摘要
为了有效地对灰度图像进行自动分割,本文基于代价函数最小化方法,提出一种自适应免疫遗传算于图像分割。文中图像分割问题被表示为组合优化问题,而自适应免疫遗传算法作为一种优化算法用来寻找(准)最优的分割图像。在该算法中,交叉、变异及免疫算子采用了自适应变化的概率,同时利用问题的先验知识和进化个体的历史信息自适应地提取疫苗,使算法的整体性能得到提高,产生了较令人满意的分割结果,并对噪声有较好的抑制作用。
In order to automatically segment a gray-scale image, this paper presents an adaptive immune genetic algorithm based on the cost minimization technique for image segmentation. The image segmentation problem is firstly cast as one of combinatorial optimization. A cost function which incorporates both edge information and region gray-scale uniformity is used. Then, the immune genetic algorithm is treated as an optimization technique to find the optimal solution. The presented algorithm recommends the usage of adaptive probabilities of crossover, mutation and immune operation. Furthermore, it effectively exploits some prior knowledge of pending problem and the information of evolved individual past history to make vaccines. Experimental results show that the algorithm performs well in terms of quality of the final segmented image and robustness to noise.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2005年第2期193-197,共5页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金(No.60141002)
关键词
图像分割
免疫遗传算法
费用最小化
Image Segmentation
Immune Genetic Algorithm
Cost Minimization
