Single Image Super-Resolution Based on Deep Learning Features and Dictionary Model

Abstract

In traditional single image super-resolution (SR) methods based on dictionary model, a large number of image features are needed to train the SR dictionary. In general, these features are extracted by artificial rules, such as pixel gray, gradient, and texture structure. But, the dictionary model trained by these artificial features or their combinations has exhibited poor expression especially for the images with complex and rich structures. Therefore, how to improve the dictionary expression ability and make the dictionary have more accurate description of the image features is a problem worthy of further study. In this paper, based on the advantage of dictionary training and deep learning, a new method of single image SR based on deep learning features and dictionary model is proposed. The new algorithm contains three steps. First, the features of high-resolution and low-resolution training images are extracted by a Kernel deep learning network. Second, in the sparse representation of SR framework, the dictionary model is trained by these deep learning features. Finally, an LR image SR is completed. Theoretical analysis show that the dictionary trained by deep learning features can improve in the ability to express image complex structure and texture, and it has more advantage than traditional artificial features dictionary. The experimental results indicate that the proposed algorithm can produce good SR visual results than the comparison algorithm, such as Bicubic, sparse coding super-resolution, and super-resolution convolutional neural network. And the peak signal to noise ratio and structural similarity index measurement are improved, the Computation Time is also reasonable.