期刊论文

Chen, Yuantao(chenyt@csust.edu.cn)

英文

Computers & Electrical Engineering

0045-7906

2021

95

107422

10.1016/j.compeleceng.2021.107422

This work is supported by the Natural Science Foundation of Hunan Province of China [ 2020JJ4623 ], the Scientific Research Fund of Hunan Provincial Education Department [ 19C0028 , 19B005 ], the Junior Faculty Development Program Project of Changsha University of Science and Technology [ 2019QJCZ011 ], the Hunan Province Teaching and Reforming Research Project [ (2020)232-HNJG-2020-1292 ], the Undergraduates Innovating Experimentation Project of Changsha University of Science and Technology [ 2020-2-17 , The ECU Simulation Testing System Based on USBCAN-2C Adapter]. The authors also thank undergraduates Shaocong Huo and Qi Zhang for their effective works for research content. Shaocong Huo and Qi Zhang had provided useful feedback and helped shape the research and analysis.

本校为第一机构

The existing image processing methods had aimed at the problems of blurred image reconstruction, large noise, and poor visual perception. The improved image super-resolution algorithm based on mixed deep convolutional networks is proposed in the paper. Firstly, the proposed method can shrink the low-resolution image to the specified size in upsampling phase. Secondly, it can extract features from low-resolution images. It sends the extracted initial features into the convolutional coding and decoding structure for image features. Thirdly, the f...