Spectral analysis based fingerprint image enhancement algorithm

Many fingerprint images are of very poor quality, which will greatly damage the performance of the automatic fingerprint identification system (AFIS). In order to ensure that the performance is robust with respect to the quality of input fingerprint images, an enhancement algorithm is necessary. Gabor filter is a very effective tool for image enhancement. In this paper, an algorithm that take advantage of the characteristics of gabor filter functions both in spectral and spatial domain are proposed to dynamically estimate the gabor filter´s parameters and bandwidth. Finally, the images are filtered in frequency domain using the obtained gabor Frequency-domain filter function. The filtering results show that images are greatly improved.