Palmprint recognition using binary wavelet transform and LBP representation

Proposed work aims to explore the discrimination capability of palmprint using Binary Wavelet Transform (BWT). As BWT transform is able to cluster the energy corresponding the edge location so, it can better represent the edges of the bit planes in its sub-bands. Firstly, a gray scale palmprint image is transformed into bit planes and then most significant of these bit planes are transformed through BWT. Further, micro and macro pattern histograms are extracted using Local Binary Pattern (LBP) from different transformed bit planes, and concatenated to form the feature vector. Experimental results validate that proposed approach is effective in terms of Genuine acceptance rate (GAR) of 98.71%.