基于自适应整体退火遗传算法层叠滤波器的优化设计  

Optimizing stack filters by adaptive whole annealing genetic algorithm

作　　者：赵春晖[1] 崔颖[1] 李刚 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《哈尔滨工程大学学报》2006年第1期136-140,146,共6页Journal of Harbin Engineering University

基　　金：全国优秀博士学位论文作者基金资助项目(200037);高校博士点基金资助项目(20020217006);黑龙江省杰出青年科学基金资助项目(JC-02-07)

摘　　要：层叠滤波器是基于信号阈值分解而发展起来的一种具有层叠性和阈值性的新型非线性数字滤波器.层叠滤波器的优化设计过程实际上就是对正布尔函数不断调整、逐步适应图像环境的优化学习过程.原有遗传算法优化的层叠滤波器易陷于局部最优化,文中鉴于这一点,将退火因子引入到选择算子中,并根据每代优化个体的不同,自适应的选取交叉概率和变异概率,提出一种自适应整体退火遗传算法(AWAGA)优化层叠滤波器,并研究在MSE准则下优化算法的性能.仿真结果表明用AWAGA优化的层叠滤波器在处理噪声图像时,能有效地去除噪声和保持图像细节.Stack filters are a class of nonlinear digital filters that satisfy a weak superposition property known as the threshold decomposition and stacking property. Their design is formulated as a course of optimizing positive Boolean function （PBF）. OPtimizing stack filters by an existing genetic algorithm easily relapses into a local best result, Due to this aspect, using an annealing mechanism as a selection operator is proposed. Cross probability and mutation probability were selected adaptively according to different individuals. Experiment results show that stack filters optimized by an adaptive whole annealing genetic algorithm （AWAGA） under mean squared error （MSE） criteria can suppress noise and protect the details of image effectively.

关 键 词：层叠滤波器 自适应整体退火遗传算法 图像处理 

分 类 号：TN911.26[电子电信—通信与信息系统]