A method of the region of interest extraction based on orientation entropy

In this paper, a novel method based on orientation entropy is proposed for incomplete fingerprint to extract the Region of Interest (ROI) centered at the reference point, which is applied to achieve fingerprint matching and fingerprint classification instead of the whole fingerprint information. Firstly, according to the properties of competition of the local fingerprint, complementation and redundancy of the global fingerprint, the gradient dispersion function is proposed, adaptively. Secondly, the orientation entropy is computed. Then, the proposed method is based on orientation entropy and Poincare Index to detect the reference point of fingerprints, and then extract ROI. Experiment results executed on FVC2004 Set B prove that it could locate the position of reference point of all type fingerprints more effectively and precisely. In addition, it is robust to resolution and rotation.