Fabric Defect Detection Based on Membership Degree of Regions

Abstract

The detection of fabric defects is an important part of fabric quality control, and hence is thus a research hotspot in the textile industry. With the aim of effectively detecting fabric defects, this paper describes an improved fabric defect detection method based on the membership degree of each fabric region (TPA). By analyzing the regional features of fabric surface defects, the saliency of defect regions can be determined using the extreme point density map of the image and the features of the membership function region. A threshold iterative method and morphological processing are used to ensure the precise and accurate detection of fabric defects. Experimental results show that compared with two classical fabric defect detection methods, the proposed detection method can detect fabric defects more effectively while also suppressing the interference of noise and background textures. Additionally, numerical results demonstrate the validity and feasibility of the proposed method to satisfy the requirements of online detection.