Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10361546 | Pattern Recognition Letters | 2005 | 9 Pages |
Abstract
Minutiae matching is the most popular approach to fingerprint verification. In this paper, we propose a novel fingerprint feature named the adjacent feature vector (AFV) for fingerprint matching. An AFV consists of four adjacent relative orientations and six ridge counts of a minutia. Given a fingerprint image, the optimal matching score is computed in three stages: (1) minutiae candidate pairs searching based on AFVs; (2) coordinate transform for image rotation and translation; and (3) transformed minutiae matching to get matching score. The experimental results show that the proposed method provides a good trade-off between speed and accuracy.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Xifeng Tong, Jianhua Huang, Xianglong Tang, Daming Shi,