基于多结构鲁棒估计的虹膜外边缘定位方法

Iris Location Method for Outer Edge Based on Robust Estimation for Multi-structure

在Adaboost检测人脸区域的基础上,提出了基于多结构鲁棒估计的虹膜外边缘定位方法.通过对200幅单人脸的图像数据集的仿真实验,结果表明,本方法相比于传统的RANSAC模型生成算法以及Hough变换等方法,能得到更精确的定位结果,而且能加快有效的模型生成,虹膜外边缘定位精度达到94%.

On the basic of detecting the area of human face with Adaboost algorithm, a iris location method for the outer edge based on robust estimation for multi-structure was proposed. For 200 single human face image data set, the simulation experiments showed that more accurate location was obtained and the valid hypothesis generation was accelerated by the proposed method which compared with the conventional hypothesis generation method of RANSAC and Hough Transform. In addition, the accuracy of iris location for outer edge achieves 94%.