Gradient-based texture cartoon decomposition

Author

Nguyen, Chuong T. ; Havlicek, Joseph P.

Author_Institution

Sch. of Electr. & Comput. Eng., Univ. of Oklahoma, Norman, OK, USA

fYear

2012

fDate

22-24 April 2012

Firstpage

85

Lastpage

88

Abstract

We proposed an automatic nonlinear texture-cartoon decomposition based on the frequency behavior of texture and cartoon across different scales. We measured the ratio of gradient magnitude across modulation domain components and used this ratio to classify the texture and cartoon pixels. The algorithm computed the modulation domain component where texture and cartoon are separated. Our simulation results showed that the proposed algorithm is able to extract meaningful texture and cartoon components from images efficiently.

Keywords

feature extraction; image classification; image texture; automatic nonlinear texture-cartoon decomposition; cartoon component extraction; cartoon frequency behavior; cartoon pixel classification; gradient magnitude ration; gradient-based texture cartoon decomposition; modulation domain components; texture classification; texture extraction; texture frequency behavior; Bandwidth; Classification algorithms; Frequency modulation; Image coding; Image edge detection; Mathematical model; AM-FM; cartoon; modulation domain; texture;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Interpretation (SSIAI), 2012 IEEE Southwest Symposium on

Conference_Location

Santa Fe, NM

Print_ISBN

978-1-4673-1831-0

Electronic_ISBN

978-1-4673-1829-7

Type

conf

DOI

10.1109/SSIAI.2012.6202459

Filename

6202459