An adaptive fingerprint image segmentation algorithm based on multiple features

Fingerprint image segmentation heavily influences the performance of fingerprint verification systems. In recent years, some new methods have been introduced to the image segmenting processing in order to get better disposal results. And most of the proposed algorithms are based on threshold segmentation. In this paper, a novel approach is put forward to segment fingerprint images based on multiple features. It makes use of local and global features to determine block threshold adaptively without the experience. Meanwhile, the algorithm combines the point level segmentation with the block level segmentation in order that it could be capable of avoiding the appearance of the blocking effect of the foreground image edges at a low computational cost. The performance of the new algorithm is evaluated on FVC2004 database. Experiment results show that the proposed adaptive segmentation algorithm is effective and robust.