A Novel Fingerprint Algorithm Based on Line-Segment Chain

A novel representation of fingerprint image based on Line-Segment features which are extracted from a bank of Gabor-filtered fingerprint images is proposed in this paper. In the feature matching stage, quadrangles constructed with Perpendicularity Line-Segments are used to obtain the alignment parameters. Compared with the existing representations of fingerprint, line-Segment based representation employs not only rich discriminatory ridge information of the fingerprint images but also obviates the need for extracting minutiae points or the core point to align the fingerprint images. Experimental results show that the proposed method is robust and effective. Key-Words: Fingerint matching, Line-Segment, Edit-Distance, Gabor-Filter, Approximate String Matching 1 Sponsored by the National Natural Science Foundation of China (60472069)