Face recognition with support vector machine

Author

Zhang, Shaoyan ; Qiao, Hong

Author_Institution

Dept. of Comput., Univ. of Manchester Inst. of Sci. & Technol., UK

Volume

2

fYear

2003

fDate

8-13 Oct. 2003

Firstpage

726

Abstract

The application of support vector machines (SVMs) in face recognition is investigated in this paper. SVM is a classification algorithm developed by V. Vapnik and his team. Based on the underlying optimization and statistical learning theories, SVMs provide a new approach to the problem of pattern recognition. In this paper, both linear and nonlinear SVM training models are used in face recognition. Faces in different orientations are taken as training samples. Primary results show that nonlinear training machine is better than linear machine; the former one always has a much larger margin, which means that it has a much stronger ability in classification and recognition.

Keywords

face recognition; image classification; learning (artificial intelligence); optimisation; support vector machines; face recognition; linear SVM training models; linear training machine; nonlinear SVM training models; nonlinear training machine; optimization; pattern classification algorithm; pattern recognition; statistical learning theories; support vector machines; training samples; Application software; Computer interfaces; Face recognition; Hidden Markov models; Pattern recognition; Quadratic programming; Statistical learning; Support vector machine classification; Support vector machines; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics, Intelligent Systems and Signal Processing, 2003. Proceedings. 2003 IEEE International Conference on

Print_ISBN

0-7803-7925-X

Type

conf

DOI

10.1109/RISSP.2003.1285674

Filename

1285674