
For FullText PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.

A KernelBased Fisher Discriminant Analysis for Face Detection
Takio KURITA Toshiharu TAGUCHI
Publication
IEICE TRANSACTIONS on Information and Systems
Vol.E88D
No.3
pp.628635 Publication Date: 2005/03/01
Online ISSN:
DOI: 10.1093/ietisy/e88d.3.628
Print ISSN: 09168532 Type of Manuscript: PAPER Category: Pattern Recognition Keyword: face detection, kernel Fisher discriminant analysis, kernel principal component analysis,
Full Text: PDF(556.8KB) >>Buy this Article
Summary:
This paper presents a modification of kernelbased Fisher discriminant analysis (FDA) to design oneclass classifier for face detection. In face detection, it is reasonable to assume "face" images to cluster in certain way, but "non face" images usually do not cluster since different kinds of images are included. It is difficult to model "non face" images as a single distribution in the discriminant space constructed by the usual twoclass FDA. Also the dimension of the discriminant space constructed by the usual twoclass FDA is bounded by 1. This means that we can not obtain higher dimensional discriminant space. To overcome these drawbacks of the usual twoclass FDA, the discriminant criterion of FDA is modified such that the trace of covariance matrix of "face" class is minimized and the sum of squared errors between the average vector of "face" class and feature vectors of "non face" images are maximized. By this modification a higher dimensional discriminant space can be obtained. Experiments are conducted on "face" and "non face" classification using face images gathered from the available face databases and many face images on the Web. The results show that the proposed method can outperform the support vector machine (SVM). A close relationship between the proposed kernelbased FDA and kernelbased Principal Component Analysis (PCA) is also discussed.

