Plain Woven Fabric Defect Detection using GLCM based Feature Extraction

Abstract

An accurate fabric defect detection is done in based on extraction of features from Gray level co -occurrence matrix(GLCM). The process of extracting salient features plays a crucial role in Automatic fabric defect detection. The proposed system makes a fabric analysis to classify whether the fabric is defect free or defected using several Digital image processing techniques. This paper presents the application of gray level co-occurrence matrix (GLCM) to extract second order statistical texture features for classification of various defects in plain woven fabric images. The salient features namely area, entropy, standard deviation, smoothness, skewness, max intensity, min intensity, mean, standard deviation and energy are calculated from GLCM. The results show that these texture features have high discrimination accuracy in classification of various defects in Automatic fabric defect detection where a support vector machine (SVM ) is being used as the classifier.