Defect detection in textile fabric images using wavelet transforms and independent component analysis
In this paper, a new method based on the use of wavelet transformation prior to independent component analysis for solving the problem of defect detection in textile fabric images is presented. Different subbands of the wavelet packet tree scheme of the defect-free subwindows are obtained and independent components of these subbands are calculated as basis vectors. The true feature vectors corresponding to these basis vectors are computed. The test subwindow is labeled as defective, or not according to the Euclidean distance between the true feature vector representing the non-defective regions and the feature vector of the subwindow under test. The advantage of adding wavelet analysis prior to the independent component analysis is presented.
Unable to display preview. Download preview PDF.
- 1.A. Atlay, “Automated Defect Inspection of Textile Fabrics Using Machine Vision Techniques,” MS Thesis (Boğaziçi University, 1995).Google Scholar
- 2.R. Meylani, C. Öden, A. Ertüzün, A. Erçil, “2-D Iteratively Reweighted Algorithm for Adaptive Detection of Defects in Textured Images,” to appear in IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences (2006). “Texture Analysis Using Adaptive Two-Dimensional Lattice Filters,” MS Thesis (Boğaziçi University, Istanbul, Turkey, 1997).Google Scholar
- 4.O. G. Sezer, A. Ertuzun, and A. Ercil, “Independent Component Analysis for Texture Defect Detection,” Pattern Recognition and Image Analysis 14(2), 303–307 (2004).Google Scholar
- 5.A. Hyvarinen and E. Oja, “Independent Component Analysis: Algorithms and Applications,” Neural Networks, 411–430 (2000).Google Scholar
- 6.A. Hyvarinen, “Survey on Independent Component Analysis,” Neural Computing Surveys, 94–128 (1999).Google Scholar
- 7.J. Hurri, A. Hyvarinen, J. Karhunen, and E. Oja, “Image Feature Extraction Using Independent Component Analysis,” http://citeseer.nj.nec.com/hurri96image.html.