Textural Defect Segmentation Using a Fourier-Domain Maximum Likelihood Estimation Method

Abstract

When automatically inspecting textured surface defects, the most important step is to segment the defects from the background. For complicated textures, however, defect segmentation is still a challenging problem. In this paper, we use a Fourier-domain maximum likelihood estimator (FDMLE) based on the fractional Brownian motion (FBM) model to inspect surface defects of textile fabrics. From the experiments, we obtain good results for defect segmentation, and find the method's performance is invariant under geometric transformation.

Get full access to this article

View all access options for this article.

References

Amet, A.L. , Ertüzün, A. , and Ercil, A. , Texture Defect Detection Using Domain Co-occurrence Matrices, in "Image Analysis and Interpretation, IEEE Southwest Symposium ," 1998, pp. 205-210.

Benhamou, C.L. , Lespessailles, E. , and Jacquet, G. , Fractal Organization of Trabecular Bone Images, on Calcaneus Radiographs, J. Bone Miner. Res. 9, 1909-1918 (1994).

Chetverikov, D. , Texture Imperfections, Patt. Recog. Lett. 6(1), 45-50 (1987).

Conci, A. , and Proenca, C.B. , A Fractal Image Analysis System for Fabric Inspection Based on a Box-counting Method, Comput. Net. ISDN Sys. 30, 1887-1895 (1998).

Descombes, X. , and Sigelle, M. , Estimating Gaussian Markov Filed Parameters in a Nonstationary Framework: Application to Remote Sensing Imaging , IEEE Trans. Image Proc. 8 (4), 490-503 (1999).

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. 14 (1), 139-146 (1984).

Fortin, C. , Kumaresan, R. , Ohley, W. , and Hoefer, S. Fractal Dimension in the Analysis of Medical Images, IEEE Eng. Med. Biol. 6, 65-71 (1992).

Haralick, R.M. , Shanmugan, K. , and Dinstein. I. , Textural Features for Image Classification , IEEE Trans. Sys. Man Cybernet. 3 (6), 610-621 (1973).

Hoefer. S. , Hannachi, H. , Pandit, M. , and Kumaresan. R. , Isotropic Two-Dimensional Fractional Brownian Motion and its Application in Ultrasonic Analysis, in "Proc. 14th IEEE Engineering in Medicine and Biology Society Conference." 1992, pp. 1267-1269.

10.

Huang, Q. , Lorch, J.R. , and Dubes, R.C. , Can the Fractal Dimension of Images Be Measured? Pan. Recogn. 27 (3), 339-349 (1994).

11.

Ibarra, P.F. , Asensi, M.D. Almagro , L.A. , and Garcia-Chamizo , J.M. , Segmentation of Defect in Textile Fabric Using Semi-cover Vector and Self-organization , in " International Conference on Quality Control by Artificial Vision," 1995. pp. 58-64.

12.

Jasper. W.J. , Garnier, S.J. , and Potlapalli . H. , Texture Characterization and Defect Detection Using Adaptive Wavelets, Optic. Eng. 35 (11), 3140-3148 (1996 ).

13.

Lundahl, T. , Ohley, W.J. , Kay, S.M. , and Siffert, R. , Fractional Brownian Motion: A Maximum Likelihood Estimator and Its Application to Image Texture, IEEE Trans. Med. Imaging 5 (3), 152-161 (1986).

14.

Mandelbrot, B.B. , How Long is the Coast of Britain? Statistical Self-Similarity and Fractional Dimension, Science 156, 636-638 (1967).

15.

Mandelbrot, B.B. , and Ness, J.W. , Fractional Brownian Motion, Fractional Noises and Applications, SIAM Rev. 10 (4), 422-436 (1968).

16.

Mandelbrot, B.B. , "The Fractal Geometry of Nature," W.H. Freeman and Company, NY, 1983 , pp. 4-73.

17.

Paget, R. , and Longstaff, I.D. , Texture Synthesis via a Noncausal Nonparametric Multiscale Markov Random Field , IEEE Trans. Image Proc. 7 (6), 925-931 (1998).

18.

Sari-Sarraf, H. , and Goddard, J.S. , Robust Defect Segmentation in Woven Fabrics , in "Proc. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition," 1998 , pp. 938-944.

19.

Sarkar, N. , and Chaudhuri, B.B. , An Efficient Approach to Estimate Fractal Dimension of Textural Images , Patt. Recog. 25 (9), 1035-1041 (1992).

20.

Sarkar, N. , and Chaudhuri, B.B. , An Efficient Differential Box-counting Approach to Compute Fractal Dimension of Images, IEEE Trans. Sys. Man Cybernet. 24 (1), 115-120 (1994).

21.

Siew, L.H. , Hodgson, R.M. , and Wood, E.J. , Texture Measures for Carpet Wear Assessment, IEEE Trans. Patt. Anal. Mach. Intell. 10 (1) (1988).

22.

Voss, R.F. , Characterization and Measurement of Random Fractals, Phys. Scrip. 13, 27-32 (1986).

23.

Wen, C.-Y. , and Acharya, R. , Self-Similar Texture Characterization Using a Fourier-domain Maximum Likelihood Estimation Method, Patt. Recog. Lett. 19, 735-739 (1998).

24.

Wen, C.-Y. , Chiu, S.-H. , Hsu, W.-S. , and Hsu, G.-H. , Defect Segmentation of Texture Images with Wavelet Transform and a Co-occurrence Matrix, Textile Res. J. 71 (8), 743-749 (2001).

25.

Weszka, J.S. , Dyer, C.R. , and Rosenfeld , A. , A Comparative Study of Texture Measures for Terrain Classification, IEEE Trans. Sys. Man Cybernet. 6 (4), 269-285 (1976).

26.

Zeichen, G. , Hufnagand, H. , and Berger, M. , Flexible Industrial Inspection of Surface Defects Using a Transputer Image Processing Systems, SPIE 2183, 112-119 (1994).

27.

Zhang, J. , and Oe, S. , Texture Image Segmentation Method Based on Wavelet Transform and Neural Networks , in "Proc. 1998 IEEE International Conference on Systems, Man, and Cybernetics," Part 5, 1998, pp. 4595-4600.

28.

Zhang, J. , Wang, D. , and Tran, Q.N. , A Wavelet-Based Multiresolution Statistical Model for Texture, IEEE Trans. Image Proc. 7 (11), 1621-1627 (1998).