D. Richards and B.-H. Kang (Eds.): PKAW 2008, LNAI 5465, pp. 231–241, 2009.
© Springer-Verlag Berlin Heidelberg 2009
Facial Feature Extraction Using Geometric Feature
and Independent Component Analysis
Toan Thanh Do
1
and Thai Hoang Le
2
1
Department of Computer Sciences, University of Natural Sciences, HCMC, Vietnam
dttoan@fit.hcmuns.edu.vn
2
Department of Computer Sciences, University of Natural Sciences, HCMC, Vietnam
lhthai@fit.hcmuns.edu.vn
Abstract. Automatic facial feature extraction is one of the most important and
attempted problems in computer vision. It is a necessary step in face recogni-
tion, facial image compression. There are many methods have been proposed in
the literature for the facial feature extraction task. However, all of them have
still disadvantage such as not complete reflection about face structure, face tex-
ture. Therefore, a combination of different feature extraction methods which
can integrate the complementary information should lead to improve the effi-
ciency of feature extraction stage. In this paper we describe a methodology for
improving the efficiency of feature extraction stage based on the association of
two methods: geometric feature based method and Independent Component
Analysis (ICA) method. Comparison of two methods of facial feature extrac-
tion: geometric feature based method combined with PCA method (called
GPCA) versus geometric feature based method combined with ICA method
(called GICA) on CalTech dataset has demonstrated the efficiency of GICA
method. Our results show that GICA achieved good performance 96.57% com-
pared to 94.70% of GPCA method. Furthermore, we compare two methods
mentioned above on our dataset, with performance of GICA being 98.94% bet-
ter 96.78% of GPCA method. The experiment results have confirmed the bene-
fits of the association geometric feature based method and ICA method in facial
feature extraction.
Keywords: Face recognition; independent component analysis (ICA); principal
component analysis (PCA); geometric features.
1 Introduction
Face recognition has a variety of potential applications in public security, law en-
forcement and commerce such as identity authentication for credit card or driver li-
cense, access control, information security, and video surveillance, etc.. In addition,
there are many emerging fields that can benefit from face recognition such as human-
computer interfaces and e-services, including e-home, tele-shopping and tele-banking.
However, one of the most difficult from face recognition problem is the facial
feature extraction step. A good feature extraction will increase performance of face
recognition system. Various techniques have been proposed in the literature for this
purpose, and are mainly classified in four groups.