| 一种基于双重网络模型的单幅图像超分辨率方法 |
| |
| 引用本文： | 倪翠,王朋,张广渊,李克峰.一种基于双重网络模型的单幅图像超分辨率方法[J].应用科学学报,2021,39(2):321-329. |
| |
| 作者姓名： | 倪翠 王朋 张广渊 李克峰 |
| |
| 作者单位： | 山东交通学院 信息科学与电气工程学院, 山东 济南 250357 |
| |
| 基金项目： | 国家自然科学基金青年基金（No.61502277）资助 |
| |
| 摘 要： | 本文对深度学习领域中的高效亚像素卷积神经网络（efficient sub-pixel convolutional neural network，ESPCN）算法进行了改进，通过加入残差网络知识，调整原有的ESPCN构造结构，提出了一种双重网络模型下单幅图像超分辨率重建方法。通过实验证明：该算法能够有效地提高单幅图像超分辨率重建的精度，丰富重建后的细节信息。
|
| 关 键 词： | 残差网络 亚像素卷积 带组归一化 隐藏层 |
| 收稿时间： | 2020-10-23 |
A Single Image Super-Resolution Method Based on the Dual Network Model |
| |
| NI Cui,WANG Peng,ZHANG Guangyuan,LI Kefeng.A Single Image Super-Resolution Method Based on the Dual Network Model[J].Journal of Applied Sciences,2021,39(2):321-329. |
| |
| Authors: | NI Cui WANG Peng ZHANG Guangyuan LI Kefeng |
| |
| Institution: | School of Information Science and Electric Engineering, Shandong JiaoTong University, Jinan 250357, Shandong, China |
| |
| Abstract: | This article mainly improves the efficient sub-pixel convolutional neural network (ESPCN) algorithm in the field of deep learning. By adding residual network knowledge and adjusting original ESPCN structure, a dual network model is proposed for single frame image super-resolution reconstruction method. Experimental results show that this algorithm can effectively improve the accuracy of single-image super-resolution reconstruction and enrich the detailed information after reconstruction. |
| |
| Keywords: | residual network sub-pixel convolution band group normalization hidden layer |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《应用科学学报》浏览原始摘要信息 |
| 点击此处可从《应用科学学报》下载免费的PDF全文 |
