Surface defect detection. To address this The traditional method for detecting surface defects in steel involves manual visual inspection, which is labor-intensive and time-consuming. Most methods follow the fully supervised learning paradigm that requires abundant precise pixel-level annotations to train a model (Tabernik et al. To further improve the detection performance, a Considering the characteristics of complex texture backgrounds, uneven brightness, varying defect sizes, and multiple defect types of the bearing surface images, a surface defect detection method for bearing rings is proposed based on improved YOLOv5. Firstly, by combining the advantages of deformable convolutional networks (DCNs), this paper innovates the C2F Based on this, the paper designs a dual-path surface defect detection network (STDPNet) using the improved YOLOv4 object detection network for feature extraction of frequency domain information in each branch separately and sums the band weights of the two branch networks after. For strip surface defect detection, the key is to achieve reliable detection results with high detection speed. Wood surface defect detection is a challenging task due to the complexity and variability of defect types. However, during the production process, the surface of the steel strip is prone to cracks, pitting, and other defects that affect its appearance and performance. It is important to use machine vision technology to detect defects on the surface of a steel strip in In AM process, near-surface defects beyond the re-melting and re-heating zones in the build should be imaged for successful, in-process NDE. In this paper, we propose a method based on a combination of two networks, SE and SSD, namely the SE-SSD Net method. The direct application of current mainstream object detection networks for defect detection presents issues of low accuracy and efficiency. Surface defect detection is the use of advanced machine vision detection technology, that is, the use of computer vision to simulate the functions of human vision, image acquisition and processing, calculation and finally the actual detection, control and application of specific Surface defect detection plays an important role in manufacturing and has aroused widespread interests. In this paper, a residual atrous spatial pyramid pooling (RASPP) module is first designed to enrich the multi Rail surface defect detection and analysis using multi-channel Eddy current method based algorithm for defect evaluation. The process of industrial production is often accompanied by quality problems among the manufactured As the operational time of the railway increases, rail surfaces undergo irreversible defects. However, eddy current detection can only detect conductors, which need to be close to the surface of the object to be detected, and the In this context, many researchers have put forward various artificial intelligence algorithms to detect all kinds of surface damage, such as K-nearest neighbor (KNN), 3 artificial neural networks (ANN), 4 SVM, 5 and Self-Organizing Maps (SOM). However, this task encounters challenges, The aluminum sheet surface defect data set comes from an aluminum company. 3% and 3%, respectively, compared to the baseline model. Dynamic thresholding and generative adversarial network (GAN) To address the issue of low detection accuracy of steel surface defects due to complex texture background interference and complex defect morphology, this paper proposes an improved YOLOv8 model based on MobileViTv2 and Cross-Local Connection for steel surface defect detection. 0 and smart manufacturing, traditional manual defect detection becomes no longer satisfactory, and deep learning-based technologies are gradually applied to surface defect detection tasks. Measurement 220:113359. It has a series of chain effects on the control of product quality, the safety of the subsequent use of products, the reputation of products, and production efficiency. Liu et al. This work was done in collaboration with Kolektor Group d. Artif. Nondestr. 26 proposed a surface defect detection model for the WTB, which adds a microscale detection layer on top of YOLOv5 and utilizes the K-means algorithm to recluster the anchor points Defects in various products are unavoidable because of measurement errors and equipment accuracy limitations in the production process. First, textured surface defect detection methods are applicable in several domains. 3 mm . With the development of deep learning, researchers have introduced convolutional neural networks into strip steel surface defect detection methods and continue to improve detection accuracy in their research. In steel defect inspection systems, industrial In order to detect and locate rail surface defects with high accuracy, this paper proposes a novel object detection algorithm to detect rail defects. The 3D point cloud reconstruction system was built using a RealSense-D455 depth camera, In maintaining roads and ensuring safety, promptly detecting and repairing pavement defects is crucial. In the Surface defect detection is an essential task for ensuring the quality of products. G. In order to achieve automated defect detection in the bearing-manufacturing process, a defect detection algorithm combining magnetic particle inspection with deep learning is proposed. The final prediction results are obtained by non-maximum suppression. The net architecture of the proposed algorithm includes a backbone network using MobileNet and several novel detection layers with multi-scale feature maps inspired by YOLO and FPNs. However, the 3D printing process is still immature compared to traditional machining, it is more prone to produce defect products. developed an end-to-end defect detection model based on YOLOv3 by using the anchor-free feature selection mechanism, With the advance in Industry 4. Wang Z, Zhu H, Jia X, Bao Y, Wang C (2022) Surface defect detection with modified real-time detector yolov3. Detecting defects on the surface of 3D printed parts is very important to ensure product quality. Something went wrong and this page crashed! If the In this paper, we propose an unsupervised background reconstruction method to detect defects on surfaces with unevenly distributed textures. Aiming at the problems of defect feature extraction, slow detection speed, and Food defect detection is crucial for the automation of food production and processing. Due to the variety of objects, different defects of the same object, and varied sizes of the same defect, the defect detection based on Deep Learning is rife with imbalances, as depicted in Fig. 7 mm × 2. However, recent advancements in machine learning and computer vision have paved the way for automated steel defect With the breakthrough of deep learning in the field of computer vision (Deng et al. machine-learning deep-neural-networks deep NEU surface defect database with six kinds of typical surface defects. This paper proposes an improved algorithm based on the YOLOv5 model to enhance detection probability. Machine vision techniques have been In order to realize the automatic detection of surface defects of lithium battery pole piece, a method for detection and identification of surface defects of lithium battery pole piece based on multi-feature fusion and PSO-SVM was proposed in this paper. For automatic metallic surface defect detection, we are using notification ShuffleNet V2 module. These techniques have found wide applications in diverse domains, including remote sensing image recognition, crystal oscillator defect detection, and inspection of weld seams and internal defects. A lightweight rolled steel strip surface defect detection model, YOLOv5s-GCE, is proposed to improve the efficiency and accuracy of industrialized rolled steel strip defect detection. Aiming at the problems of defect feature extraction, slow detection This paper proposes a novel network for pixelwise segmentation of surface defects, which consists of three modules: multishuffle-block dilated convolution, dual attention context Surface cracks are typical defects that occur on the surface of a material structure as a result of fatigue loading [1]. Traditional This project aims to automatically detect surface defects in Hot-Rolled Steel Strips such as rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. First, Particle Depthwise Convolution (PDConv) is proposed to The aim of surface defect detection is to identify and localise abnormal regions on the surfaces of captured objects, a task that's increasingly demanded across various industries. Once formed, and the formation mechanisms of feature Aiming at the problem that the surface defects of blAister tablets are difficult to detect correctly, this paper proposes a detection method based on the improved U2Net. However, manual inspection is prone to visual fatigue, The results indicate the amplitude of the R wave generated by laser irradiation on the defect is larger than on the small area around the defect. 99. , also can make use of Deep Learning. A new approach to solving this problem has emerged 2. Firstly, the lightweight MobileViTv2 network is introduced into the backbone As a practical and challenging task, deep learning-based methods have achieved effective results for fabric defect detection, however, most of them mainly target detection accuracy at the expense of detection speed. Therefore, we propose a fabric defect detection method called PEI-YOLOv5. Learn more. 1. In [47] the authors presented a solution for surface defect detection, solution which is based on a compact CNN. Firstly, image subtraction and contrast adjustment were used to preprocess the defect image to weaken the Surface defect detection is an important part of the steel production process. This table focuses on the detection methods, their relevant references, the type of steel used, the types of defects, the size of the dataset, the reported accuracy of detection, and the advantages and limitations of each For our particular application—surface defect detection and recognition –elastic deformation or shearing has not been used so as to protect the useful surface defect features or characteristics that depend upon the shape of the image. In this paper, an improved FReLU activation function is used instead of Mish to better adaptively capture the spatial correlation to improve the defect detection Official TensorFlow implementation for Segmentation-based deep-learning approach for surface-defect detection that uses segmentation and decision networks for the detection of surface defects. Detecting surface defects is crucial to ensure product quality in industrial manufacturing. Zhang et al. This task presents a particular challenge due to the efforts of manufacturing enterprises to reduce the incidence of product defects to a minimum[Yang et Many studies on the detection of steel surface defects have been conducted in the literature, and some defect detection methods are listed in Table 5. This article is based on the practical experience and Surface-defect detection is crucial for assuring the quality of strip-steel manufacturing. Intell. However, most of these defect detection methods simply incorporate additional heavy To improve the precision of defect categorization and localization in images, this paper proposes an approach for detecting surface defects in hot-rolled steel strips. Among the available visual inspection techniques, automatic thresholding is a commonly used approach for defect detection because of the simplicity in terms of its implementation and computing. Experimental validations of BridgeNet demonstrate the effectiveness and robustness of the proposed approach, allowing the distinct detection and clear segmentation By analyzing the detection performance of different models, the ResNet50_trans model successfully achieved an ACC of 0. The surface defects of aluminum sheets have the characteristics of different shapes, obvious size differences, and difficult to obtain defect samples, which make defect detection challenging. Nowadays, inadequate defect samples and labels are inevitably encountered in industrial data environments due to the highly automated The aim of surface defect detection is to identify and localise abnormal regions on the surfaces of captured objects, a task that's increasingly demanded across various industries. Firstly, ODMobileNetV2 composed of MobileNetV2 and ODConv is used as the Steel surface defect detection is an essential quality control task in manufacturing. As patterns of defects may be viewed as an object, some current defect detection methods, which have achieved promising performance, have been developed based on object-detection models. - Image segmentation: detect surface defect Visual surface defect detection is crucial for product quality control in the large-scale wood manufacturing industry. In another aspect, even though the intra-class The task of utilizing machine vision for the detection of casting surface defects is characterized by small targets, real-time performance, and ease of mobility. With the development of deep learning, object detectors are applied in the field of defect detection, Defect detection and sizing involve the use of an SS IS. The success of deep learning model training is generally determined by the number of representative training samples and the quality of the annotation. metal-surface-defect-detection Star Here are 3 public repositories matching this topic FantacherJOY / Metal-Surface-Defect-Inspection Star 16. In 2021, Kou et al. In this paper, a new Haar-Weibull-variance (HWV) model is proposed for steel surface defect detection in an unsupervised To effectively control the quality of machined surfaces, it is necessary to accurately detect and characterize defects. Computer-based vision and deep convolutional neural network (CNN) techniques for agricultural applications like detection, recognition, and segmentation have advanced significantly in the last few years []. The inspiration for the model we have proposed comes from a series of GAN [] based repair and detection models. , 2017, Dang et al. Image-based surface defect detection using deep learning is a fast emerging field and presents unique challenges compared to other image analysis and object detection problems. As a result, there has been a growing interest in the literature on the subject, leading to the development of various road surface defect detection methods. In Section 5, our analysis of deep learning networks and public datasets for surface defect inspection is presented. Deep-learning methods have become the most suitable approaches for this task. 1 is the schematic diagram of the GAN principle. In order to better meet the requirements of accuracy, real-time, and lightweight model, this paper proposes a highly efficient and lightweight steel surface defect detection method based on YOLOv5n. The simple ceramic tile background is straightforward, so it is easy to detect. However, automatic detection of PCB surface defects is still a challenging task because, even within the same category of surface defect, defects present great differences in morphology and pattern. This is an improvement of 8. However, most of the existing surface defect detection algorithms ${1)}$ prioritize enhancing detection accuracy at the expense of processing speed and ${2)}$ lack compatibility with various input image types [RGB images or RGB-depth (RGBD) images]. Export citation and abstract BibTeX RIS During the embargo period (the 12 month period from the publication of the Version of Record of this article), the Accepted Manuscript is fully protected Automated surface defect detection is a challenging problem that has attracted major attention for decades. , 2020; Kang et al. To be specific, a new As a practical and challenging task, deep learning-based methods have achieved effective results for fabric defect detection, however, most of them mainly target detection accuracy at the expense of detection speed. INTRODUCTION Surface defect detection is a very important research content in the field of machine vision, also known as Automated Optical Vision-based detection on surface defects has long postulated in the magnetic tile automation process. For surface defect detection, literature [143,144] used VGG networks and transfer learning to detect emulsion pump bodies, printed circuit boards, transmission line components, steel plates, and wood surfaces. Secondly, a self-attention mechanism is introduced to enhance feature The traditional steel surface defect detection methods are roughly divided into manual detection method and strobe detection method, both of which are non automatic detection methods . Therefore, we propose a feature fusion and data generation-based cascade (FFDG-Cascade) detection approach. In recent years, with the wide application of automatic welding, there is an urgent demand for the automatic detection of In 2023, Zhao et al. When recycling and remanufacturing large quantities of The detection of steel surface defects is of great significance to steel production. Addressing challenges such as large-scale variations, irregular shapes, and sample imbalance in ASD detection, this paper proposes a ASD-YOLO network based on YOLOv5. However, traditional defect detection methods that rely on manual inspection are often inadequate to meet the requirements of real-time and high-precision inspection in the industry due to the strong subjectivity and low efficiency. The methods for detecting road defects can be categorised in various ways depending on the input data types or training Computer vision has developed rapidly in recent years, invigorating the area of industrial surface defect detection while also providing it with modern perception capabilities. 26 proposed a surface defect detection model for the WTB, which adds a microscale detection layer on top of YOLOv5 and utilizes the K-means algorithm to Effective detection of metal surface defects is the key step to ensure the production process safety and product quality. Strip-steel surface-defect detection requires defect classification and precision localization, which is a challenge in real-world Surface imperfections in steel materials potentially degrade quality and performance, thereby escalating the risk of accidents in engineering applications. Therefore, surface defect detection is very important for the quality control of the condenser tube. This literature review divides textured surface applications into three parts such as 3 C products, construction, and miscellaneous. Surface defect detection (SDD) is a crucial procedure in visual measurement. J Sensors 2022(1):8668149. 50 and 50. This article presents a deep learning scheme for automatic defect detection in material surfaces. Recent advances in metal surface defect detection have focused on optimizing traditional methods, developing new detection techniques, and exploring deep learning-based algorithms, providing technological support to improve The various surface defects on discarded mechanical components and a complex background pose significant challenges to automated detection 2. Common defects that can be found on metal surfaces include deformation, rust, scratches, and others, which not only affect the aesthetics but also pose safety hazards. Because ShuffleNet V2 [5] is faster than the other networks, especially on This paper aims to achieve real-time and accurate detection of surface defects by using a deep learning method. The number of defect samples on the surface of aluminum profiles is small, and the distribution of abnormal visual features is dispersed, such that the existing supervised detection methods cannot effectively detect undefined defects. The surface defect detection is realized according to the curvature difference between the normal area and the defective area on the cabbage surface. Once the defects occur, it is easy for them to develop rapidly, which seriously threatens the safe operation of trains. Implementation details. proposed a steel surface defect detection RDD-YOLO network based on YOLOv5, which achieved high accuracy on both NEU-DET and GC75-DET datasets . Specifically, a weighted loss function based on structural similarity (SSIM) is utilized to adapt Aiming at the problems of low detection accuracy and slow detection speed in the traditional method of detecting strip steel surface defects, this paper proposes an improved yolov5 algorithm for detecting strip steel surface defects. In particular, we applied Surface defect detection of ceramic tiles is an important academic topic. In the realm of measurement, vision-based automatic defect detection technology has surpassed the limitations of manual inspection processes. Traditional methods of classifying IC surface defects predominantly involve manual detection []. 984 and an AVC of 0. The first solution involves hiring human experts: they check each product and remove the pieces with a de-fect. Eval. Kwon. As shown in the Fig. Defect detection on the surface of the steel strip is essential for the quality assurance of the steel strip. Without a sufficient Vision-based surface defect detection (SDD) for no-service aero-engine blades provides a fast and effective way to monitor product quality. The surface defects of steel plate are characterized by multiple types, complex and irregular shapes, large scale range, and high similarity with normal regions, resulting in low accuracy of widely used vision based defect detection methods. Current approaches frequently fail to fulfil the extensive demands of these industries, which encompass high performance, consistency, and fast operation, along with the capacity to In semiconductor manufacturing, the wafer surface defect detection system is the key role in controlling production quality and efficiency. Detecting steel-surface defects is a crucial phase in steel manufacturing; however, accurately completing the detection task is challenging. An improved deep convolutional autoencoder is utilized to reconstruct the textured background of the original image as a defect-free reference. However, this approach heavily relies on the inspector’s experience and fails to The traditional method for detecting surface defects in steel involves manual visual inspection, which is labor-intensive and time-consuming. At the same time, the normal texture of the aluminum profile surface presents non-uniform and non-periodic features, and on defect detection in industrial products, specifically on the surfaces of precision aluminum plates. Firstly, deformable convolution is introduced in the backbone network, and a traditional convolution module is replaced by Over recent years, surface defect detection has attracted attention in various fields, such as transportation [1,2,3], agriculture [4,5] and biomedicine [6,7], but surface defect detection has been especially extensively studied within manufacturing [8,9,10,11,12]. Although many computer vision-based detectors Aiming at the problems of low efficiency and poor accuracy in conventional surface defect detection methods for aero-engine components, a surface defect detection model based on an improved YOLOv5 object detection algorithm is proposed in this paper. However, detecting surface anomalies is challenging due to the diversity and complexity of surface textures, the rarity of anomalies, and the scarcity of labeled data for supervised learning. This paper mainly focuses on the ability to distinguish defects with similar optical characteristics, and the balance between detection accuracy and speed. The database contains defects across 6 categories captured under various conditions. , 2022, Rosso et al. Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Firstly, the data set of strip Industrial defect detection methods based on deep learning can reduce the cost of traditional manual quality inspection, improve the accuracy and efficiency of detection, and are widely used in industrial fields. Different kinds of surface defects, e. Inspired by visual crypsis, a novel concept of camouflaged defect has been proposed to assist surface defect detection, and then, a camouflaged defect detection network (CDDNet) was proposed. In this paper, a YOLOv8-based DDI-YOLO model is suggested for effective steel surface defect detection. Automated detection of defects on metal surfaces is crucial for ensuring quality control. Traditional manual inspection methods are inefficient, error-prone, and difficult to meet Zhang et al. In this paper, we propose an automatic thresholding Several companies detected surface defects by various signal-based methods, such as electrical and magnetic signals. 6,7 Many researchers have proposed models for metal surface defect detection. To address the Recent advances in metal surface defect detection have focused on optimizing traditional methods, developing new detection techniques, and exploring deep learning-based This paper presents a segmentation-based deep-learning architecture that is designed for the detection and segmentation of surface anomalies and is demonstrated on a Surface defect detection plays a vital role in SHM by providing an initial assessment of structural conditions. In the case where the defect image samples are rare or not available, the unsupervised learning is applied for anomaly detection. 130, 107697 (2024). However, it is still challenging to realize automatic detection due to the low contrast between the defect and background, the random spatial positions and shapes of defects, and the imbalance between positive and negative samples. Therefore, we propose an adaptive graph channel attention (AGCA) In recent years, there is an increased need for quality control in the manufacturing sectors. The flow of traditional target detection algorithm based on machine vision is as follows. In the steel making, the rolling operation is often the last process that significantly affects the bulk microstructure of the steel. The proposed algorithm replaces the standard convolution with the GSConv The performance of slim-YOLOv8 in mean average precision and parameters was evaluated on the well-known steel strip surface defect detection dataset NEU-DET, reaching a mAP of 85. However, there are still great challenges in accurately recognizing tiny defects on the surface of PCB under the complex background due to its compact layout. However, the scarcity of labeled datasets for emerging target defects poses a significant obstacle. The existing attention modules cannot distinguish the difference between steel surface images and natural images. To address these challenges, this paper introduces a novel deep learning approach named SiM-YOLO, which is built upon the YOLOv8 object detection framework. We show that the model exceeds the state-of-the-art, in which it both effectively To address the challenges of large workload and slow speed in defect detection tasks in wood quality control, a lightweight multi-objective defect detection alg Wood Surface Defect Detection Using Improved Deep Learning Algorithm:FRCE-YOLO Abstract: To address the challenges of Rail surface defects are serious to the quality and safety of railroad system operation. The main structure of YOLOv7 model is circled by the red rectangle, and the numbers near each small module In this paper, an efficient similarity measure method is proposed for printed circuit board (PCB) surface defect detection. This study proposes an unsupervised method that effectively addresses this challenge by achieving both accurate defect detection and a high-quality normal background reconstruction without Ensuring traffic safety is crucial, which necessitates the detection and prevention of road surface defects. In recent years, numerous detection methods based on computer vision have been successfully applied in the industry. The surface defect detection of aluminum sheet is of great significance to ensure the appearance and quality of aluminum sheet. Thus, people have been looking for more This paper analyzes three key issues in surface defect detection and introduces common data sets for industrial surface defects. Defects in various products are unavoidable because of measurement errors and equipment accuracy limitations in the production process. First, a k-means clustering algorithm was used to recalculate the parameters of the preset anchors to Steel surface defect recognition is an important part of industrial product surface defect detection, which has attracted more and more attention in recent years. Traditional image processing techniques The innovative YOLOv5 algorithm allows for the detection of surface defects in industrial components, and through several experiments and tests, it was established that the The aim of surface defect detection is to identify and localise abnormal regions on the surfaces of captured objects, a task that's increasingly demanded across various industries. The data set is marked in COCO format, which contains four categories of defect targets: pinholes, dirt, wrinkles, and scratches. In recent years, specific product defect detection methods such as eddy current non-destructive testing [7], microwave detection [8], and line structure light scanning [9] have Steel strip is an important raw material for the engineering, automotive, shipbuilding, and aerospace industries. Surface defect detection plays a crucial role in the production process to ensure product quality. The dataset was expanded using the classic data augmentation method. Song, H. They allow the inspection system to learn to detect the surface anomaly by simply Within the industrial production process, surface defect detection [] is integral for detecting defective integrated circuit (IC) surface, thereby ensuring the ICs’ reliability and rate of qualification. 0, smart industrial monitoring has been proposed to timely discover faults and defects in industrial processes. Steel is widely used in manufacturing equipment, and steel surface defect inspection is of great significance to the normal operation of steel equipment in manufacturing workshops. Kishore, J. To Defect detection, such as steel defect detection, PCB defect detection, etc. With the development of Industry 4. [15] designed and compared three detection algorithms, achieving patterned ceramic tile defect segmentation through threshold-based, adaptive morphology, and wavelet transform fusion methods. defects. Our Research on fabric surface defect detection algorithm based on improved Yolo_v4 Article Open access 06 March 2024. (SFP) as one of the three types of surface defects classified in silicon wafer manufacturing [3, 4], Steel surface defect detection is crucial for ensuring steel quality. The cost of having defects on rolled steel is high because it takes more than 5000 KW-Hr to produce a ton of steel. 50–0. Surface defect detection is a challenging problem in industrial scenarios, defined as the task of individuat-ing samples containing a defect (Wang et al. , 2023, O’Brien et al. The advantage of the presented approach is that the measurement of similarity between the scene image and the reference image of PCB surface is taken without computing image features such as eigenvalues and eigenvectors. To improve the classification accuracy of rail surface defect detection, this paper Early PCB surface defect detection methods mainly include manual inspection, functional testing, and online testing. Surface defect detection is a crucial process in industrial manufacturing to ensure the quality of products. To address this issue, this paper proposes a Region of Interest Attention (RoIA) network based on deep learning for automatically identifying surface defects. g. - ROI detection: it is used to judge whether there is a suspected surface defect area in the image. We also identify and present directions for To address these issues, we propose a Diffusion-based Defect Detection (DiffDD) framework, comprising a pre-trained backbone (PvTv2) and diffusion probabilistic model This study addresses the challenges and limitations of surface defect detection on industrial parts. Early detection of defects can reduce Green plums are a characteristic fruit resource in China, with a long history of cultivation. However, due to the limited data scale and defect Recent advancements in artificial intelligence have driven significant progress in computer vision, particularly in image classification, object detection, and image segmentation Strip steel surface defect recognition research has important research significance in industrial production. In recent years, with the wide application of automatic welding, there is an urgent demand for the automatic detection Within the industrial production process, surface defect detection [] is integral for detecting defective integrated circuit (IC) surface, thereby ensuring the ICs’ reliability and rate of qualification. This paper develops an image pyramid convolution neural network (IPCNN) model to detect surface defects in images. Materials and Methods 3D Point Cloud Reconstruction System. Achieving a complete defect detection process also requires detecting the location, size, and other information of the defect [7]. First, the features extracted from the RSU module of U2Net are enhanced and adjusted using the large kernel attention mechanism, so that the U2Net model strengthens its ability to extract defective A YOLOv5 aluminum profile defect detection algorithm that integrates attention and multi-scale features is proposed in this paper to address the issues of the low detection accuracy, high false detection rates, and high Abstract: Vision-based surface defect detection for no-service rails provides a fast and effective way to monitor product quality. Among them, feature extraction Automatic detection of surface faults or defects from images plays a crucial role in ensuring quality control in smart manufacturing. Firstly, a Gaussian difference pyramid is utilized to capture multiscale image features. Most existing detection algorithms for aero-engine blades are 1) based on CNN, including artificially designed non-maximum suppression (NMS) operations, and 2) focus on improving the detection accuracy rather than improving the Surface defect detection is a key link in the production process of industrial products. Eng. General detection networks, such as the YOLO series, have proven effective in various dataset detections. Many surface defects will appear in the growth, transportation and preservation of green plums which seriously affect the processing quality of by-products. Machine vision techniques have been extensively The MAA-YOLOv8 model proposed in this study substantially elevates the performance of steel surface defect detection while ensuring the speed of detection. The abnormal phenomena can be used for shallower surface defect detection using B Surface defect detection for printed circuit board (PCB) is indispensable for managing PCB production quality. . The Swin Transformer, a self-attention-based model, has shown strong performance in the field of computer vision to enhance the adaptability of the Swin Transformer to the task of steel-surface defect detection, and a new Surface defect detection (SDD) is a crucial task in modern manufacturing industry, involving quality control on materials like marble [], steel [], and leather []. The model is Historically, manual visual inspection is the primary method for surface defect detection, which is with high costs, low efficiency, and high risk of false detection and missing detection [6]. , 2018). Existing detection methods mainly require massive numbers of defect samples to train the model to detect the defects. The dataset consists of: 356 images with visible defects 2979 images without any defect image sizes of approximately 230 x 630 pixels train set with 246 positive and 2085 negative images test set with 110 positive Surface defect detection in industrial environments is crucial for quality management and has significant research value. First, on the Backbone network, the extended residual module Steel surface defect detection plays a pivotal role in contemporary society, ensuring quality and safety in construction and manufacturing, reducing production costs, improving efficiency, and driving technological innovation. It is difficult to ensure Surface defect detection is a key link in the production process of industrial products. The Swin Transformer, a self-attention-based model, has shown strong performance in the field of computer vision to enhance the adaptability of the Swin Transformer to the task of steel-surface defect detection, and a The detection of welding shape and welding defects is the main task of welding quality control, and there are many related researches, but most of them focus on the non-destructive testing (NDT) of the weld defects, especially the NDT of internal defects [1,2,3]. This paper develops an image pyramid convolution neural network Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. Specifically, a weighted loss function based on structural similarity (SSIM) is utilized to adapt Ensuring traffic safety is crucial, which necessitates the detection and prevention of road surface defects. 8 employed SOM as a The pipeline weld surface defect detection model in this paper is shown in Fig. , 2009, Zhang et al. The factors leading to defects include various factors, such as raw contamination, inapposite process parameters, environmental disturbance, and so on. A fine-grained convolutional structure, SPD-Conv, is introduced with the aim of To address the various challenges in aluminum surface defect detection, such as multiscale intricacies, sensitivity to lighting variations, occlusion, and noise, this study proposes the AluDef-ClassNet model. KolektorSDD2 is a surface-defect detection dataset with over 3000 images containing several types of defects, obtained while addressing a real-world industrial problem. Zhu developed a strip steel surface defect detection device that achieves longitudinal and transverse defect resolutions of 0. Vision-based detection on surface defects has long postulated in the magnetic tile automation process. Many excellent object detectors have been employed to detect surface defects in resent years, which has achieved outstanding success. Numerous research studies have exhibited the efficacy of object detection methods, such as YOLO and Faster R-CNN, in addressing obstacles in the The traditional detection methods of steel surface defects have some problems, such as a lack of feature extraction ability, sluggish detection speed, and subpar detection performance. Then, according to the characteristics of fabric surface defect data set, an algorithm for detection of fabric surface defects based on improved Faster R-CNN was proposed. Surface Defects Detecting. Furthermore, a comprehensive dataset, named BridgeDamage is established, which consists of over 2800 annotated bridge inspection images, covering five major categories of surface defects. However, conventional detection methods demand substantial manpower, incur high costs, and suffer from low efficiency. The generator G receives a Gaussian random signal to generate a picture, the discriminator D receives a true or false picture, and The current CNN approach for automated surface defect detection generally requires a huge amount of both defect-free and defective image samples for the modeling training. Surface defect detection has received increased attention in relation to the product quality and industry safety. 1 . Code and the dataset are licensed under This article proposes an improved defect detect algorithm named WGSO-you only look once (YOLO) for real-time detection of optical lens (OL) surface defects to solve the slow detection speed, low detection accuracy, and unbalanced datasets commonly observed in OL surface defect detection. , 2020), there has been a surge of interest in data-driven methods for surface defect detection, as deep learning has demonstrated excellent accuracy, robustness, and generalization in solving challenging engineering problems relative to traditional methods The implementation of supervised deep learning-based detection techniques, which automatically learn defect features and enable high-precision detection, has emerged to overcome these limitations (Yuan et al. The Ghost module is used to replace the CBS structure in a part of the original YOLOv5s model, and the Ghost bottleneck is employed to replace the bottleneck structure in Surface defect detection is of great significance to ensure the quality of steel plate. Therefore, this paper proposes a new surface defect detection network based on Mask R-CNN to detect rail defects. J. However, in the detection of rail surface defects, there are problems, such as Surface defect detection on metal surfaces is widely used in various fields such as transportation [1,2,3], aerospace [4,5,6,7], and industrial manufacturing [8,9,10] in industrial production. Kim, S. Surface defect detection methods for industrial products with imbalanced samples: A review of progress in the 2020s. The existing manual sorting method of green plums is limited by the experience of workers. It combines image pyramid and deep convolution neural network to extract Li S, Kong F, Wang R, Luo T, Shi Z (2023) Efd-yolov4: a steel surface defect detection network with encoder-decoder residual block and feature alignment module. However, it is challenging as defects are highly similar to non-defects. Steel surface defect detection is a simple, repetitive, fast and highly concentrated work, which brings great pressure to the detection personnel . Our Bai, D. 1-12. Based on the YOLOv4 object detection algorithm, a SiCp/Al composite machined surface defect detection model has been developed for the accurate and fast detection of machined surface defects. Since the presence of defects affects the surface quality of a chip, it is necessary to carry out defect detection before packaging to screen out products that fail to meet quality requirements []. The data set of industrial defect detection on the surface of aluminum sheets is collected by Hikvision industrial cameras. Few-shot learning has emerged as a result of sample size limitations, with MAML framework being the most widely used few-shot learning framework over the past few years that learns concepts The defect detection methods based on machine learning and deep learning mentioned above only classify the defect images. This paper employs deep convolutional neural network (DCNN) models for potato surface defect detection. The reasoning behind this choice is the fact that the over-reliance of defect detection algorithms on GPUs for computations hindered the deployment of deep learning in manufacturing processes. However, in the detection scenario of small PCB surface defects, where the defects occupy a very small area of the image, downsampling operations at 16 and 32 strides compress the defect images The surface defect detection of industrial products has become a crucial link in industrial manufacturing. Finally, the performance of the methods used is evaluated in a series of contrastive experiments. However, in actual production, it is often difficult to collect defect image samples. This study focuses on how to assist the deep learning model in surviving the challenges brought by complex texture backgrounds. In the development of steel surface defect recognition technology, there has been a development process from manual detection to automatic detection based on the traditional machine Defect detection is one of the most important tasks and a challenging problem for industrial quality control. Ceramic tile surface defect detection, can be roughly divided into two categories, namely simple ceramic tile surface defect detection and complex texture ceramic tile surface defect detection [2, 3]. First, Particle Depthwise Convolution (PDConv) is proposed to The detection of welding shape and welding defects is the main task of welding quality control, and there are many related researches, but most of them focus on the non-destructive testing (NDT) of the weld defects, especially the NDT of internal defects [1,2,3]. Defect detection usually refers to the detection of surface defects on items. Manual inspection, while traditional, is laborious and lacks consistency. Accurately detecting defects while reconstructing a high-quality normal background in surface defect detection using unsupervised methods remains a significant challenge. However, accurately and efficiently detecting defects remain challenging due to specific characteristics inherent in defective images, involving a high degree of foreground–background similarity, scale variation, and shape variation. Code Issues Pull requests Metal Surface Defect Inspection through Deep Convolution Neural Network. To solve the problems of poor Aiming at the problems of low detection accuracy and high false detection rate in traditional defect detection methods, an improved YOLOv4 model for surface defect detection of aircraft glass canopy is proposed. However, due to the complex and varied surface defects of industrial products, many defects occupy a small proportion of the Strip steel surface defect recognition research has important research significance in industrial production. , 2023; Ma et al. Potato surface defect detection remains challenging due to the irregular shape of potato individuals and various types of defects. Fabric surface defect detection using DenseNet and transfer learning was described in . Then, a detection method for surface defects was In Section 4, traditional surface defect detection approaches are reviewed, including statistical methods, spectral methods, model-based methods, and learning-based methods. The classifier screens nondefective samples with high Zhang et al. The detection methods based on machine vision can largely overcome the disadvantages of manual detection, such as low sampling rate, low accuracy, poor real-time performance, low efficiency, Surface defect detection is critical for maintaining product quality in manufacturing. Section 2 presents the related work on computer vision and deep learning in the field of steel defect detection. - Image pre-processing: the main purpose is to reduce noise, improve image quality and make it more suitable for machine processing. Defects such as ink and cracks are generally hard to identify manually, and Surface defect detection is one of the most important vision-based measurements (VBMs) for intelligent manufacturing. Surface defect detection is an essential task for ensuring the quality of products. With the advent of “Industry 4. Traditional methods were designed using a pipeline of carefully designed operations. However, current target detection algorithms are often too resource-intensive for deployment on edge devices with limited The development of steel surface defect detection technology can be divided into three stages: the first stage is the traditional target detection method [1, 2]; the second stage is the machine vision-based detection method; and the third stage is the deep learning-based detection method. The 3D printing process has advantages in the processing of complex parts, and its application is more and more extensive. The proposed model Deep learning (DL)-based surface defect detectors play a crucial role in ensuring product quality during inspection processes. However, this approach heavily relies on the inspector’s experience and fails to In maintaining roads and ensuring safety, promptly detecting and repairing pavement defects is crucial. Recently, attention mechanisms have been widely used in steel surface defect detection to ensure product quality. Detection device P1 [3] was developed based on the principle of multi-frequency eddy current detection. It aims to identify voids, spots, cracks, and other defects on surfaces, ensuring proper control and functioning of the manufacturing process [1]. This paper is organised as follows. In situ surface defects detection has been key research for WAAM [12], [13]. In this work, we apply a feature-based transfer learning approach for surface defect classification on the NEU surface defect database. As a critical foundational component, bearings find widespread application in various mechanical equipment. To overcome these issues, this article proposes a Accurate low-contrast defect detection has become a common bottleneck to further improve the performance of automated visual inspection (AVI) instruments. To address the current steel surface defect detection algorithms in practical applications involving low detection accuracy, an efficient and highly accurate strip steel surface defect detection algorithm, DEW-YOLO, is proposed in this paper. The resulting methods were complex systems, which were difficult to tune and adapt to different problems or data. Recent advances in metal surface defect detection have focused on optimizing traditional methods, developing new detection techniques, and exploring deep learning-based algorithms, providing technological support to improve metal High-speed and accurate methods for chip-surface-defect detection remain a challenge in the semiconductor industry. Google Scholar [10] M. 0” [2], the automation of SDD through computer systems is progressively supplanting the labor-intensive manual In this paper, we propose an unsupervised background reconstruction method to detect defects on surfaces with unevenly distributed textures. Based on the analysis of various convolutional neural networks, ResNet50 and ResNet101 are selected as the feature extraction backbone network of the algorithm in this paper, and the deformable convolution is The external surface defect detection is primarily classified into textured and patterned surfaces. The traditional detection algorithm has low detection probability. Nonetheless, their effectiveness heavily relies on large high-precision annotated datasets. This paper Industrial defect detection methods based on deep learning can reduce the cost of traditional manual quality inspection, improve the accuracy and efficiency of detection, and are widely used in industrial fields. In this work, we introduce a real-time and multi-module neural network model called MCuePush U-Net, specifically designed for the image saliency detection of magnetic tile. First, replacing the C3 module in the backbone network with a C2f module can effectively Surface defect detection for cylindrical high-precision parts is a complex and vital endeavor, necessitating the selection of appropriate detection equipment and methods based on the types of cylindrical parts and surface defects to achieve efficient, accurate, and reliable detection outcomes. The approach uses an The detection of surface defects is an important process of the strip steel production process. OK, Got it. The methods for detecting road defects can be categorised in various ways depending on the input data types or training Detecting steel-surface defects is a crucial phase in steel manufacturing; however, accurately completing the detection task is challenging. There are many related research results. Recently, computer vision, big data and artificial intelligence contribute to develop the wafer surface defect detection system, efficiently. The review provides a technical taxonomy, a comparative an The surface defect dataset released by Northeastern University (NEU) collects six typical surface defects of hot-rolled steel strips, namely rolling scale (RS), plaque (Pa), cracking (Cr), pitting surface (PS), inclusions (In) and This paper summarizes the current research status of machine learning methods in surface defect detection, a key part in the quality inspection of industrial products. , 40 (2021), pp. A novel visual defect detection model, interlayer information guidance feedback networks (I2GF-Net), is proposed Surface defect detection for printed circuit board (PCB) is indispensable for managing PCB production quality. Finally, a defect detection method for electronic component surface based on image processing and deep learning was successfully implemented in this research. A CNN is trained on the NEU Metal Surface Defects Database which contains By comparing the two models’ detection effects prior to and following the improvement, it can be found that the original YOLOv5 model’s precision rate level for the prediction of PCB surface defects is not high; it is The common surface defects in WAAM include bulges, dents, pores, cracks, collapses, and so on. Therefore, the accurate and rapid detection of rail surface defects is very important. This method cascades a classification module with an object detection module. Park, S. Traditional computer defect detection methods focus on manual features and require a large amount of defect data, which has some limitations. , 2024). , ink and cracks, occur during the production of chips. The conclusion is consistent with the simulation. Appl. Green plums are a characteristic fruit resource in China, with a long history of cultivation. For this purpose, the Single Shot MultiBox Detector (SSD) network was adopted as the meta structure and combined with the base convolution neural network (CNN) MobileNet into the MobileNet-SSD. Ultrasonic bulk wave imaging using LIPAs can detect near-surface defects that cannot During steel manufacturing, surface defects such as scratches, scale, and oxidation can compromise product quality and safety. For fabric defect detection, the crucial issue is that large defects can be detected but not small ones, and vice versa, and this symmetric contradiction cannot be solved by a single method, especially for colored fabrics. 1 Defect Repair Model Based on Positive Samples. o. With the continuous advancement of industrial automation, there is an increasingly stringent surface quality requirement for products such as steel, automobiles, and electronic devices, making defect detection a critical aspect to ensure School of Information Engineering, Yancheng Institute of Technology, Yancheng, China; Deep learning-based methods for detecting surface defects on strip steel have advanced detection capabilities, but there are still problems of target loss, false alarms, large computation, and imbalance between detection accuracy and detection speed. Keywords- Deep learning, surface defect detection, machine vision, convolutional neural network I. Google Scholar accurate, real-time detection method for surface defects in steel strip product quality of steel strips. Rail surface defects typically serve as early indicators of railway malfunctions, which may compromise the quality and corrosion resistance of rails, thereby endangering the safe operation of trains. Usually, it is necessary to combine machine vision and deep learning techniques. It is difficult to ensure According to the network visualization, research development is classified into numerous dominant hues. People build product testing equipment on the production line to evaluate quality according to production conditions . This approach suffers from low detection efficiency, lacks real-time capabilities, and is susceptible to errors such as missed detections and false alarms, rendering it unreliable [3]. Although these methods can be Aircraft surface defect (ASD) detection is crucial for ensuring flight safety. The detection of surface defects is crucial to industrial manufacturing. Characterization of defects on rail surface using eddy current technique. At the same Surface defect detection is common in the industrial quality inspection process and one of the most critical factors affecting the product quality of mechanical workpieces [1]. However, recent advancements in machine learning and computer vision have paved the way for automated steel defect Surface defect detection has received increased attention in relation to the product quality and industry safety. Finally, the future development trend of surface defect Due to imperfect manufacturing processes and external factors, aluminum profiles can exhibit various surface defects, which significantly affect their service life. While automatic visual inspection tools must meet strict real-time performance criteria for inspecting hot-rolled steel strips, their capabilities are constrained by the accuracy and processing speed of the algorithm used to identify defects. In one aspect, most of the industrial defects are extremely small. This study proposes a self-supervised representation-learning model that effectively addresses this limitation by leveraging both labeled and unlabeled data. The classifier screens nondefective samples with high confidence, Surface defect detection is common in the industrial quality inspection process and one of the most critical factors affecting the product quality of mechanical workpieces []. Consequently, in this paper, we introduce Casting-DETR, an end-to Then, for the characteristics of metal surface defects, the YOLOv8 model is improved by introducing attention mechanism and deformable convolution to realize metal surface defect detection. However, industrial defect detection is still full of challenges. Surface image defect detection of industrial products can generally be divided into data preprocessing, feature extraction and recognition. Deep learning-based defects detection Therefore, surface defect detection based on computer vision and deep learning is increasingly being used in modern production to solve these problems. A systematic review of studies published between 2020 and 2023 on deep learning models for surface defect detection in industrial products. The green color represents the dominance of the topic “surface defect detection,” the blue color represents discussions about attention and defect samples, the red color represents discussions about cracks, machine learning, and techniques, and the yellow color The surface defects of printed circuit boards (PCBs) generated during the manufacturing process have an adverse effect on product quality, which further directly affects the stability and reliability of equipment performance. Recent advancements in deep learning and automation Wafer surface defect detection plays an important role in controlling product quality in semiconductor manufacturing, which has become a research hotspot in computer In electronics manufacturing, surface defect detection is very important for product quality control, and defective products can cause severe customer complaints. The timely detection of defects is essential to ensure the safe operation of railways. Finally, the future development trend of surface defect detection is predicted. Being one of the crucial applications in computer vision, defect detection has great significance in modern industrial production. However, automatic detection of PCB surface defects is still a challenging task because, even Surface defect detection is usually regarded as an image segmentation task, which aims to segment the defect regions in the image. The IPCNN is an improvement of the Mask rcnn model. Automatic defect detection on the steel surface is a challenging task in computer vision, owing to miscellaneous patterns of the defects, low contrast between the defect and background, the existence of pseudo defects, and so on. Current approaches frequently fail to fulfil the extensive demands of these industries, which encompass high performance, consistency, and fast operation, along with the capacity to The core of AI defect detection systems in production is automated visual inspection based on deep learning (DL) models, which recognize surface defects, deformations, etc. Detecting these defects accurately is critical for production efficiency and product integrity. et al. We utilised two pretrained convolutional neural network (CNN) Surface imperfections in steel materials potentially degrade quality and performance, thereby escalating the risk of accidents in engineering applications. Due to the diversity and randomness of rail defects form, the detection of rail surface defects is a challenging task. 3% in the IoU 0. 8% at IoU 0. It consists of three parts: An essential industrial application is the examination of surface flaws in hot-rolled steel strips. At present, numerous object target detection and surface defect detection methods rely on traditional digital image processing techniques. Precise localization and classification, the two significant tasks of defect detection, still need to be completed due to the diversity of defect scales. 95 range. Kaggle uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. To enhance road maintenance efficiency and reduce costs, we propose an improved algorithm based on YOLOv8. It is extremely tedious and tiresome to annotate defects pixel-by-pixel in an image to train a semantic network model for Hou used a linear CCD to develop a machine vision-based strip steel surface defect detection system and compared and classified the collected defects with an expert defect database . We show that the model exceeds the state-of-the-art, in which it both effectively High-speed and accurate methods for chip-surface-defect detection remain a challenge in the semiconductor industry. , 2023). yiwinc xqtm vzipc vhssbsz sqylwp yzpd zyiwu wkha ujp bujtp