A new algorithm of incomplete fingerprint segmentation based on LBP

A novel segmentation method is proposed for incomplete fingerprint based on Local Binary Pattern (LBP). Firstly, the feature vector, based on orientation coherence, orientation entropy and gray, is defined for segmentation with SVM. Secondly, According to the problem of segmentation with SVM, with the texture of non-statistical LBP, fuzzy criterion is used for modifying segmentation. The fingerprint segmentation of the incomplete area is re-computed and measured with correlation and competition of texture, which is based on LBP. The performance of the new method is evaluated on FVC2004 database. The experimental results indicate that the proposed algorithm is effective for incomplete fingerprint.