基于模拟退火算法的最优层叠滤波器设计  

Optimal stacked filters by simulated annealing

作　　者：崔颖[1] 赵春晖[1] 

机构地区：[1]哈尔滨工程大学信息与信通工程学院,黑龙江哈尔滨150001

出　　处：《应用科技》2005年第10期1-3,共3页Applied Science and Technology

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);黑龙江省杰出青年基金资助项目(JC-02-07);博士后启动基金;高校青年教师教学科研奖励计划基金资助项目

摘　　要：为了改进层叠滤波器的优化方法,提出基于模拟退火算法的层叠滤波优化设计方法,用来处理灰度图像.层叠滤波器是基于阈值分解发展起来的一种非线性滤波器,它的优化过程是对正布尔函数不断学习的过程.模拟退火算法是一种通用的优化算法,目前已在工程中得到广泛的应用,优化的时间相对于遗传算法要短.仿真结果可知,应用模拟退火算法的优化层叠滤波器,可有效滤除噪声和保持图像细节.In order to improve optimization algorithm of staked filters, an algorithm based on simulated annealing（SA） is proposed to deal with grey images. Stacked filters are a class of nonlinear digital filters based on threshold decomposition, whose optimizing process is a course of optimizing PBF. SA is a conventional optimization algorithm, and is widely used in engineering. The consumed time is less than genetic algorithm. In this paper, SA is employed to optimize stacked filters. Experimental results indicate that the optimized stacked filters can eliminate noise and protect the details of image effectively.

关 键 词：层叠滤波 模拟退火 灰度图像 图像处理 

分 类 号：TN911.72[电子电信—通信与信息系统]