SIA OpenIR  > 光电信息技术研究室
一种基于卷积神经网络的图像超分辨率重建方法
Alternative TitleImage super-resolution reconstruction method based on convolutional neural network
赵怀慈; 刘明第; 郝明国; 王立勇; 刘鹏飞; 赵洋
Department光电信息技术研究室
Rights Holder中国科学院沈阳自动化研究所
Patent Agent21002 沈阳科苑专利商标代理有限公司
Country中国
Subtype发明授权
Status有权
Abstract本发明涉及一种基于卷积神经网络的图像超分辨率重建方法,通过数据集训练SRCNN卷积神经网络模型,得到浅层纹理特征信息;建立基于特征转移的八层端到端神经网络模型,将浅层纹理特征信息迁移至该神经网络模型的前四层,得到前四层的模型参数;得到该神经网络模型后四层的模型参数,增强学习到的特征;输入待重建的图像数据,预处理;得到Y通道的高分辨率图像;将Y通道的高分辨率图像、Cb通道图像和Cr通道图像进行融合,得到重建的图像。本发明提出的卷积神经网络模型取得了更佳的超分辨率结果,不管是在主观视觉上还是在客观评价指标上均有明显改善,图像清晰度和边缘锐度明显提高,收敛速度更快,在精细度方面具有更高的优势。
Other AbstractThe invention relates to an image super-resolution reconstruction method based on a convolutional neural network, and the method comprises the steps: training an SRCNN convolutional neural network model through a data set, and obtaining the shallow texture feature information; establishing an eight-layer end-to-end neural network model based on feature transfer, and migrating shallow texture feature information to the first four layers of the neural network model to obtain model parameters of the first four layers; obtaining model parameters of four rear layers of the neural network model, andenhancing learnt characteristics; inputting image data to be reconstructed, and preprocessing the image data; obtaining a high-resolution image of the Y channel; and fusing the high-resolution imageof the Y channel, the image of the Cb channel and the image of the Cr channel to obtain a reconstructed image. According to the convolutional neural network model provided by the invention, a better super-resolution result is obtained, the subjective vision and objective evaluation indexes are obviously improved, the image definition and the edge sharpness are obviously improved, the convergence speed is higher, and the method has higher advantages in the aspect of fineness.
PCT Attributes
Application Date2017-12-25
2019-07-02
Date Available2020-12-22
Application NumberCN201711417919.0
Open (Notice) NumberCN109961396B
Language中文
Contribution Rank1
Document Type专利
Identifierhttp://ir.sia.cn/handle/173321/28074
Collection光电信息技术研究室
Affiliation中国科学院沈阳自动化研究所
Recommended Citation
GB/T 7714
赵怀慈,刘明第,郝明国,等. 一种基于卷积神经网络的图像超分辨率重建方法[P]. 2019-07-02.
Files in This Item:
File Name/Size DocType Version Access License
CN201711417919.0授权.p(358KB)专利 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[赵怀慈]'s Articles
[刘明第]'s Articles
[郝明国]'s Articles
Baidu academic
Similar articles in Baidu academic
[赵怀慈]'s Articles
[刘明第]'s Articles
[郝明国]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[赵怀慈]'s Articles
[刘明第]'s Articles
[郝明国]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CN201711417919.0授权.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.