摘要
首先利用小尺度高斯低通滤波器对虹膜图像进行预处理,去除可能存在的眼睑和睫毛干扰;然后用Canny边缘检测算子得到虹膜的内边缘,通过自适应选取非极大值抑制的高阈值,并对不连续边缘进行修整,得到比较理想的虹膜内边缘;最后利用圆周上任意不共线的3点可以确定一组圆心及半径的参数的性质得到虹膜内边缘的圆心及半径,完成虹膜内边缘定位。实验结果表明,该算法可以比较准确地定位出虹膜的内边缘。
This paper firstly uses a small scale Gaussian filter as the pre-processing function.It can wipe off the influence of eyelid and eyelash which may occur within the pupil field.Then the inner edge is detected by the canny detector and then we use morphology transform to make a continuous edge.After that we choose the property of circle that three different points which are not in the same line can make certain a set of parameters of the centre and the radius of a circle.The results show that the proposed method can locate the inner boundary of the iris relatively accurate.
出处
《莆田学院学报》
2011年第2期46-49,共4页
Journal of putian University
基金
福建省自然科学基金资助项目(2009J01283)
