Progressive refined redistribution pyramid network for defect detection in complex scenarios

Yu, Xuyi; Lyu, Wentao; Wang, Chengqun; Guo, Qing; Zhou, Di; Xu, Weiqiang

doi:10.1016/j.knosys.2022.110176

Cited by 14 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yu et al [108] proposed CS-YOLO, a progressively refined redistribution pyramid network with supervised attention, based on the YOLOv5 model. This network was designed for defect detection in complex scenarios.…”

Section: A: Two-stage Target Detection Algorithmsmentioning

confidence: 99%

“…18] The considered references demonstrate one-stage target detection algorithms that excel in detection speed. Reference [108] proposed CS-YOLO, which exhibited the fastest detection speed of up to 87 f/s on the Alibaba Cloud Tianchi Fabric Dataset. In addition, reference [110] introduced the DenseNet-SSD model, and reference [107] presented the improved YOLOv5 model, achieving FPSs of 61 f/s and 58.8 f/s respectively, meeting the requirement for real-time detection.…”

Section: A Nomenclature and Analysis Of Fabric Defectsmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Quality Control of Surface Defects in Fabrics: A Comprehensive Research Progress

Guo,

Liu,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Fabric defect detection is a crucial step of quality control in textile enterprises. The use of computer vision inspection technology in the textile industry is key to achieving intelligent manufacturing. This study sought to determine the progress made and future research directions in intelligent fabric surface defect detection by comprehensively reviewing published literature in terms of algorithms, datasets, and detection systems. Initially, the detection methods are classified as traditional and learning-based methods. The traditional methods are subdivided into model, spectral, statistical, and structural approaches. Learningbased methods are categorized into classical machine learning methods and deep learning methods. The principles, model performance, detection rate, real-time performance, and applicability of deep learning methods are highlighted and compared. In addition, the strengths and weaknesses of all the approaches are elaborated. The use of fabric defect datasets and deep learning frameworks is analyzed. Public datasets and commonly used frameworks are collated and organized. The application of existing fabric inspection systems on the market is outlined. Fabric defect types are systematically named and analyzed. Finally, future research directions are discussed to provide guidance for researchers in related fields.

show abstract

Section: A: Two-stage Target Detection Algorithmsmentioning

confidence: 99%

Section: A Nomenclature and Analysis Of Fabric Defectsmentioning

confidence: 99%

Intelligent Quality Control of Surface Defects in Fabrics: A Comprehensive Research Progress

Guo,

Liu,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To fully verify the outstanding performance of the proposed model, this study conducted comparative experiments not only with other state-of-the-art models, such as Faster RCNN, Cascade RCNN, RetinaNet, YOLOv4, YOLOv7 [41], YOLOv8, and YOLOv5s (original model), but also with models utilizing the same patterned fabric dataset, such as Tianchi Top1, ES-Net [42], and CS-YOLO [43]. Table 6 summarized the results of the P and mAP@0.5.…”

Section: Comparative Experiments With Other Defect Detection Modelsmentioning

confidence: 99%

Surface defect detection for intricate pattern fabrics based on deep learning

Wang,

Zhu,

Liu

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

To tackle the challenges in the current detection of patterned fabric defects, such as unbalanced and limited data volume, incomplete extraction of defect features by the network, aliasing effect in feature fusion by the pyramid network, and low accuracy in identifying small targets, this paper proposes a novel single-stage network named ASC-YOLO. Firstly, the CoT-CSP module is introduced into the Backbone network of the YOLOv5s to model the global contextual relationships of defective features. This module compensates for the limitations of the original Cross-Stage Partial Network, which can only extract local feature information. It effectively enhances the comprehensive extraction of various irregular defect features in fabrics and reduces redundant interactions with texture background noise. Subsequently, three types of AttentionC3 modules are proposed and integrated into the Neck enables the model to focus on valuable details related to defect features through weight allocation, significantly enhancing the capability to identify small defects. Finally, an adaptive spatial feature fusion network is designed to optimize the pyramid network by redistributing weights across different feature layers for efficient utilization of multi-level feature information. Additionally, a random erasing approach is proposed to individually enhance the defect images of specific types with a limited number and adjust the corresponding labels simultaneously. This process aims to improve the robustness of the ASC-YOLO network against data noise. Experimental results demonstrate that ASC-YOLO achieves 95.8% accuracy, with mAP@0.5 reaching 83.1%, and significantly reduces frames per second(FPS) from 769 to 159. Meanwhile, the experiments also verify its superiority over other fabric detection methods and its ability to effectively improve the accuracy of fabric defect detection.

show abstract

“…Addressing one of the challenges, this paper focuses on the issue of background noise [7,8]. The complexity of backgrounds in the detection process can lead to confusion due to the mistaking of noise for relevant information [9].…”

Section: Introductionmentioning

confidence: 99%

Automotive Parts Defect Detection Based on YOLOv7

Huang,

Zhu

2024

Electronics

View full text Add to dashboard Cite

Various complex defects can occur on the surfaces of small automobile parts during manufacturing. Compared with other datasets, the auto parts defect dataset used in this paper has low detection accuracy due to various defects with large size differences, and traditional target detection algorithms have been proven to be ineffective, which often leads to missing detection or wrong identification. To address these issues, this paper introduces a defect detection algorithm based on YOLOv7. To enhance the detection of small objects and streamline the model, we incorporate the ECA attention mechanism into the network structure’s backbone. Considering the small sizes of defect targets on automotive parts and the complexity of their backgrounds, we redesign the neck portion of the model. This redesign includes the integration of the BiFPN feature fusion module to enhance feature fusion, with the aim of minimizing missed detections and false alarms. Additionally, we employ the Alpha-IoU loss function in the prediction phase to enhance the model’s accuracy, which is crucial for reducing false detection. The IoU loss function also boosts the model’s efficiency at converging. The evaluation of this model utilized the Northeastern University steel dataset and a proprietary dataset and demonstrated that the average accuracy (mAP) of the MBEA-YOLOv7 detection network was 76.2% and 94.1%, respectively. These figures represent improvements of 5.7% and 4.7% over the original YOLOv7 network. Moreover, the detection speed for individual images ranges between 1–2 ms. This enhancement in detection accuracy for small targets does not compromise detection speed, fulfilling the requirements for real-time, dynamic inspection of defects.

show abstract

Progressive refined redistribution pyramid network for defect detection in complex scenarios

Cited by 14 publications

References 42 publications

Intelligent Quality Control of Surface Defects in Fabrics: A Comprehensive Research Progress

Intelligent Quality Control of Surface Defects in Fabrics: A Comprehensive Research Progress

Surface defect detection for intricate pattern fabrics based on deep learning

Automotive Parts Defect Detection Based on YOLOv7

Contact Info

Product

Resources

About