一个基于特征点匹配的联机指纹鉴别系统

A minutiae matching based on-line fingerprint verification system

描述了一个基于特征点匹配的联机指纹验证系统设计思想和实现方法 .专用的CCD指纹采集设备通过自动跟踪二值化电路 ,可向处理软件提供高质量的二值图像 .专门设计的一种两遍扫描串行迭代细化算法可以获得高质量的指纹的骨架 .设计了一种新方法在细化后的点线图上计算指纹的中心点 .特征点匹配算法通过动态建立极坐标系和弹性配对特征点来实现 .预先计算出的中心点可使搜索范围大大减少 。

Describes the design and implementation of an on line fingerprint verification system based on minutiae matching. A special CCD input device provides the processing software with high quality binary images by means of an automated following technique. A specially designed two pass sequential iterative thinning algorithm helps to acquire high quality skeleton of fingerprints. We use a new method to calculate the fingerprint's center point from the thinned image. Rotary coordinates are dynamically established in our matching algorithm, in which an elastic minutiae paring method is used. The pre calculated center points of the two fingerprints greatly restrict the searching scale and make this matching strategy quick enough to be used in an on-line automatic fingerprint authentication system.