Open AccessOne-Class Model for Fabric Defect Detection
Author(s) -
Hao Zhou,
Yixin Chen,
David Troendle,
Byunghyun Jang
Publication year - 2021
Publication title -
natural language processing
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5121/csit.2021.112314
Subject(s) - computer science , artificial intelligence , robustness (evolution) , leverage (statistics) , autoencoder , pattern recognition (psychology) , filter bank , gabor filter , computer vision , woven fabric , filter (signal processing) , feature extraction , deep learning , engineering , biochemistry , chemistry , gene , operations management
An automated and accurate fabric defect inspection system is in high demand as a replacement for slow, inconsistent, error-prone, and expensive human operators in the textile industry. Previous efforts focused on certain types of fabrics or defects, which is not an ideal solution. In this paper, we propose a novel one-class model that is capable of detecting various defects on different fabric types. Our model takes advantage of a well designed Gabor filter bank to analyze fabric texture. We then leverage an advanced deep learning algorithm, autoencoder, to learn general feature representations from the outputs of the Gabor filter bank. Lastly, we develop a nearest neighbor density estimator to locate potential defects and draw them on the fabric images. We demonstrate the effectiveness and robustness of the proposed model by testing it on various types of fabrics such as plain, patterned, and rotated fabrics. Our model also achieves a true positive rate (a.k.a recall) value of 0.895 with no false alarms on our dataset based upon the Standard Fabric Defect Glossary.