Fingerprint image segmentation method based on normal distribution model

In this paper, the advantages and disadvantages of the gray variance directional image segmentation methods were analyzed. On the base of gray normalization, a new approach to segment the fingerprint images was proposed using the normal distribution model of the fingerprint image graypsilas character. This approach makes use of the gray characters of the local and global images. Meanwhile, it has the advantage to choose the threshold automatic without the experience. The experimental results show that the method for the fingerprint image segmentation is effective, adaptive and quick and it can meet the need of fingerprint recognition system.