Bimodal biometrics based on a two-stage test sample representation

Authors:
Yu Hou;Caikou Chen
Affiliations:
Information Engineering College, Yangzhou University, Yangzhou, China;Information Engineering College, Yangzhou University, Yangzhou, China
Venue:
AICI'12 Proceedings of the 4th international conference on Artificial Intelligence and Computational Intelligence
Year:
2012

Citing 2
Cited 0

A feature extraction method for use with bimodal biometrics

Pattern Recognition
Is face recognition really a Compressive Sensing problem?

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Bimodal biometrics based on a two-stage test sample representation method for use with face recognition is presented in this paper. Until now a large amount of research has been proved that multi-biometrics can outperform single biometrics. The proposed method first let the test sample be linearly constructed from all the training samples each with a complex vector. By this step we find k 'nearest neighbors' for the test sample. Then we re-expressed the test sample as a linear combination of the k samples obtained above and classify the test sample into the class that makes the greatest contribution. The experimental results on CSIST and AR face image database demonstrate the efficiency and effectiveness of our method.