A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network

DOI

10.2991/icmia-16.2016.115How to use a DOI?

Keywords

Super-resolution, Deep Convolutional Neural Networks, Multi-frame Color Images.

Abstract

With the extensive application of machine learning. Deep convolution neural network (DCNN) learning method is developed on the basis of a multi-layer neural network for image classification and identification of specially designed. It has been improved and applied for single image super-resolution problem and demonstrated state-of-the-art quality. In this paper, we presents a novel framework based on deep convolutional neural network to realize the multi-frame color images super-resolution. The system contains two parts, multi-frame Image pixel processing and structure design of DCNN. The prior information could be utilized during the image pixel processing. Experimental results prove its effectiveness and confirm out framework can be effectively applied to multi-frame color images super-resolution. The generated super-resolution image achieves a better restoration image quality compared to state-of-the-art methods.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhe Li
AU  - Shu Li
AU  - Jianmin Wang
AU  - Hongyang Wang
PY  - 2016/11
DA  - 2016/11
TI  - A Novel Multi-Frame Color Images Super-Resolution Framework based on Deep Convolutional Neural Network
BT  - Proceedings of the 2016 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016)
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmia-16.2016.115
DO  - 10.2991/icmia-16.2016.115
ID  - Li2016/11
ER  -