一种基于噪声拓扑结构的滤波算法  

A Filtering Algorithm Based on Topological Structure of Noise

作　　者：黄文涛[1] 毕笃彦[1] 毛柏鑫[1] 马时平[1] 

机构地区：[1]空军工程大学工程学院四系,西安710038

出　　处：《中国图象图形学报》2005年第9期1105-1111,共7页Journal of Image and Graphics

摘　　要：基于脉冲噪声的特点,提出了一种新的非常有效的脉冲噪声的滤波算法。该算法将滤波过程分为两步进行,即第1步对图像的脉冲噪声点进行标识,第2步再对标识的噪声点进行滤波。在第1步这中,充分考虑到脉冲噪声的特点,主要利用了噪声的拓扑连通性;在第2步时,利用噪声点周围非噪声点的信息,来对噪声点进行修复。最后进行了仿真试验,并与传统中值滤波算法和开关中值滤波算法进行了比较,试验表明,在信噪比和细节保留方面,该算法要明显优于它们,特别是对高强度的脉冲噪声也有比较好的效果。A new efficient approach for the removal of impulse noise is presented based on the characteristic of impulse noise in this paper. The algorithm is composed of two steps. The first step is to identify the impulse noise of image. The following step is to smooth the identified noise pixel, where we take into account the impulse noise characteristic and utilize the topological connectedness of impulse noise. In the second step, using the information around the noise pixel restores the noise pixel. Simulation results demonstrate that the proposed algorithm is obviously better than traditional median-based filters and switching median filter, and is particularly effective for the cases where the images are very highly corrupted.

关 键 词：滤波 脉冲噪声 拓扑连通性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]