Local composition derivative pattern for palmprint recognition

Abstract

Palmprint is a reliable and unique biometric trait with high acceptability. In this paper, we propose a new Local Composition Derivative Pattern (LCDP) for palmprint recognition. LCDP extracts first order derivative information of images along radial and directional directions which can capture more detailed information than the non-directional local binary pattern (LBP). Different from LBP encoding just the binary result of the radial derivative among central pixel and local neighbors by using a simple threshold function with static threshold value, the LCDP extracts discriminative local information by composition of both radial and directional derivatives information by using a threshold function with dynamic threshold value which obtains by first-order derivative information among local neighbors. Experimental evaluation through palmprint recognition on the Hong Kong Polytechnic University 2D_3D_palmprint database demonstrates the LCDP performs much better than LBP for palmprint identification.