一种指纹特征点连线穿越脊线数的计算方法

Counting Method for Ridges Crossed by Connection Line of Two Minutiae

指纹中特征点间连线穿越的脊线数由于不受指纹图像缩放、旋转、平移及轻微变形的影响,被越来越多地用于指纹匹配,其计算精度直接影响指纹匹配结果。现有算法大多基于Bresenham及其改进方法,计算误差较大。给出了一种基于细化指纹图像的新方法,该方法首先由两特征点连线上的像素点灰度值确定其穿越的黑点坐标,然后根据连线与其相邻脊线、特征点的几何关系综合处理得到其穿越的脊线数。实验结果表明,该算法稳定可靠,能够准确有效地获得特征点间连线穿越的脊线数。

The number of ridges crossing the connection line of two minutiae is increasingly used in fingerprint matching for its robustness in fingerprint scaling, rotation, translation and slight deformation, and affects the accuracy and robust- ness of fingerprint matching directly. Most ridges counting algorithms based on Bresenham or its improved algorithm are not accuracy enough now. A new ridge counting algorithm based on the thinned fingerprint was presented in this paper. The pixels of the connection line are calculated firstly,and the black pixels on or nearby the connection line are achieved. Then the number of ridges crossing the connection line is obtained according to the geometric relationship among the connection line, adjacent ridges and minutiae. Experiment results show that the algorithm can accurately and effectively get the number of ridges which across the connection line of two minutiae.