Feature purification fusion structure for fabric defect detection

Liu, Guohua; Ren, Jiawei

doi:10.1007/s00371-023-03066-8

Cited by 2 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the adaptability of our improved model to new situations, we conducted generalization experiments on three datasets: the solid color background fabric defect dataset from Alibaba Cloud Tianchi (Dataset 1) [22], the patterned dataset collected from a textile technology company in Wuhan, Hubei (Dataset 2) [42]…”

Section: Generalization Experimentsmentioning

confidence: 99%

“…To tackle the high similarity between fabric backgrounds and defects, Wang et al [21] introduced a coordinate attention mechanism into the feature extraction part of the YOLOv5 network, guiding the model to focus all attention on the target defect areas, suppressing background noise in patterned fabrics, and reducing false detections. Liu et al [22] proposed semantic information supplementation and detail information supplementation strategies on the YOLOv5 network, effectively increasing the network's attention to defects and suppressing the influence of irrelevant background information. Although researchers have improved the performance of the YOLO networks in detecting fabric defects through various improvement strategies, there is still a problem of feature information loss in shallow and deep networks when dealing with small defects in fabrics.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fabric defect detection based on feature enhancement and complementary neighboring information

Liu,

Guo,

Lian

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Fabric defect detection is a crucial aspect of quality control in the textile industry. Given the complexities of fabric backgrounds, the high similarity between patterned backgrounds and defects, and the variety of defect scales, we propose a fabric defect detection method based on feature enhancement and complementary neighboring information . The core of this method lies in two main components: the feature enhancement module and the neighboring information complementation strategy. The feature enhancement module includes two sub-modules: similarity feature enhancement(SFE) and edge detail feature enhancement(EDFE). The SFE aims to capture the similarities between features to strengthen the distinction between defects and complex backgrounds, thereby highlighting the correlations among defects and the differences between defects and the background. The EDFE focuses on improving the network's ability to capture the edge details of fabrics, preventing edge information from becoming blurred or lost due to deeper network layers. The neighboring information complementation strategy consists of shallow-level information complementation(SLIC) and top-down information fusion complementation(TDIFC). The SLIC integrates newly introduced shallow features with neighboring features that have a smaller semantic gap, injecting richer detail information into the network. The TDIFC adaptively guides the interaction of information between adjacent feature maps, effectively aggregating multi-scale features to ensure information complementarity between features of different scales. Additionally, to further optimize model performance, we introduced partial convolution(PConv) in the backbone of the feature extraction network. PConv reduces redundant computations and decreases the model's parameter count. Experimental results show that our proposed method achieved an mAP@50 of 82.4%, which is a 6.6% improvement over the baseline model YOLOv8s. The average inference frame rate reached 61.8 FPS, meeting the real-time detection requirements for fabric defects. Moreover, the model demonstrated good generalization capabilities, effectively adapting to detecting defects in different types and colors of fabrics.

show abstract

Section: Generalization Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fabric defect detection based on feature enhancement and complementary neighboring information

Liu,

Guo,

Lian

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…used an ECA module integrated into Ghost convolution with dense connectivity, to enhance the feature mining and reuse capabilities of the network in fabric defect detection and to reduce the amount of computation effectively. [ 21 ] Huang et al. integrated the Ghost Conv module to improve YOLOv7, enhancing feature extraction while reducing parameters and computation.…”

Section: Introductionmentioning

confidence: 99%

A Lightweight YOLO Object Detection Algorithm Based on Bidirectional Multi‐Scale Feature Enhancement

Liu,

Zhang,

Zhang

et al. 2024

Advcd Theory and Sims

View full text Add to dashboard Cite

This paper proposes a lightweight YOLO object detection algorithm based on bidirectional multi‐scale feature enhancement. The problem is that the original YOLOv5 algorithm does not make full use of the relationship between the feature layers, resulting in the loss of target semantic information and a large number of parameters. First, a bidirectional multi‐scale feature‐enhanced weighted fusion backbone network is constructed to extract target features repeatedly. It enhances the fusion ability of shallow detail features and high‐level semantic information to capture richer multi‐scale semantic information. Second, the NCA attention module is built and integrated into the feature fusion network to enhance the critical characteristics of the target region. Finally, the Ghost module is used instead of the convolutional blocks in the original network to lighten the model while reducing the network complexity and training difficulty. Experimental results show that the improved YOLOv5 algorithm achieves 78.8% mAP@0.5 for the PASCAL VOC2012 dataset, which is 1.5% higher than the original algorithm, at 62.5 FPS. The number of parameters is also reduced by 43.6%. The mAP@0.5 on the self‐made metal foreign object dataset reached 98.4%, at 58.8 FPS, which can meet the requirements of end‐device deployment and real‐time detection.

show abstract

Feature purification fusion structure for fabric defect detection

Cited by 2 publications

References 28 publications

Fabric defect detection based on feature enhancement and complementary neighboring information

Fabric defect detection based on feature enhancement and complementary neighboring information

A Lightweight YOLO Object Detection Algorithm Based on Bidirectional Multi‐Scale Feature Enhancement

Contact Info

Product

Resources

About