A fingerprint matching technique based on phase-only correlation - Algorithm design and implementation for fingerprint matching devices dedicated to home applications

A major approach for fingerprint recognition today is to extract minutiae from fingerprint images and to perform fingerprint matching based on the number of corresponding minutiae pairings. One of the most difficult problems in minutiae-based fingerprint recognition has been that the recognition performance is significantly influenced by fingertip surface condition, which may vary depending on environmental or personal causes. Addressing this problem, we have proposed an efficient fingerprint recognition algorithm using phase-based image matching. The use of phase components in 2D discrete Fourier transforms of fingerprint images makes possible to achieve highly robust fingerprint recognition for low-quality fingerprints. However, due to its high computational complexity, the proposed algorithm is not suitable to be implemented in compact fingerprint matching devices for home applications. In this paper, we propose an improved fingerprint recognition algorithm using phase-based image matching, which significantly reduces computational complexity without degrading recognition performance, compared with the reported algorithm. We also present prototype implementation of a high-performance, easy-to-use fingerprint matching device for home applications, which employ a specially designed ASIC for executing the proposed algorithm in real time.