改进的基于邻域嵌入的图像超分辨率重构

李强; 刘哲; 南炳炳; 顾淑音

doi:10.7510/jgjs.issn.1001-3806.2015.01.003

改进的基于邻域嵌入的图像超分辨率重构

1.
西北工业大学理学院, 西安 710129

作者简介: 李强(1989-),男,硕士研究生,现主要从事图像超分辨率重构的研究。.

通讯作者: 刘哲, liuzhe@nwpu.edu.cn ;

中图分类号:
TN911.73

Improved image super-resolution reconstruction based neighbor embedding

1.
School of Science, Northwestern Polytechnical University, Xi'an 710129, China

Corresponding author: LIU Zhe, liuzhe@nwpu.edu.cn ;

CLC number:
TN911.73

摘要: 为了提高传统的基于邻域嵌入的图像超分辨率重构算法的时间效率,采用了一种利用图像块方向信息进行邻域选择和训练集分类的新方法。该方法首先利用图像块方向的不同对训练集进行分类,然后在分类后的子训练集中选择与待重构图像块的方向相似的图像块作为邻域进行重构,并对重构结果进行迭代反投影全局后处理,进一步提高重构质量,最后对改进方法进行数值实验验证。结果表明,该方法不仅把超分辨率重构的时间效率提高了10倍以上,而且重构质量也得到了改善,具有较好的实际应用价值。
- 图像处理 /
- 超分辨率重构 /
- 邻域嵌入 /
- 方向 /
- 迭代反投影
Abstract: In order to improve the time-efficiency of traditional super-resolution reconstruction based on neighbor embedding, a new method was proposed using direction information of image patches to choose neighborhood and classify the training set. Firstly, the training set was classified through the differences of patches directions. Secondly, the neighborhood used to reconstruct was chosen in the sub-sets by selecting training patches with the similar direction, and then the iterative back-projection was applied during the reconstruction to further enhance the super-resolution image quality. Finally, numerical experiments were conducted to verify the new method. The results show that the proposed algorithm increases time-efficiency more than 10 times and super-resolution performance is improved. The new method has better practical value.
- image processing /
- super-resolution /
- neighbor embedding /
- direction /
- iterative back-projection

[1]	CHANG H, YEUNG D Y, XIONG Y. Super-resolution through neighbor embedding[C]// Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.New York,USA:IEEE,2004:1-8.
[2]	SEUNG H S, LEE D D. The manifold ways of perception[J]. Science, 2000, 290(5500): 2268-2269.
[3]	FAN W, YEUNG D Y. Image hallucination using neighbor embedding over visual primitive manifolds[C]// IEEE Conference on Computer Vision and Pattern Recognition, 2007.New York, USA:IEEE, 2007: 1-7.
[4]	CHAN T K, ZHANG J P, PU J, et al. Neighbor embedding based super-resolution algorithm through edge detection and feature selection[J]. Pattern Recognition Letters, 2009, 30(5): 494-502.
[5]	KOVESI P. Image features from phase congruency[J]. Journal of Computer Vision Research, 1999, 1(3): 1-26.
[6]	SU K, TIAN Q, XUE Q, et al. Neighborhood issue in single-frame image super-resolution[C]// IEEE International Conference on Multimedia and Expo, 2005.New York,USA:IEEE, 2005:4.
[7]	LIAO X X, HAN G Q, WO Y, et al. New feature selection for neighbor embedding based super-resolution[C]// 2011 International Conference on Multimedia Technology (ICMT). New York, USA:IEEE, 2011: 441-444.
[8]	CAO M M, GAN Z L, ZHU X C. Super-resolution algorithm through neighbor embedding with new feature selection and example training[C]// 2012 IEEE 11th International Conference on Signal Processing (ICSP). New York, USA:IEEE, 2012: 825-828.
[9]	YANG S Y, WANG M, CHEN Y G, et al. Single-image super-resolution reconstruction via learned geometric dictionaries and clustered sparse coding[J]. IEEE Transactions on Image Processing, 2012, 21(9): 4016-4028.
[10]	WAN B, MENG L, MING D, et al. Video image super-resolution restoration based on iterative back-projection algorithm[C]// IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, 2009.New York, USA:IEEE, 2009: 46-49.
[11]	EDELMAN A. Eigenvalues and condition numbers of random matrices[J]. SIAM Journal on Matrix Analysis and Applications, 1988, 9(4): 543-560.
[12]	BIGUN J, GRANLUND G H, WIKLUND J. Multidimensional orientation estimation with applications to texture analysis and optical flow[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(8): 775-790.
[13]	SAYOOD K. Statistical evaluation of image quality measures [J]. Journal of Electronic Imaging, 2002, 11(2):206-213.
[14]	WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004, 13(4): 600-612.

[1]	胡江涛 , 黄峰 , 张雏 , 刘秉琦 , 王元铂 . 超分辨率重构复眼成像技术的研究进展. 激光技术, 2015, 39(4): 492-496. doi: 10.7510/jgjs.issn.1001-3806.2015.04.014
[2]	房垚鑫 , 郭宝峰 , 马超 . 基于改进点扩散函数的遥感图像超分辨率重建. 激光技术, 2019, 43(5): 713-718. doi: 10.7510/jgjs.issn.1001-3806.2019.05.024
[3]	郭佑东 , 凌福日 , 姚建铨 . 基于梯度变换的太赫兹图像超分辨率重建. 激光技术, 2020, 44(3): 271-277. doi: 10.7510/jgjs.issn.1001-3806.2020.03.001
[4]	向志聪 , 张程潇 , 白玉磊 , 赖文敬 , 王钦若 , 周延周 . 一种高分辨率3维图像的自适应降噪算法. 激光技术, 2015, 39(5): 697-701. doi: 10.7510/jgjs.issn.1001-3806.2015.05.024
[5]	温承华 , 黄磊 , 张海涛 , 邱运涛 , 巩马理 . 大口径低分辨率干涉图的3维形貌还原方法. 激光技术, 2011, 35(2): 214-217. doi: 10.3969/j.issn.1001-3806.2011.02.020
[6]	李文龙 , 戈海龙 , 任远 , 成巍 . 图像处理技术在激光熔池温度检测的应用. 激光技术, 2018, 42(5): 599-604. doi: 10.7510/jgjs.issn.1001-3806.2018.05.004
[7]	张海庄 , 姚梅 , 雷萍 , 李鹏 , 曾庆平 . 远场激光光斑图像处理方法研究. 激光技术, 2013, 37(4): 460-463. doi: 10.7510/jgjs.issn.1001-3806.2013.04.010
[8]	汤敏 , 王惠南 . 激光扫描共聚焦显微镜图像的计算机处理. 激光技术, 2007, 31(5): 558-560.
[9]	张羽鹏 , 王开福 . LabVIEW和MATLAB在电子散斑干涉图像处理中的应用. 激光技术, 2009, 33(6): 582-585,589. doi: 10.3969/j.issn.1001-3806.2009.06.007
[10]	冯煦 , 张瑞瑛 , 周萍 , 李松 . 大功率半导体线激光图像处理方法研究. 激光技术, 2010, 34(5): 624-627. doi: 10.3969/j.issn.1001-3806.2010.O5.013
[11]	顾国庆 , 王开福 , 燕新九 . 基于同态滤波的电子散斑干涉图像处理. 激光技术, 2010, 34(6): 750-752,797. doi: 10.3969/j.issn.1001-3806.2010.06.009
[12]	苏平 , 牛燕雄 , 李大乾 , 牛海莎 , 李易难 , 张超 . 基于面阵CCD的激光告警系统的图像采集与处理. 激光技术, 2013, 37(3): 394-399. doi: 10.7510/jgjs.issn.1001-3806.2013.03.028
[13]	刘逸飞 , 苏亚 , 姚晓天 , 崔省伟 , 杨丽君 , 周聪聪 , 何松 . OCT无创血糖检测图像处理最优化方法研究. 激光技术, 2023, 47(2): 178-184. doi: 10.7510/jgjs.issn.1001-3806.2023.02.004
[14]	朱金辉 , 张宝华 , 谷宇 , 李建军 , 张明 . 基于双邻域对比度的红外小目标检测算法. 激光技术, 2021, 45(6): 794-798. doi: 10.7510/jgjs.issn.1001-3806.2021.06.020
[15]	张怡霄 , 杜惊雷 , 高福华 , 姚军 , 曾阳素 , 郭永康 . 分数域啁啾滤波及其在数字图像处理中的应用. 激光技术, 2003, 27(1): 78-80.
[16]	葛如海 , 符鸿玉 , 符凯 , 金桥 . 基于红外差分和积分投影的驾驶员眼睛定位. 激光技术, 2013, 37(6): 769-772. doi: 10.7510/jgjs.issn.1001-3806.2013.06.014
[17]	艾列富 , 程宏俊 , 冯学军 . 近似最近邻搜索中投影增强型残差量化方法. 激光技术, 2020, 44(6): 742-748. doi: 10.7510/jgjs.issn.1001-3806.2020.06.017
[18]	陈树越 , 刘金星 , 丁艺 . 基于小波变换的红外与X光图像融合方法研究. 激光技术, 2015, 39(5): 685-688. doi: 10.7510/jgjs.issn.1001-3806.2015.05.021
[19]	赵蓉 , 顾国华 , 杨蔚 . 基于偏振成像的可见光图像增强. 激光技术, 2016, 40(2): 227-231. doi: 10.7510/jgjs.issn.1001-3806.2016.02.016
[20]	虞文俊 , 顾国华 , 刘骋昊 . 红外偏振图像的仿真. 激光技术, 2014, 38(1): 76-78. doi: 10.7510/jgjs.issn.1001-3806.2014.01.016

点击查看大图

计量

文章访问数: 3266
HTML全文浏览量: 732
PDF下载量: 545
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

改进的基于邻域嵌入的图像超分辨率重构

作者简介: 李强(1989-),男,硕士研究生,现主要从事图像超分辨率重构的研究。.

通讯作者: 刘哲, liuzhe@nwpu.edu.cn ;

Improved image super-resolution reconstruction based neighbor embedding

Corresponding author: LIU Zhe, liuzhe@nwpu.edu.cn ;

计量

改进的基于邻域嵌入的图像超分辨率重构

通讯作者: 刘哲, liuzhe@nwpu.edu.cn;

作者简介: 李强(1989-),男,硕士研究生,现主要从事图像超分辨率重构的研究。

English Abstract

Improved image super-resolution reconstruction based neighbor embedding

Corresponding author: LIU Zhe, liuzhe@nwpu.edu.cn

全文HTML

目录

留言板

改进的基于邻域嵌入的图像超分辨率重构

作者简介: 李强(1989-),男,硕士研究生,现主要从事图像超分辨率重构的研究。.

通讯作者: 刘哲, liuzhe@nwpu.edu.cn ;

Improved image super-resolution reconstruction based neighbor embedding

Corresponding author: LIU Zhe, liuzhe@nwpu.edu.cn ;

计量

出版历程

改进的基于邻域嵌入的图像超分辨率重构

通讯作者: 刘哲, liuzhe@nwpu.edu.cn;

作者简介: 李强(1989-),男,硕士研究生,现主要从事图像超分辨率重构的研究。

English Abstract

Improved image super-resolution reconstruction based neighbor embedding

Corresponding author: LIU Zhe, liuzhe@nwpu.edu.cn

全文HTML

目录