Singular points detection in fingerprint images using Gabor transform

• Published in: 2008 9th International Conference on Signal Processing pp. 2078 - 2081
• Main Authors: Chih-Jen Lee, I-Homg Jeng, Tai-Ning Yang, Chun-Jung Chen, Keng-Li Lin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2008
• Subjects: Access control; Authentication; Computer science; Fingerprint recognition; Frequency; Gabor filters; Image matching; Internet; Robustness; Sampling methods
• DOI: 10.1109/ICOSP.2008.4697554
• ISBN: 1424421780; 9781424421787
• ISSN: 2164-5221

In fingerprints, singular points, including cores and deltas, are very important features. To classify the types of fingerprints, the number and the position of cores and deltas are concerned. For fingerprint matching, some approaches used the core point to align two fingerprint images to overcome the problems from rotation and translation. Therefore, singular points detection is a critical process for both fingerprint matching and fingerprint classification. The process of singular points detection must be robust; otherwise, the performance of the whole fingerprint recognition system would be influenced heavily. In this paper, we will use Gabor transform, sampling by a complete set of Gabor basis functions, to demonstrate the phenomenon of the regions of singular points. Besides, we will develop a robust method to detect singular points.