Automated defect detection in uniform and structured fabrics using Gabor filters and PCA

This paper describes an algorithm for texture defect detection in uniform and structured fabrics, which has been tested on the TILDA image database. The proposed approach is structured in a feature extraction phase, which relies on a complex symmetric Gabor filter bank and Principal Component Analysis (PCA), and on a defect identification phase, which is based on the Euclidean norm of features and on the comparison with fabric type specific parameters. Our analysis is performed on a patch basis, instead of considering single pixels. The performance has been evaluated with uniformly textured fabrics and fabrics with visible texture and grid-like structures, using as reference defect locations identified by human observers. The results show that our algorithm outperforms previous approaches in most cases, achieving a detection rate of 98.8% and a false alarm rate as low as 0.20-0.37%, whereas for heavily structured yarns misdetection rate can be as low as 5%. (C) 2013 Elsevier Inc. All rights reserved.