自适应邻域加权模拟退火层叠滤波器

Adaptive Neighbor Weight Simulated Annealing Stack Filters

图像处理问题的研究中,层叠滤波器的优化设计实际上是寻找最优正布尔函数的过程,如何有效地获得最优正布尔函数是优化设计的难点问题,为了改进层叠滤波器的优化方法,提出在自适应邻域加权平均绝对值(ANWMAE)准则的基础上建立数学优化模型,设计层叠滤波器,算法相对遗传算法优化时间较短,同时将邻域像素点的影响考虑在内,通过在迭代过程中得到最优正布尔函数。在传统阈值分解的基础上,构建自适应邻域加权模拟退火层叠滤波器(ANWSA)和自适应邻域加权递归模拟退火层叠滤波器(RANWSA)。对最优ANWSA和RANWSA进行了性能分析,结果表明,层叠滤波器在有效地滤除噪声的同时,能更好地保持图像的细节信息。

The design of stack filters was formulated as a course of optimizing PBF,and how to effectively gain optimal Boolean function was difficult problem.In order to solve the above problem,simulated annealing algorithm（SA） was presented to design stack filters,whose optimization time was less than genetic algorithm,and the effect of neighbor pixel was considered,and the optimal mathematical model was constructed based on adaptive neighbor weight error（ANWMAE） criterion.The adaptive neighbor weight simulated annealing stack filters（ANWSA） and the adaptive neighbor weight recursive simulated annealing stack filters（RANWSA） were constructed based on the traditional threshold decomposition.In order to testify the filtering capability,ANWSA and RANWSA were simulated,the results show that they can suppress noise and protect the details of image effectively.