Defect Detection in Textile Fabric Images Using Sub-Band Domain Subspace Analysis

In this work, a new model that combines the concepts of wavelet transformation and subspace analysis tools, like Independent Component Analysis, Topographic Independent Component Analysis, and Independent Subspace Analysis, is developed for the purpose of defect detection in textile images. In previous works, it has been shown that reduction of the textural components of the textile image by preprocessing has increased the performance of the system. Based on this observation, in present work, the aforementioned subspace analysis tools are aimed to be applied on the sub-band images. The feature vector of a sub-window of a test image is compared with that of the defect-free image in order to make a decision. This decision is based on a Euclidean distance classifier. The performance increase that results using wavelet transformation prior to subspace analysis has been discussed in detail. While all the subspace analysis methods has been found to lead to the same detection performances, as a further step, independent subspace analysis is used to classify the detected defects according to their directionalities.