Education, Science, Technology, Innovation and Life
Open Access
Sign In

Fabric defect detection algorithm based on improved RT-DETR

Download as PDF

DOI: 10.23977/autml.2025.060118 | Downloads: 12 | Views: 1220

Author(s)

Ruiming Liu 1, Shuai Huang 1, Xuesong Duan 1, Yunliang Du 1

Affiliation(s)

1 School of Electronic Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu, China

Corresponding Author

Shuai Huang

ABSTRACT

Textiles are important raw materials in industry and life, and China's textile industry plays a key role, but there are more than 80 kinds of surface defects in fabric production, which affect the quality and development of the industry. Current detection algorithms have problems such as insufficient accuracy and limited application scenarios. Manual detection and traditional machine vision methods also have obvious defects. Although algorithms based on deep learning have applications, they have their own shortcomings. Therefore, an improved RT-DETR fabric detection algorithm RT-FDTR is proposed in this study: optimizing the backbone network, introducing C2f_AdditiveBlock module to enhance feature extraction ability; designing DHSA-AIFI module to enhance small target detection and anti-interference ability; developing SCOK-CCFF feature pyramid to optimize feature fusion. Experiments on the fabric defect dataset of Aliyun Tianchi show that the P, R and AP50 of the improved model are 82.2%, 77.1% and 76.5% respectively, which are 6.9%, 2.5% and 3% higher than those of the original RT-DETR-r18, and the parameters are reduced by 20.6%. The detection speed is increased by 9.7FPS, which meets the accuracy and real-time requirements of fabric defect detection in industry.

KEYWORDS

RT-DETR, fabric defect, feature fusion, attention mechanism, ablation experiment

CITE THIS PAPER

Ruiming Liu, Shuai Huang, Xuesong Duan, Yunliang Du, Fabric defect detection algorithm based on improved RT-DETR. Automation and Machine Learning (2025) Vol. 6: 156-169. DOI: http://dx.doi.org/10.23977/autml.2025.060118.

REFERENCES

[1] Jia X J, Ye L H, Deng H T, et al. Classification of primitive patterns of blue calico based on convolutional neural network[J]. Journal of Textile Research, 2020, 41(1): 110-117.
[2] WANG X B, FANG W J, XIANG S. Fabric defect detection based on anchor ⁃ free network [J]. Measurement science and technology, 2023, 34(12): 12.
[3] Zhang L, Zhu W J, Zhu S W. Progress in automatic detection methods and applications of fabric defects[J]. Progress in Textile Science & Technology, 2022(2): 21-26.
[4] Zhang K X, Du J L. Fabric defect detection method based on improved YOLOv5[J]. Modern Electronics Technique, 2024, 47(20): 109-117.
[5] Liu Zhoufeng,Tian Bo,Li Chunlei,Ding Shumin & Xi Jiangtao. CACFNet: Fabric defect detection via context-aware attention cascaded feedback network.Textile Research Journal, 2023, 93(13-14), 3036-3055.
[6] Chen C ,Zhou Q ,Li S , et al.Fabric defect detection algorithm based on improved YOLOv8[J].Textile Research Journal,2025,95(3-4):235-251.
[7] M. Zhang, W. Yu, H. Qiu, J. Yin and J. He, "A Fabric Defect Detection Algorithm Based on YOLOv8," 2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), Chengdu, China, 2023, pp. 1040-1043.
[8] S. S. Mohammed and H. G. Clarke, "Advanced Convolutional Neural Network Approach for Fabric Defect Detection,"2024 Innovations in Intelligent Systems and Applications Conference (ASYU), Ankara, Turkiye, 2024, pp. 1-5.
[9] L. Yao, S. Song and Y. Wan, "Fabric Defect Detection Based on Hybrid Attention Transformer and Improved Cascade R-CNN," 2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Kuching, Malaysia, 2024, pp. 1933-1938.
[10] Zhang Hongwei,Qiao Guanhua,Lu Shuai,Yao Le & Chen Xia. Attention-based Feature Fusion Generative Adversarial Network for yarn-dyed fabric defect detection.Textile Research Journal, 2023, 93(5-6), 1178-1195.
[11] Qin J H, Chen Z L, Wan B X, et al. Green orange detection method in complex orchard environment based on RT-DETR[J]. Electronic Measurement Technology, 2025, 48(11): 175-186.
[12] Y. Zhao et al., "DETRs Beat YOLOs on Real-time Object Detection,"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2024, pp. 16965-16974.

Downloads: 3870
Visits: 177443

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.