基于跨尺度字典学习的图像盲解卷积算法

在模糊核未知情况下利用模糊图像对清晰图像进行复原称为图像盲解卷积问题,这是一个欠定逆问题,现有的大部分算法通过引入模糊核和清晰图像的先验知识来约束问题的解空间。本文提出了一种基于跨尺度字典学习的图像盲解卷积算法,采用降采样图像训练稀疏表示的字典,并将图像纹理区域在该字典下的稀疏表示作为正则化约束引入盲解卷积目标函数中。图像降采样过程减弱了图像的模糊程度,且图像中存在冗余的跨尺度相似块,利用更清晰的图像块训练字典能够更好地对清晰图像进行稀疏表示,减小稀疏表示误差;同时,由于在纹理区域清晰图像的稀疏表示误差小于模糊图像的稀疏表示误差,在该字典下对图像中的纹理块进行稀疏表示,使重建图像偏向清晰图像。本文的算法在Kohler数据集上复原结果的平均峰值信噪比为29.54 dB。在大量模糊图像上的实验验证了本文的算法能够有效解决大尺寸模糊核的复原,并具有良好的鲁棒性。

Blind image deconvolution via cross-scale dictionary learning

Blind image deconvolution recovers a sharp image from a blurred image when the blur kernel is unknown.To solve this underdetermined inverse problem,most existing methods exploit various image priors to constrain the solution.In this study,we propose a blind deconvolution method based on crossscale dictionary learning,in which the down-sampled blurry image is used to learn a dictionary as training samples and the texture region is represented sparsely over the dictionary as the regularization term.Because the down-sampling process weakens the blur of the image,it will result in the formation of redundant cross-scale similar patches.To ensure that a sharp image is represented sparsely,sharper image patches from the down-sampled image in this study were used to learn the dictionary as training samples.The results showed that the sparse representation error of the texture patch from the sharp image was less than that from the blurred image,further diminishing the sparse representation error over the dictionary,and the intermediate latent image approached the sharp image.The mean peak signal-to-noise ratio of the results by our method on the dataset of Kohler et al.is 29.54 dB.Experimental results on blurry images demonstrated that our method can estimate large blur kernels accurately and that it has good robustness.