A fingerprint enhancement algorithm in spatial and wavelet domain

Abstract

Fingerprinting is one form of biometrics, which people’s physical characteristics to identify them. Fingerprints are ideal for this purpose because they’re inexpensive to be collected and analysed. They never change, even as people grow old. The performance of a fingerprint image-matching algorithm depends heavily on the quality of the input fingerprint images. The acquired fingerprint images from the scanner are often with low contrast, noisy and the ridges are blurred. The enhancement is an essential step required to improve the quality of the fingerprint image. In this paper, we propose an enhancement method in spatial and wavelet domain. The fingerprint image contrast is increased, the histogram is equalized and ridges are deblurred. The image is then filtered by Gabor filters and denoised in wavelet domain. Experimental results show that this method increases the number of true minutiae extracted.