Surface Defect Detection Method Research Articles

QRNet: Query-based reparameterization net for real-time detection of power adapter surface defects

In industrial production, automated surface defect detection holds paramount importance. While current techniques can handle complex background power adapter surface defect detection with high precision, they have many parameters, low speed, slow convergence, and complex post-processing (such as non-maximum suppression). To this end, this study aims to develop a more efficient and effective method for surface defect detection. The primary objective of this research is to enhance the speed of detection without sacrificing accuracy. This paper designs the Separable-reparam Feature Module (SFM), which is based on depth-wise convolution, to fuse multi-branch features through reparameterization techniques. SFM has low parameters and excels in feature extraction without increasing the model’s Memory Access Cost (MAC). SFM combines cross-stage fusion to construct the backbone, enabling the extraction of multi-scale features. Following the standard query decoder architecture, a QRNet was built to learn the query set of objects, and predict the surface defect set for power adapter. Additionally, a novel two-stage mixed-supervised transfer-learning approach is proposed to expedite the convergence process. Experimental results on the power adapter defect dataset demonstrate QRNet’s remarkable performance. It achieved a mean average precision (mAP) of 98.94 % with just 0.841 M parameters and a latency of 5.72 ms. In conclusion, QRNet represents an advancement in surface defect detection, offering a balance between accuracy and efficiency.

REDef-DETR: real-time and efficient DETR for industrial surface defect detection

Abstract Industrial surface defect detection is an important part of industrial production, which aims to identify and detecting various defects on the surface of product to ensure quality and meet customer requirements. With the development of deep learning and image processing technologies, the surface defect detection methods based on computer vision has become the mainstream method. However, the prevalent convolutional neural network-based defect detection methods also have many problems. For example, these methods rely on post-processing of Non-Maximum Suppression and have poor detection ability for small targets, which affects the speed and accuracy of surface defect detection in industrial scenarios. Therefore, we propose a novel DEtection TRansformer-based surface defect detection method. Firstly, we propose a Multi-scale Contextual Information Dilated module and fuse it into the backbone. The module is mainly composed of large kernel convolutions, which aims to expand the receptive field of the model, thus reducing the leakage rate of the model. Moreover, we design an efficient encoder which mainly contains two important modules, namely feature enhancement based on cascaded group attention module and efficient feature fusion module based on content-aware. The former module effectively enhances the high-level semantic information extracted by the backbone, thus enabling the model to better interpret features, and it can improve the problem of high computational cost of transformer encoder, thus increasing the detection speed. The latter module performs multi-scale feature fusion across the feature information of various scales, thus improving the detection accuracy of the model for small-size defects. Experimental results show that the proposed method achieves 80.6%mAP and 80.3FPS on NEU-DET, and 98.0%mAP and 79.4FPS on PCB-DET. Our proposed method exhibits excellent detection performance and achieves real-time and efficient surface defect detection capability to meet the needs of industrial surface defect detection.

High-speed wafer surface defect detection with edge enhancement via optical spatial filtering in serial time-encoded imaging

With the rapid development of the chip and metasurface industries, high-speed defect detection of wafer during semiconductor batch manufacturing has become increasingly important for yield control. Here, we propose a high-speed, macro-scale wafer surface defect detection method with enhanced image edges, via optical spatial filtering in serial time-encoded imaging. By using blazed gratings to spatially project different wavelength components of pulsed light into a one-dimensional line, together with dispersive Fourier time stretching technology, a high-speed serial time-encoded imaging system based on a single pixel detector is constructed for testing the wafer surface defects, and optical spatial filtering is introduced to improve the imaging quality. Experiments show high-pass spatial filtering effectively restrains environmental interference and enhances image edge detection. Small target detection is achieved without a complex image algorithm. Our solution extends optical spatial filtering to serial time-encoded imaging, not only permitting wafer macro scale defect detection with edge enhancement, but also having potential significance for imaging lidar, imaging spectrometers, ghost imaging technology, and more.

An Efficient and Accurate Surface Defect Detection Method for Wood Based on Improved YOLOv8

Accurate detection of wood surface defects plays a pivotal role in enhancing wood grade sorting precision, maintaining high standards in wood processing quality, and safeguarding forest resources. This paper introduces an efficient and precise approach to detecting wood surface defects, building upon enhancements to the YOLOv8 model, which demonstrates significant performance enhancements in handling multi-scale and small-target defects commonly found in wood. The proposed method incorporates the dilation-wise residual (DWR) module in the trunk and the deformable large kernel attention (DLKA) module in the neck of the YOLOv8 architecture to enhance the network’s capability in extracting and fusing multi-scale defective features. To further improve the detection accuracy of small-target defects, the model replaces all the detector heads of YOLOv8 with dynamic heads and adds an additional small-target dynamic detector head in the shallower layers. Additionally, to facilitate faster and more-efficient regression, the original complete intersection over union (CIoU) loss function of YOLOv8 is replaced with the IoU with minimum points distance (MPDIoU) loss function. Experimental results indicate that compared with the YOLOv8n baseline model, the proposed method improves the mean average precision (mAP) by 5.5%, with enhanced detection accuracy across all seven defect types tested. These findings suggest that the proposed model exhibits a superior ability to detect wood surface defects accurately.

Rail Surface Defect Detection Based on Dual-Path Feature Fusion

With the rapid development of rail transit, the workload of track maintenance has increased, making the intelligent identification of rail surface defects crucial for improving detection efficiency. To address issues such as low defect detection accuracy, the loss of feature information due to single-path architecture backbones, and insufficient information interaction in existing rail defect detection methods, we propose a rail surface defect detection method based on dual-path feature fusion (DPF). This method initially employs a dual-path structure to separately extract low-level and high-level features. It then utilizes a combination of attention mechanisms and feature fusion techniques to integrate these features. By doing so, it preserves richer information and enhances detection accuracy and robustness. The experimental results demonstrate that the comprehensive performance of the proposed model is superior to mainstream algorithms.

SLGA-YOLO: A Lightweight Castings Surface Defect Detection Method Based on Fusion-Enhanced Attention Mechanism and Self-Architecture.

Castings' surface-defect detection is a crucial machine vision-based automation technology. This paper proposes a fusion-enhanced attention mechanism and efficient self-architecture lightweight YOLO (SLGA-YOLO) to overcome the existing target detection algorithms' poor computational efficiency and low defect-detection accuracy. We used the SlimNeck module to improve the neck module and reduce redundant information interference. The integration of simplified attention module (SimAM) and Large Separable Kernel Attention (LSKA) fusion strengthens the attention mechanism, improving the detection performance, while significantly reducing computational complexity and memory usage. To enhance the generalization ability of the model's feature extraction, we replaced part of the basic convolutional blocks with the self-designed GhostConvML (GCML) module, based on the addition of p2 detection. We also constructed the Alpha-EIoU loss function to accelerate model convergence. The experimental results demonstrate that the enhanced algorithm increases the average detection accuracy (mAP@0.5) by 3% and the average detection accuracy (mAP@0.5:0.95) by 1.6% in the castings' surface defects dataset.

An efficient and real-time steel surface defect detection method based on single-stage detection algorithm

An efficient and real-time steel surface defect detection method based on single-stage detection algorithm

A more efficient method for wire rope surface defect detection based on fusing cross-stage features and lightweight convolution modules

Abstract Detecting surface defects in industrial production presents challenges, including deploying lightweight algorithms on edge devices and balance between detection speed and accuracy. This paper introduces a novel lightweight method YOLO-FP for real-time detection of wire rope defects in industrial environments. Utilizing the YOLOv7tiny framework, we developed a lightweight cross-stage feature fusion module to enhance processing feature information. This mitigates the impact of redundant information from traditional convolution, reducing network size and improving detection speed. Additionally, the YOLO-FP network integrates lightweight convolution modules and an attention mechanism. Trained and tested on data from Changan, Great Wall, and Guangzhou Automobile models, our method achieved a 96.06% mean average precision, surpassing the original YOLOv7tiny model. Furthermore, it reduces the model size by 41.09% and enhances detection speed by 18.53%, making it promising for real-time edge device applications in wire rope production.

A method for multi-view surface defect detection of Si3N4 ceramic bearing balls integrating features enhanced by the Gabor salient domain

Si3N4 ceramic bearing balls exhibit wear, pits, scratches, and delamination defects on the surface during manufacturing processes. Current Si3N4 ceramic ball detection methods mainly focus on a single view input, which leads to insufficient fusion of boundary, color, and shape features, consequently resulting in a low detection accuracy. In this research, propose multi-view surface defect detection of Si3N4 ceramic bearing balls integrating features enhanced by the Gabor salient domain (GSMF). Firstly, color, shape, and boundary information of defects are extracted from different angles, distances, and GSMF enhancement views. Secondly, by designing a salient domain enhancement module, GSMF enhancement boundary features are extracted, addressing the feature loss problem that results in scarce border information during decoding. By improving the co-attention of multi-view to prevent memory loss caused by long-distance transmission, more feature information is preserved. Finally, the accuracy of the detection method is validated through experimental tests.

Efficient online surface defect detection using multiple instance learning

Artificial intelligence (AI)-empowered defect detection has emerged as a promising solution for enhancing quality control in manufacturing. While prevalent object detection-based methods have achieved competitive performance, they do carry inherent limitations that necessitate further refinement prior to their practical application in online surface defect detection. This study introduces an efficient online surface defect detection method that makes predictions on the presence of defects based on image-level labels. The method leverages the multiple instance learning (MIL) framework, and utilizes convolutional neural network (CNN) as feature extractor. Extensive experiments are conducted on two real-world datasets to evaluate the method with a custom CNN and Resnet50 as feature extractors (referred to as MIL-CNN and MIL-Resnet50). The results demonstrate the superiority of the proposed method compared with the well-established benchmark methods, especially highlighting the advantage of MIL-Resnet50. Without requiring fine-grained labeling, MIL-Resnet50 enhances F1-macro by 2.5% and 1.5% within the two datasets compared to the second-ranking. Notably, it excels in detecting small-object defects. It also exhibits advantages in terms of detection speed, and are lightweight, making it easy to deploy even in resource-limited scenarios. Additionally, MIL-Resnet50 exhibits the capability to provide approximate defect localization through feature maps. These findings highlight the significant potential of the proposed method within industrial applications.

Solar Surface Defect Detection Based on Optimized YOLOv5

This study introduces an advanced Solar Cell Surface Defect Detection method utilizing an improved YOLO v5, FaserRCNN and YOLOV6 algorithms. Addressing the challenges posed by complex image backgrounds, variable defect morphology, and large-scale differences, our approach incorporates deformable convolution in the CSP module for adaptive learning scale and perceptual field size. The integration of the ECA-Net attention mechanism enhances feature extraction capabilities, while the addition of a tiny defect prediction head improves detection accuracy across different scales. Optimization techniques, including Mosaic and MixUp data augmentation, K-meansCC clustering anchor box algorithm, and the CIOU loss function, contribute to superior model performance. Experimental results demonstrate an impressive accuracy of 97.14% for YOLOv5, outperforming Faster R-CNN's 90.66%. Further extension studies on YOLOv6, YOLOv7, and YOLOv8 reveal YOLOv6 as the most effective, achieving a remarkable accuracy of 98.28%. This research establishes a robust solution for solar cell defect detection, showcasing the efficacy of our proposed algorithm for industrial applications.

A bearing surface defect detection method based on multi-attention mechanism Yolov8

Surface defects in bearings not only affect the appearance but also impact the service life and performance. Therefore, it is imperative for bearing manufacturers to conduct quality inspections before bearings leave the factory. However, traditional visual inspection methods exhibit shortcomings such as high omission rates, insufficient feature fusion and oversized models when dealing with multiple target defects in bearings. To address these challenges, this paper proposes a surface defect detection method for bearings based on an improved Yolov8 algorithm (G-Yolov8). Firstly, a C3Ghost convolutional module based on the Ghost module is constructed in YOLOv8 to simplify model computational costs. Secondly, a global attention mechanism module is designed at the end of the backbone network to increase sensitivity to implicit small target area features and optimize feature extraction efficiency. Subsequently, a deep deformable convolution feature pyramid network is constructed by introducing the deformable convolutional networks version 2 (DCNv2) and the lightweight content-aware reassembly of features upsampling operator to reduce sampling information loss and improve the fusion of multi-scale target defects. Finally, different attention mechanisms are embedded in the detection network to construct a multi-attention detection head to replace the decoupled head, refining classification and localization tasks, reducing feature confusion, and improving the model’s detection accuracy. Experimental results demonstrate that the improved algorithm achieves a 3.5% increase in mean average precision on a self-made small-scale train bearing surface defect dataset, with a 17.3% reduction in model size. This improvement not only enhances accuracy but also addresses the requirement for lightweight deployment in subsequent stages.

Research on Surface Defect Detection Method of Photovoltaic Power Generation Panels——Comparative Analysis of Detecting Model Accuracy

INTRODUCTION: Research on intelligent defect detection technology using machine vision was conducted to address the challenging problem of detecting and localizing PV defects in photovoltaic power generation system operation and maintenance.
 OBJECTIVES: The aim is to improve the accuracy of PV defect detection and enhance the operation and maintenance efficiency of PV power plants.
 METHODS: In this paper, three detection methods such as image processing based detection, traditional machine learning based detection, and deep learning algorithm based detection are discussed and compared, and analyzed respectively. It is finally concluded that the deep learning based detection is more efficient in comparison. Then further analysis and simulation experiments are done through several detection algorithms based on deep learning.
 RESULTS: The experiment yields a high accuracy of the detection model based on the Faster-RCNN algorithm. Its mAP value reaches 92.6%. The detection model based on the YOLOv5 algorithm reaches a mAP value of 91.4%. But its speed is as much as 7 times faster than the model based on the Faster-RCNN algorithm.
 CONCLUSION: Comprehensive speed and accuracy index. Combining the needs of PV defect detection in the operation and maintenance of PV power generation systems with the results of simulation experiments. It is concluded that the detection model based on the YOLOv5 algorithm can provide better detection capability. Modeling with this algorithm is more suitable for PV defect detection.

Surface defect detection method for discarded mechanical parts under heavy rust coverage

With a significant number of mechanical products approaching the retirement phase, the batch recycling of discarded mechanical parts necessitates a preliminary assessment of their surface condition. However, the presence of surface rust poses a challenge to defect identification. Therefore, this paper proposes a method for detecting heavily rusted surface defects based on an improved YOLOv8n network. In the Backbone, the C2f-DBB module of re-parameterized deep feature extraction was introduced, and the attention module was designed to improve the accuracy of information extraction. In the Neck part, a Bi-Afpn multiscale feature fusion strategy is designed to facilitate information exchange between features at different scales. Finally, Focal-CIoU is employed as the bounding box loss function to enhance the network’s localization performance and accuracy for defects. Experimentally, it is proved that the improved network in this paper improves the Recall, Precision, and mAP0.5 by 1.2%, 2.1%, and 1.9%, respectively, on the original basis, which is better than other network models.

Steel strip surface defect detection based on multiscale feature sensing and adaptive feature fusion

A surface defect detection method for hot-rolled steel strips was proposed to address the challenges of detecting small target defects, significant differences in morphology, and unclear defect characteristics. This method is based on multiscale feature perception and adaptive feature fusion. First, based on the spatial distribution characteristics of the steel strip image, redundant background interference is removed using automatic gamma correction and Otsu thresholding. Second, based on the characteristics of surface defects in steel strips, this paper proposes TDB-YOLO (YOLO with a small target detection layer), a Bidirectional Feature Pyramid Network (BiFPN), and Double Cross Stage Partial (CSP) Bottleneck with three convolutions (DC3). To detect small object defects, a small target detection layer with a smaller receptive field focuses on fine-grained features, reducing the model’s probability of missed detection. In terms of feature extraction, DC3 enhances the interaction of feature information from different spatial scales, enabling the model to effectively handle features of varying scales. In terms of feature fusion, the BiFPN is used to adaptively fuse deep-level and shallow-level feature information, enhancing the semantic richness of the feature information. Ultimately, the proposed model in this paper achieved an accuracy of 90.3% and a recall rate of 88.0% for surface defects in steel strips. The mean average precision was 90.4%, and the frames per second was 33. The detection performance of this model outperformed those of other detection models, demonstrating its ability to effectively meet the real-time detection requirements of surface defects in industrial scenarios on steel strips.

Multi-scale surface defect detection method for bottled products based on variable receptive fields and Gather–Distribute feature fusion mechanism

The inspection of visual quality represents a crucial step in the production process of bottled products. Numerous machine vision methodologies have demonstrated proficient identification of significant defects on bottle surfaces in well-controlled imaging environments. However, the actual production scenario introduces a myriad of surface defect types on bottled products, exhibiting diverse shapes, with the majority of defect instances characterized by relatively small individual areas. Faced with such diverse and small-sized defects, traditional convolutional neural networks (CNNs) encounter limitations due to the utilization of fixed-size convolutional kernels. This choice results in a constrained receptive field, hindering the capture of sufficiently effective contextual information. Additionally, pooling operations within traditional CNNs lead to a substantial reduction in feature map dimensions, causing excessive blurring or outright neglect of small-sized defects. Consequently, this detrimentally impacts the accuracy of surface defect detection and recognition. This study proposes a novel multi-scale defect detection model incorporating a variable receptive field and Gather–Distribute feature fusion mechanism to overcome limitations of traditional CNNs. Nine different scale defect images of bottled products, including worn, wrinkles, joint markings and etc, were collected and enhanced to construct a surface defect detection dataset for the actual production of bottled products. Enhancements to convolutional layers and the C2f module improve feature extraction for different defect shapes and sizes. Integration of the Gather–Distribute feature fusion module (GDFFM) reduces feature information loss and enhances shallow-layer feature utilization. An efficient detection head (E-Detect) with ”parameter sharing” is proposed to reduce computational complexity and improve detection speed without experiencing significant accuracy loss. Experimental results demonstrate that the model’s superiority over advanced defect detection algorithms across various categories. Notably, it achieves accuracies of 89.9%, 55.6%, 89.4%, and 75% for challenging defects like small worn, subtle wrinkles, inclined external cover, and misaligned labels, with improvements of 3.2%, 7%, 2%, and 11.8% over the baseline model, respectively. The model’s mean Average Precision (mAP) also increases by 2.7%.

Human–machine knowledge hybrid augmentation method for surface defect detection based few-data learning

Human–machine knowledge hybrid augmentation method for surface defect detection based few-data learning

A lightweight image-level segmentation method for steel surface defects based on cross-layer feature fusion

Steel is widely used in the aerospace, machinery and automotive industries. Surface defects not only have a negative impact on the appearance of steel but also significantly reduce its wear resistance, high temperature resistance, corrosion resistance and fatigue strength. Therefore, the detection of steel surface defects is very important to improve the quality of steel production. The limited availability of surface defect samples in the industrial sector poses significant challenges for the accurate detection of defects in high-quality materials. In addition, the existing defect detection model is highly complex and not easy to deploy. To solve this problem, a lightweight defect detection network suitable for steel defects is proposed. The cross-layer feature fusion (CFF) in the design enables effective utilisation of multi-layer semantic features, facilitating the detection of small defects in steel. Secondly, a new loss function is designed to make up for the problems of small data volume and uneven data distribution. The experimental results demonstrate that the steel surface defect detection method proposed in this paper achieves the highest detection performance on widely used public datasets such as RSDDS, NEUS and NRSD-CR(test), while maintaining the lowest model complexity.

RER-YOLO: improved method for surface defect detection of aluminum ingot alloy based on YOLOv5.

Aluminum ingot alloy is one of the commonly used materials in industrial production and intelligent manufacturing, whose quality directly affects the performance of aluminum processed products. Therefore, the inspection of surface defects of aluminum ingot alloy is extremely valuable for actual industrial engineering. Aiming at the issues of low detecting precision and the slowly processing rate thatexisted in the traditional target detection methods for aluminum ingot alloy dataset, the YOLOv5-based improvement model RER-YOLO is proposed. Firstly, the aluminum ingot alloy dataset is coped with the image pretreatment methods of rotation, translation, contrast and brightness transformations in a random combination so as to boost the capacity of generalization for model training. Secondly, a multi-scale characteristic extraction network block (Res2Net) is utilized to take the place of the C3 block in the previous YOLOv5 to augment the model's ability that can accurately extract rich features. Finally, an over-parameterization-based re-parameterized convolutional block is utilized in place of the 3×3 convolutional blocks in the Res2Net residual block and baseline model, enlarging the search space of the network and boosting the model's fitting ability while maintaining inference rate. The comparison experimental results demonstrate that the RER-YOLO reaches a mean average precision of 75.1% on the aluminum ingot alloy dataset, which is higher 4.9% than the conventional YOLOv5 and does not increase the inference delay. It also improves the detection accuracy by 12.7% for burr defects, which are fewer in number in the dataset and the defect features are difficult to extract. It can be seen that the presented model in this study has an important reference value towards detecting surface defects in aluminum ingot alloy.

An efficient and accurate surface defect detection method for quality supervision of wood panels

The wood panel processing sector is integral to the landscape of industrial manufacturing, and automated detection of wood panel surface defects has become an important guarantee for improving the efficiency and quality of processing production. However, due to the diverse scales and shapes of wood panel surface defects, as well as their complex and varied colors and texture characteristics, the efforts to efficiently and accurately detect surface defects in wood panels through existing methods have fallen short. Therefore, the paper proposes an enhanced YOLOx-tiny deep learning network for wood panel surface defect detection. We introduce new modules multi-pooling feature fusion module and comprehensive feature extraction module, instead of the original SPP and Bottleneck modules to enhance key feature extraction and reduce the number of computational parameters. The experimental results conducted on the self-constructed wood panel surface defects dataset show that the mAP of our proposed method is 95.01%, which is 9.58% higher than the original YOLOx-tiny network model, and the defects recall is 91.46%, which is 13.21% higher compared to the original network. Meanwhile, the method is able to reduce 12.22% of computational parameters, which effectively improves the efficiency of the detection of surface defects on wood panels. In summary, the proposed intelligent surface defect detection approach for wood panels, which utilizes an enhanced YOLOx-tiny deep learning network, has yielded notable outcomes in enhancing both accuracy and efficiency. This method holds significant practical relevance for the wood panel manufacturing sector, offering the potential to enhance both production efficiency and quality. It also explores the automation and intelligent technology in the process of man-made board processing, which provides a valuable reference for the research in related fields.