Convolutional Neural Network Based Models for Improving Super-Resolution Imaging

IEEE Access

Hao Gu¹  Jie Yang¹  Wenhua Xu¹  Guan Gui¹  Yingyi Sun¹  Sheng Hong¹  Wei Zhang²  Chao Liu³ 

[1] College of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China;School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China;School of Management, Nanjing University of Posts and Telecommunications, Nanjing, China;

关键词: Super-resolution imaging;    deep learning;    convolutional neural networks;    adaptive moment estimation;   

DOI  :  10.1109/ACCESS.2019.2908501

来源: DOAJ

【 摘 要 】

Many fields, such as remote sensing, medical imaging, and biological detection, pose a technical challenge for achieving super-resolution imaging. Convolutional neural networks (CNNs) are considered one of the potential solutions to realize the super-resolution. In this paper three-layer, CNN-based models are proposed to reconstruct the super-resolution images using four optimization algorithms, i.e., stochastic gradient descent, adaptive gradient (AdaGrad), root mean square prop (RMSprop), and adaptive moment estimation (ADAM). Among these four optimizations, ADAM is considered to have the best performance. To further verify the impact of the number of convolution layers on performance, a selection of CNN-based models with four convolutional layers is then proposed, each of which is named with the convolution parameters. All the four-layer models are optimized with ADAM, and the experimental results indicate that the 9-3-3-5 model achieves the best performance in the super-resolution reconstruction task.

【 授权许可】

Unknown