Local and holistic texture analysis approach for face recognition

Author

Srisuk, Sanun ; Petchpon, Amnart

Author_Institution

Dept. of Comput. Eng., Mahanakorn Univ. of Technol., Bangkok, Thailand

fYear

2010

fDate

26-29 Sept. 2010

Firstpage

3825

Lastpage

3828

Abstract

In this paper, we present a new framework for face recognition under varying illumination based on DCT total variation minimization (DTV), gabor filter, a sub-micro pattern analysis (SMP) and discriminant accumulative feature transform (DAFT). We first suppress the illumination effect by using the DCT with the helps of TV as a tool for face normalization. The DTV image is then emphasized by the gabor filter. The facial features are encoded by our proposed method, the SMP. The SMP image is then transformed to the 2D histogram by using DAFT. Our system is verified with experiments on the AR and the Yale face database B.

Keywords

Gabor filters; discrete cosine transforms; face recognition; image texture; minimisation; 2D histogram; DAFT; DCT total variation minimization; DTV; Gabor filter; SMP; discriminant accumulative feature transform; face normalization; face recognition; holistic texture analysis; illumination; local texture analysis; submicro pattern analysis; Databases; Digital TV; Discrete cosine transforms; Face; Face recognition; Histograms; Lighting; Discriminant feature transform; SMP;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2010 17th IEEE International Conference on

Conference_Location

Hong Kong

ISSN

1522-4880

Print_ISBN

978-1-4244-7992-4

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2010.5654063

Filename

5654063