A Coarse to Fine Minutiae-Based Latent Palm print Matching and fusion

Abstract

In this paper, a coarse to fine matching strategy based on minutiae clustering and minutiae match propagation is designed specifically for palmprint matching and to deal with the large database and local feature-based minutiae clustering algorithm is designed to cluster minutiae into several groups such that minutiae belonging to the same group have similar local characteristics. The proposed palmprint matching algorithm has been evaluated on a latent-tofull palmprint database consisting of 44 latents and 12,489 background full prints. Our method involves image acquisition via a dedicated device under contact-free and multi-spectral environment, preprocessing to extract features and locate region of interest (ROI) from each individual hand images, future-level registration to combine ROIs from different spectral images in one sequence and fusion to combine two multispectral palm images. The matching results show a rank-1 identification accuracy of 80 percent, which is more accurate than the state-of-the-art latent palmprint matching algorithm. The computation time of our algorithm is an order of magnitude faster than a previous algorithm.