A New Method Based on Image Restoration for Defocused Fingerprint Image

Abstract

A new method based on image restoration is proposed for defocused fingerprint image enhancement in this paper. First, a model of the sources of fingerprint image degradationis constructed to remove or reduce the effects of the sources of fingerprint image degradation. The defocused fingerprint images can be considered as unknown focused fingerprint images filtered by a low-pass filter. Then, a circular defocus model is used to approximate the degree of the defocusing inan optical system. The Lucy-Richardson (L-R) algorithm combined with the Point Spread Function (PSF) based on the circular defocus model is proposed for fingerprint image restoration. Eventually, the enhanced fingerprint images are obtained by using the L-R iterative algorithm. The proposed method is experimented on two sets of defocused fingerprint images. Experimental results show the method proposed in this paper is more effective and feasible than the traditional method.