Research on anticipation within sport has been recently advanced by the isolation of visual spatial frequencies. The present study seeks to adapt this body of work for the context of anticipating penalty kicks within soccer. Across two experiments, participants had to anticipate the direction of pre-recorded penalty kicks that were occluded at the point of ball contact. The penalty kicks were presented with low (LSF; 'blurred'), high (HSF; 'edge detection' [i.e., sharp image outlines]) or unfiltered (i.e., original footage) spatial frequencies. Experiment 1 involved a lab-controlled setting using a life-sized display of the non-deceptive penalty kicks with outfield participants, which indicated no effect of visual condition. Experiment 2 involved a remote online protocol that displayed deceptive and non-deceptive penalty kicks with goalkeeper participants. While there was a decline in the anticipation of deceptive compared to non-deceptive kicks for the unfiltered condition, there was no such decline for the LSF and HSF conditions. We suggest that the LSF and HSF conditions were able to overcome deception because of the isolating global kinematic and local detailed cues, respectively.

MAFNet: A multi-modal adaptive fusion network-based approach for individual building extraction from oblique photogrammetry

A telecentric vision system tailored for high-precision dimensional measurement: Calibration and subpixel edge detection

Abstract -Edge detection is a fundamental operation inimage processing, widely used in applications such as object recognition, medical imaging, pattern recognition, and computer vision. It identifies significant intensity changes in an image that correspond to object boundaries and structural details. Among various techniques, the Sobel operator is commonly used due to its simplicity and efficiency in approximating image gradients using horizontal and vertical convolution masks. However, the conventional Sobel method has limitations, including sensitivity to noise, restricted directional detection, and reduced accuracy in capturing fine or diagonal edges. To address these issues, this project proposes a low- power Sobel Edge-8 detection algorithm implemented using Verilog. The enhanced approach computes gradients in eight different directions, enabling better detection of edges with varying orientations and finer details. The system is designed using Verilog HDL and evaluated through simulation and synthesisusingXilinxVivadoandMATLABR2020a.Results show improved edge detection accuracy with low computational complexity, making the design suitable forreal-time image processing and embedded vision applications due to its high speed, efficiency, reliability, and low power consumption. Keywords:Sobeledgedetector,Vivado,Matlab.

Accurate identification of blood groups is essential in medical diagnostics, transfusion management, and emergency healthcare. Conventional blood typing methods are typically manual, time-consuming, and require skilled laboratory personnel, which can lead to delays and potential human errors. This paper presents an automated system titled “AI-Based Blood Group Classification and Prediction Using Image Processing,” which leverages artificial intelligence and computer vision techniques to improve the efficiency and accuracy of blood group detection.The proposed system utilizes image processing methods to analyze microscopic images of blood samples and identify agglutination patterns associated with different blood groups. Features are extracted using techniques such as segmentation, edge detection, and pattern recognition, and are then classified using machine learning and deep learning models such as Convolutional Neural Networks (CNN). The system is capable of accurately classifying blood groups (A, B, AB, and O) and predicting Rh factors with high precision. Experimental results demonstrate that the approach significantly reduces processing time, minimizes human intervention, and improves diagnostic reliability, making it a valuable tool for automated and scalable blood typing in healthcare systems.

With the rapid urbanization, the problem of municipal solid waste has become increasingly severe, and waste classification has become a key measure to achieve sustainable development. However, traditional manual sorting is inefficient and expensive, and the existing automatic identification methods based on deep learning have different limitations. In order to solve these problems, this paper proposes a waste classification scheme that combines Canny edge detection pretreatment with the lightweight ShuffleNet v2 network. First, denoise the image, and then use Canny edge detection to extract the waste profile to enhance the target characteristics and suppress background interference. Finally, enter the processed images into the ShuffleNet v2 network for classification. Experiments conducted on the kitchen garbage subset of Huawei’s garbage classification data set show that the proposed method achieves superior overall performance than SSD, YOLOv3 and unprocessed ShuffleNet v2. While maintaining the advantages of lightweight architecture, the method significantly improves the identification accuracy, thus expanding the technical path of garbage classification and accelerating its intelligent development.

This paper presents Ant Colony Optimization (ACO) along with genetic algorithm-based optimization technique for edge detection. The problem of edge detection is formulated as one of choosing a minimum cost edge configuration. ACO can be used to find good solutions to combinatorial optimization problems that can be transformed into the problem of finding good paths through a weighted construction graph. Similarly, the genetic algorithm views edge configurations as two-dimensional chromosomes with fitness values inversely proportional to their costs. The design of the crossover and the mutation operators in the context of the twodimensional chromosomal representation is described. In this paper, an edge detection technique that is based on ACO and genetic algorithm is presented. The proposed method establishes a pheromone matrix that represents the edge information at each pixel based on the routes formed by the ants dispatched on the image. The movement of the ants is guided by the local variation in the image’s intensity values. The proposed ACO-based edge detection method takes advantage of the improvements introduced in ant colony system, one of the main extensions to the original ant system.In genetic algorithm, the design of the crossover and the mutation operators in the context of the two-dimensional chromosomal representation is described. The knowledgeaugmented mutation operator which exploits knowledge of the local edge structure is shown to result in rapid convergence. The incorporation of meta-level operators and strategies such as the elitism strategy and various combinations of meta-level operators can be tested on synthetic and natural images.

Blind super-resolution (SR) aims to reconstruct high-resolution images from low-quality inputs under unknown degradation conditions. While numerous blind SR methods have been proposed in recent years, they still face critical limitations. Most approaches perform well under specific degradation patterns but struggle with complex scenarios involving multiple degradation factors and varying noise levels. This often leads to loss of structural integrity and fine details, resulting in suboptimal restoration quality. Furthermore, existing methods typically rely on convolutional neural networks (CNNs) with limited receptive fields, which hinders effective cross-domain information integration. Their inability to capture long-range dependencies compromises the reconstruction of global structures. In edge detection, conventional techniques frequently produce inaccurate or false edges, further degrading the quality of cross-domain integration and image restoration. To address these challenges, we propose Structural Integrity and Texture Fidelity Transformer (SITFFormer), a novel transformer-based framework for blind single-image SR. Our approach incorporates the Canny edge detection algorithm to accurately preserve true edges and suppress noise-induced artifacts, enhancing edge localization in complex and noisy environments. We also introduce the Cross-Domain Structure-Texture-Aware Network (CDSTNet), designed to integrate intra-domain and cross-domain features for comprehensive structure preservation and texture recovery. CDSTNet comprises two key modules: Cross-Domain Integration (CDI) that fuses intra- and cross-domain features to retain structural and textural details. Cross-Domain Learnable Attention (CDLA) that explores global dependencies, adaptively refines feature similarity, and filters out redundant non-local information. Both modules are equipped with a Cross-Attention Mechanism (CAM) to facilitate effective interaction and complementarity between domains, enhancing reconstruction fidelity. Extensive experiments on synthetic, noisy, and real-world datasets demonstrate that SITFFormer surpasses state-of-the-art methods in quantitative performance and visual quality, particularly in preserving structural integrity and recovering fine textures.

Accurate lung segmentation from chest X-rays is crucial for early disease diagnosis and monitoring of pulmonary diseases. For lung segmentation, CNN-based architecture plays a crucial role but still lacks some edge boundary detection issues while working with low-feature images. Previous research shows that there is still an issue in proper image segmentation with proper edge detection as in earlier methods like TVAC, Active Spline, Random Walker, U-Net as they focus on only high-level feature extraction from images and not low-level features, resulting in poor boundary detection. This research addresses this gap by proposing an Edge Attention-based U-Net architecture for proper edge boundary detection. This Edge Attention-based U-Net uses edge attention mechanisms to precisely locate lung boundaries while working with noisy and challenging X-ray imaging conditions. This improves segmentation accuracy and works efficiently in noisy situations, making it suitable for real-world clinical applications. Unlike previous methods the EA-U-Net surpasses them significantly. This superiority is evident through comprehensive comparisons conducted on the same Montgomery dataset of X-ray images during the training, validation, and testing phases. The EA-UNet consistently outperforms its predecessors, demonstrating higher accuracy metrics, including Dice mean, Jaccard Mean, and Pixel accuracy, while exhibiting superior boundary detection capabilities. The EA-U-Net's exceptional performance in lung segmentation enhances reliability and paves the way for advancements in computer-aided diagnosis and personalized healthcare. By providing clinicians with more accurate and reliable tools for analyzing chest X-rays, the EA-U-Net contributes significantly to improving patient care and medical decision-making processes.

Reconstructing shredded and ripped-up documents is an essential component of forensic investigations, intelligence gathering, and legal evidence restoration. Criminals frequently destroy evidence by tearing or shredding documents to conceal information related to fraud, financial crimes, identity theft, and confidential operations. Traditional reconstruction methods rely heavily on manual labor, expert judgment, and time-consuming physical assembly. These manual processes are limited in scalability and accuracy, especially when handling thousands of irregular fragments generated by cross-cut shredders or irregular tearing patterns. With advancements in artificial intelligence, deep learning has emerged as a promising solution for automating the reconstruction of shredded documents. This paper presents a deep learning–driven framework that integrates computer vision, convolutional neural networks (CNNs), feature extraction, edge detection, similarity learning, and transformer-based OCR to reconstruct shredded and ripped documents with high accuracy. The proposed methodology begins with preprocessing and segmentation of shredded fragments, followed by CNNbased feature extraction to capture edge patterns, texture consistency, and shape signatures. A Siamese network architecture is employed to evaluate the similarity between fragment pairs and determine potential adjacency relationships. The reconstruction module utilizes graph-based alignment algorithms that combine edge compatibility scores with spatial arrangement predictions to generate a candidate layout for the reassembled document. Once reconstruction is complete or partially complete, an OCR-based text extraction module retrieves textual content from the reassembled page to support forensic interpretation. Experimental results demonstrate the model’s capability to reconstruct mechanically shredded, hand-torn, and irregularly fragmented documents under varying degrees of damage. Performance metrics indicate significant improvements in accuracy, time efficiency, and completeness compared to traditional methods. This research provides a scalable, intelligent, and automated approach for forensic teams, reducing reliance on manual sorting and improving investigation efficiency. The deep learning pipeline has the potential to assist law enforcement agencies, digital forensics experts, and intelligence organizations in cases where recovering destroyed documents is critical for solving crimes or preventing security threats. Overall, the proposed framework advances the application of AI in forensic science and establishes a foundation for future enhancements using generative models and multimodal learning.

Computational ghost imaging (CGI) for edge detection, particularly speckle-shifting ghost imaging (SSGI), faces a severe trade-off between sampling cost and edge quality. We propose energy-descending ordered compressed ghost edge imaging (EDO-CGEI), an adaptive edge detection method that reorders binary illumination patterns in descending order of energy. Simulations and experiments show that EDO-CGEI outperforms existing schemes at low sampling rates, achieving a satisfactory 256×256 edge image with a sampling rate of only 15%. This approach effectively pushes forward the trade-off between efficiency and clarity in ghost imaging edge detection under resource constraints.

Digital image processing is a field of computer science that focuses on analyzing and interpreting digital images to extract meaningful information. One of its applications is Optical Mark Recognition (OMR), a technology used to detect marks on documents. OMR is commonly utilized for evaluating answer sheets. However, conventional OMR systems typically rely on specialized scanners that are expensive and lack flexibility. Although Computer-Based Testing (CBT) offers the convenience of automated scoring, its implementation heavily depends on the availability of technological infrastructure such as computers, internet connectivity, and a stable power supply. This study develops a real-time Optical Mark Recognition (OMR) application capable of performing answer sheet assessment directly on the client side. The system utilizes the DexiNed method for edge detection of the answer areas. The application is web-based and built using JavaScript and OpenCV.js to process images directly from the user's device camera. Testing was carried out under various scenarios, including different lighting intensities, scanner positions, pencil types, and shading quality. The results show that the application can detect marked answers with an accuracy up to 100%, although some limitations were observed under certain technical conditions. Weaknesses were found in low lighting conditions using a 5 watt lamp at a distance of 3 meters, light reflections, and the camera angle was not aligned with the answer sheet. Overall, the application provides an efficient and flexible alternative for answer sheet assessment without requiring dedicated scanning devices, making it suitable for educational institutions with limited infrastructure.

Print, check, repeat: digital quality by design for 3D-printed medicines using OpenAI models.

In-sensor computing is proposed to reduce energy expenditure and processing latency by unifying sensing and computation within the hardware layer, yet the application under extreme illuminating scenario remains constrained by simultaneously obtaining broadband responsivity, large linear dynamic range and fast response. Here, we report a fully vapor-deposited graded Pb-Sn alloyed perovskite heterojunction photodiode with improved crystal quality. It enables the detection of light from visible to infrared light with a 230 dB linear dynamic range and 33 ns response time. We also develop a wafer-scale imaging processor by integrating the photodiode to a reconfigurable array. With this approach, we demonstrate biomedical detection and spatiotemporal trajectory encoding. The in-sensor processor realizes low-power high-resolution visible to infrared wavelength edge detection, adaptive background suppression under dim light and noise-immune high-speed dynamic imaging. Our results extend the options for in-sensor computing hardware, and thus pave a way toward practical artificial intelligent machine vision.

Metasurfaces are confined to static functionalities and lack reconfigurability-a key characteristic urgently needed for their practical applications in dynamic environments. To address the critical challenges of traditional metasurfaces, including fixed functions, polarization dependence, bulky imaging systems, difficulties in integrating edge detection with bright-field imaging, and the requirement for additional digital post-processing, we propose to leverage the dynamic reconfigurability enabled by phase change materials, combining it with polarization insensitivity and omnidirectional dynamic switching between high-resolution edge extraction and clear bright-field imaging. In this paper, we propose a dual-polarization Laplacian differentiator operating in the terahertz band based on a nonlocal perforated metasurface, with dynamic function switching achieved by regulating the phase transition of vanadium dioxide (VO2). When VO2 is in the insulating state, the device can directly perform two-dimensional second-order image edge detection. When VO2 transitions to the metallic state, it switches to bright-field imaging mode. The Optical Transfer Function (OTF) required for Laplacian operations is achieved by exciting the Quasi-Bound States in the Continuum (Q-BIC) mode under p- and s-polarized terahertz wave illumination, which endows the device with an angular dispersive response matching the Laplacian operator's requirements. This differentiator offers dual-polarization-compatible edge detection, and its efficient, high-performance function switching-coupled with the benefits of dual-polarization imaging-provides robust technical support for terahertz-band applications including machine vision, biomedical detection, and image processing.

ABSTRACT Riverbank erosion is a natural process in meandering rivers that contributes to sediment supply and geomorphic diversity, yet it can threaten infrastructure and human activities within the floodplain. Recently, many studies have used high‐resolution remote sensing technologies to measure bank erosion, but they often focus on technical aspects or platform comparisons rather than analyzing the geomorphic and hydrological drivers of its spatial variability. This research aimed to investigate short‐term patterns and controlling factors of bank erosion at 10 meander bends along an actively eroding gravel‐bed river. Repeated field surveys involving UAV (unmanned aerial vehicle) data acquisition and GNSS (Global Navigation Satellite System) measurements were conducted between March 2022 and May 2024, covering periods of both significant floods and low‐flow conditions. Three key bank erosion metrics were calculated: bank retreat rate, area of eroded floodplain, and volume of eroded material. Riverbank lines were automatically vectorized using Laplacian edge detection filtering of digital surface models (DSMs) in GIS, and erosion volumes were quantified through temporal DSM differencing. The results indicated that erosion rates were positively correlated with meander sinuosity only during the high discharge period. Greater erosion was generally measured in meanders with grass‐covered banks compared to those stabilized by woody vegetation. This study contributes to understanding the short‐term dynamics of riverbank erosion at high spatial resolution, particularly under varying flow conditions. It also presents a practical workflow based on UAV data for rapid bankline delineation and erosion quantification, offering a valuable tool for river management.

Edge detection is a fundamental aspect of computer vision, facilitating the extraction of crucial features such as corners, edges, and line segments, which are vital for Visual Odometry-based applications. While adding more stages to an edge detector can enhance feature precision, it also increases time consumption and resource requirements, necessitating hardware optimizations. To address these challenges, this paper presents a hardware/software co-design for an efficient pipeline implementation of a Multi-level Edge Detector (MED) on a low-cost FPGA-based heterogeneous architecture. Leveraging this framework, we developed cascading duplicate shift registers based on the Single-Task (ST) mode of OpenCL, which achieves an efficient pipeline execution model for conventional cascade filters. Our ST implementation of the MED significantly outperforms the traditional NDRange implementation in both execution time and resource utilization on the targeted FPGA platform. This allows for effective deployment on the low-cost embedded DE1-SoC, with results validated through comparisons to the NVIDIA Jetson Nano GPU.

Face detection and recognition technologies are increasingly vital in security and surveillance. This article covers two main areas with real-time application: the basics of image processing, such as edge detection and filters, and an overview of global methods for face detection and recognition. The Viola-Jones algorithm, based on Haar-like features and a cascade of classifiers, has been utilized for detecting objects within the images. MATLAB’s toolbox has been used to further enhance face detection performance by identifying human facial patterns in webcam-captured frames. For face recognition, the algorithm compares a detected face with reference images, counting zero-valued differences. If these zero elements exceed a certain threshold, a match is confirmed, indicating a high similarity between the captured face and the reference image. This study presents a low-cost MATLAB prototype emphasizing practical, educational demonstration of real-time face analysis.

A digital twin approach for real-time monitoring of amasi acidity using non-invasive computer vision, IoT, and machine learning

Dual-functional fractal-fractional Sobel operator for efficient image enhancement and edge detection