Palmprint verification using binary orientation co-occurrence vector

The development of accurate and robust palmprint verification algorithms is a critical issue in automatic palmprint authentication systems. Among various palmprint verification approaches, the orientation based coding methods, such as competitive code (CompCode), palmprint orientation code (POC) and robust line orientation code (RLOC), are state-of-the-art ones. They extract and code the locally dominant orientation as features and could match the input palmprint in real-time and with high accuracy. However, using only one dominant orientation to represent a local region may lose some valuable information because there are cross lines in the palmprint. In this paper, we propose a novel feature extraction algorithm, namely binary orientation co-occurrence vector (BOCV), to represent multiple orientations for a local region. The BOCV can better describe the local orientation features and it is more robust to image rotation. Our experimental results on the public palmprint database show that the proposed BOCV outperforms the CompCode, POC and RLOC by reducing the equal error rate (EER) significantly.