一种高效去除椒盐噪声的中值滤波方法  

An Efficient Salt-and-Pepper Noise Removal by Median Filter

作　　者：罗玲[1] 王修信[1] 

机构地区：[1]广西师范大学计算机科学与信息工程学院,广西桂林541004

出　　处：《微电子学与计算机》2011年第11期118-121,共4页Microelectronics & Computer

基　　金：国家自然科学基金项目(41061040);广西研究生教育创新计划项目(2010106020812M59)

摘　　要：提出了一种基于先检测、后滤波的椒盐噪声滤除算法.将像素值为0或255附近的像素点作为疑似噪声点,其余点为信号点.信号点不做任何处理,以保留更多的图像细节.而对于疑似噪声点,首先用改进的自适应极值中值方法进行噪声检测,并将检测结果记录在一个二值矩阵flag中,其中信号点记为1,噪声点记为0.然后根据图像像素值矩阵与flag的点积进行自适应中值滤波处理.实验结果表明,不仅对真实含噪图像处理有很强的适应性,而且对噪声密度高的图像,能在有效去除椒盐噪声的同时保护图像细节.在不同噪声率下均优于标准中值(SMF)滤波法及其一些改进方法,在噪声密度为10%～90%其峰值信噪比(PSNR)平均提高6dB.A simple algorithm based on noise--detected is presented to remove salt--and--pepper noise from gray-- scale image. Each pixel is classified to be signal pixel or possible noise pixel, and the value of possible noise pixels is near 0 or 255. The signal pixels are kept untouched in the filtering process to preserve the detail of the image, while the possible noise pixels are removed by using an improved Adaptive Median Filter, which fixes the noise pixels by utilizing the dot product of the matrix of gray value and a binary matrix, named flag, that is used to record the noise detection results based on improved adaptive Extremum and Median value. A signal pixel is for the value of 1 while a noise is 0 in flag. Simulation results show that the algorithm has strong adaptability to deal with the real noise images. And it can suppress noise effectively and preserve the image details in the high noisy rate. This algorithm outperforms the Standard Median Filtering （SMF） and its improved algorittuns for different noise ratio. The PSNR is increased about 6dB on average when the noise rate ranging from 10% to 90%.

关 键 词：椒盐噪声 自适应中值滤波 噪声检测 噪声去除 峰值信噪比 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]