Question Generation (VQG) from images is a rising research topic in both fields of natural language processing and computer vision. Although there are some recent efforts towards generating questions from images in the open domain, the VQG task in the medical domain has not been well-studied so far due to the lack of labeled data. In this paper, we introduce a goal-driven VQG approach for radiology images called VQGRaD that generates questions targeting specific image aspects such as modality and abnormality. In particular, we study generating natural language questions based on the visual content of the image and on additional information such as the image caption and the question category. VQGRaD encodes the dense vectors of different inputs into two latent spaces, which allows generating, for a specific question category, relevant questions about the images, with or without their captions. We also explore the impact of domain knowledge incorporation (e.g., medical entities and semantic types) and data augmentation techniques on visual question generation in the medical domain. Experiments performed on the VQA-RAD dataset of clinical visual questions showed that VQGRaD achieves 61.86% BLEU score and outperforms strong baselines. We also performed a blinded human evaluation of the grammaticality, fluency, and relevance of the generated questions. The human evaluation demonstrated the better quality of VQGRaD outputs and showed that incorporating medical entities improves the quality of the generated questions. Using the test data and evaluation process of the ImageCLEF 2020 VQA-Med challenge, we found that relying on the proposed data augmentation technique to generate new training samples by applying different kinds of transformations, can mitigate the lack of data, avoid overfitting, and bring a substantial improvement in medical VQG.

As people grow a custom to effortless outdoor navigation there is a rising demand for similar possibility indoors as well. Unfortunately, indoor localization, being one of the necessary requirements for navigation, continues to be problem without a clear solution. In this article we are proposing a method for an indoor positioning system using a single image. This is made possible using small preprocessed database of images with known control points as the only preprocessing needed. Using feature detection with SIFT algorithm we can look through the database and find image which is the most similar to the image taken by user. Pair of images is then used to find coordinates of database image using PnP problem. Furthermore, projection and essential matrices are determined allowing for the user image localization ~ determining the position of the user in indoor environment. Benefits of this approach lies in the single image being the only input from user and no requirements for new onsite infrastructure and thus enables a simpler realization for the building management.

In this paper, we redefine the boundaries of blood cell classification, expanding from 5 to 11 distinct blood cell types using the challenging 11-class PBC dataset. This shift enables a deeper understanding of blood cell diversity, overcoming previous limitations in medical image analysis. Our approach combines state-of-the-art deep learning techniques, including pre-trained ConvNets, ViTb16 models, and custom CNN architectures. We employ transfer learning, fine-tuning, and ensemble strategies, such as CBAM and Averaging ensembles, to achieve unprecedented accuracy and interpretability. Our fully fine-tuned EfficientNetV2 B0 model sets a new standard, with a macro-average precision, recall, and F1-score of 91%, 90%, and 90%, respectively, and an average accuracy of 93%. This breakthrough underscores the transformative potential of 11-class blood cell classification for more precise medical diagnoses. Moreover, our groundbreaking "Naturalize" augmentation technique produces remarkable results. The 2K-PBC dataset generated with "Naturalize" boasts a macro-average precision, recall, and F1-score of 97%, along with an average accuracy of 96% when leveraging the fully fine-tuned EfficientNetV2 B0 model. This innovation not only elevates classification performance but also addresses data scarcity and bias in medical deep learning. Our research marks a paradigm shift in blood cell classification, enabling more nuanced and insightful medical analyses. The "Naturalize" technique’s impact extends beyond blood cell classification, emphasizing the vital role of diverse and comprehensive datasets in advancing healthcare applications through deep learning.

Artificial intelligence (AI) and 3D printing (3DP) play critical roles in what is known as the 4th Industrial Revolution by developing data- and machine-intelligence-based integrated production technologies. This shift has led to increasingly complex design requirements and fabrication methods, posing several challenges for implementing design, fabrication process, and architectural quality standardization. This paper systematically reviews AI techniques applied in diverse stages of 3DP production in architecture. The research goals are to (1) offer a comprehensive critical analysis of the body of literature; (2) identify and categorize approaches to integrating AI in the production of 3D-printed structures; (3) identify and discuss challenges and opportunities of AI integration in architectural production of 3DP structures; and (4) identify gap and provide recommendations for future research. The findings indicate that topics related to AI applications are current and trending, receiving increasing attention from researchers in general and particularly those working in machine and deep learning, artificial neural networks, and pattern recognition. However, the potential of the application of AI in architectural production using additive manufacturing still needs to be explored. Considering this, the paper emphasizes the necessity of redefining traditional field boundaries and opening new opportunities in the sector.

Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes.

Gyroscopes are fascinating instruments with a history of about 200 years. When J.G.F. Bohnenberger presented his machine to his students in 1810 at the University of Tuebingen, Germany, nobody could have foreseen that this fascinating development would be used for complex orientation and positioning. At the University of Stuttgart, Germany, a collection of 160 exhibits is available and in transition for a sustainable future. Here, the systems are digitized in 2D, 2.5D and 3D and are made available for a world-wide community using OpenAccess platforms. The technologies being used are Computed Tomography, Computer Vision, Endoscopy and Photogrammetry. The workflows for combining voxel representations and colored point clouds are described, to create Digital Twins of the tangible assets. Advantages and disadvantages are discussed und work for near future is outlined in this new and challenging field of Tech Heritage digitization.

Deep Learning (DL) has made significant advances in computer vision with the advent of Vision Transformers (ViT). Unlike Convolutional Neural Networks (CNNs), ViTs use self-attention to extract both local and global features from image data, and then use residual connections to feed these features directly into a fully networked multilayer perceptron head. In hospitals, hematologists prepare peripheral blood smears (PBSs) and read them under a medical microscope to detect abnormalities in blood counts such as leukemia. However, this task is time-consuming and prone to human error. This study investigates the transfer learning process of Google ViT and ImageNet CNNs to automate the reading of PBSs. The study used two online PBS datasets, PBC and BCCD, and transferred them into balanced datasets to investigate the influence of data amount and noise immunity on both neural networks. The PBC results show that Google ViT is an excellent DL neural solution for data scarcity. The BCCD results show that Google ViT is superior to ImageNet CNNs in dealing with unclean, noisy image data because it is able to extract both global and local features and use residual connections, despite the additional time and computational overhead.

Background: This study addresses the burgeoning impact of Large Language Models (LLMs) such as ChatGPT on the integrity of online examinations and seeks to demonstrate latent and advanced LLM reasoning capabilities. The research devises an iterative self-reflective strategy for invoking critical thinking and higher-order reasoning in LLMs based on multimodal exam questions using visuals and text. Methods: The proposed strategy was demonstrated and evaluated on real exam questions by subject experts and the performance of ChatGPT (GPT-4) with vision was estimated on an additional dataset of 600 text descriptions of multimodal exam questions, focusing on its response to complex, visual, and textual prompts. Results: The results indicate that latent multi-hop reasoning capabilities can be invoked using the proposed self-reflective strategy, which can effectively steer ChatGPT towards correct answers by integrating critical thinking from each modality into the final response. Meanwhile, ChatGPT demonstrated considerable proficiency in being able to answer multimodal exam questions across 12 subjects. Conclusions: This work challenges findings from recent studies which claim that existing LLMs are unable to reason on complex multimodal tasks, and therefore this study underscores the need for enhanced online exam security measures like proctoring software, that can mitigate the potential misuse of AI technologies in educational settings.

Increased screen time during the COVID-19 pandemic and the accelerated incorporation of technology into daily practices have directly contributed to the increased prevalence of eye disease. The human eye is not built for continual technological use and must adjust to exposure to digital screens. Overexposure to technology can result in eye strain and an increased risk of eye diseases such as myopia with complications later in life, including retinal tears, cataracts, and macular degeneration. As vision and ocular diseases become more prevalent, the study of eye diseases, including their causes and treatments, is especially relevant. There is a need to prevent ocular diseases before they become a burden to individuals, their families, and their communities by better understanding the pathophysiology of ocular diseases. Several ocular diseases are thought to be caused by imbalances in reactive oxygen species (ROS) and autophagy. ROS refers to a class of highly reactive oxygen-containing molecules that can undergo damaging reactions with other molecules in the cell. Autophagy is a cellular process of self-eating whereby damaged, harmful, or dead material in cells is broken down to maintain cellular homeostasis. This paper discusses the role of ROS and autophagy in the pathogenesis of computer vision syndrome (CVS), digital eye strain (DES), myopia, cataracts, glaucoma, diabetic retinopathy (DR), age-related macular degeneration (AMD), optic nerve crush injury (OCN), optic nerve gliomas, and retinoblastoma. Lifestyle changes such as limiting screen time, ensuring adequate exposure to evening sunlight, and using blue light protection measures or protective eyewear are important in the prevention of eye disease. Nutrition also contributes significantly to eye health. A balanced diet rich in vitamins and antioxidants may help to prevent ROS and autophagy imbalance-induced eye disease. Medical and surgical treatments become necessary when preventative measures fail. This paper also addresses how government measures to decrease the onset of eye disease, including targeted programs to increase access to fresh vegetables and fruits in food deserts, are a critical macro-level avenue to reduce eye disease prevalence in the US, which according to the National Eye Institute, costs $139 billion yearly.