A Super-resolution Algorithm through Neighbor Embedding

ZHAO Yang; LI Guo-lin; XIE Xiang; MAI Song-ping

Chinese

您当前的位置：

首页 >

文章列表页 >

A Super-resolution Algorithm through Neighbor Embedding

更新时间：2026-09-04

- A Super-resolution Algorithm through Neighbor Embedding
- Vol. 34, Issue 2, Pages: 10-14(2017)
- 作者机构：
  
  1. 清华大学微电子系,北京,100084
  2. 清华大学电子系,北京,100084
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2017
- 稿件说明：
移动端阅览
赵阳, 李国林, 谢翔, 麦宋平. 一种邻域嵌入超分辨率算法[J]. 微电子学与计算机, 2017, 34(2): 10-14.

ZHAO Yang, LI Guo-lin, XIE Xiang, et al. A Super-resolution Algorithm through Neighbor Embedding[J]. 2017, 34(2): 10-14.
赵阳, 李国林, 谢翔, 麦宋平. 一种邻域嵌入超分辨率算法[J]. 微电子学与计算机, 2017, 34(2): 10-14. DOI：

ZHAO Yang, LI Guo-lin, XIE Xiang, et al. A Super-resolution Algorithm through Neighbor Embedding[J]. 2017, 34(2): 10-14. DOI：

摘要

邻域嵌入算法是一种基于学习的超分辨率算法

但是存在图像特征计算复杂和分类搜索难度大的问题.本文提出了一种基于二阶梯度比例特征的邻域嵌入超分辨率算法

其图像特征简单

分类和搜索复杂度低

同时图像库存储量小

适合于硬件实现.实验结果表明

与传统超分辨率算法相比

本文算法重建的高分辨率图像具有更丰富的纹理和更锐利的边缘

具有更好的主客观质量.

Abstract

Super-resolution algorithm through neighbor embedding (NE) is based on learning. But the algorithm have the problems that the feature of image is complex and difficult to classify and search. A super-resolution algorithm through neighbor embedding by the feature based on the ratio of multiple directions of two-step grade is proposed. The computational complexity of the feature is low

and classifying and searching the feature is simple. Meanwhile the memory space of the algorithm is small. The super resolution algorithm is easy to implement on hardware. The experiment results shows that

high resolution images reconstructed by the algorithm have a great improvement than other state-of-the-art SR algorithms

also subjectively recover more high frequency detail and sharp edge. The recover images have better subjective and objective quality.

关键词

Keywords

references

Andrea G, Nicola A. Real-time artifact-free image upscaling[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2011, 20(10): 2760-2768. DOI: 2760

Park S C, Park M K, Kang M G. Super-resolution image reconstruction: a technicaloverview[J]. Signal Processing Magazine IEEE, 2003, 20(4): 21-36. DOI: 21

Pulak P, Nikhil Ranjan P, Bhabatosh C. A fuzzy-rule-based approach for single frame super resolution[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2014, 23(5): 2277-2290. DOI: 2277

Yan X, Shen J. Fast gradient-aware upsampling for cartoon video[C]//Image Analysis and Signal Processing (IASP), 2010 International Conference on IEEE. China, Zhejiang, 2010: 636-639.

Asuni N, Giachetti A. Accuracy improvements and artifacts removal in edge based image interpolation[C]//roc. 3rd Int. Conf. Comput. Vis. Theory Appl. (VISAPP) Portugal, Madeira, 2008: 58-65.

Yang C Y, Yang M H. Fast direct super-resolution by simple functions[C]//Computer Vision (ICCV), 2013 IEEE International Conference on. Australia, Sydney, IEEE, 2013: 561-568.

Yang J, Wright J, Huang T, et al. Image super-resolution as sparse representation of raw image patches. [C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. USA, Portland, IEEE, 2008: 1-8.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hardware Architecture for the Montgomery Multiplication Algorithm

Simulation on the DC characteristics of double heterojunction p-GaN HEMT with AlN/GaN hybrid buffer layer

Aerial small object detection algorithm based on improved RT-DETR

Steganography model guided by attention mechanism and improved dense convolution

A review of large model development: technological evolution from BERT to Deepseek

Related Author

WANG Di-li

BAI Guo-qiang

CHEN Hong-yi

Related Institution

Institute of Microelectronics, Tsinghua University

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰