Recognition Based on Fusion of Gait, Ear and Face Features Using KPCA Method

In this paper, a simple multimodal biometrics recognition system having three modalities i.e. Gait, Ear and Face is used and for different biometric traits features Kernel Principal Component method is used for fusion. Because of these biometric traits, our proposed method requires no significant user co-operation and also work from a long distance. The method has been successfully tested on 300 images corresponding to 30 subjects from three databases including ORL face database, USTB ear database and CASIA gait database. The experimental results exhibit excellent recognition performance than Gait, Ear and Face unimodal biometric recognition. As, the every database contain the data of different persons so we can use them only for testing for the given subject.

[1]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[2]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[3]  James C. Bezdek,et al.  Decision templates for multiple classifier fusion: an experimental comparison , 2001, Pattern Recognit..

[4]  Zhengguang Xu,et al.  Using Ear Biometrics for Personal Recognition , 2005, IWBRS.

[5]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[6]  G. Aguilar,et al.  Multimodal biometric system using fingerprint , 2007, 2007 International Conference on Intelligent and Advanced Systems.

[7]  L. Hong,et al.  Can multibiometrics improve performance , 1999 .