A Palmprint Recognition Algorithm Using Phase Information and Its Performance Evaluation

A palm, a large inner surface of a hand, contains patterns of ridges and valleys much like a fingertip. The palmprint is expected to be more distinctive than the fingerprint, since the area of the palm is much larger than that of the finger and the palm has additional distinctive features such as principle lines, ridges, minutia points and texture. This paper proposes a palmprint recognition algorithm using two-dimensional (2D) phase information. The proposed algorithm (i) reduces the registered data size by registering quantized phase information and (ii) deals with nonlinear distortion between palmprint images by local block matching. Experimental evaluation using palmprint image databases clearly demonstrates efficient matching performance of the proposed algorithm compared with the conventional palmprint recognition algorithms.