Fabric defect detection based on visual saliency map and SVM

To improve the accuracy of surface defect detection, an approach of defect inspection based on visual saliency map and Support Vector Machine(SVM) is proposed. Monochrome fabric defect images are taken as examples in this paper. By analyzing the visual saliency maps of these images, the global associated value and the background associated value are extracted as the two features. After being normalized, the two features are taken as the input of Support Vector Machine(SVM). Then, the classifier is trained and the images with fabric defects or not are classified. Experiments results show that the method can achieve higher classification accuracy. Due to the way of extracting features, the proposed approach has a nice adaptability.