Search

Hot forging is one of the common manufacturing processes for producing brass workpieces. However forging produces flash which is a thin metal part around the desired part formed with an excessive material. Using robots with vision system to manipulate this workpiece has encountered several challenging issues, e.g. the uncertain shape of flash, color, reflection of brass surface, different lighting condition, and the uncertainty surrounding the position and orientation of the workpiece. In this research, Mask region-based convolutional neural network together with image processing is used to resolve these issues. The depth camera can provide images for visual detection. Machine learning Mask region-based convolutional neural network model was trained with color images and the position of the object is determined by the depth image. A dual arm 7 degree of freedom collaborative robot with proposed grasping strategy is used to grasp the workpiece that can be in inappropriate position and pose. Eventually, experiments were conducted to assess the visual detection process and the grasp planning of the robot. [ABSTRACT FROM AUTHOR]

Creutzfeldt–Jakob disease (CJD) is a rare, degenerative, and fatal brain disorder caused by abnormal proteins called prions. This research introduces a novel approach combining AI and graph theory to analyze histopathological microscopic images of brain tissues affected by CJD. The detection and quantification of spongiosis, characterized by the presence of vacuoles in the brain tissue, plays a crucial role in aiding the accurate diagnosis of CJD. The proposed methodology employs image processing techniques to identify these pathological features in high-resolution medical images. By developing an automatic pipeline for the detection of spongiosis, we aim to overcome some limitations of manual feature extraction. The results demonstrate that our method correctly identifies and characterize spongiosis and allows the extraction of features that will help to better understand the spongiosis patterns in different CJD patients. [ABSTRACT FROM AUTHOR]

The early detection of breast cancer is essential for improving treatment outcomes, and recent advancements in artificial intelligence (AI), combined with image processing techniques, have shown great potential in enhancing diagnostic accuracy. This study explores the effects of various image processing methods and AI models on the performance of early breast cancer diagnostic systems. By focusing on techniques such as Wiener filtering and total variation filtering, we aim to improve image quality and diagnostic precision. The novelty of this study lies in the comprehensive evaluation of these techniques across multiple medical imaging datasets, including a DCE-MRI dataset for breast-tumor image segmentation and classification (BreastDM) and the Breast Ultrasound Image (BUSI), Mammographic Image Analysis Society (MIAS), Breast Cancer Histopathological Image (BreakHis), and Digital Database for Screening Mammography (DDSM) datasets. The integration of advanced AI models, such as the vision transformer (ViT) and the U-KAN model—a U-Net structure combined with Kolmogorov–Arnold Networks (KANs)—is another key aspect, offering new insights into the efficacy of these approaches in different imaging contexts. Experiments revealed that Wiener filtering significantly improved image quality, achieving a peak signal-to-noise ratio (PSNR) of 23.06 dB and a structural similarity index measure (SSIM) of 0.79 using the BreastDM dataset and a PSNR of 20.09 dB with an SSIM of 0.35 using the BUSI dataset. When combined filtering techniques were applied, the results varied, with the MIAS dataset showing a decrease in SSIM and an increase in the mean squared error (MSE), while the BUSI dataset exhibited enhanced perceptual quality and structural preservation. The vision transformer (ViT) framework excelled in processing complex image data, particularly with the BreastDM and BUSI datasets. Notably, the Wiener filter using the BreastDM dataset resulted in an accuracy of 96.9% and a recall of 96.7%, while the combined filtering approach further enhanced these metrics to 99.3% accuracy and 98.3% recall. In the BUSI dataset, the Wiener filter achieved an accuracy of 98.0% and a specificity of 98.5%. Additionally, the U-KAN model demonstrated superior performance in breast cancer lesion segmentation, outperforming traditional models like U-Net and U-Net++ across datasets, with an accuracy of 93.3% and a sensitivity of 97.4% in the BUSI dataset. These findings highlight the importance of dataset-specific preprocessing techniques and the potential of advanced AI models like ViT and U-KAN to significantly improve the accuracy of early breast cancer diagnostics. [ABSTRACT FROM AUTHOR]

Many major diseases can cause changes in the morphology of blood vessels, and the segmentation of retinal blood vessels is of great significance for preventing these diseases. Obtaining complete, continuous, and high-resolution segmentation results is very challenging due to the diverse structures of retinal tissues, the complex spatial structures of blood vessels, and the presence of many small ships. In recent years, deep learning networks like UNet have been widely used in medical image processing. However, the continuous down-sampling operations in UNet can result in the loss of a significant amount of information. Although skip connections between the encoder and decoder can help address this issue, the encoder features still contain a large amount of irrelevant information that cannot be efficiently utilized by the decoder. To alleviate the irrelevant information, this paper proposes a feature selection module between the decoder and encoder that utilizes the self-attention mechanism of transformers to accurately and efficiently select the relevant encoder features for the decoder. Additionally, a lightweight Residual Global Context module is proposed to obtain dense global contextual information and establish dependencies between pixels, which can effectively preserve vascular details and segment small vessels accurately and continuously. Experimental results on three publicly available color fundus image datasets (DRIVE, CHASE, and STARE) demonstrate that the proposed algorithm outperforms existing methods in terms of both performance metrics and visual quality. [ABSTRACT FROM AUTHOR]

Skin diseases and lesions can be ambiguous to recognize due to the similarity of lesions and enhanced imaging features. In this study, we compared three cutting-edge deep learning frameworks for dermoscopic segmentation: U-Net, SegAN, and MultiResUNet. We used a dermoscopic dataset including detailed lesion annotations with segmentation masks to help train and evaluate models on the precise localization of melanomas. SegAN is a special type of Generative Adversarial Network (GAN) that introduces a new architecture by adding generator and discriminator steps. U-Net has become a common strategy in segmentation to encode and decode image features for limited data. MultiResUNet is a U-Net-based architecture that overcomes the insufficient data problem in medical imaging by extracting contextual details. We trained the three frameworks on colored images after preprocessing. We added incremental Gaussian noise to measure the robustness of segmentation performance. We evaluated the frameworks using the following parameters: accuracy, sensitivity, specificity, Dice and Jaccard coefficients. Our accuracy results show that SegAN (92%) and MultiResUNet (92%) both outperform U-Net (86%), which is a well-known segmentation framework for skin lesion analysis. MultiResUNet sensitivity (96%) outperforms the methods in the challenge leaderboard. These results suggest that SegAN and MultiResUNet are more resistant techniques against noise in dermoscopic segmentation. [ABSTRACT FROM AUTHOR]

With the swift progress of deep learning and its wide application in semantic segmentation, the effect of semantic segmentation has been significantly improved. However, how to achieve a reasonable compromise between accuracy, model size, and inference speed is crucial. In this paper, we propose a lightweight multi-scale asymmetric encoder–decoder network (LMANet) that is designed on the basis of an encoder–decoder structure. First, an optimized bottleneck module is used to extract features from different levels, and different receptive fields are applied to obtain effective information on different scales. Then, a channel-attention module and a feature-extraction module are introduced to constitute the residual structure, and different feature maps are connected by a feature-fusion module to effectively improve segmentation accuracy. Finally, a lightweight multi-scale decoder is designed to recover the image, and a spatial attention module is added to recover the spatial details effectively. This paper has verified the proposed method on the Cityscapes dataset and CamVid dataset and achieved mean intersection over union (mIoU) of 73.9% and 71.3% with the inference speeds of 111 FPS and 118 FPS, respectively, and the number of parameters is only 0.85 M. [ABSTRACT FROM AUTHOR]

The global path planning system is one of the basic systems ensuring the autonomous operation of unmanned underwater vehicles (UUVs) and unmanned surface vehicles (USVs) in a complex aquatic environment. The A* path planning algorithm is one of the most well-known algorithms used to obtain an almost optimal path, avoiding obstacles even in a complex environment containing objects with specific shapes and non-uniform arrangements. The main disadvantage of this algorithm is the computational cost of path calculation. This article presents a new approach based on the image processing of the map before determining the path using A*. The results of numerical research based on a large-sized map expressing the port area confirm the proposed method's effectiveness, which reduces the calculation time by over 500 times with a slight increase in the path length compared to the basic version of the A* algorithm. Based on the obtained results, the proposed approach also increases the path's safety by designating narrow and risky areas as closed to vehicle movement. For this reason, the method seems suitable for use in global path planning for autonomous underwater vehicles (AUVs) and autonomous surface vehicles (ASVs) operating in large areas. [ABSTRACT FROM AUTHOR]

Intravenous fluid bags are essential in hospitals, but foreign particles can contaminate them during mass production, posing significant risks. Although produced in sanitary environments, contamination can cause severe problems if products reach consumers. Traditional inspection methods struggle with the flexible nature of these bags, which deform easily, complicating particle detection. Recent deep learning advancements offer promising solutions in regard to quality inspection, but high-resolution image processing remains challenging. This paper introduces a real-time deep learning-based inspection system addressing bag deformation and memory constraints for high-resolution images. The system uses object-level background rejection, filtering out objects similar to the background to isolate moving foreign particles. To further enhance performance, the method aggregates object patches, reducing unnecessary data and preserving spatial resolution for accurate detection. During aggregation, candidate objects are tracked across frames, forming tracks re-identified as bubbles or particles by the deep learning model. Ensemble detection results provide robust final decisions. Experiments demonstrate that this system effectively detects particles in real-time with over 98% accuracy, leveraging deep learning advancements to tackle the complexities of inspecting flexible fluid bags. [ABSTRACT FROM AUTHOR]

The identification of the yarn roll's margin represents a critical phase in the automated production of textiles. At present, conventional visual detection techniques are inadequate for accurately measuring, filtering out background noise, and generalizing the margin of the yarn roll. To address this issue, this study constructed a semantic segmentation dataset for the yarn roll and proposed a new method for detecting the margin of the yarn roll based on deep learning. By replacing the encoder component of the U-Net with the initial 13 convolutional layers of VGG16 and incorporating pre-trained weights, we constructed a VGG-UNet model that is well suited for yarn roll segmentation. A comparison of the results obtained on the test set revealed that the model achieved an average Intersection over Union (IoU) of 98.70%. Subsequently, the contour edge point set was obtained through the application of traditional image processing techniques, and contour fitting was performed. Finally, the actual yarn roll margin was calculated based on the relationship between pixel dimensions and actual dimensions. The experiments demonstrate that the margin of the yarn roll can be accurately measured with an error of less than 3 mm. This is particularly important in situations where the margin is narrow, as the detection accuracy remains high. This study provides significant technical support and a theoretical foundation for the automation of the textile industry. [ABSTRACT FROM AUTHOR]

The current object detection algorithm based on CNN makes it difficult to effectively capture the characteristics of subtle defects in online industrial product packaging bags. These defects are often visually similar to the texture or background of normal product packaging bags, and the model cannot effectively distinguish them. In order to deal with these challenges, this paper optimizes and improves the network structure based on YOLOv8 to achieve accurate identification of defects. First, in order to solve the long-tail distribution problem of data, a fuzzy search data enhancement algorithm is introduced to effectively increase the number of samples. Secondly, a joint network of FasterNet and SPD-Conv is proposed to replace the original backbone network of YOLOv8, which effectively reduces the computing load and improves the accuracy of defect identification. In addition, in order to further improve the performance of multiscale feature fusion, a weighted bidirectional feature pyramid network (BiFPN) is introduced, which effectively enhances the model's ability to detect defects at different scales through the fusion of deep information and shallow information. Finally, in order to reduce the sensitivity of the defect position deviation, the NWD loss function is used to optimize the positioning performance of the model better and reduce detection errors caused by position errors. Experimental results show that the FSNB_YOLOv8 model proposed in this paper can reach 98.8% mAP50 accuracy. This success not only verifies the effectiveness of the optimization and improvement of this article's model but also provides an efficient and accurate solution for surface defect detection of industrial product packaging bags on artificial assembly systems. [ABSTRACT FROM AUTHOR]

Several numerical simulations of fluid flow were performed using the Lattice Boltzmann method and image processing techniques to estimate the effective properties of 2-D porous rocks. The effective properties evaluated were the physical characteristics that allow fluid flow including the effective porosity, permeability, tortuosity, and average throat size to determine the storage and transport of fluids in porous rocks. The permeability was compared using the Darcy model simulation and the empirical Kozeny–Carman Equation. The results showed that the Lattice Boltzmann method and image processing techniques can estimate the effective parameters of porous rocks. Furthermore, there was a good correlation between permeability and parameters such as effective porosity, tortuosity, and average throat size. The Darcy model simulation revealed a gamma distribution in the permeability, while the empirical Kozeny–Carman Equation showed a log-normal distribution. [ABSTRACT FROM AUTHOR]

We establish a sample‐ and data‐processing pipeline that allows for high‐throughput optical microscope measurement of porous films, provided they are sufficiently optically scattering. Here, self‐limiting electrospray deposition (SLED) is used to manufacture scattering films of different morphologies. This technique compensates for the scattering of the films through background subtraction of the reflection image with the transmission image. This process is implemented through a combination of an ImageJ and MATLAB data pipeline; the Canny edge‐detector is used as the image‐processing algorithm to identify the boundaries of the film. This process is verified against manually measured images; a comparative study between cross‐sectional scanning electron microscopy (where scattering effects are diminished) and optical microscopy also verifies that our optical microscopy technique can be used to consistently, non‐destructively measure film thickness regardless of film morphology. In addition, this technique can be used in combination with dense film measurements to measure film porosity. [ABSTRACT FROM AUTHOR]

The restoration of fine motor function in the hand is crucial for stroke survivors with hemiplegia to reintegrate into daily life and presents a significant challenge in post-stroke rehabilitation. Current mirror rehabilitation systems based on wearable devices require medical professionals or caregivers to assist patients in donning sensor gloves on the healthy side, thus hindering autonomous training, increasing labor costs, and imposing psychological burdens on patients. This study developed a low-load wearable hand function mirror rehabilitation robotic system based on visual gesture recognition. The system incorporates an active visual apparatus capable of adjusting its position and viewpoint autonomously, enabling the subtle monitoring of the healthy side's gesture throughout the rehabilitation process. Consequently, patients only need to wear the device on their impaired hand to complete the mirror training, facilitating independent rehabilitation exercises. An algorithm based on hand key point gesture recognition was developed, which is capable of automatically identifying eight distinct gestures. Additionally, the system supports remote audio–video interaction during training sessions, addressing the lack of professional guidance in independent rehabilitation. A prototype of the system was constructed, a dataset for hand gesture recognition was collected, and the system's performance as well as functionality were rigorously tested. The results indicate that the gesture recognition accuracy exceeds 90% under ten-fold cross-validation. The system enables operators to independently complete hand rehabilitation training, while the active visual system accommodates a patient's rehabilitation needs across different postures. This study explores methods for autonomous hand function rehabilitation training, thereby offering valuable insights for future research on hand function recovery. [ABSTRACT FROM AUTHOR]

Board games like chess serve as an excellent testbed for human–robot interactions, where advancements can lead to broader human–robot cooperation systems. This paper presents a chess-playing robotic system to demonstrate controlled pick and place operations using a 3-DoF manipulator with image and speech recognition. The system identifies chessboard square coordinates through image processing and centroid detection before mapping them onto the physical board. User voice input is processed and transcribed into a string from which the system extracts the current and destination locations of a chess piece with a word error rate of 8.64%. Using an inverse-kinematics algorithm, the system calculates the joint angles needed to position the end effector at the desired coordinates actuating the robot. The developed system was evaluated experimentally on the 3-DoF manipulator with a voice command used to direct the robot movement in grasping a chess piece. Consideration was made involving both the own pieces as well as capturing the opponent's pieces and moving the captured piece outside the board workspace. [ABSTRACT FROM AUTHOR]

Traditional health care relies on biomedical image categorization to identify and treat various medical conditions. In machine learning and medical imaging, biomedical image classification for colon and lung cancer diagnosis is significant. The work focuses on building novel models and algorithms to accurately detect and categorize tumorous lesions using computer tomography (CT) scans and histopathology slides. These systems use image processing, deep learning (DL), and convolutional neural networks (CNN) to assist medical professionals diagnose cancer sooner and improve patient outcomes. Biomedical image classification using seagull optimization with deep learning (BIC-SGODL) addresses colon and lung cancer diagnosis. The BIC-SGODL method improves cancer diagnosis using hyperparameter optimized DL model. BIC-SGODL utilizes DenseNet to learn complicated features. The convolutional long short-term memory (CLSTM) standard captures spatiotemporal information in sequential picture data. Finally, the SGO method adjusts hyperparameters to improve model performance and generalization. BIC-SGODL performs well with biomedical image dataset simulations. Thus, medical picture cancer diagnosis may be automated using BIC-SGODL. [ABSTRACT FROM AUTHOR]

Effective communication is crucial in daily life, and for people with hearing disabilities, sign language is no exception, serving as their primary means of interaction. Various technologies, such as cochlear implants and mobile sign language translation applications, have been explored to enhance communication and improve the quality of life of the deaf community. This article presents a new, innovative method that uses real-time machine learning (ML) to accurately identify Mexican sign language (MSL) and is adaptable to any sign language. Our method is based on analyzing six features that represent the angles between the distal phalanges and the palm, thus eliminating the need for complex image processing. Our ML approach achieves accurate sign language identification in real-time, with an accuracy and F1 score of 99%. These results demonstrate that a simple approach can effectively identify sign language. This advance is significant, as it offers an effective and accessible solution to improve communication for people with hearing impairments. Furthermore, the proposed method has the potential to be implemented in mobile applications and other devices to provide practical support to the deaf community. [ABSTRACT FROM AUTHOR]

This paper presents an advanced automatic number plate recognition (ANPR) system designed specifically for Qatar's diverse license plate landscape and challenging environmental conditions. Leveraging the YOLOv8 deep learning model, particularly the YOLOv8s variant, we achieve state-of-the-art accuracy in both license plate detection and number recognition. Our innovative approach includes a comprehensive dataset enhancement technique that simulates adverse conditions, significantly improving the model's robustness in real-world scenarios. We integrate edge computing using a Raspberry Pi with server-side processing, demonstrating an efficient solution for real-time ANPR applications. The system maintains greater than 93% overall performance across various environmental conditions, including night-time and rainy scenarios. We also explore the impact of various pre-processing techniques, including edge detection, k-mean thresholding, DBSCAN, and Gaussian mixture models, on the ANPR system's performance. Our findings indicate that modern deep learning models like YOLOv8 are sufficiently robust to handle raw input images and do not significantly benefit from additional pre-processing. With its high accuracy and real-time processing capability, the proposed system represents a significant advancement in ANPR technology and is particularly suited for Qatar's unique traffic management needs and smart city initiatives. [ABSTRACT FROM AUTHOR]

An online inspection method based on machine vision was proposed and validated to address the issues of high work intensity, low efficiency, low accuracy, and risk of missed inspection in traditional sampling methods for screw threads of rebar head. Firstly, an industrial camera was used to capture real-time images of the processed rebar thread heads, preprocess the images, and locate the target positions in the images to reduce the complexity and running time of subsequent algorithms. Then, the Canny operator was used to roughly extract the edge feature information of the rebar head, and the Shi–Tomasi algorithm was used for corner inspection to achieve precise optimization of sub-pixel level corners. Based on robust linear regression, the diagonal points were fitted with lines to detect the corresponding size parameters. Finally, an inspection system on screw threads of rebar head parameter was designed and developed, which consisted of an image-acquisition device, Siemens PLC controller, and inspection software. Test results show that this method can achieve online inspection without contact, with inspection accuracy reaching the micrometer level, and 8–10 rebar heads can be inspected per second. [ABSTRACT FROM AUTHOR]

Ground-penetrating radar (GPR) is widely employed as a non-destructive tool for subsurface detection of transport infrastructures. Typically, data collected by high-frequency antennas offer high resolution but limited penetration depth, whereas data from low-frequency antennas provide deeper penetration but lower resolution. To simultaneously achieve high resolution and deep penetration via a composite radargram, a Non-Subsampled Contourlet Transform (NSCT) algorithm-based multifrequency GPR data-fusion method is proposed by integrating NSCT with appropriate fusion rules, respectively, for high-frequency and low-frequency coefficients of decomposed radargrams and by incorporating quantitative assessment metrics. Despite the advantages of NSCT in image processing, its applications to GPR data fusion for concealed damage identification of transport infrastructures are rarely reported. Numerical simulation, tunnel model test, and on-site road test are conducted for performance validation. The comparison between the evaluation metrics before and after fusion demonstrates the effectiveness of the proposed fusion method. Both shallow and deep hollow targets hidden in the simulated concrete structure, real tunnel model, and road are identified through one radargram obtained by fusing different radargrams. The significance of this study is producing a high-quality composite radargram to enable multi-depth concealed damage detection and exempting human interference in the interpretation of multiple radargrams. [ABSTRACT FROM AUTHOR]

In response to the recent formalization of Filipino Sign Language (FSL) and the lack of comprehensive studies, this paper introduces a real-time FSL gesture recognition system. Unlike existing systems, which are often limited to static signs and asynchronous recognition, it offers dynamic gesture capturing and recognition of 10 common expressions and five transactional inquiries. To this end, the system sequentially employs cropping, contrast adjustment, grayscale conversion, resizing, and normalization of input image streams. These steps serve to extract the region of interest, reduce the computational load, ensure uniform input size, and maintain consistent pixel value distribution. Subsequently, a Convolutional Neural Network and Long-Short Term Memory (CNN-LSTM) model was employed to recognize nuances of real-time FSL gestures. The results demonstrate the superiority of the proposed technique over existing FSL recognition systems, achieving an impressive average accuracy, recall, and precision rate of 98%, marking an 11.3% improvement in accuracy. Furthermore, this article also explores lightweight conversion methods, including post-quantization and quantization-aware training, to facilitate the deployment of the model on resource-constrained platforms. The lightweight models show a significant reduction in model size and memory utilization with respect to the base model when executed in a Raspberry Pi minicomputer. Lastly, the lightweight model trained with the quantization-aware technique (99%) outperforms the post-quantization approach (97%), showing a notable 2% improvement in accuracy. [ABSTRACT FROM AUTHOR]

This review is focused on the current status of quantitative MRI (qMRI) of skeletal muscle. The first section covers the techniques of qMRI in muscle with the focus on each quantitative parameter, the corresponding imaging sequence, discussion of the relation of the measured parameter to underlying physiology/pathophysiology, the image processing and analysis approaches, and studies on normal subjects. We cover the more established parametric mapping from T1-weighted imaging for morphometrics including image segmentation, proton density fat fraction, T2 mapping, and diffusion tensor imaging to emerging qMRI features such as magnetization transfer including ultralow TE imaging for macromolecular fraction, and strain mapping. The second section is a summary of current clinical applications of qMRI of muscle; the intent is to demonstrate the utility of qMRI in different disease states of the muscle rather than a complete comprehensive survey. [ABSTRACT FROM AUTHOR]

This experimental study focused on the measurement and analysis of the impact force caused by a tsunami bore on a coastal structure. The bore wave was produced by a dam break mechanism. The water depth in the reservoir and the location of the coastal structures were varied to simulate different impact scenarios. The time history of the force resulting from the impact of the bore wave on the coastal structure was measured. The propagation of the bore wave along the flume was recorded and the video recordings were converted into digital data using an image-processing technique in order to determine the flow depth variations with time. The hydrostatic forces and the corresponding depth and time-averaged hydrodynamic forces as well as the maximum hydrodynamic forces were acquired for each scenario. The ratio of hydrodynamic to hydrostatic forces were obtained, and it was observed that the calculated averaged ratio was within the recommended design ratio. The results indicate that an increase in the reservoir level caused an increase in the magnitude and intensity of the impact forces, however, the relationship was non-linear. Moreover, it was found that the location of the structure did not play a significant role on the intensity of the impact forces. [ABSTRACT FROM AUTHOR]

Digital images play a particular role in a wide range of systems. Image processing, storing and transferring via networks require a lot of memory, time and traffic. Also, appropriate protection is required in the case of confidential data. Discrete atomic compression (DAC) is an approach providing image compression and encryption simultaneously. It has two processing modes: lossless and lossy. The latter one ensures a higher compression ratio in combination with inevitable quality loss that may affect decompressed image analysis, in particular, classification. In this paper, we explore the impact of distortions produced by DAC on performance of several state-of-the-art classifiers based on convolutional neural networks (CNNs). The classic, block-splitting and chroma subsampling modes of DAC are considered. It is shown that each of them produces a quite small effect on MobileNetV2, VGG16, VGG19, ResNet50, NASNetMobile and NASNetLarge models. This research shows that, using the DAC approach, memory expenses can be reduced without significant degradation of performance of the aforementioned CNN-based classifiers. [ABSTRACT FROM AUTHOR]

In the process of laser-based direct energy deposition (DED-LB), the quality of the deposited layer will be affected by the process parameters and the external environment, and there are problems such as poor stability and low accuracy. A molten pool monitoring method based on coaxial vision is proposed. Firstly, the molten pool image is captured by a coaxial CCD camera, and the geometric features of the molten pool are accurately extracted by image processing techniques such as grayscale, median filtering noise reduction, and K-means clustering combined with threshold segmentation. The molten pool width is accurately extracted by the Canny operator combined with the minimum boundary rectangle method, and it is used as the feedback of weld pool control. The influence of process parameters on the molten pool was further analyzed. The results show that with an increase in laser power, the width and area of the molten pool increase monotonously, but exceeding the material limit will cause distortion. Increasing the scanning speed will reduce the size of the molten pool. By comparing the molten pool under constant power mode and width control mode, it is found that in width control mode, the melt pool width fluctuates less, and the machining accuracy is improved, validating the effectiveness of the real-time control system. [ABSTRACT FROM AUTHOR]

Potholes are a significant hazard, causing severe damage to vehicles and potentially leading to fatal accidents. The automatic detection of potholes is crucial for timely maintenance and reducing these risks. This research evaluates the performance of three pre-trained Convolutional Neural Network models—ResNet 50, ResNet 18, and MobileNet—in classifying pavement images. Initially, the models distinguish between images containing potholes and those without (Potholes vs. Normal). Subsequently, they categorize pavement images into three classes: Small Pothole, Large Pothole, and Normal. Pavement images were captured from two different heights: 3.5 feet (waist height) and 2 feet. Among the models, MobileNet v2 demonstrated the highest accuracy of 98% for detecting potholes. For images taken at 2 feet, the classification accuracies for large potholes, small potholes, and normal pavement were 87.33%, 88.67%, and 92%, respectively. For images taken from waist height, the accuracies increased to 98.67%, 98.67%, and 100%, respectively. The study highlights the potential of these models in enhancing road safety through reliable and automated pothole detection, providing valuable insights for infrastructure maintenance. Article Highlights: Potholes are dangerous and can cause serious vehicle damage. Train CNN models for the classification of potholes These CNNs, for different sizes of potholes can be used for the rehabilitation of potholes. Among all CNN modes, MobileNet v2 achieves 98% accuracy in detecting the presence of a pothole. [ABSTRACT FROM AUTHOR]

The current manual inspection of transmission line images captured by unmanned aerial vehicles (UAVs) is not only time-consuming and labor-intensive but also prone to high rates of false detections and missed inspections. With the development of artificial intelligence, deep learning-based image recognition methods can automatically detect various defect categories of transmission lines based on images captured by UAVs. However, existing methods are often constrained by incomplete feature extraction and imbalanced sample categories, which limit the precision of detection. To address these issues, a novel method based on multi-strategy image processing and an improved deep network is proposed to conduct defect diagnosis of transmission lines. Firstly, multi-strategy image processing is proposed to extract the effective area of transmission lines. Then, a generative adversarial network is employed to generate images of transmission lines to enhance the trained samples' diversity. Finally, the deep network GoogLeNet is improved by superseding the original cross-entropy loss function with a focal loss function to achieve the deep feature extraction of images and defect diagnosis of transmission lines. An actual imbalance transmission line dataset including normal, broken strands, and loose strands is applied to validate the effectiveness of the proposed method. The experimental results, as well as contrastive analysis, reveal that the proposed method is suitable for recognizing defects of transmission lines. [ABSTRACT FROM AUTHOR]

Currently, there are various types of microscales and the conventional line detection system usually has only one detection method, which is difficult to adapt to the diverse calibration needs of microscales. This article investigates the high-precision measurement method of a microscale based on optoelectronics and the image integration method to solve the diversified calibration needs of microscales. The automatic measurement and processing system integrates two methods: the photoelectric signal measurement method and the photoelectric image measurement method. This article studies the smooth motion method based on ordinary linear guides, investigates the method of reducing the cosine error of a small-range interference length measurement, proposes an image-based line positioning method, and studies the edge and center recognition algorithms of the line. According to the experimental data, the system's measurement accuracy was analyzed using the photoelectric signal measurement method to measure the 1 mm microscale, the maximum difference from the reference value was 0.105 μm, the standard uncertainty was 0.068 μm, and the absolute value of normalized error was less than 1. The accuracy of the image measurement method to measure the 1 mm microscale was consistent with that of the photoelectric signal method. The results show good consistency in the measurement results between the two methods of the integrated measurement system. The photoelectric signal method has the technical characteristics of high measurement efficiency and high accuracy, while the pixel-based measurement of the image method has two-dimensional measurement characteristics, which can realize measurements that cannot be realized by the photoelectric signal method; therefore, the measurement system of optoelectronics and image integration is characterized by high precision and a wide range of measurement adaptations. [ABSTRACT FROM AUTHOR]

Roads can experience a variety of distresses due to the combined effects of heavy traffic, weather, the materials used to build them, the underlying soil, and the way they were constructed. Some of these distresses that occur in flexible pavements are longitudinal and transverse cracks, potholes, patching, and depressions. The severity of these distresses increases over time, which has a negative impact on ride quality. To maintain the pavement in a safe and serviceable condition, early detection and measurement of the severity of distresses are required. Image processing techniques are a modern method for detecting and measuring pavement distresses using digital images and image processing software. Traditional methods for measuring distress are laborious, slow, and risky for the measurers. In contrast, image processing techniques are simple, safe, and quick to complete. This research paper performs image processing methods and measurements using two image processing programs, one for detection and the other for measuring pavement distresses. A comparison of image measurements with traditional measurements showed that the two methods are highly correlated, with image measurements being very close to those obtained using the traditional method. The results of the study showed that the measurements of the length, width, and area of road distresses obtained using image processing techniques were similar to those obtained using the traditional method, with high coefficients of determination R² of 0.9999, 0.9257, and 0.9451, respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Education & Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Counting high‐density objects quickly and accurately is a popular area of research. Crowd counting has significant social and economic value and is a major focus in artificial intelligence. Despite many advancements in this field, many of them are not widely known, especially in terms of research data. The authors proposed a three‐tier standardised dataset taxonomy (TSDT). The Taxonomy divides datasets into small‐scale, large‐scale and hyper‐scale, according to different application scenarios. This theory can help researchers make more efficient use of datasets and improve the performance of AI algorithms in specific fields. Additionally, the authors proposed a new evaluation index for the clarity of the dataset: average pixel occupied by each object (APO). This new evaluation index is more suitable for evaluating the clarity of the dataset in the object counting task than the image resolution. Moreover, the authors classified the crowd counting methods from a data‐driven perspective: multi‐scale networks, single‐column networks, multi‐column networks, multi‐task networks, attention networks and weak‐supervised networks and introduced the classic crowd counting methods of each class. The authors classified the existing 36 datasets according to the theory of three‐tier standardised dataset taxonomy and discussed and evaluated these datasets. The authors evaluated the performance of more than 100 methods in the past five years on different levels of popular datasets. Recently, progress in research on small‐scale datasets has slowed down. There are few new datasets and algorithms on small‐scale datasets. The studies focused on large or hyper‐scale datasets appear to be reaching a saturation point. The combined use of multiple approaches began to be a major research direction. The authors discussed the theoretical and practical challenges of crowd counting from the perspective of data, algorithms and computing resources. The field of crowd counting is moving towards combining multiple methods and requires fresh, targeted datasets. Despite advancements, the field still faces challenges such as handling real‐world scenarios and processing large crowds in real‐time. Researchers are exploring transfer learning to overcome the limitations of small datasets. The development of effective algorithms for crowd counting remains a challenging and important task in computer vision and AI, with many opportunities for future research.

Abstract Due to the richness of natural image semantics, natural image colourisation is a challenging problem. Existing methods often suffer from semantic confusion due to insufficient semantic understanding, resulting in unreasonable colour assignments, especially at the edges of objects. This phenomenon is referred to as colour bleeding. The authors have found that using the self‐attention mechanism benefits the model's understanding and recognition of object semantics. However, this leads to another problem in colourisation, namely dull colour. With this in mind, a Position‐Spatial Attention Network(PSANet) is proposed to address the colour bleeding and the dull colour. Firstly, a novel new attention module called position‐spatial attention module (PSAM) is introduced. Through the proposed PSAM module, the model enhances the semantic understanding of images while solving the dull colour problem caused by self‐attention. Then, in order to further prevent colour bleeding on object boundaries, a gradient‐aware loss is proposed. Lastly, the colour bleeding phenomenon is further improved by the combined effect of gradient‐aware loss and edge‐aware loss. Experimental results show that this method can reduce colour bleeding largely while maintaining good perceptual quality.

Abstract Although many new methods have emerged in text‐driven images, the large computational power required for model training causes these methods to have a slow training process. Additionally, these methods consume a considerable amount of video random access memory (VRAM) resources during training. When generating high‐resolution images, the VRAM resources are often insufficient, which results in the inability to generate high‐resolution images. Nevertheless, recent Vision Transformers (ViTs) advancements have demonstrated their image classification and recognition capabilities. Unlike the traditional Convolutional Neural Networks based methods, ViTs have a Transformer‐based architecture, leverage attention mechanisms to capture comprehensive global information, moreover enabling enhanced global understanding of images through inherent long‐range dependencies, thus extracting more robust features and achieving comparable results with reduced computational load. The adaptability of ViTs to text‐driven image manipulation was investigated. Specifically, existing image generation methods were refined and the FastFaceCLIP method was proposed by combining the image‐text semantic alignment function of the pre‐trained CLIP model with the high‐resolution image generation function of the proposed FastFace. Additionally, the Multi‐Axis Nested Transformer module was incorporated for advanced feature extraction from the latent space, generating higher‐resolution images that are further enhanced using the Real‐ESRGAN algorithm. Eventually, extensive face manipulation‐related tests on the CelebA‐HQ dataset challenge the proposed method and other related schemes, demonstrating that FastFaceCLIP effectively generates semantically accurate, visually realistic, and clear images using fewer parameters and less time.

Abstract Visible imaging is a fast, cheap, and accurate technique in the assessment of food quality and safety. The technique was used in the present research to detect sea foam adulterant levels in black and red peppers. The fraud levels included 0, 5, 15, 30, and 50%. Sample preparation, image acquisition and preprocessing, and feature engineering (feature extraction, selection, and classification) were the conducted steps in the present research. The efficient features were classified using artificial neural networks and support vector machine methods. The classifiers were evaluated using the specificity, sensitivity, precision, and accuracy metrics. The artificial neural networks had better results than the support vector machine method for the classification of different adulterant levels in black pepper with the metrics’ values of 98.89, 95.67, 95.56, and 98.22%, respectively. Reversely, the support vector machine method had higher metrics’ values (99.46, 98.00, 97.78, and 99.11%, respectively) for red pepper. The results showed the ability of visible imaging and machine learning methods to detect fraud levels in black and red pepper.

Abstract In recent years, deep learning models have dramatically influenced image inpainting. However, many existing studies still suffer from over‐smoothed or blurred textures when missing regions are large or contain rich visual details. To restore textures at a fine‐grained level, a multi‐stage inpainting approach is proposed, which applies a series of partial inpainting modules as well as a progressive inpainting module to inpaint missing areas from their boundaries to the centre successively. Some improvements are made on the partial convolutions to reduce artifacts like blurriness, which require a convolution kernel to contain known pixels more than a certain proportion. Towards photorealistic inpainting results, the intermediate outputs from each stage are used to compute the loss. Finally, to facilitate the training process, a multi‐step training is designed that progressively adds inpainting modules to optimize the model. Experiments show that this method outperforms the current excellent techniques on the publicly available datasets: CelebA, Places2 and Paris StreetView.

Abstract Target detection in autonomous driving tasks presents a complex and critical challenge due to the diversity of targets and the intricacy of the environment. To address this issue, this paper proposes an enhanced YOLOv8 model. Firstly, the original large target detection head is removed and replaced with a detection head tailored for small targets and high‐level semantic details. Secondly, an adaptive feature fusion method is proposed, where input feature maps are processed using dilated convolutions with different dilation rates, followed by adaptive feature fusion to generate adaptive weights. Finally, an improved attention mechanism is incorporated to enhance the model's focus on target regions. Additionally, the impact of Group Shuffle Convolution (GSConv) on the model's detection speed is investigated. Validated on two public datasets, the model achieves a mean Average Precision (mAP) of 53.7% and 53.5%. Although introducing GSConv results in a slight decrease in mAP, it significantly improves frames per second. These findings underscore the effectiveness of the proposed model in autonomous driving tasks.

Abstract A recent approach to image steganography is to use deep learning. Mainly, convolutional neural networks can extract complex features and use them as patterns to combine hidden messages and images. Also, by using generative adversarial networks, it is possible to generate realistic and high‐quality stego images without any noticeable artifacts. Previous methods suffered from challenges such as simple architecture, low network accuracy, imbalance between capacity and transparency, vanishing gradients, and low capacity. This study introduces a steganography framework named VidaGAN that utilizes deep learning techniques. The network being proposed is made up of three components: an encoder, a decoder, and a critic, and introduces a novel architecture and several innovations to address some of the unresolved challenges mentioned above. This study introduces a novel method for embedding any type of binary data into images using generative adversarial networks, enabling us to enhance the visual appeal of images generated by the specified model. This neural network called VarIable aDAptive GAN (VidaGAN) achieved state‐of‐the‐art status by reaching a hiding capacity of 3.9 bits per pixel in the DIV2K dataset. Furthermore, examination by the StegExpose steganalysis tool shows an AUC of 0.6, a suitable threshold for transparency.

Abstract This paper proposes a novel approach for absolute velocity estimation of unmanned aerial vehicles in unknown and unmapped GNSS‐denied environments. The proposed method leverages the advantages of Fourier‐based image phase correlation and utilizes off‐the‐shelf onboard sensors, including a downward‐facing monocular camera, an inertial sensor, and a sonar. The non‐matching tracking approach is particularly appealing, offering accurate estimation while remaining robust against frequency‐dependent noise, significant intensity variations, and time‐varying illumination disturbances. In the proposed method, the first step involves computing global pixel motion from consecutive images using phase correlation, which utilizes the shift property of the Fourier transform. This pixel motion estimation serves as the basis for creating a closed‐loop solution for absolute velocity estimation. To further enhance accuracy, a Kalman filter is implemented to fuse all available data and provide a reliable velocity estimate. Validation of the proposed visual‐inertial technique is conducted through simulation experiments using AirSim and real‐world flight tests. The results demonstrate the practicality and effectiveness of the approach across a range of challenging scenarios.

Abstract Most multiple object tracking algorithms depend on the output of the detector. Aiming at the problem that the higher detection quality model is restricted by the computing power, and the robustness of the lightweight detection model is easily affected by motion blur, this paper proposes a lightweight moving object detector based on improved YOLOv8 combined with dynamic confidence compensation algorithm. The algorithm combines various technical means such as network structure optimization, lightweight design, self‐knowledge distillation, loss function improvement and dynamic confidence compensation. ByteTrack is used as a tracker to conduct experiments on PASCAL VOC07+12 data set and UA‐DETRAC test sequence. Compared with the baseline YOLOv8n+ByteTrack, the proposed algorithm improves the HOTA by 1.3% when the single frame tracking delay is reduced by 1.1%. Mostly tracked target is improved by 79.7%, mostly lost target is reduced by 10.9%, and the detection effect is better than the original detector and other popular object detectors. The YOLODCC model achieves a balance between lightweight and multi‐object motion blur.

Abstract Visual smoke semantic segmentation is a challenging task due to semi‐transparency, variable shapes, and complex textures of smoke. To improve segmentation performance, a convolutional neural network and transformer hybrid network are proposed based on pyramid Gaussian pooling (PGP) for smoke segmentation. In order to utilize low‐pass filtering to suppress noise, a PGP method is designed. Then, the output of PGP is reshaped to construct a set of visual tokens for transformers, thus a PGP‐transformer module is presented to make full use of the self‐attention mechanism. Finally, the PGP‐transformer module is inserted into the U‐shaped architecture with skip connections. A large number of experiments have proved that the method is significantly superior to existing state‐of‐the‐art algorithms on virtual and real smoke datasets, and ablation experiments have also verified the effectiveness of the proposed modules.

Abstract Image super‐resolution (SR) has been widely applied in remote sensing to generate high‐resolution (HR) images without increasing hardware costs. However, SR is a severe ill‐posed problem. As deep learning advances, existing methods have solved this problem to a certain extent. However, the complex spatial distribution of remote sensing images still poses a challenge in effectively extracting abundant high‐frequency details from the images. Here, a single‐image super‐resolution (SISR) network based on the generative adversarial network (GAN) for remote sensing is presented, called JOA‐GAN. Firstly, a joint‐attention module (JOA) is proposed to focus the network on high‐frequency regions in remote sensing images to enhance the quality of image reconstruction. In the generator network, a multi‐scale densely connected feature extraction block (ERRDB) is proposed, which acquires features at different scales using MSconv blocks containing multi‐scale convolutions and automatically adjusts the features by JOA. In the discriminator network, the relative discriminator is used to compute the relative probability instead of the absolute probability, which helps the network learn clearer and more realistic texture details. JOA‐GAN is compared with other advanced methods, and the results demonstrate that JOA‐GAN has improved objective evaluation metrics and achieved superior visual effects.

Abstract Face shape priors such as landmarks, heatmaps, and parsing maps are widely used to improve face super resolution (SR). It is observed that face priors provide locations of high‐frequency details in key facial areas such as the eyes and mouth. However, existing methods fail to effectively exploit the high‐frequency information by using the priors as either constraints or inputs. This paper proposes a novel high frequency highway (H2F) framework to better utilize prior information for face SR, which dynamically decomposes the final SR face into a coarse SR face and a high frequency (HF) face. The coarse SR face is reconstructed from a low‐resolution face via a texture branch, using only pixel‐wise reconstruction loss. Meanwhile, the HF face is directly generated from face priors via an HF branch that employs the proposed inception–hourglass model. As a result, H2F allows the face priors to have a direct impact on the SR face by adding the outputs of both branches as the final result and provides an extra face editing function. Extensive experiments show that H2F significantly outperforms state‐of‐the‐art face SR methods, is general for different texture branch models and face priors, and is robust to dataset mismatch and pose variations.

Abstract Considering the challenges of low multi‐object detection accuracy and difficulty in identifying small targets caused by challenging environmental conditions including irregular lighting patterns and ambient noise levels in the mining environment with autonomous electric locomotives. A new network model based on SOD−YOLOv5s−4L has been proposed to detect multi‐objects for autonomous electric locomotives in underground coal mines. Improvements have been applied in YOLOv5s to construct the SOD−YOLOv5s−4L model, by introducing the SIoU loss function to address the mismatch between real and predicted bounding box directions, facilitating the model to learn target position information more efficiently. This research introduces a decoupled head to enhance feature fusion and improve the positioning precision of the network model, enabling rapid capture of multi‐scale target features. Furthermore, the detection capability of the model has been increased by introducing the small target detection layer which is developed by increasing the number of detection layers from three to four. The experimental results on multiple object detection dataset show that the proposed model achieves significant improvement in mean average precision (mAP) of almost 98% for various types of targets and an average precision (AP) of nearly 99% for small targets on the other hand it achieves 5.19% (mAP) and 9.79% (AP) compared to the YOLOv5s model. Furthermore, comparative analysis with other models like YOLOv7 and YOLOv8 shows that the proposed model has superior performance in terms of object detection.

Abstract Currently, in the field of processing 3D point cloud data, two primary representation methods have emerged: point‐based methods and voxel‐based methods. However, the former suffer from significant computational costs and lack the ease of handling exhibited by voxel‐based methods. Conversely, the later often encounter challenges related to information loss resulting from downsampling operations, thereby impeding subsequent tasks. To address these limitations, this article introduces a novel density‐based representation method for voxel partitioning. Additionally, a corresponding network structure is devised to extract features from this specific density representation, thereby facilitating the successful completion of classification tasks. The experiments are implemented on ModelNet40 and MNIST demonstrate that the proposed 3D convolution can achieve the‐state‐of‐the‐art performance based on the voxels.

Abstract Taken in low‐light intensity conditions, image with low brightness affects processing precision. In this article, the Gamma Function based on the brightness average and weighted fusion method according to gray entropy is proposed, which is combined with the improved Retinex algorithm. First, the maximum values of R, G, and B channels in original image are extracted to generate the primary illumination map. Second, the illumination map is optimized and adjusted via the Gamma correction function based on the average brightness value. Finally, the illumination map and detail layer are fused by a weighted fusion algorithm of gray entropy to obtain the reflection map. Reflection maps are used as enhancement. The algorithm proposed in this article can improve the brightness and maintain light distribution in the original image with higher precision and less color distortion.

Abstract Developing real‐time cloud segmentation technology is urgent for many remote sensing based applications such as weather forecasting. Existing deep learning based cloud segmentation methods involve two shortcomings. (a): They tend to produce discontinuous boundaries and fail to capture less salient feature, which corresponds to thin cloud pixels; (b): they are unrobust towards different scenarios. Those issues are circumvented by integrating U‐Net and the swin transformer together, with an efficiently designed dual attention mechanism based skip connection. Typically, a swin transformer based encoder‐decoder network, by incorporating a dual attentional skip connection with Swin‐UNet (DASUNet) is proposed. DASUNet captures the global relationship of image patches based on its window attention mechanism, which fits the real‐time requirement. Moreover, DASUNet characterizes the less salient features by equipping with token dual attention modules among the skip connection, which compensates the ignorance of less salient features incurred from traditional attention mechanism during the stacking of transformer layers. Experiments on ground‐based images (SWINySeg) and remote sensing images (HRC‐WHU, 38‐Cloud) show that, DASUNet achieves the state‐of‐the‐art or competitive results for cloud segmentation (six top‐1 positions of six metrics among 11 methods on SWINySeg, two top‐1 positions of five metrics among 10 methods on HRC‐WHU, two top‐1 positions of four metrics among 12 methods with ParaNum ≤30M on 38‐Cloud), with 100FPS implementation speed averagely for each 224×224 image.

Abstract In recent years, multi‐human parsing has become a focal point in research, yet prevailing methods often rely on intermediate stages and lacking pixel‐level analysis. Moreover, their high computational demands limit real‐world efficiency. To address these challenges and enable real‐time performance, low‐latency end‐to‐end network is proposed. This approach leverages vision transformer and convolutional neural network in a dual‐encoded network, featuring a lightweight Transformer‐based vision encoder) and a convolution encoder based on Darknet. This combination adeptly captures long‐range dependencies and spatial relationships. Incorporating a fuse block enables the seamless merging of features from the encoders. Residual connections in the decoder design amplify information flow. Experimental validation on crowd instance‐level human parsing and look into person datasets showcases the WNet's effectiveness, achieving high‐speed multi‐human parsing at 26.7 frames per second. Ablation studies further underscore WNet's capabilities, emphasizing its efficiency and accuracy in complex multi‐human parsing tasks.

Abstract Driving while inattentive or fatigued significantly contributes to traffic accidents and puts road users at a significantly higher risk of collision. The rise in road accidents due to driver inattention resulting from distractive objects, for example, mobile phones, drinking, or tiredness, requires intelligent traffic monitoring systems to promote road safety. However, outdated detection technologies cannot handle the poor accuracy and the lack of real‐time processing possibility especially when combined with the variations of driving environment. This paper introduces “ME‐YOLOv8” which operates driver`s distraction and fatigue through a modified version of YOLOv8, which includes modules multi‐head self‐attention (MHSA) and efficient channel attention (ECA) modules applied, where the goal of MHSA is to improve the sensitivity of global features and the ECA attentions focus on critical features. Additionally, a dataset was created containing 3660 images covering multiple distracted and drowsy driver scenarios. The results reflect the enhanced detection capabilities of ME‐YOLOv8 and demonstrate its effectiveness in real‐time scenarios. This study demonstrates a significant advancement in the application of AI to public safety and highlights the critical role that state‐of‐the‐art deep learning algorithms play in lowering the risks associated with distracted and tired driving.

Abstract Road damage detection (RDD) is critical to society's safety and the efficient allocation of resources. Most road damage detection methods which directly adopt various object detection models face some significant challenges due to the characteristics of the RDD task. First, the damaged objects in the road images are highly diverse in scales and difficult to differentiate, making it more challenging than other tasks. Second, existing methods neglect the relationship between the feature distribution and model structure, which makes it difficult for optimization. To address these challenges, this study proposes an efficient dense attention fusion network with channel correlation loss for road damage detection. First, the K‐Means++ algorithm is applied for data preprocessing to optimize the initial cluster centers and improve the model detection accuracy. Second, a dense attention fusion module is proposed to learn spatial‐spectral attention to enhance multi‐scale fusion features and improve the ability of the model to detect damage areas at different scales. Third, the channel correlation loss is adopted in the class prediction process to maintain the separability of intra and inter‐class. The experimental results on the collected RDDA dataset and RDD2022 dataset show that the proposed method achieves state‐of‐the‐art performance.

Concrete structure damage and severity are determined by examining the width of cracks in various forms. This categorisation of cracks is based on their specific types, which is crucial for engineers and professionals. It allows them to efficiently prioritise maintenance and repair efforts, extending the lifespan of concrete structures. Thus, the classification of cracks is based on the type of cracks needed. This study combines a wall-climbing robot equipped with imaging capabilities to automate the detection and classification of cracks in concrete surfaces. We used machine learning to classify the crack orientation and OTSU to segment the crack shapes. Based on this study, four experiments were carried out using machine learning methods to classify types of cracks, which are SVM, Random Forest, KNN, and Decision Tree. These experiments were categorised using multiclass classification with types of the orientation of crack such as Not crack, Crocodile, Transverse, and Longitudinal. The classification one-class results show that the Decision Tree achieved 86.50%, SVM 99.50%, Random Forest 97%, and KNN 40%. In multiclass classification, Decision Tree achieved 64%, Random Forest 80%, and KNN 37%. The higher accuracy from SVM is achieved at 87%.

Abstract Background In today’s digital age, various diseases drastically reduce people’s quality of life. Arthritis is one amongst the most common and debilitating maladies. Osteoarthritis affects several joints, including the hands, knees, spine, and hips. This study focuses on the medical disorder underlying Knee Osteoarthritis (KOA) which severely impairs people’s quality of life. KOA is characterised by restricted mobility, stiffness, and terrible pain and can be caused by a range of factors such as ageing, obesity, and traumas. This degenerative disorder leads to progressive wear and tear of the knee joint. Methods To combat arthritis in the kneecap, this study employs a 12-layer Convolutional Neural Network (CNN) to reach deep learning capabilities. A collection of data from the Osteoarthritis Initiative (OAI) is used to classify KOA. Through the use of medical image processing; the study ascertains whether an individual has this ailment. A sophisticated CNN architecture created especially for binary classification and KOA severity utilising deep learning algorithms is the main component of this work. Results The cross-entropy loss function is an important component of the model’s laborious design that classifies data into two groups. The remaining section uses the Kellgren-Lawrence (KL) grade to classify the disease’s severity. In the binary classification, the proposed algorithm outperforms previous methods with an accuracy rate of 92.3%, and in the multiclassification, its accuracy rate is 78.4% which is superior to the previous findings. Conclusion Looking ahead, the research broadens the scope of this work by gathering information from various sources and using these methods on a wider range of datasets and situations. The potential for major advancements in the field of osteoarthritis detection and classification is highlighted by this forward-looking approach. Furthermore, this method reduces the intervention of medical practitioners and ultimately results in accurate diagnosis. Clinical trial number Not applicable.