An Effective and Robust Fingerprint Enhancement Method

Fingerprint enhancement is a critical part in an automatic fingerprint verification system, which can improve the quality of the fingerprint and extract reliable minutiae in a fingerprint. In this paper, we proposed an effective and robust algorithm for fingerprint enhancement. Firstly, we use contrast stretching approach to improve the clarity between foreground and background of the fingerprint image. Then we utilize the structure tensor property to estimate the fingerprint orientation to improve the accuracy of orientation estimation. Finally, we combine the advantages of Gabor filtering method and diffusion filtering method, and adopt low-pass filter at the direction that is parallel to the ridge, and adopt band-pass filter at the direction that is perpendicular to the ridge. In the experiment, we have evaluated the performance of our method for fingerprint enhancement, and the results show that our algorithm performs much better within less time.