Tiny Defect Detection Research Articles

EEMNet: an end-to-end efficient model for PCB surface tiny defect detection

EEMNet: an end-to-end efficient model for PCB surface tiny defect detection

TD-Net:tiny defect detection network for industrial products

AbstractThe detection of tiny defects in industrial products is important for improving the quality of industrial products and maintaining production safety. Currently, image-based defect detection methods are ineffective in detecting tiny and variously shaped defects. Therefore, this paper proposes a tiny defect detection network (TD-Net) for industrial products to improve the effectiveness of tiny defect detection. TD-Net improves the overall defect detection effect, especially the detection effect of tiny defects, by solving the problems of downsampling of tiny defects, pre-filtering of conflicting deep and shallow semantic information, and cascading fusion of multi-scale information. Specifically, this paper proposes the Defect Downsampling (DD) module to realize the defect information supplementation during the backbone downsampling process and improve the problem that the stepwise convolution easily misses the detection of tiny defects. Meanwhile, the Semantic Information Interaction Module (SIIM) is proposed, which fuses deep and shallow semantic features, and is designed to interact the fused features with shallow features to optimize the detection of tiny defects. Finally, the Scale Information Fusion Module (SIFM) is proposed to improve the Path Aggregation Network (PANet) for cascading fusion and information focus on different scale information, which enables further improvement of defect detection performance of TD-Net. Extensive experimental results on the NEU–DET data set (76.8$$\%$$ % mAP), the Peking University PCB defect data set (96.2$$\%$$ % mAP) and the GC10-DET data set (71.5$$\%$$ % mAP) show that the proposed TD-Net achieves competitive results compared with SOTA methods with the equivalent parameter quantity.

Enhanced SSD framework for detecting defects in cigarette appearance using variational Bayesian inference under limited sample conditions.

In high-speed cigarette manufacturing industries, occasional minor cosmetic cigarette defects and a scarcity of samples significantly hinder the rapid and accurate detection of defects. To tackle this challenge, we propose an enhanced single-shot multibox detector (SSD) model that uses variational Bayesian inference for improved detection of tiny defects given sporadic occurrences and limited samples. The enhanced SSD model incorporates a bounded intersection over union (BIoU) loss function to reduce sensitivity to minor deviations and uses exponential linear unit (ELU) and leaky rectified linear unit (ReLU) activation functions to mitigate vanishing gradients and neuron death in deep neural networks. Empirical results show that the enhanced SSD300 and SSD512 models increase the model's detection accuracy mean average precision (mAP) by up to 1.2% for small defects. Ablation studies further reveal that the model's mAP increases by 1.5%, which reduces the computational requirements by 5.92 GFLOPs. The model also shows improved inference in scenarios with limited samples, thus highlighting its effectiveness and applicability in high-speed, precision-oriented cigarette manufacturing industries.

An Efficient Tiny Defect Detection Method for PCB With Improved YOLO Through a Compression Training Strategy

An Efficient Tiny Defect Detection Method for PCB With Improved YOLO Through a Compression Training Strategy

Fabric defect detection based on anchor-free network

Fabrics play a pivotal role in human life and production, and surface defects can directly affect the quality and value of fabrics. Many methods for fabric defect detection have been proposed, but tiny defects are still difficult to be detected effectively, and the accuracy of defect localization and classification is low. To address these issues, a modified YOLOX network called YOLOX-CATD is proposed, which was supplemented with a coordinate attention module (CAM) and tiny defect detection layer (TDDL) for fast and efficient detection of fabric defects, especially tiny defects. Firstly, the anchor-free network is used as the detection framework to avoid the influence of hyperparameters of the setting anchor. Secondly, a CAM is proposed to enhance the representation of the object of interest in the input feature map and suppress the background regions. Finally, a TDDL is added to introduce high-resolution features to improve the localization accuracy of tiny defects. The experimental results on the Aliyun Tianchi Fabric dataset and NEU-DET demonstrate the superiority and generalization of the modified model. The mean average precision (mAP) of YOLOX-CATD on the fabric defect dataset is improved by 5.67% compared to the original YOLOX, and the detection speed can reach 35–36 frames per second (FPS). This proves that YOLOX-CATD can obtain excellent fabric defect detection performance and meet the urgent need for real-time detection in industrial applications.

Aeroengine Blade Surface Defect Detection System Based on Improved Faster RCNN

Aiming at the difficulty of automatic blade detection and the discontinuous defects on the full image, an aeroengine blade surface defect detection system based on improved faster RCNN is designed. Firstly, a dataset of blade surface defects is constructed. To solve the problem that the original faster RCNN is hard to detect tiny defects, RoI align is adopted to replace RoI pooling in the improved faster RCNN and the feature pyramid networks (FPN) combined with ResNet-50 are introduced for feature extraction. To address the issue of discontinuous defects on the full image, the nonmaximum suppression (NMS) algorithm is improved to ensure the continuity of defects. A four-degree-of-freedom (4-DOF) motion platform and an industrial camera are used to collect images of blade surfaces. The detection results generated by the improved faster RCNN are compared with the results of the unimproved method. The experimental results prove that the defect detection system based on the improved faster RCNN can realize automatic defect detection on the blade surface with high accuracy. It also solves the issues of tiny defect detection and discontinuous defects on the full result image of the blade.

A deep context learning based PCB defect detection model with anomalous trend alarming system

The quality of a printed circuit board (PCB) is paramount towards ensuring proper functionality of electronic products. To achieve the required quality standards, substantial research and development efforts were invested to automate PCB inspection for defect detection, primarily using computer vision techniques. Despite these advancements, the accuracy of such techniques is often susceptible towards varying board and component size. Efforts to increase its accuracy especially for small or tiny defects on a PCB often lead to a tradeoff with reduced real-time performance, which in turn limits its applicability in the manufacturing industry. Hence, this paper puts forward an enhanced deep learning network which addresses the difficulty in inferring tiny or varying defects on a PCB in real-time. Our proposed enhancements consist of i) A novel multi-scale feature pyramid network to enhance tiny defect detection through context information inclusion; and ii) A refined complete intersection over union loss function to precisely encapsulate tiny defects. Experimental results on a publicly available PCB defects dataset demonstrate that our model achieves 99.17% mean-average precision, while maintaining real-time inferencing speed at 90 frames per second. In addition, we introduce three trend detection algorithms which alert an operator when abnormal development of defect characteristics is detected. Each algorithm is responsible for localizing defect buildups, increasing defect size and increasing defect occurrences, respectively. As a whole, the proposed model is capable of performing accurate and reliable real-time PCB inspection with the aid of an automated alert capability. The dataset and trained models are available at: https://github.com/JiaLim98/YOLO-PCB.

Convolution With Rotation Invariance for Online Detection of Tiny Defects on Magnetic Tile Surface

Convolution With Rotation Invariance for Online Detection of Tiny Defects on Magnetic Tile Surface

A Tiny Defect Detection System for Tire Mold Surfaces Based on Consecutive Frames

The purpose of the study is to achieve the precise location of each defect on the surfaces of the customized tire mold. Traditional image processing systems typically face significant challenges when processing images, including noise, distortions, and tiny objects, resulting in low computing efficiency and detection accuracy. To address these concerns, a comprehensive defect detection system is developed. The system consists of an inspection platform and a surface defect detection method. In order to achieve highly sensitive detection, an inspection platform and a novel filtering mechanism are proposed. The inspection platform is suitable for various customized tire molds and can be adjusted according to different situations. The effect of noise is effectively reduced by the novel filtering mechanism using a continuous image. Defect features are also prevented from being filtered out. In addition, to remove unnecessary parts of the image, U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Net is adopted to avoid detecting defective features outside the mold. Finally, a tire mold dataset—STM is set up for training and evaluating U <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -Net. The proposed method achieves 83.6% precision and 87.9% recall, which is the best performance among all comparisons. Furthermore, this system can provide defect details for subsequent analysis and automatic defect repair.

MCTSR: A super‐resolution method for defects in gas‐insulated switchgear X‐ray images based on multi‐scale contextual transformers

AbstractAs the core equipment of transmission and distribution hubs, the operational status of gas‐insulated switchgear (GIS) is closely linked to the safety of the power system. Recently, X‐ray digital imaging technology has been extensively used in GIS equipment fault detection. However, the X‐ray image of GIS is blurred, which is not conducive to the detection of tiny defects. Thus, a super‐resolution method for GIS X‐ray images based on multi‐scale context transformers is proposed in this study, namely MCTSR. Firstly, a second‐order image degradation model is introduced to generate GIS X‐ray low‐resolution images that more closely resemble the real world. Secondly, a contextual transformer gate module is constructed to improve attention to tiny defects in GIS X‐ray images. Thirdly, a U‐Net discriminator network based on multi‐scale contextual transformers is intended to enrich the information of the generated images. Finally, the proposed discriminator is combined with the existing generator to compose a super‐resolution method applicable to GIS X‐ray images. The experimental results demonstrate that the method outperforms other methods in peak signal‐to‐noise ratio and structural similarity on the constructed GIS X‐ray image dataset. In addition, the output image of the proposed method facilitates the subsequent defect detection.

A review of non-destructive methods for the detection tiny defects within organic insulating materials

In recent years, solid organic materials such as silicone rubber and epoxy resin have been widely used in electrical equipment due to their excellent insulation properties. However, as a result of manufacturing and design flaws as well as aging issues during operation, the insulating materials in the linked state no longer fit tightly and tiny structural defects (defect size less than 10 mm) develop, such as debonding at the composite interface, pores or cracks within the insulating material, etc. Tiny defects are prone to partial discharges and breakdowns, compromising the safety of high-voltage power equipment, particularly when subjected to strong electric fields. Therefore, it is necessary to carry out non-destructive testing (NDT) for such tiny defects. Such defects are small in size, easily buried in the material, and even some are wrapped in metal, which in turn requires very high detection accuracy, but traditional methods are difficult to achieve, so NDT technologies for tiny defects within insulating materials have become a research hotspot in the field of electric power in recent years. This paper firstly introduces the sources of tiny defects in solid organic insulating materials for electrical equipment. Secondly, the harm caused by structural defects is elaborated. Finally, emerging NDT methods and their advantages and limitations in defect detection are described in detail. The review aims to provide the reader with a comprehensive overview of most of the NDT techniques used in the detection of tiny defects within solid organic insulating materials for electrical equipment and their most salient features.

Unsupervised defect detection with patch-aware mutual reasoning network in image data

Current defect detection studies in the industrial fields mainly adopt supervised strategies, which require large amounts of annotated defective samples to achieve superior results. However, it is hard to meet such large-scale data requirements in the actual industrial scenarios where defects commonly exhibit intensive scarcity and huge intraclass variation. To address the above limitations, we propose a novel Patch-aware Mutual Reasoning Network (PMRN) that utilizes only the prior knowledge of non-defective samples for defect detection. Concretely, a patch-aware mutual reasoning module and a spatial shuffle perception module are devised to reason mutual dependencies and explore dislocations relationships. Besides, an adaptive soft gated anomaly measurement function is developed to calculate reconstruction deviations, which can soft control the information flow according to the complexity of the current scenario. Extensive experimental results (five benchmark datasets: average AUC of 0.951) demonstrate that the PMRN can accurately detect defects with complex backgrounds and weak textures using only non-defective data for training, thus relieving the dependence on large-scale annotated defective samples. Future work will focus on the unsupervised detection of tiny defects.

A lightweight and efficient model for surface tiny defect detection

A lightweight and efficient model for surface tiny defect detection

Cylinder Liner Defect Detection and Classification based on Deep Learning

The machine vision-based defect detection for cylinder liner is a challenging task due to irregular shape, various and small defects on the cylinder liner surface. To improve the accuracy of defect detection by machine vision a deep learning-based defect detection method for cylinder liner was explored in this paper. First, a machine vision system was designed based on the analysis of the causes and types of defects to obtain the field images for establishing an original dataset. Then the dataset was augmented by a modified augmentation method which combines the region of interest automatic extraction method with the traditional augmentation methods. Except for introduction of the anchor configuration optimization method, an XML file-based method of highlighting defect area was proposed to address the problem of tiny defect detection. The optimal model was experimentally determined by considering the network model, the training strategy and the sample size. Finally, the detection system was developed and the network model was deployed. Experiments are carried out and the results of the proposed method compared with those of the traditional methods. The results show that the detection accuracies of sand, scratch and wear defects are 77.5%, 70% and 66.3% which are improved by at least 26.3% compared with the traditional methods. The proposal can be used for field defect detection of cylinder liner.

Fast and accurate detection of surface defect based on improved YOLOv4

PurposeThe current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems.Design/methodology/approachOn the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects.FindingsThe effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model.Originality/valueThis paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

Single‐shot detector with enriched semantics for PCB tiny defect detection

Printed circuit board (PCB) defect detection is one of the primary problems in quality control of the most electronic products. Usually, the industrial PCB imagery has high resolution, but defects take up a small proportion (often only ∼10 pixels in size), which makes it difficult to use traditional machine vision methods. To this end, a novel single shot object detector (SSDT) is proposed for tiny defect detection in PCBs in this study. Specifically, a semantic ascending module, which propagates the semantic property of deep layers to shallow layers, is presented by fusing features of different levels. An attention mechanism is utilised to learn the relationship of the features to be fused across channels and a shuffle module is used to eliminate the aliasing effect after fusion. Moreover, the improved non-maximum suppression is proposed to extenuate the overlap effect for testing the whole PCB image. The proposed detector can rapidly detect tiny defects and the results of SSD and SSDT are further compared not only in PCB defect dataset but also the object detection public dataset PASCAL VOC2007 where SSDT achieves 81.3% mAP, better than SSD (79.5%). In final, the proposed detector is validated to be robust to rotation and blur.

An automatic system for bearing surface tiny defect detection based on multi-angle illuminations

Bearings are very common mechanical components that are widely used in all kinds of machines. Currently, bearing surface defect detection is mainly completed by naked-eye observation. This manual detection mode has low reliability and is time consuming (especially for miniature bearings). In this paper, we present an automatic synthetic tiny defect (small defects that are difficult to find at vertical angles) detection system for bearing surfaces with self-developed software and hardware. Under two illumination modes in this system, thresholding segmentation, contour extraction, contour filtering, center location, region zoning and text recognition are successively implemented. Finally, four common defects (gap, stain, shrunken lid and scratch defects) are automatically detected. The experimental results show that this system has a high detection success rate and short time consumption. This method can provide technical support for real engineering applications involving bearing manufacturing and screening.

A mobile vision inspection system for tiny defect detection on smooth car-body surfaces based on deep ensemble learning

Defect inspection of car-body surfaces is a crucial step for assessing the appearance quality of car coatings. However, some problems such as uncertain imaging conditions, complicated local areas of car-body surfaces and tiny defects with ambiguous edges and low contrast in large images make defect detection more challenging. In order to overcome these challenges, a novel mobile inspection system based on computer vision technology is developed to inspect tiny defects on smooth car-body surfaces automatically. In our system, a dedicated image acquisition module (IAM) with a high-resolution camera, plane light-emitting diode light source and laser rangefinder is designed to capture surface images over bright field illumination. A specific deep ensemble learning algorithm, named TinyDefectNet, is proposed to identify tiny defects in large images acquired from the IAM online. The experiment results indicate our inspection system is on par with the average performance of experienced inspectors but it is much faster than artificial visual inspection. The developed inspection system has been successfully deployed in practice at a car coating plant and it has made inspection more efficient.

Automatic visual defects inspection of wind turbine blades via YOLO-based small object detection approach

Regular inspection of wind turbine blades (WTBs), especially the detection of tiny defects, is necessary to maintain safe operation of wind turbine systems. However, current detections are inefficient and subjective because they are conducted merely by human inspectors. An autonomous visual inspection system is proposed in this paper for WTBs, in which a deep learning framework is developed by combining the convolutional neural network (CNN) and the you only look once (YOLO) model. To achieve practically acceptable detection accuracy for small-sized defects on the WTBs, a YOLO-based small object detection approach (YSODA) using a multiscale feature pyramid is proposed by amalgamating features of more layers. To evaluate the proposed YSODA, a database including 23,807 images labeled for three types of defect—crack, oil pollution, and sand inclusion, is developed. Then, the YSODA is with its architecture modified, and is trained, validated, and tested using the images from the database to provide autonomous and accurate visual inspection. After training and testing, resulting detection accuracy reaches 92.7%, 90.7%, and 90.3% for the three types of defect with the average accuracy being 91.3%. The robustness of the trained YSODA is demonstrated and verified in detecting small-sized defects. It is also compared with that of the traditional CNN-based and machine learning methods by applying to a real WTB system, which proved that the proposed YSODA is superior to existing approaches in terms of detection accuracy and reliability.

TDD‐net: a tiny defect detection network for printed circuit boards

Tiny defect detection (TDD) which aims to perform the quality control of printed circuit boards (PCBs) is a basic and essential task in the production of most electronic products. Though significant progress has been made in PCB defect detection, traditional methods are still difficult to cope with the complex and diverse PCBs. To deal with these problems, this article proposes a tiny defect detection network (TDD-Net) to improve performance for PCB defect detection. In this method, the inherent multi-scale and pyramidal hierarchies of deep convolutional networks are exploited to construct feature pyramids. Compared with existing approaches, the TDD-Net has three novel changes. First, reasonable anchors are designed by using k-means clustering. Second, TDD-Net strengthens the relationship of feature maps from different levels and benefits from low-level structural information, which is suitable for tiny defect detection. Finally, considering the small and imbalance dataset, online hard example mining is adopted in the whole training phase in order to improve the quality of region-of-interest (ROI) proposals and make more effective use of data information. Quantitative results on the PCB defect dataset show that the proposed method has better portability and can achieve 98.90% mAP, which outperforms the state-of-arts. The code will be publicly available.