基于RGB通道下模糊核估计的图像去模糊

图像去模糊旨在从受损图像中恢复出清晰图像。由于模糊过程未知,精确地估计出模糊核函数,成为得到清晰复原图像的关键。对于彩色图像来讲,现存的方法只考虑在灰度域估计模糊核。事实上,各个通道的色彩分量图所受到的模糊核函数的影响是不同的。为此,提出一种获得更加精确的模糊核的方法,利用彩色图像的3个色彩通道(RGB channels)代替灰度域分别进行模糊核估计,并将估计出的模糊核应用到基于细稀疏表示的复原模型中进行去模糊处理。仿真实验表明,提出的方法比目前的方法能够获得更好的图像复原效果。

Image deblurring with blur kernel estimation in RGB channels

Image deblurring aims to recover the clear image from the damaged image. The main factor of the image deblurring is to precisely estimate the blur kernel in the unknown blurring process. For color images, the most existing blind image deblurring approaches only estimate the blur kernel in the gray domain. In fact, the blur effects for each color channel are usually different. This paper proposes a new approach to acquire more precise blur kernels by estimating blur kernels through RGB channels independently instead of just using the gray domain, and then the group sparse representation model is used to perform blur kernel estimation in each channel. The numerical results demonstrate that the proposed approach achieves better performance compared with the state-of-the-art methods.