基于相关性的二级检测图像滤波算法  

Secondary Signal Detection Filtering Algorithm Based on Correlation

作　　者：赵国栋[1] 刘少平[2] 

机构地区：[1]上海电机学院数理教学部,上海200240 [2]华中科技大学数理与统计学院,武汉430074

出　　处：《上海电机学院学报》2010年第5期276-279,302,共5页Journal of Shanghai Dianji University

基　　金：国家自然科学基金项目(60704003)

摘　　要：为了准确检测图像中的椒盐噪声并滤除,提出了一种基于相关性的二级检测图像滤波算法。该算法根据椒盐噪声的特点,确定了准噪声点的范围;根据信号局部相关性,准确地分离出信号点和噪声点,对噪声点,取滤波窗口内的信号点的中值进行滤波。试验结果表明:该算法对椒盐噪声有很好的抑制作用。In order to accurately detect salt and pepper noise in an image and filter it out,a secondary noise detection filter algorithm based on extreme value is proposed.The algorithm sets the range of noise pixels based on the characteristics of salt and pepper noise.According to local correlation of signal,signal and noise are classified,and noise pixels are replaced with the median of the signal in a window.Experimental results show that the algorithm can effectively suppress salt and pepper noise.

关 键 词：图像滤波 椒盐噪声 极值滤波 二级检测 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] TP391.41[自动化与计算机技术—计算机科学与技术]