A significant attention of researchers has been drawn by automated textile inspection systems in order to replace manual\ninspection, which is time consuming and not accurate enough. Automated textile inspection systems mainly involve two\nchallenging problems, one of which is defect classification. The amount of research done to solve the defect classification problem\nis inadequate. Scene analysis and feature selection play a very important role in the classification process. Inadequate scene analysis\nresults in an inappropriate set of features. Selection of an inappropriate feature set increases the complexities of the subsequent\nsteps and makes the classification task harder. By taking into account this observation, we present a possibly appropriate set of\ngeometric features in order to address the problem of neural network-based textile defect classification. We justify the features\nfrom the point of view of discriminatory quality and feature extraction difficulty.We conduct some experiments in order to show\nthe utility of the features. Our proposed feature set has obtained classification accuracy of more than 98%, which appears to be\nbetter than reported results to date.
Loading....