Robust partial fingerprint recognition using wavelet SIFT descriptors

Abstract

Even though there have been many advancements in the fingerprint identification, matching of the partial and overlapped fingerprints is yet to be resolved. This problem has drawn more attention with the evolution of small-sized scanners. The research attempts to resolve this issue whenever there are no core points available in the partial fingerprints. Moreover, the scaled or rotated versions of the image may also lead to poor matching performance. In order to overcome these challenges, a robust partial fingerprint matching method using the scale-invariant feature transform (SIFT) features of the wavelet decomposed image is proposed. The performance of the proposed method is compared with the baseline (minutiae) and the state-of-the-art (SIFT) techniques for partial fingerprint recognition. The method is experimented for different cropped levels (horizontal, vertical, diagonal, quadrant-wise random cuts and the region around a core point) of the image. Experimental studies with 100 subjects show that the proposed method improves recognition accuracy and reduces false acceptance rate (FAR) and false rejection rate (FRR) even for images with 75% occlusion.