Coupled deep auto-encoder with image edge information for image super-resolution

Yinggan Tang, Chunning Bu, Liying Zhao

Abstract: Image super-resolution aims to recover a fine-resolution image from one or more low-resolution image(s). In this paper, we propose a novel image super-resolution approach based on the recent development of coupled deep auto-encoder. In the training step, the vector of the local low resolution (LR) and high resolution image (HR) patches and the corresponding edge information are extracted to be the input of the autoencoder. Then we learn the intrinsic representations of LR and HR image patches by auto-encoders respectively. Then we learn their relationship by a two-layer neural network. In the test step, given a LR image patch, we can obtain the corresponding HR patch through the trained deep network efficiently and effectively. Expensive experimentation results show that the proposed algorithm generates higher-quality super-resolution image compared to other state-of-the-art methods.