Open AccessA Novel Image Super-Resolution Method Based on Attention Mechanism
Author(s) -
Da Li,
Yan Wang,
Dong Liu,
Ruifang Li
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1518/1/012036
Subject(s) - computer science , artificial intelligence , convolution (computer science) , image (mathematics) , feature (linguistics) , residual , feature extraction , computer vision , pattern recognition (psychology) , channel (broadcasting) , image processing , resolution (logic) , artificial neural network , feature detection (computer vision) , algorithm , telecommunications , philosophy , linguistics
Image super-resolution processing technology is used to reconstruct high-resolution images from low-resolution images. With the development of deep convolution neural network, image super-resolution processing methods based on deep learning have become the main technology. A novel image super-resolution processing method which is based on attention mechanism is proposed in this paper. The network framework consists of two modules: one is an improved position feature extraction network based on residual network and dense network, and another is a channel feature extraction based on channel attention mechanism. Meanwhile, this paper extracts features directly from low-resolution images, and then amplifies them to reduce the computational complexity. From the experimental results, we can find that the proposed method can enlarge the image better and increase the PSNR on Set5, Set14 and B100.