A template matching approach based on the discrepancy norm for defect detection on regularly textured surfaces

Autoren Jean-Luc Bouchot
Gernot Stübl
Bernhard Moser
Editoren J.-C. Pinoli
J. Debayle
Y. Gavet
F. Gruy
C. Lambert
TitelA template matching approach based on the discrepancy norm for defect detection on regularly textured surfaces
BuchtitelProceedings of the 10th International Conference on Quality Control by Artificial Vision (QCAV'2011)
Typin Konferenzband
VerlagSPIE
Band800
AbteilungKVS
ISBN978-081948573-1
MonatMay
Jahr2012
SeitenDOI: 10.1117/12.889865
SCCH ID#1102
Abstract

In this paper we introduce a novel algorithm for automatic fault detection in textures. We study the problem of finding a defect in regularly textured images with an approach based on a template matching principle. We aim at registering patches of an input image in a defect-free reference sample according to some admissible transformations. This approach becomes feasible by introducing the so-called discrepancy norm as fitness function which shows particular behaviour like monotonicity and a Lipschitz property. The proposed approach relies only on few parameters which make it an easily adaptable algorithm for industrial applications and, above all, it avoids complex tuning of configuration parameters. Experiments demonstrate the feasibility and the reliability of the proposed algorithms with textures from real-world applications in the context of quality inspection of woven textiles.