摘要
虹膜分割是虹膜识别的前提,针对分割出的环状区域含有眼睑、眼睫毛和光斑等干扰,本文提出一种虹膜分割中的眼睑和睫毛的检测方法。基于数学形态学知识,采用边缘检测结合最小二乘法定位眼睑,利用阈值法来检测上眼睫毛和光斑。结果表明,该算法可准确而有效地检测出这些干扰,并从虹膜区域中剔除,从而提高虹膜识别的性能,是一种可行的检测方法。
Iris segmentation is the premise for iris recognition. In view of disturbances of eyelids,eyelashes spots locate in the annular section, a detection method of eyelids and eyelashes in the iris segmentation is proposed. Based on mathematical morphology knowledge, the proposed method uses the least squares method combined with edge detection to determine eyelid occlusion regions, up eyelashes and light spots are detected with threshold method. The experimental results show that the segmentation algorithm can detect these disturbance accuratly and effectively, then reject them from the iris region, so that the performance of iris recognition is improved, which indicate that it is a feasible method.
出处
《石河子大学学报（自然科学版）》
CAS
2009年第3期379-382,共4页
Journal of Shihezi University(Natural Science)
基金
国家自然科学基金项目(60472006)
关键词
虹膜分割
眼睑检测
睫毛检测
最小二乘法
阈值法
iris segmentation
eyelid detection
eyelash detection
least squares method
threshold method
