邻域自适应调整的Snake算法  

Snake Algorithm of Neighborhood Adaptive Modification

作　　者：秦中元[1] 牟轩沁[1] 蔡元龙[1] 

机构地区：[1]西安交通大学电子与信息工程学院图像所

出　　处：《小型微型计算机系统》2005年第4期684-686,共3页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(30070225)资助

摘　　要：提出了一种自适应的Snake算法,对于初始包络上的每一点,按照Greedy算法中的能量公式计算其邻域内各点的能量.如果邻域不包含目标的轮廓,则将邻域半径加大,再次计算邻域内各点的能量,直到邻域内包含轮廓点为止.该算法只需迭代一次即可得到目标轮廓,而且增大了初始包络的收敛半径,并能够有效处理较高曲率凸形边缘的情况.对比实验说明了这种方法的有效性.An adaptive Snake algorithm is presented in this paper. To every point in the initial position, the energy of the point in its neighbors is calculated using the formula given in Greedy algorithm. If the target contour is not included in its neighbors, the radius of its neighbors is increased and energy of all the points are calculated again until target contour is included. The target contour can be got after only one iteration and the convergent radius is increased. The bulge in contour can also be processed. Comparative experiments indicate the validity of this method.

关 键 词：主动轮廓模型 邻域 自适应 

分 类 号：TP319.41[自动化与计算机技术—计算机软件与理论]