摘要
针对均值滤波在抑制噪声的过程中会损失图像的边缘等细节信息从而导致整幅图像模糊的问题,提出一种均值滤波改进算法。算法中局部窗口内中心像素灰度均值的计算既考虑了窗口内各像素与中心像素间的灰度值差异,又顾及了窗口内各像素与中心像素间的距离。实验结果表明,该算法能有效去除噪声,较好地保留图像边缘细节,相比传统均值滤波和自适应均值滤波算法有更好的去噪能力。
Details of image are broken by mean fiher in image processing, and consequently the image turns out to be blurry. In light of this, we propose a modified average filtering algorithm. In the algorithm, the computation of gray averaging value of central pixel in local window considers both the gray value difference and the spatial distance between the central pixel and other neighbouring pixels in current local window. Experimental results show that the presented algorithm can effectively remove Gaussian noise as well as preserving the edge details of the image well. It is superior to tradition mean filter and adaptive averaging filter algorithms in de-noise capability.
出处
《计算机应用与软件》
CSCD
北大核心
2013年第12期97-99,116,共4页
Computer Applications and Software
基金
国家自然科学青年基金项目(41104096)
江苏师范大学自然科学重点基金项目(09XLA04)
关键词
高斯噪声
图像去噪
均值滤波
噪声方差
Gaussian noise Image de-noising Average fihering Noise variance