Gender and ethnic classification of face images

被引：88

作者：

Gutta, S ^{[1
]}

Wechsler, H ^{[1
]}

Phillips, PJ ^{[1
]}

机构：

[1] George Mason Univ, Dept Comp Sci, Fairfax, VA 22030 USA

来源：

AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS | 1998年

关键词：

D O I：

10.1109/AFGR.1998.670948

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper considers hybrid classification architectures for gender and ethnic classification of human faces and shows their feasibility using a collection of 3006 face images corresponding to 1009 subjects from the FERET database. The hybrid approach consists of an ensemble of RBF networks and inductive decision trees (DT). Experimental Cross Validation (CV) results yield an average accuracy rate of -(a) 96% on the gender classification task and (b) 94% on the ethnic classification task. The benefits of our hybrid architecture include (i) robustness via query by consensus provided by the ensembles of RBF networks, and (ii) flexible and adaptive thresholds as opposed to an hoc and hard thresholds provided by using only DT.

引用

页码：194 / 199

页数：2