MODIFIED HOUGH TRANSFORMS FOR FEATURE RECOGNITION ON DEFORMABLE PATTERNED MATERIALS

Authors
Citation
Lg. Tao et Tg. King, MODIFIED HOUGH TRANSFORMS FOR FEATURE RECOGNITION ON DEFORMABLE PATTERNED MATERIALS, Image and vision computing, 12(7), 1994, pp. 465-472
Citations number
16
Categorie Soggetti
Computer Sciences, Special Topics",Optics,"Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence","Computer Science Software Graphycs Programming","Computer Science Theory & Methods
Journal title
ISSN journal
02628856
Volume
12
Issue
7
Year of publication
1994
Pages
465 - 472
Database
ISI
SICI code
0262-8856(1994)12:7<465:MHTFFR>2.0.ZU;2-X
Abstract
This paper reports on the use of a modified Hough transform, particula rly its generalized version (GHT). The purpose of the analysis is to r ecognize features on deformable patterned materials, particularly elas ticated textile fabrics such as lace. To cope with arbitrary geometric distortion of the features to be found, a feature is divided into sev eral sub-features and the model of the feature is built by choosing a set of points s from these sub-features instead of boundary points. Th e method is tested on a pattern stretched by up to 20% in one directio n, with or without a moderate degree of pattern skew.