摘要

A fusion scheme is proposed for incomplete fingerprint to extract the Region of interest (ROI) centered at the reference point. Firstly, the orientation entropy is computed. Secondly, it is necessary for ROT extraction to segment foreground and background efficiently. So, the feature vector, based on orientation and gray, is defined for segmentation with SVM. Then, the fingerprint segmentation of the incomplete area is re-computed and measured with correlation and competition of texture, which is based on Local binary pattern (LBP). Finally, the proposed method is based on mutual information of fingerprint orientation and Poincare Index to detect the reference point of fingerprints, and then extract ROT. The performance of the new method is evaluated on FVC2004 database. And the performance is shown in the experiments and proves that it could locate the position of reference point of all type fingerprints more effectively and precisely.

全文