摘要
针对虹膜图像中复杂的层次结构使得虹膜卷缩轮难以提取问题,提出了一种基于Snake的虹膜卷缩轮提取方法。以轮廓采样点到相邻采样点的中点距离为内部能量函数,以每个采样点与相邻两采样点线段上所有点的梯度的平均值为外部能量函数,并且根据内、外部能量的比值动态调整权值参数。该方法将虹膜卷缩轮特征点的提取转化成求总能量函数的最小值问题。实验结果表明基于Snake的虹膜卷缩轮提取方法的可行性和有效性。
To solve the problem of collarette extraction in complex and layered iris image, A method based on Snake is proposed. In the method, the internal energy is composed of the distance between the sample points on the contour and the midpoint between its two neighboring sample points, the external energy is composed of the average gradient of all points on the lines between the sample points and its two neighboring points. An adaptive weighting parameter adjustment is applied based on the ratio of the total energy. Under this method, the extraction on eollarette feature points is turned to minimization of the total energy. The experimental result shows the feasibility and validity of the method for collarette extraction based on Snake.
出处
《微计算机信息》
北大核心
2006年第07S期197-199,共3页
Control & Automation
基金
国家自然科学基金:90209020
