Fusion of palmprint and palm vein images for person recognition

This paper designed an embedded multimodal palm biometric system using Exynos5410 platform. Feature extraction is accomplished using Non-Halo Complex Matched Filtering (NH-CMF) approach, enhance the system anti-spoof by integrating the palm print with palm vein, and at the same time improve system matching accuracy of EER of 15.25 % and a verification processing time of 0.7 seconds. When implementing the system on Exynos5410, Cortex-A15 processor with powerful operation capability is employed to concentrate on the complicated feature extraction operation, and the Cortex-A7 processor is engaged in peripheral control, task scheduling and user interaction. Person´s palm print and palm vein images are captured, then system extracts biometric data, encrypts it, and prepares for comparison. The comparison of the biometric data is performed on smart card for additional security.