Deep Residual Neural Network Design for Super-Resolution Imaging

Wei Ting Chen, Pei Yin Chen, Bo Chen Lin

研究成果: Conference contribution

摘要

Convolution neural network recently confirmed the high-quality reconstruction for single-image super-resolution (SR). In this paper we present a Deep Level Residual Network (DLNR), a low-memory effective neural network to reconstruct super-resolution images. This neural network also has the following characteristics. (1) Ability to perform different convolution size operations on the image which can achieve more comprehensive feature extraction effects. (2) Using residual learning to expand the depth of the network and increase the capacity of learning. (3) Taking the skill of parameter sharing between the network module to reduce the number of parameters. After the experiment, we find that DLNR can achieve 37.78 in PSNR and 0.975 in SSIM when using Manga109 as testing set for 2× SR.

原文English
主出版物標題New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers
編輯Chuan-Yu Chang, Chien-Chou Lin, Horng-Horng Lin
發行者Springer Verlag
頁面95-105
頁數11
ISBN(列印)9789811391897
DOIs
出版狀態Published - 2019
事件23rd International Computer Symposium, ICS 2018 - Yunlin, Taiwan
持續時間: 2018 12月 202018 12月 22

出版系列

名字Communications in Computer and Information Science
1013
ISSN(列印)1865-0929
ISSN(電子)1865-0937

Conference

Conference23rd International Computer Symposium, ICS 2018
國家/地區Taiwan
城市Yunlin
期間18-12-2018-12-22

All Science Journal Classification (ASJC) codes

  • 一般電腦科學
  • 一般數學

指紋

深入研究「Deep Residual Neural Network Design for Super-Resolution Imaging」主題。共同形成了獨特的指紋。

引用此