A Gabor filter based fingerprint enhancement algorithm in wavelet domain

Fingerprint image enhancement is very essential in an automated fingerprint identification system. In this paper, we propose a new fingerprint enhancement algorithm, which can improve the clarity and continuity of ridge and valley structures. A normalized fingerprint image is decomposed into approximation and detail sub-images, then estimate the approximation image´s orientation. Finally, using Gabor filter to enhance the fingerprint image in wavelet domain and reconstruct the fingerprint. We have tested the algorithm on FVC2004 fingerprint database DBl. Experiment results indicate that the algorithm has dramatic effect to low quality fingerprint images and processing time is short than fingerprint image enhancement based on Gabor filter.