Image super-resolution based on two-level residual learning CNN

• Published in: Multimedia tools and applications 2020-02, Vol.79 (7-8), p.4831-4846
• Main Authors: Gao, Min, Han, Xian-Hua, Li, Jing, Ji, Hui, Zhang, Huaxiang, Sun, Jiande
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computer Communication Networks; Computer Science; Computer vision; Data Structures and Information Theory; High resolution; Image resolution; Learning; Multimedia communications; Multimedia Information Systems; Special Purpose and Application-Based Systems; Television networks
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-018-6751-5

In recent years, CNN has been used for single image super-resolution (SR) with its success of in the field of computer vision. However, in the recovery process, there are always some high-frequency components that cant be recovered from low-resolution images to high-resolution ones by using existing CNN-based methods. In this paper, we propose an image super-resolution method based on CNN, which uses a two-level residual learning network to learn residual components, i.e., high-frequency components. We use the Super-Resolution Convolutional Neural Network (SRCNN) as the network structure in each level so that our proposed method can achieve the high-resolution images with high-frequency components that cant be obtained by the existing methods. In addition, we analyze the proposed method with considering three kinds of residual learning networks, which are different in the structure and superimposed layers of the residual learning network. In the experiments, we investigate the performance of the proposed method with various residual learning networks and the effect of image super-resolution to image captioning task.