On the Use of Binary Features in a Rule-Based Approach for Defect Detection on Patterned Textiles

The quality assurance of fabrics is a fundamental issue in the textile manufacturing industry. Automatic and accurate detection of defects is one of the most important and challenging tasks in order to guarantee the quality of fabrics. In this paper, we propose an approach for the defect detection on textiles with patterned texture using a rule-based classification system and the local binary features. In our proposal, rules are automatically learned from the textile samples using a rough-set-based approach. The proposed system analyzes the texture of fabrics using a combination of local binary features, which have shown to be highly discriminatory. Our approach is performed in two stages: training and testing. During the training stage, binary features from both defective and defect-free images are extracted and used to formulate an ensemble of the rough-set-based rules. For the testing stage, we submit different samples of fabrics, and they are classified as defective or defect-free. The proposed method is quantitatively evaluated on an extensive dataset of images of the defective fabrics. These experiments show that the proposed approach results in higher accuracy, in comparison with those obtained by the state-of-the-art methods.