Institutional Repository of Coll Elect & Informat Engn
Deep CNN jointing low-high level feature for image super-resolution | |
Song, Xuhui1; Liu, Weirong1![]() ![]() ![]() | |
2019 | |
会议名称 | 10th International Conference on Graphics and Image Processing, ICGIP 2018 |
会议录名称 | Proceedings of SPIE - The International Society for Optical Engineering
![]() |
卷号 | 11069 |
会议日期 | December 12, 2018 - December 14, 2018 |
会议地点 | Chengdu, China |
出版者 | SPIE |
摘要 | Image super-resolution methods based on forward-feed convolutional neural networks (CNN) reconstruct the image with more details and sharper texture. However, most of these methods do not consider the influence of high level semantic feature to improve image perceptual effect. In this paper, we propose a deep CNN architecture jointing low-high level feature for image super-resolution. Our method uses 17 weight layers to predict residual between the high resolution and low resolution image. And we joint the low level and high level image features to constraint the network parameters updating. Experimental results validate that our method reconstruct the high resolution images with clear edge and less warp. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. |
关键词 | Image reconstruction Neural networks Optical resolving power Semantics Textures Convolutional neural network High resolution image High-level semantic features Image super resolutions Low resolution images Low-high Perceptual effects Residual learning |
DOI | 10.1117/12.2524412 |
收录类别 | EI |
语种 | 英语 |
EI入藏号 | 20192106949092 |
EI主题词 | Image enhancement |
ISSN | 0277786X |
来源库 | Compendex |
分类代码 | 741.1 Light/Optics |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | https://ir.lut.edu.cn/handle/2XXMBERH/117950 |
专题 | 电气工程与信息工程学院 党委教师工作部(人事处、教师发展中心) |
作者单位 | 1.College of Electrical and Information Engineering, Lanzhou University of Technology, China; 2.National Demonstration Center for Experimental Electrical and Control Engineering Education, Lanzhou University of Technology, China; 3.KEY Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology, China |
第一作者单位 | 兰州理工大学 |
推荐引用方式 GB/T 7714 | Song, Xuhui,Liu, Weirong,Liu, Jie,et al. Deep CNN jointing low-high level feature for image super-resolution[C]:SPIE,2019. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论