An intelligent model for detecting and classifying color-textured fabric defects using genetic algorithms and the Elman neural network

Abstract

In this paper, an intelligent color-textured fabric defect detection and classification model using genetic algorithms and the Elman neural network is introduced. A color ring projection is used for image processing, and the solution for optimization of parameters is based on the genetic algorithm method. The new modified Elman network is proposed to classify the type of fabric defects, which have proportional, integral, and derivative properties. The proposed inspecting model in this study is more feasible and applicable in fabric and stitching garment defect detection and classification.

Keywords

color ring-projection classification Elman neural network fabric defect detection genetic algorithm

Get full access to this article

View all access options for this article.

References

Dorrity JL , Vachtsevanos G. and Jasper W. Real-time fabric defect detection and control in weaving process. Nat Textil Center Annu Rep 1994; 20: 193-202.

Munden L. and Norton WL Machine vision in textile manufacture. Textil Asia 1988; 19: 85-88.

Sirikasemlert A. and Tao XM Objective evaluation of textural changes in knitted fabrics by laser triangulation. Textil Res J 2000; 70: 1076-1087.

Rohrmus D. Invariant texture features for web defect detection and classification . SPIE Proc Mach Vision Syst Inspection Metrol 1999; 38: 144-155.

Song KY , Kittler J. and Petrou M. Defect In random colour textures. Image Vision Comput 1996; 60: 667-683.

Arivazhagan S. and Ganesan L. Texture segmentation using wavelet transform . Pattern Recognit Lett 2003; 24: 3197-3203.

Kumar A. Inspection of surface defects using optimal FIR filters In. Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003; 3(2): 241-244.

Jain AK and Farrokhnia F. Unsupervised texture segmentation using Gabor filters. Pattern Recognit 1991; 24: 1167-1186.

Suen PH and Healey G. Modeling and classifying color textures using random fields in a random environment . Pattern Recognit 1999; 32: 1009-1017.

10.

Panjwan DK and Healey G. Markov random field for unsupervised segmentation of texture color images . IEEE Trans Pattern Anal Mach Intell 1995 ; 17: 939-954.

11.

Sengur A. Wavelet transform and adaptive neuro-fuzzy inference system for color texture classification. Expert Syst Appl, 2007; 34: 2120-2128.

12.

Escofet J. , Navarro RB , Millan MS and Pladellorens JM Detection of local defects in textile webs using Gabor filter. Proc SPIE 1996; 2785: 163-170.

13.

Thai B. and Healey G. Optimal spatial filter selection for illumination-invariant color texture discrimination. IEEE Trans Syst Man Cybern Part B Cybern 2000; 30: 7610-7616.

14.

Kim SC and Kang TJ Fabric surface roughness evaluation using wavelet-fractal method: part II: fabric pilling evaluation. Textil Res J 2005 ; 75: 761-770.

15.

Tsai IS and Hu MC Automatic inspection of fabric defects using an artificial neural network technique. Textil Res J 1996; 66: 474-482.

16.

Tsai DM and Chiang CH Automatic band selection for wavelet reconstruction in the application of defect detection. Image Vision Comput 2003 ; 21: 413-431.

17.

Ngan YT , Pang KH , Yung SP and Ng K. Wavelet based methods on patterned fabric defect detection. Pattern Recognit 2005; 38: 559-576.

18.

Yuen CWM , Wong WK and Qian SQ A hybrid model using genetic algorithm and neural network for classifying garment defects. Expert Syst Appl 2008; 36: 2037-2047.

19.

Shiau YR , Tsai IS and Lin CS Classifying web defects with a back-propagation neural network by color image processing. Textil Res J 2000; 70: 633-640.

20.

Boukouvalas C. , Kittler J. , Marik R. and Petrou M. Color grading of randomly textured ceramic tiles using color histograms. IEEE Trans Ind Electron 1999; 46: 219-226.

21.

Caelli T. and Reye D. On the classification of image regions by colour texture and shape . Pattern Recognit 1993; 26: 461-470.

22.

Tang YY , Li BF , Ma H. and Liu J. Ring-projection-wavelet-fractal signatures: a novel approach to feature to feature extraction. IEEE Trans Circuits Syst Analog Digital Signal Process 1998; 45: 1130-1134.

23.

Tan SC and Kittler J. On colour texture representation and classification In. Proceedings of the 2nd International Conference on Image Processing 1992; 390-395.

24.

Inui S. A computer aided system using a genetic algorithm applied to apparel design . Sen’i Gakkaishi 1994; 50: 593-598.

25.

Zhang YF and Bresee RR Fabric defect detection and classification using image analysis. Textil Res J 1995; 65(1): 1-9.

26.

Jasper W. , Joines J. and Brenzovich J. Fabric defect detection using a genetic algorithm tuned wavelet filter . J Textil Inst 2005; 96: 43-54.

27.

Bounsaythip C. and Alander JT Genetic algorithms applied to image processing In. Proceedings of the 3rd Nordic Workshop on Genetic Algorithms 1997; 14: 423-431, Helsinki .

28.

Elman J. Finding structure in time. Cognitive Sci 1994 ; 14: 179-211.

29.

Sastry PS , Santharam G. and Unnikrishnan KP Memory neuron networks for identification and control of dynamic systems . IEEE Trans Neural Networks 1994; 5: 306-319.

30.

Cheng YC , Qi WM and Jie Z. A new Elman neural network and its dynamic properties. IEEE Conf Cybern Intell 2008; 70: 971-975.

31.

Wong WK , Yuen CWM and Fan DD Stitching inspection using segmented windows technique and BP neural network . Expert Syst Appl 2009; 36: 3845-3856.

32.

Shady E. , Gowayed Y. , Abouiiana M. , Youssef S. and Pastore C. Detection and classification of defects in knitted fabric structures . Textil Res J 2006; 76: 295-300.