摘要
提出了一种新的图像去噪方法。此方法通过二维经验模态(BEMD)将噪声图像分解为一系列不同频带的子图像。对低频近似图像保持不变,对高频细节图像采用不同的模板进行均值滤波,最后将低频近似图像和均值滤波后的图像合成为去噪后的图像。实验结果表明该方法在滤除图像噪声的同时,又能较好地保留图像的边缘细节,其滤波效果优于单一的BEMD图像去噪和均值滤波图像去噪以及小波变换和均值滤波图像去噪方法。
A new image-denoising method was proposed. Noised image was decomposed to a series of sub-band images by Bimensional Empirical Mode Decomposition ( BEMD). High frequency sub-band images were denoised by mean filtering using different filter templates, and low frequency approximation image remained unchanged in this process. Then the denoisedimage was obtained by composing the low frequency approximation images and the high frequency detailed images with mean filtering. Experimental result shows that the noise is effectively removed and the detail of the image is well preserved. This method has better denoising effect than single BEMD method and mean filtering method and the method combining wavelet transform with mean filtering.
出处
《计算机应用》
CSCD
北大核心
2008年第11期2884-2886,共3页
journal of Computer Applications
基金
国家科技支撑计划项目(2007BAG06B06)
重庆大学自然科学青年基金项目
关键词
图像去噪
小波变换
二维经验模态
均值滤波
image denoising
wavelet transform
bidimensional empirical mode decomposition
mean filtering.
作者简介
(rxy80@sina.com)让晓勇(1980-),男,山西忻州人,硕士研究生,主要研究方向:数字图像处理
叶俊勇(1973-),男,四川西昌人,副教授,博士,主要研究方向:数字图像处理、模式识别、机器视觉、无损检测;
郭春华(1978-),女,湖北随州人,博士研究生.主要研究方向:数字图像处理、模式识别。