A New Voting Approach to Texture Defect Detection Based on Multiresolutional Decomposition

Wavelets have provided the researchers with significant positive results, by entering the texture defect detection domain. The weak point of wavelets is that they are one-dimensional by nature so they are not efficient enough to describe and analyze two-dimensional functions. In this paper we present a new method to detect the defect of texture images by using curvelet transform. Simulation results of the proposed method on a set of standard texture images confirm its correctness. Comparing the obtained results indicates the ability of curvelet transform in describing discontinuity in two-dimensional functions compared to wavelet transform

Authors:

• B. B. M. Moasheri
• S. Azadinia

Keywords:

• Curvelet
• Defect detection
• Wavelet.

References:

[1] Y. Han, P.Shi, 2007, Image and Vision Computing 25, An adaptive level-selecting wavelet transform for texture defect detection, pp. 1239-1248.
[2] A.Monadjemi, PHD thesis, October 2004, university of Bristol, Towards
Efficient Texture Classification and Abnormality Detection
[3] X X.Xie, M.Mirmehdi, IEEE Transaction on Pattern Analysis and Machine Intelligence, 2007, TEXEMS: Texture Exemplars for Defect
Detection on Random Textured Surfaces, vol. 29, no. 8, pp. 1454-1464.
[4] J.L.Sobral, Springer 2005, Leather Inspection based on Wavelets.
[5] H.Yan-fang, S.Peng-fei,2006, Zhejiang University Press, co-published
with Springer-Verlag GmbH, Mean shift texture surface detection based
on WT and COM feature image selection, Vol. 7, Np. 6, pp 969-975.
[6] A. Latif-Amet, A. Ertu¨zu¨n, A. Ercil, 2000, Image and Vision Computing, An efficient method for texture defect detection: sub-band
domain co-occurrence matrices, Vol. 18, pp 543-553.
[7] Y. X. Zhi, K. H. Pang and H. C. Yung, IEEE 2001, Fabric Defect Detection Using Adaptive Wavelet, pp. 3697-3700.
[8] E.Kulak, October 2002, Sabanc1 University, Analysis of Textural Image
Features for Content Based Retrieva.
[9] G.Fan, and X.Xia, 2003, IEEE Trans, Wavelet-Based Texture Analysis
and Synthesis Using Hidden Markov Models, pp. 106-120.
[10] C.K.Mohan, M.Vijayaraghavan, J.Rengarajan, 2002, Dept. of IEEE, Real Time Texture Defect Detection using Sub-Band Domain Feature
Extraction.
[11] M.C.Lee, C.Pun, Image Analysis and Interpretation, 2000, Texture
Classification Using Dominant Wavelet Packet Energy Features, pp. 301-304.
[12] G.Lambert, F.Bock, IEEE Proceedings of the International Conference
on Image Processing, 1997 , Wavelet Methods for Texture Defect
Detection,Vol. 3, p. 201.
[13] S.Kim, H.Bae, S.Cheon, and K.Kim, Computational Science and Its
Applications - ICCSA 2005, On-line Fabric-Defects Detection Based on
Wavelet Analysis, pp. 1075-1084.
[14] D.A. Karras and B.G. Mertzios, Springer-Verlag Berlin Heidelberg
2002, Improved Defect Detection in Manufacturing Using Novel
Multidimensional Wavelet Feature Extraction Involving Vector
Quantization and PCA Techniques.
[15] C.kwak, J. A.Ventura and K.Tfang-sazi, Journal of Intelligent
Manufacturing, 2000, A neural network approach for defect
identification and classification on leather fabric, pp. 485-499.
[16] E.J.Candés and L.Demanet; 2004, Curvelets and Wave Equations.
[17] L.Dettori,and L.Semler; April 2007, A comparison of wavelet, ridgelet,
and curvelet-based texture classification algorithms in computed
tomography , vol. 37, no. 4 , pp. 486-498.
[18] Boubchir,L. Fadili, J.M.; "Multivariate statistical modeling of images
with the curvelet transform", Proceedings of the 8th International
Symposium, pp. 747- 750, vol. 2, 2005.