一种基于区域标记的虹膜内边缘定位新算法

提出了一种新颖简单的虹膜内边缘(瞳孔)定位算法.首先,采用Soble边缘检测算子和形态学变换进行边缘检测;然后,利用区域标记法为边缘检测后形成的各连通成分赋予相应的灰度值,并利用直方图的方法分离出瞳孔区域;最后,采用投影的方法进行瞳孔的定位.实验结果表明,文中提出的方法能够准确地进行虹膜内边缘定位.

A new algorithm for location of iris inner boundary based on region marking

The location of iris inner boundary is a key problem in the iris recognition. This article puts forward a new and simple algorithm for the location of the iris inner edge (i.e. pupil). Firstly, the Sobel operator and morphology transform are used to detect the edge of the iris image. Then, all connected regions in the detected edges are given the relevant gray-scale. Furthermore, the pupil area can be separated by the method of gray-scale histogram. At last, the pupil is located by the projection method. The results of experimentation prove that the proposed algorithm can be used to locate the inner boundary of iris exactly.