Detection of repetitive patterns in near regular texture images

Author

Cai, Yunliang ; Baciu, George

Author_Institution

Dept. of Comput., Hong Kong Polytech. Univ., Kowloon, China

fYear

2011

fDate

16-17 June 2011

Firstpage

60

Lastpage

65

Abstract

Detection of repetitive patterns in texture images is a longstanding problem in texture analysis. In the textile industry, this is particularly useful in isolating repeats in woven fabric designs. Based on repetitive patterns, textile designers can identify and classify complex textures. In this paper, we propose a new method for detecting, locating, and grouping the repetitive patterns, particularly for near regular textures (NRT) based on a mid-level patch descriptor. A NRT is parameterized as a vector-valued function representing a texton unit together with a set of geometric transformations. We perform shape alignment by image congealing and correlation matching. Our experiments demonstrate that our patch-based method significantly improves the performance and the versatility of repetitive pattern detection in NRT images.

Keywords

fabrics; image texture; pattern matching; NRT images; correlation matching; geometric transformations; image congealing; mid-level patch descriptor; near regular texture images; repetitive pattern detection; texton unit; texture analysis; vector-valued function; woven fabric; Equations; Jacobian matrices; Joints; Minimization; Pixel; Shape; Transforms; Near regular texture; image analysis; pattern recognition; texton; texture analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

IVMSP Workshop, 2011 IEEE 10th

Conference_Location

Ithaca, NY

Print_ISBN

978-1-4577-1284-5

Type

conf

DOI

10.1109/IVMSPW.2011.5970355

Filename

5970355