Complete Binary Representation for 3-D Palmprint Recognition

3-D palmprint recognition has attracted a wide range of attentions due to its potential for civilian applications. Designing an effective representation is a key problem for the 3-D palmprint recognition. In this paper, we propose a complete binary representation (CBR) for the 3-D palmprint multiple-dimensional feature representation and recognition. First, we propose a multiple orientation binary representation (MOBR) to extract 2-D gray-level features of 3-D palmprint. Then, we propose a novel and effective compact surface type (CST) to characterize 3-D palmprint surface feature, and design a CST binary representation (CSTBR) to capture the surface consistency within a local patch. Finally, we develop a CBR method by integrating the MOBR and CSTBR, which can effectively represent both 2-D orientation-level and 3-D surface-level features of 3-D palmprint images. We conduct extensive intercomparison experiments to demonstrate the effectiveness of the proposed CBR method on a benchmark 3-D palmprint database. Also, we carry out multiple intracomparisons to validate the superiority of the MOBR- and CST-based representations.