自适应饱和度–明度全变差的彩色图像去噪算法

A Color Image Denoising Algorithm with Adaptive Saturation-Value Total Variation

基于饱和度–明度全变差的图像去噪模型(SV-TV模型)能有效去除彩色图像中的高斯噪声,但去噪效果依赖于模型中正则化参数的选取。本文在SV-TV模型的基础上,结合交替迭代极小化方法,提出一种自适应饱和度–明度全变差的彩色图像去噪算法。该算法利用广义交叉验证技术,使得SV-TV模型中的正则化参数在算法迭代过程中可以自动更新。数值实验结果验证了所提自适应算法的有效性与可行性。

Saturation-value total variation (SV-TV) model can effectively remove Gaussian noise in color imag-es, and its denoising effect depends on the selection of regularization parameters. Based on the SV-TV model, this article proposes an adaptive color image denoising algorithm by using the alter-nating minimization method. The algorithm utilizes the generalized cross-validation technique to automatically update the regularization parameters in the SV-TV model. Numerical experimental results validate the effectiveness and feasibility of the proposed adaptive algorithm.