一种基于噪声估计的彩色噪声滤除算法  

A Color Noise Filter Algorithm Based on Noise Estimation

作　　者：沈磊[1] 陈贵灿[1] 谷宁静[2] 

机构地区：[1]西安交通大学微电子系,陕西西安710049 [2]西安交通大学计算机系,陕西西安710049

出　　处：《微电子学与计算机》2006年第6期96-98,102,共4页Microelectronics & Computer

摘　　要：在视频处理中,为了提高电视画面的清晰度,不但需要对亮度噪声进行滤除,对色度噪声的滤除也是必不可少的。文章的滤波算法是:先基于块操作对图像的噪声情况做一个大概的估计,然后根据估计的噪声情况对图像进行降噪或者不作处理。降噪的时候,对彩色脉冲和高斯噪声分别选择不同的降噪算法。文章着重介绍了彩色脉冲噪声的滤除,该算法综合了线性和非线性矢量滤波,降噪效果明显.对高斯噪声采用矢量均值滤波。in video processing, to improve the definition of the digital TV, removing of the color noise is necessary. The algorithm can be described as following： Firstly make an estimation of the current picture basing on the blocks. Secondly according to the results of estimation process the picture or not. This algorithm aims at removing the different color noise with different algorithms. Main of the paper describes how to remove the color pulse noise. The method combines the linear and nonlinear vector filters and get good effect. Vector mean filter is used to process the gauss noise.

关 键 词：噪声估计 色度降噪 自适应 视频处理 向量中值滤波 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]