置换滤波器的简化形式  

Simplification version of permutation filter

作　　者：宋焕生[1] 王养利[2] 樊海玮[1] 

机构地区：[1]长安大学信息工程学院,陕西西安710064 [2]西安电子科技大学计算机学院,陕西西安710071

出　　处：《长安大学学报（自然科学版）》2005年第5期113-116,共4页Journal of Chang’an University(Natural Science Edition)

基　　金：国家自然科学基金项目(60272050)

摘　　要：置换滤波器是一种重要的非线性滤波器,它包括了几乎所有的基于排序操作的非线性滤波器,但巨大的计算量和存储量要求限制了其在图像处理等领域中的应用。针对图像处理的应用目的,提出了简化置换滤波器的几种方法:减少特征向量的量化级、减少特征空间的维数和对特征空间映射函数施加自偶约束。试验比较了简化前后的滤波器的效果。结果表明,经过适当简化,在滤波性能损失很小的情况下,置换滤波器所需要的计算量和存储量可以大大减少。Permutation filter （PF） is a very important nonlinear filter structure. The permutation filters include nearly all the rank based filters. But because of their very high computational and memory cost, they can not be used in many application areas such as image processing. Some methods for simplifying the permutation filters used for image processing are presented, include reducing the quantity levels of the eigenvector element,cutting down the dimensions of the eigenvector and adding self-dual restrictions on the permutation filters. Simulation results show that the modified permutation filters require much less computation and memory with minimum performance loss. 2 tabs, 1 fig, 6 refs.

关 键 词：图像处理 非线性滤波器 滤波器设计 算法 

分 类 号：TN919.8[电子电信—通信与信息系统]