Sage Journals: Discover world-class research

Abstract

A fabric defect detecting system that uses an advanced method involving computer vision and image analysis is capable of defect classification. Image pre-processing techniques that enhance raw images are applied before defect classification by a K-means algorithm and statistical method. These generate a Bayes classifier from which a decision surface is created for a classification procedure that can categorize defective or nondefective regions. Defect detection of the test fabric image is implemented by the decision surface from the training fabric image. The advantages of using the decision surface are a reduction in the training step and the ability to rapidly classify fabric. Experimental results confirm the reliable and reasonable classification ability of the proposed system.

Get full access to this article

View all access options for this article.

References

1. ASTM Standard, D1 170-94, Standard test neps, vegetable matter and colored fibers in wool top.

2. ASTM Standard, D3990-93, Standard terminology relating to fabric defects.

3. Balakrishnan, H. , Venkataraman, S. , and Jayaraman, S. , FDICS: A Vision-based System for the Identification and Classification of Fabric Defects, J. Textile Inst. 89, 365–380 (1998).

4. Castleman, K. R. , “Digital Image Processing,” Prentice-Hall, NY, 1996.

5. Fernand, S. C. , Zhigang, F. , and Stephane, A. , Automated Inspection of Textile Fabrics Using Textural Models, IEEE Trans. Pattern Anal. Mach. Intell. 13, 803–808 (1991).

6. Harwood, R. J. , Norton, L. , and Campbell, R. A. , Inspection of the Back of Woven Carpets for Pattern Distortion, J. Textile Inst. 89, 381–389 (1998).

7. IMAQ Vision for G Reference manual, National Instrument, 1997.

8. Jasper, W. J. , and Potlapalli, H. , Image Analysis of Mispicks in Woven Fabric, Textile Res. J. 65, 683–692 (1995).

9. Jeong, S. H. , and Kim, S. H. , A Study on the Evaluation of Evenness of the Areal Density of Nonwoven Fabrics (I), J. Kor. Fiber Soc. 35, 626–631 (1998).

10.

10. Jeong, S. H. , and Kim, S. H. , A Study on the Evaluation of Evenness of the Areal Density of Nonwoven Fabrics (II), J. Kor. Fiber Soc. 35, 702–708 (1998).

11.

11. Kim, J. J. , A Study on the Evaluation of Appearance of Solid-Shade Fabrics, J. Kor. Fiber Soc. 32, 1047–1055 (1995).

12.

12. Mallik, B. , and Datta, A. K. , Defect Detection in Fabrics with a Joint Transform Correlation Technique: Theoretical Basis and Simulation, Textile Res. J. 69, 829–835 (1999).

13.

13. Mcgregor, R. , Mershon, D. H. , and Pastore, C. M. , Perception, Detection, and Diagnosis of Appearance Defects in Fabrics, Textile Res. J. 64, 584–591 (1994).

14.

14. Parker, J. R. , “Practical Computer Vision Using C,” John Wiley & Sons, NY, 1994, pp. 123–1999.

15.

15. Pourdeyhimi, B. , Dent, R. , Jerbi, A. , Tanaka, S. , and Deshpande, A. , Measuring Fiber Orientation in Nonwovens, Part V: Real Webs, Textile Res. J. 69, 185–192 (1999).

16.

16. Srinivasan, K. , Dastoor, P. H. , Padhakrishnaiah, P. , and Jayaraman, S. , FDAS: A Knowledge-based Framework for Analysis of Defects in Woven Textile Structures, J. Textile Inst. 83, 431–448 (1992).

17.

17. Thompson, C. M. , Image Processing Toolbox For Use with MATLAB®, The Math Works Inc., 1-54-1-83, 1993.

18.

18. Tou, J. T., and Gonzalez, R. C., “Pattern Recognition Principles,” Addison Wesley, NY, 1974.

19.

19. Xu, B. , and Ting, Y. L. , Fiber-image Analysis, Part I: Fiberimage Enhancement, J. Textile Inst. 87, 274–283 (1996).

20.

20. Xu, B. , and Yu, L. , Determining Fiber Orientation Distribution in Nonwovens with Hough Transform Techniques, Textile Res. J. 67, 563–571 (1997).

21.

21. Xu, B. , Fang, C. , and Watson, M. D. , Clustering Analysis for Cotton Trash Classification, Textile Res. J. 69, 656–662 (1999).

22.

22. Xu, B. , Instrumental Evaluation of Fabric Pilling, J. Textile Inst. 88, 488–499 (1997).

23.

23. Zhang, Y. F. , and Breesee, R. R. , Fabric Defect Detection and Classification Using Image Analysis, Textile Res. J. 65, 1–9 (1995).

Detecting Fabric Defects with Computer Vision and Fuzzy Rule Generation. Part I: Defect Classification by Image Processing

Abstract

Get full access to this article

References