基于阈值分割及边缘检测的虹膜定位算法

摘要

为了提高虹膜图像定位分割的速度和精度，提出了一种改进的虹膜定位分割算法。首先采取聚类法来对虹膜图像阈值分割，快速分割出瞳孔区域，并根据圆形的几何特性对虹膜内边缘粗定位；然后根据圆的对称性计算虹膜内边缘的圆心和半径；最后利用已经提取的瞳孔圆周参数等先验知识检测虹膜外径与圆心。测验结果表明，该算法提高了虹膜定位分割的速度而且定位准确度可达到98．86％，在虹膜识别系统中具有很好的实用意义。%In order to improve the speed and accuracy of the iris image segmentation,an improved segmentation algorithm for iris localization is proposed.First,the iris image threshold segmentation is conducted by K-means clustering to isolate the pupil region to provide coarse location of iris inner edge as per the geometric properties of the circle.Then,the center and radius of the inner edge of the iris is calculated on the basis of the symmetry of a circle.Finally,the pupil extraction has circle parameters such as prior knowledge detecting iris diameter and center.The experimental results show that the proposed algorithm can improve the speed of iris localization with position accuracy of 98.86%,which is useful in the iris recognition system.