Fingerprint Enhancement Using Oriented Diffusion Filter

Abstract

Fingerprint enhancement is a critical step in a fingerprint identific ation system. Recently, some anisotropic nonlinear diffusion filter is applied to the fingerprint preprocessed. Impressive results are main reason for using nonlinear diffusion filtering in image processing. Poor efficiency, especially the computational load, is the main reason for not using nonlinear diffusion filtering. In order to improve the efficie ncy, a novel piecewise nonlinear diffusion for fingerprint enhancement is presented. It shows anisotropic diffusion equation using diffusion tensor which continuously depends on the gradient is not necessary to smooth the fingerprint. We simplify the anisotropic nonlinear-diffusion in order to satisfy a real-time fingerprint recognition system. According to the local character of the fingerprint, the diffusion filter is steered by the orientation of ridge. Experimental results illustrate that our enhancement algorithm can satisfy the requirement of an AFIS.

This paper is supported by the National Science Fund for Distinguished Young Scholars of China under Grant No. 60225008, the Special Project of National Grand Fundamental Research 973 Program of China under Grant No. 2002CCA03900, the National High Technology Development Program of China under Grant No. 2002AA234051, the National Natural Science Foundation of China under Grant Nos. 60172057, 69931010, 60071002?30270403?60072007