自适应蚁群算法亚像素边缘检测我要分享

Adaptive Ant Colony algorithm for subpixel edge de

matlab 算法 检测 边缘 像素 自适 应蚁群

关注次数: 331

下载次数: 0

文件大小: 87.60 kB

代码分类: 其他

开发平台: matlab

下载需要积分: 1积分

版权声明:如果侵犯了您的权益请与我们联系,我们将在24小时内删除。

代码描述

中文说明:蚁群算法是在1992年由意大利学者M.Dorigo及其同事受蚂蚁觅食过程中路径选择行为的启发而提出的仿生进化算法。在长期的研究中他们发现蚂蚁虽然没有视觉,但是在搜索食物的过程中总能找到距离食物源最短的路径。在初始阶段,蚂蚁在随机的路径上行走并释放信息激素(Pheromone),信息激素会随着时间的推迟不断挥发。蚂蚁在一条路径上完成一次搜索经历的时间越长,信息激素的挥发时间也越长,残留就越少。通过较短的路径找到因此该路径上的信息激素在挥发的同时得到了很大的补偿,总的激素强度不断增加。蚂蚁之间的信息交换和相互协作通过其在搜索路径上信息激素的强度实现,而每只蚂蚁具有感知这种信息激素强度的能力,会以较大概率选择信息激素较强的路径,从而导致选择这条路径的蚂蚁增多,这样形成了一个正反馈过程。蚁群算法中有3个参数对算法性能起关键作用,分别为信息激素强度、启发式引导信息和信息激素随时间的挥发率。


English Description:

Ant colony algorithm in 1992 by the Italian scholar M. Bionic Dorigo and his colleagues by the process of ants foraging route choice behavior inspired evolutionary algorithm proposed. In the long-term study in which they found that although there is no visual ants, but always able to find the shortest path distance food source in search of food in the process. At the initial stage, ant walking and release pheromones (Pheromone) on a random path, pheromones will continue with the delayed time of volatilization. Ants on a path to complete a search for the longer elapsed time, the volatile pheromones longer time, less residue. Through shorter path found so pheromones on the path in the same time has been greatly volatilized compensation, increasing the intensity of the total hormone. Exchange of information and mutual cooperation between ants through its search path pheromones strength to achieve, and each ant pheromones have the ability to perceive this stre


代码预览