Adaptive Fingerprint Image Enhancement with Contourlet Transform

Abstract

The quality of fingerprint images highly affects the performance of Integrated Automated Fingerprint Identification Service. An effective method is essential to enhance the fingerprint image. Based on the study of intrinsic feature of fingerprint images, we propose a new approach for fingerprint image enhancement via contourlet transform in this paper. Our method is adaptive for orientation estimation and coefficients modification, which is robust and efficient. The experimental results show that our proposed algorithm can increase the contrast between ridges and valleys, and reduce noises in the gray-scale fingerprint images from FVC2002.