Pattern Recognition of Fabric Defects Using Case-Based Reasoning

Abstract

In this paper, we evaluate the efficiency and accuracy of a method of detecting fabric defects that have been classified into different categories by case-based reasoning (CBR). It shows significant promise for improving the effectiveness of complex and unstructured decision making. Four kinds of fabric defects most likely to be found during weaving were learned by CBR, which is both a paradigm for computer-based problem-solvers and a model of human cognition. The method used for processing image feature extraction is a co-occurrence-based method, by means of which six feature parameters are obtained. However, the design of appropriate case-retrieval mechanisms is still challenging. This paper presents a genetic algorithm (GA)-based approach to enhance the case-matching process. The results show that fabric defects inspected by means of image recognition in accordance with the CBR agree approximately with initial expectation.

Keywords

pattern recognition genetic algorithm co-occurrence case-based reasoning

Get full access to this article

View all access options for this article.

References

Wood, W.H. and Agogino, A.M. , Case-based Conceptual Design Information Server for Concurrent Engineering, Comput. Aided Des. 28(5), 361-369 (1996).

Aha, D.W. , Tolerating Noisy, Irrelevant and Novel Attribute in Instanced-Based Learning Algorithms, Int. J. Man Mach. Stud. 36, 267-287 (1992).

Bradley, P. , Case-based Reasoning : Business Applications, Comm. ACM 37(3), 40-43 (1994).

Don, H.S. , Fu, K.S. , Liu, C.R. , and Lin, W.C. , Metal Surface Inspection Using Image Processing Techniques, IEEE Trans. Sys. Man Cybernet. SMS-14(1), 139-146 (1984).

Haralick, R.M. , Shanmugam, K. , and Dinstein, I. , Texture Features for Image Classification , IEEE Trans. Sys. Man Cybernet. SMC- 3, 610-621 ( 1973).

Lin, J.J. , Applying a Co-occurrence Matrix to Automatic Inspection of Weaving Density for Woven Fabrics, Textile Res. J. 72(6), 486-490 (2002).

Sobus, J. , Pourdeyhimi, B. , Gerde, J. , and Ulcay, Y. , Assessing Changes in Texture Periodicity Due to Appearance Loss in Carpets Gray Level Co-occurrence Analysis, Textile Res. J. 61(10), 557-567 (1991).

Gonzalez, R.C. , and Woods, R.E. , "Digital Image Processing", Addison-Wesley Publishing Co. , NY, 1992.

Lien, K.J. , "Digital Image Processing", Zoo-Lin Publishing Co., Taipei, R.O.C., 1992.

10.

Brieman, L. , Friedman, J.H. , Olshen, R.A. , and Stone, C.J. , "Classification and Regression Trees", Wadsworth International Group, Belmont, CA, 1984.

11.

Gen, M. and Cheng, R. , "Genetic Algorithms & Engineering Design", John Wiley & Sons, Inc., NY, 1997.

12.

Goldberg, D. , "Genetic Algorithms in Search, Optimization, and Machine Learning", Addison-Wesley, Reading, MA, 1989 .

13.

Lin, J.J. , A Genetic Algorithm for Searching Weaving Parameters for Woven Fabrics, Textile Res. J. 73(2), 105-112 (2003)

14.

Khotanzad, A. , and Kashyap, R.L. , Feature Selection for Texture Recognition Based on Image Synthesis, IEEE Trans. Sys. Man Cybernet. SMC- 17(6), 1087-1095 (1987 ).

15.

Albright, S.C. , Winston, W.L. , and Zappe, C. "Data Analysis and Decision Making with Microsoft Excel", International Thomson Publishing Co., NY, 1999.