Design of Finger Vein Recognition SOC Based on FPGA

Finger vein recognition technology is a new generation of biometric technology. The System on Chip (SOC) solution based on the ARM Cortex-M3 kernel and Xilinx XC7A75T FPGA for the portable finger vein recognition system was proposed in this paper. By the research of software and hardware division, the Region of Interest (ROI) extraction module with large amount of computation was designed as a hardware accelerator to improve the speed of finger vein recognition. The obtained system realized the whole process of finger vein recognition, and displayed every image processing results on 2.8 inch LCD. A large number of tests showed that the system had high stability and the recognition accuracy was greater than 97%. Using FPGA to accelerate ROI module can increase the overall recognition speed by more than 15%. This system has high application value in biometric field.