类型2模糊系统模型组合的噪声滤波器  

New noise filter based on combination of Type-2 fuzzy system models

作　　者：王双双[1] 王士同[1] 李岳阳[1] 

机构地区：[1]江南大学信息工程学院,江苏无锡214122

出　　处：《计算机工程与应用》2011年第25期182-185,共4页Computer Engineering and Applications

摘　　要：通过对区间类型2模糊系统(intervalType-2FLS)和高斯类型2模糊系统(GaussianType-2FLS)进行组合,提出了适合图像脉冲噪声滤波的TFLS滤波器。用噪声密度不同的数字图像测试TFLS滤波器的性能,同时与区间类型2模糊系统FLS滤波器等进行对比。实验结果表明:TFLS滤波器在去除图像的脉冲噪声的同时,能较好地保留图像中的边缘细节信息,较显著改善图像视觉质量,客观评价指标PSNR值也有较明显提高。Based on the combination of interval Type-2 fuzzy systems and Gaussian Type-2 fuzzy systems,a novel TFLS filter is presented for filtering impulse noise in images.The performance of the proposed TFLS filter is evaluated for different test images corrupted at various noise densities and also compared with other impulse noise filters.The experimental results show that the proposed TFLS filter outperforms other filters in suppressing Gaussian noise while at the same time effectively preserving edges,texture,and other useful information within the image.

关 键 词：图像去噪 脉冲噪声 滤波器 Type-2模糊系统 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]