Palmprint identification using restricted fusion

Abstract

In this paper, we propose two palmprint identification schemes using fusion strategy. In the first fusion scheme, firstly, the principal lines of test image is extracted, and matched with that of all training images. Secondly, those training images with large matching scores are selected to construct a small training sub-database. At last, the decision level fusion, combing matching scores of principal lines and Locality Preserving Projections features, has been made for final identification in small training sub-database. From another point of view, it can be seen that the fusion is restricted by the previous results of principal lines matching, so we call it as restricted fusion. The second fusion scheme is similar to the first one. Just the fusion order is changed. The results of experiments conducted on PolyU palmprint database show that the proposed schemes can achieve 100% accurate recognition rate.