Fast gender recognition by using a shared-integral-image approach

Author

Shen, Bau-Cheng ; Chen, Chu-Song ; Hsu, Hui-Huang

Author_Institution

Inst. of Inf. Sci., Acad. Sinica, Taipei

fYear

2009

fDate

19-24 April 2009

Firstpage

521

Lastpage

524

Abstract

We develop a new approach for gender recognition. In this paper, our approach uses the rectangle feature vector (RFV) as a representation to identify humans´ gender from their faces. The RFV is computationally fast and effective to encode intensity variations of local regions of human face. By only using few rectangle features learned by AdaBoost, we present a gender identifier. We then use nonlinear support vector machines for classification, and obtain more accurate identification results.

Keywords

face recognition; feature extraction; gender issues; image classification; image coding; image representation; learning (artificial intelligence); support vector machines; AdaBoost learning; gender recognition; human face recognition; image classification; intensity variation encoding; nonlinear support vector machine; rectangle feature vector; shared-integral-image approach; Computer science; Detectors; Face detection; Face recognition; Humans; Image recognition; Information science; Neural networks; Support vector machine classification; Support vector machines; AdaBoost; Gender Recognition; Integral Image; Real AdaBoost; Support Vector Machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on

Conference_Location

Taipei

ISSN

1520-6149

Print_ISBN

978-1-4244-2353-8

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2009.4959635

Filename

4959635