Precision direction and compact surface type representation for 3D palmprint identification

Abstract

Compared with its 2D counterpart, a 3D palmprint image contains not only the 3D structure-based but also the 2D texture-based features of the palmprint. In this paper, we propose a precision direction code and compact surface type (PDCST) method for 3D palmprint representation and identification. Specifically, we propose the precision direction code (PDC) to depict the 2D texture-based features by exploiting not only the visible but also the potential direction features of the palmprint. Moreover, we use a simple yet efficient compact surface type (CST) to represent the 3D structure-based features of the palmprint. We combine the PDC and CST forming the PDCST descriptor to represent the multiple level and multiple dimensional features of 3D palmprint images. The two-phase sparse representation scheme is used to perform PDCST-based feature identification. Extensive inter-comparative and intra-comparative experimental results on three widely used palmprint databases clearly demonstrate the effectiveness of the proposed method.