Paper Info
Title
Automated defect detection in uniform and structured fabrics using Gabor filters and PCA
Abstract
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%.
Year
DOI
Venue
2013
10.1016/j.jvcir.2013.05.011
J. Visual Communication and Image Representation
Keywords
Field
DocType
gabor filter,yarns misdetection rate,feature extraction phase,reference defect location,visible texture,structured fabric,false alarm rate,detection rate,euclidean norm,texture defect detection,defect identification phase,automated defect detection,tilda
Computer vision,Pattern recognition,Gabor filter bank,Euclidean distance,Feature extraction,Pixel,Artificial intelligence,Image database,Constant false alarm rate,Principal component analysis,Mathematics
Journal
Volume
Issue
ISSN
24
7
1047-3203
Citations 
PageRank 
References 
11
0.65
17
Authors
6
Name
Order
Citations
PageRank
Lucia Bissi1224.49
Giuseppe Baruffa212318.06
Pisana Placidi3318.59
Elisa Ricci 00024139373.75
Andrea Scorzoni5275.26
Paolo Valigi616525.12