A Fingerprint Identification Algorithm Based on Local Minutiae Topological Property

摘要

Minutiae is widely used in fingerprint recognition, however, single minutiae feature is still unable to cover the influences from the acquisition process. Interferes such as dirty fingers, uncertain pressing position and so on can easily affect the accuracy. In order to improve this situation, we propose a new feature model called local minutiae topological. Unlike other methods, the proposed model is based on the relative location of minutiae and core point, in which a core point of the fingerprint is firstly confirmed, and then minutiae around the core point is extracted by an improved FVS algorithm. The topological relationship is built on the extracted minutiae and the core point. Finally we adopt Neural Network to verify the proposed feature model. The experiments are based on FVC2000, the comparison results to several similar excellent algorithms show that the proposed model has high computational efficiency and a significant improvement on robustness.