Fabric Defect Detection: A Novel Approach Using Hybrid Deep Learning and Image Segmentation

  • Khan M. A.
  • Sayyed Ajij. D
  • Mazher Khan
Keywords: Fabric defects, Image analysis, Convolutional Neural Networks

Abstract

Abstract: Fabric defects significantly impact the textile industry, leading to production delays, material waste, and customer dissatisfaction. Existing image processing methods for fabric defect detection often struggle with complex defect patterns or require extensive training data for specific defect types. This paper proposes a novel approach that combines deep learning and image segmentation techniques for robust and adaptable fabric defect detection. This hybrid approach leverages the power of deep learning for feature extraction and image segmentation for precise defect localization.

Author Biographies

Khan M. A.

Research Scholar Dr. BAMU, CSN (Aurangabad)

Sayyed Ajij. D

Department of ECE, Maharashtra Institute of Technology, CSN (Aurangabad)

Mazher Khan

Department of ECE, Maharashtra Institute of Technology, CSN (Aurangabad)

References

1. M. Kuo et al., An Automated Inspection System for Textile Fabrics Based on Visual Image Processing, Computers in Industry, vol. 30, no. 2, pp. 71-81, 1996.
2. H. P. Ngan et al., Automated Fabric Defect Detection—A Review, Image and Vision Computing, vol. 29, no. 7, pp. 442-458, 2011.
3. S. Kumar et al., Computer-Vision-Based Fabric Defect Detection: A Comprehensive Review, IEEE Transactions on Industrial Electronics, vol. 55, no. 1, pp. 348-363, 2008.
4. P. Perng et al., An Efficient and Effective Method for Automated Fabric Defect Detection, Textile Research Journal, vol. 75, no. 1, pp. 51-60, 2005.
5. X. Xie et al., A Review of Recent Advances in Surface Defect Detection Using Texture Analysis Techniques, Electronic Letters on Computer Vision and Image Analysis, vol. 7, no. 3, pp. 1-22, 2008.
6. R. M. Haralick et al., Statistical and Structural Approaches to Texture, Proceedings of the IEEE, vol. 67, no. 5, pp. 786-804, 1979.
7. C. J. Tsai et al., Development of a Real-Time Vision-Based Fabric Inspection System, International Journal of Advanced Manufacturing Technology, vol. 15, no. 4, pp. 594-603, 1999.
8. M. P. Papadakis et al., An Image Processing System for Real-Time Fabric Defect Detection, Pattern Recognition, vol. 28, no. 9, pp. 1535-1546, 1995.
9. Y. K. Chan et al., Fabric Inspection Based on the Segmentation of Defect Regions, Journal of Materials Processing Technology, vol. 139, no. 1-3, pp. 245-250, 2003.
10. J. Y. Hsu et al., Fabric Defect Detection and Classification Using Image Processing Techniques, Textile Research Journal, vol. 76, no. 6, pp. 442-451, 2006.
11. Y. F. Zhang et al., Fabric Defect Detection Using Local Binary Patterns and Multilevel Image Thresholding, Journal of Textile Institute, vol. 102, no. 8, pp. 679-687, 2011.
12. B. S. Rajpoot et al., Wavelet-Based Fabric Defect Detection Using Rank-Level Fusion, IEEE Transactions on Industrial Electronics, vol. 55, no. 12, pp. 4272-4280, 2008.
13. T. K. Ho et al., Image-Based Fabric Defect Detection Using Machine Learning, Journal of Manufacturing Systems, vol. 34, pp. 392-401, 2015.
14. P. K. Wong et al., Automated Vision System for Real-Time Fabric Inspection and Defect Classification, Computers in Industry, vol. 55, no. 2, pp. 165-176, 2004.
15. H. Merzlyakov et al., Hybrid Approaches to Fabric Defect Detection Based on Image Processing and Artificial Intelligence, Textile Research Journal, vol. 88, no. 5, pp. 540-552, 2018.
How to Cite
Khan M. A., Sayyed Ajij. D, & Mazher Khan. (1). Fabric Defect Detection: A Novel Approach Using Hybrid Deep Learning and Image Segmentation. Revista Electronica De Veterinaria, 25(1), 1822- 1828. https://doi.org/10.69980/redvet.v25i1.1020
Section
Articles