Fabric Faults Robust Classification Based on Logarithmic Residual Shrinkage Network in a Four-Point System
Source abstract
Abstract
Accurate and robust detection of fabric defects under noisy conditions is a major challenge in textile quality control systems. To address this issue, we introduce a new model called the Logarithmic Deep Residual Shrinkage Network (Log-DRSN), which integrates a deep attention module. Unlike standard residual shrinkage networks, the proposed Log-DRSN applies logarithmic transformation to improve resistance to noise, particularly in cases with subtle defect features. The model is trained and tested on both clean and artificially noised images to mimic real-world manufacturing conditions. The experimental results reveal that Log-DRSN achieves superior accuracy and robustness compared to the classical DRSN, with performance scores of 0.9917 on noiseless data and 0.9640 on noisy data, whereas the classical DRSN achieves 0.9686 and 0.9548, respectively. Despite its improved performance, the Log-DRSN introduces only a slight increase in computation time. These findings highlight the model’s potential for practical deployment in automated fabric defect inspection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Infrastructure Maintenance and Monitoring · Structural Health Monitoring Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Erzincan Binali Yildirim University, Erzincan 24100, Türkiye
Department of Computer Engineering, Firat University, Elazığ 23119, Türkiye
Agteks Ltd., Istanbul 34520, Türkiye
References (31)
Show source-provided references
1. Hanbay, K., Talu, M.F., Özgüven, Ö.F., and Öztürk, D. (2015, January 16–19). Fabric defect detection methods for circular knitting machines. Proceedings of the 2015 23rd Signal Processing and Communications Applications Conference (SIU), Malatya, Turkey.10.1109/SIU.2015.7129932 ↗
2. Zhang, H.-W., Zhang, L.-J., Li, P.-F., and Gu, D. (2018, January 25–27). Yarn-dyed fabric defect detection with YOLOV2 based on deep convolution neural networks. Proceedings of the 2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS), Enshi, China.10.1109/DDCLS.2018.8516094 ↗
3. Wang, P.-H., and Lin, C.-C. (2022, January 6–8). Data augmentation method for fabric defect detection. Proceedings of the 2022 IEEE International Conference on Consumer Electronics-Taiwan, Taipei, Taiwan.10.1109/ICCE-Taiwan55306.2022.9869278 ↗
4. Liu, K.-H., Chen, S.-J., and Liu, T.-J. (2022, January 6–8). Unsupervised UNet for fabric defect detection. Proceedings of the 2022 IEEE International Conference on Consumer Electronics-Taiwan, Taipei, Taiwan.10.1109/ICCE-Taiwan55306.2022.9869207 ↗
5. Liu, K.-H., Chen, S.-J., Chiu, C.-H., and Liu, T.-J. (2022, January 18–22). Fabric defect detection via unsupervised neural networks. Proceedings of the 2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), Taipei, Taiwan.10.1109/ICMEW56448.2022.9859266 ↗
6. Deep adversarial data augmentation for fabric defect classification with scarce defect data10.1109/TIM.2022.3185609 ↗
7. Tactile-Based fabric defect detection using convolutional neural network with attention mechanism10.1109/TIM.2022.3165254 ↗
8. Pixel-Wise semisupervised fabric defect detection method combined with multitask mean teacher10.1109/TIM.2022.3162286 ↗
9. Complex pattern jacquard fabrics defect detection using convolutional neural networks and multispectral imaging10.1109/ACCESS.2022.3144843 ↗
10. A fabric defect detection method based on deep learning10.1109/ACCESS.2021.3140118 ↗
11. Sudha, K.K., and Sujatha, P. (2021, January 16–17). Robust and rapid fabric defect detection using EGNet. Proceedings of the 2021 4th International Conference on Computing and Communications Technologies (ICCCT), Chennai, India.10.1109/ICCCT53315.2021.9711875 ↗
12. Xia, D., Yu, Z., and Deng, X. (2021, January 10–12). A real-time unsupervised two-stage framework for fabric defect detection. Proceedings of the 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST), Guangzhou, China.10.1109/IAECST54258.2021.9695639 ↗
13. Fabric Defect Detection Based on Attention Mechanism and Improved YOLOv5 Network
14. Sakhare, K., Kulkarni, A., Kumbhakarn, M., and Kare, N. (2015, January 28–30). Spectral and spatial domain approach for fabric defect detection and classification. Proceedings of the 2015 International Conference on Industrial Instrumentation and Control (ICIC), Pune, India.10.1109/IIC.2015.7150820 ↗
15. Durmuşoğlu, A., and Kahraman, Y. (2021, January 6–8). Detection of fabric defects using convolutional networks. Proceedings of the 2021 Innovations in Intelligent Systems and Applications Conference (ASYU), Elazig, Turkey.10.1109/ASYU52992.2021.9599071 ↗
16. Dafu, Y. (2019, January 22–24). Classification of fabric defects based on deep adaptive transfer learning. Proceedings of the 2019 Chinese Automation Congress (CAC), Hangzhou, China.10.1109/CAC48633.2019.8996969 ↗
17. Vladimir, G., Evgen, I., and Aung, N.L. (2019, January 28–31). Automatic detection and classification of weaving fabric defects based on digital image processing. Proceedings of the 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), Saint Petersburg and Moscow, Russia.10.1109/EIConRus.2019.8657318 ↗
18. Ma, Y., Wang, C., Jiang, C., and Li, Z. (2022). Deep residual shrinkage networks for EMG-based gesture identification. arXiv.
19. Deep residual shrinkage networks for fault diagnosis10.1109/TII.2019.2943898 ↗
20. Zhang, Z., Li, H., and Chen, L. (2021, January 11–13). Deep residual shrinkage networks with self-adaptive slope thresholding for fault diagnosis. Proceedings of the 2021 7th International Conference on Condition Monitoring of Machinery in Non-Stationary Operations (CMMNO), Guangzhou, China.10.1109/CMMNO53328.2021.9467549 ↗
21. Paul, A. (2022, December 25). 4 Point System. Available online: https://www.scribd.com/doc/102427507/4-Point-System.
22. Sarkar, P. (2022, December 25). How to Use 4 Point System in Fabric Inspection?. Available online: https://www.onlineclothingstudy.com/2012/08/how-to-use-4-point-system-in-fabric.html.
23. Zhou, Y., Yuan, X., Cui, X., Song, Y., Sun, Z., and Fan, J. (2021, January 22–24). Fault diagnosis based on deep residual shrinkage network and maximum mean discrepancy. Proceedings of the 2021 China Automation Congress (CAC), Beijing, China.10.1109/CAC53003.2021.9728005 ↗
24. Comparative study of different noise models and effective filtering techniques
25. Boyat, A.K., and Joshi, B.K. (2015). A review paper: Noise models in digital image processing. arXiv.10.5121/sipij.2015.6206 ↗
26. Speckle noise: Modelling and implementation
27. Salt and pepper noise: Effects and removal
28. Bhatia, A. (2013, January 16–17). Salt and pepper noise removal from medical image through adaptive median filter. Proceedings of the IT International Conference 2013, Washington, DC, USA.
29. Liu, J., Zhou, Q., and Zhang, B. (2021, January 23–25). Deep residual shrinkage network for few-shot learning. Proceedings of the 2021 3rd International Conference on Intelligent Control, Measurement and Signal Processing and Intelligent Oil Field (ICMSP), Xi′an, China.10.1109/ICMSP53480.2021.9513349 ↗
30. Cheng, L., and He, C. (2021, January 4–6). Fish recognition based on deep residual shrinkage network. Proceedings of the 2021 4th International Conference on Robotics, Control and Automation Engineering (RCAE), Wuhan, China.10.1109/RCAE53607.2021.9638791 ↗
31. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7–13). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.123 ↗