In this study, an efficient self-learning method for image super-resolution (SR) is presented. In the proposed algorithm, the input image is divided into equal size patches. Using these patches, a dictionary is learned based on K-SVD, referred to as high resolution (HR) dictionary. Then, by down-sampling, the columns of the dictionary, called atoms, a low resolution (LR) version of the dictionary is obtained. An initial estimate of the SR image is constructed using the bicubic interpolation on the input image. Then in an iterative algorithm, the difference between the down-sampled version of the estimated SR image and the input image is obtained. This difference image, which includes reconstructed details is enlarged using sparse representation and LR/HR dictionaries. The enlarged detail is added to the latest reconstructed SR image. This process gradually improves the quality of the initial SR image. After several iterations, the reconstructed image is an SR version of the input image. Experimental results confirm that the proposed method performance is promising.

中文翻译：

---

基于稀疏表示的单幅图像超分辨率，使用输入图像补丁训练的字典

在这项研究中，提出了一种有效的用于图像超分辨率（SR）的自学习方法。在提出的算法中，输入图像被分成相等大小的块。使用这些补丁，可以基于K-SVD学习字典，称为高分辨率（HR）字典。然后，通过下采样，字典的列称为原子，从而获得字典的低分辨率（LR）版本。使用双三次插值法在输入图像上构造SR图像的初始估计。然后，在迭代算法中，获得估计的SR图像的降采样版本与输入图像之间的差异。使用稀疏表示和LR / HR字典可以放大包含重构细节的差异图像。放大的细节将添加到最新重建的SR图像中。此过程逐渐提高了初始SR图像的质量。经过几次迭代后，重建的图像是输入图像的SR版本。实验结果证实了所提出的方法的性能是有希望的。