摘要
在一个小邻域里小波系数是相关的,分块在小邻域对小波系数进行阈值去噪操作,可以保留图像尽可能多的细节信息。提出了一种基于牛顿前向插值还原和邻域相关性的二维小波图像去噪方法,实验结果表明:该方法不但能保留更多的图像细节,而且还能较好地抑制"过平滑"。
Wavelet coefficients are correlated in a small neighourhood. Taking into account neighbour wavelet coefficients, we can produce smoother and clearer denoised images. In this paper, we present a new method based on Newton＇ s Forward Interpolation and Neighbour Dependency. The experimental results indicate that the proposed method can keep more images＇ detail information and clearer edge.
出处
《茂名学院学报》
2007年第4期37-39,共3页
Journal of Maoming College
关键词
小波变换
小波图像降噪
软阈值
邻域系数
wavelet transform
wavelet image denoising
soft- threshold
neighbour coefficient
