Appearance-based bidirectional representation for palmprint recognition

Jinrong Cui, Jiajun Wen, Zizhu Fan

Abstract: The palmprint recognition methods can be categorized as the feature-based methods and the appearance-based methods. The conventional appearance-based representation methods merely express the test sample as a weighting sum of training samples and exploit the deviation between the test sample and the weighting sum of the training samples from each class for classification. In this paper we exploited an appearance-based palmprint recognition method called bidirectional representation method based pattern classification (BRBPC) on palmprint recognition. The BRBPC algorithm not only used the training samples to express the test sample, but also take into account the expression of the test sample to the training sample. Experiments on PolyU multi-spectral palmprint database and 2D and 3D palmprint database show that the proposed method outperforms the conventional appearance-based palmprint recognition methods.