摘要
提出了一个包含4个自适应神经模糊推理系统和一个后处理块的网络,该网络可用于灰度图像滤波。网络中每个自适应神经模糊推理系统都是一个四输入单输出一阶Sugeno模糊推理系统。所提出的滤波方法分两步进行,首先对该网络进行优化训练,确定其参数,然后用优化后的网络对被椒盐脉冲噪声污染的图像进行噪声滤波。实验结果表明,所提出的方法在有效去除图像中椒盐脉冲噪声的同时,能够较好地保留原有图像中的边缘和细节,其滤波性能优于传统的滤波方法。
A neuro-fuzzy network approach to impulse noise filtering for gray scale images was presented. The network is constructed by combining four neuro-fuzzy filters with a postprocessor. Each neuro-fuzzy filter is a first order Sugeno type fuzzy inference system with 4-inputs and 1-output. The proposed impulse noise filter consists of two modes of op- eration, namely, training and testing (filtering). The experimental results demonstrate that the proposed filter not only has the ability of noise attenuation but also possesses desirable capability of details preservation. It significantly outper- forms other conventional filters.
出处
《计算机科学》
CSCD
北大核心
2013年第7期302-306,共5页
Computer Science
基金
国家自然科学基金(61170119)
中央高校基本科研业务费专项资金(JUSRP211A38)资助
关键词
图像滤波
神经模糊推理系统
脉冲噪声
Image filtering,Neuro-fuzzy inference system, Impulse noise