A Dynamically Reconfigurable QC-LDPC Implementation for Iris Recognition

Extracting and analyzing iris textures for biometric recognition has been extensively studied. As the transition of iris recognition from lab technology to nation-scale applications, high complexity becomes a critical concern in most systems in either time or space. It leads to unfitness for embedded devices. In this paper, an iris recognition system is introduced by employing a minimal set of computer vision modules and a multi-mode QC-LDPC decoder. This system can alleviate variability and noise caused by iris acquisition and the follow-up process. Several classes of QC-LDPC code from IEEE 802.16 are investigated for the validity of accuracy improvement. We show that we can apply Dynamic Partial Reconfiguration technology to implement the multi-mode QC-LDPC decoder for the iris recognition system. The results show that the implementation is power-efficient and the system is suitable for edge applications.