[1]张 强,张爱梅,王华敏,等.基于自训练字典学习的单幅图像的超分辨率重建[J].红外技术,2015,37(九):736-739.[doi:10.11846/j.issn.1001_8891.201509006]
 ZHANG Qiang,ZHANG Ai-mei,WANG Hua-min,et al.Single Image Super-resolution Reconstruction Based on Self-learning Dictionary[J].Infrared Technology,2015,37(九):736-739.[doi:10.11846/j.issn.1001_8891.201509006]
点击复制

基于自训练字典学习的单幅图像的超分辨率重建
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
37卷
期数:
2015年第九期
页码:
736-739
栏目:
出版日期:
2015-09-20

文章信息/Info

Title:
Single Image Super-resolution Reconstruction Based on Self-learning Dictionary
文章编号:
1001-8891(2015)09-0736-04
作者:
?张 强张爱梅王华敏陈 鹏
?郑州大学机械工程学院,河南 郑州 450001
Author(s):
?ZHANG QiangZHANG Ai-meiWANG Hua-minCHEN Peng
?School of Mechanical Engineering,Zhengzhou University,Zhengzhou 450001,China
关键词:
超分辨率重建稀疏表示自训练字典学习K-SVD
Keywords:
super-resolution reconstructionsparse representationself-learning dictionaryK-SVD
分类号:
TP391
DOI:
10.11846/j.issn.1001_8891.201509006
文献标志码:
A
摘要:
?针对单幅低分辨率图像的超分辨率重建问题,提出了一种基于自训练字典学习的超分辨率重建算法。首先根据图像的退化模型,对输入的低分辨率图像进行降质处理,然后利用K-SVD方法训练字典,获得重建所需要的先验知识,最后根据先验知识重建高分辨率图像。仿真实验的结果表明,利用该方法获得的高分辨率图像在视觉效果和客观评价上均优于传统方法,同时算法的时间效率也有很大的提升。
Abstract:
?Based on the self-learning dictionary, a super-resolution reconstruction method of single image is proposed. First of all, according to the image degradation model, the low-resolution image input is processed with blurred and downsampled operations. Then the dictionary is trained with K-SVD method, and we obtain the priori knowledge for reconstruction. Finally, the high-resolution image is reconstructed based on the priori knowledge. The result of simulation experiment shows that the method is superior to conventional methods in the visual effects and objective evaluation, and the time efficiency of the algorithm is also significantly improved.

参考文献/References:

[1] 王自桦, 刘燕文. 基于稀疏表示的图像超分辨率重建[J]. 现代计算机, 2014(3): 35-39.
Wang Zi-hua, Liu Yan-wen. Image super-resolution reconstruction based on sparse representation[J]. Modern Computer, 2014(3): 35-39.
[2] 江静, 张雪松. 图像超分辨率重建算法综述[J]. 红外技术, 2012, 34(1): 24-30.
Jiang Jing, Zhang Xue-song. A review of super-resolution reconstruction algorithms [J]. Infrared Technology, 2012, 34(1): 24-30.
[3] 浦剑, 张军平, 黄华. 超分辨率算法研究综述[J]. 山东大学学报: 工学版, 2009, 39: 27-32.
Pu Jian, Zhang Jun-ping, Huang Hua. A survey of super resolution algorithms [J]. Journal of Shandong University: Engineering Science,2009, 39: 27-32.
[4] 郑梅兰, 章品正, 郭伟伟, 等. 基于学习的人脸图像超分辨率重建方法[J]. 计算机工程与应用, 2009, 45: 170-175.
Zheng Mei-lan, Zhang Pin-zheng, Guo Wei-wei, et al. Learning-based super-resolution reconstruction of face image [J]. Computer Engineering and Applications, 2009, 45: 170-175.
[5] Yang J C, Wright J, Huang T, et al. Image super -resolution as sparse representation of raw image patches[C]//IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA: IEEE Computer Society, 2008: 1-8.
[6] Yang J C, Wright J, Huang T, et al. Image Super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873.
[7] Elad M. Sparse and Redundant Representations[M]//The Super- resolution Algorithm. [s.l.]: Springer Press, 2010.
[8] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations[C]//Lecture Notes in Computer Science, Curves and Surfaces. Heidelberg: Springer Press, 2012, 6920: 711-730.
[9] Zhang J, Zhao C, Xiong R, et al. Image super -resolution via dual- dictionary learning and sparse representation[C]//IEEE International Symposium on Circuits and Systems, Seoul, Korea, May 20-23, 2012: 1688-1691.
[10] Kjersti Engan, Karl Skrettin, John H?kon Hus?y. Family of iterative LS-based dictionary learning algorithms, ILS-DLA, for sparse signal representation[J]. Digital Signal Processing, 2007, 17(1): 32-49.
[11] Mairal J, Bach F, Ponce J, et al. Online dictionary learning for sparse coding[C]//International Conference on Machine Learning, 2009: 689-696.
[12] Aharon M, Elad M, Bruckstein A. K-svd: an algorithm for designing over complete dictionaries for sparse representation[J]. IEEE Transactions on Image Processing, 2006, 54(11): 4311-4322.
[13] Glasner Daniel, Shai Bagon, Michal Irani. Super-resolution from a single image[C]//IEEE 12th International Conference on Computer Vision, 2009: 349-356 .

相似文献/References:

[1]应莉莉,安博文,薛冰玢. 亚像元图像超分辨率重建研究[J].红外技术,2013,35(05):274.
 YING Li-li,AN Bo-wen,XUE Bing-bin. Research on Super-resolution Reconstruction of Sub-pixel Images[J].Infrared Technology,2013,35(九):274.
[2]江静,张雪松.图像超分辨率重建算法综述[J].红外技术,2012,34(01):024.
 JIANG Jing,ZHANG Xue-song.A Review of Super-resolution Reconstruction Algorithms[J].Infrared Technology,2012,34(九):024.
[3]薛模根,刘存超,徐国明,等.基于多尺度字典的红外与微光图像融合[J].红外技术,2013,35(11):696.[doi:10.11846/j.issn.1001_8891.201311005]
 XUE Mo-gen,LIU Cun-chao,XU Guo-ming,et al.Infrared and Low Light Level Image Fusion Based on Multi-scale Dictionary[J].Infrared Technology,2013,35(九):696.[doi:10.11846/j.issn.1001_8891.201311005]
[4]孙君顶,赵慧慧.图像稀疏表示及其在图像处理中的应用[J].红外技术,2014,36(7):533.[doi:10.11846/j.issn.1001_8891.201407004]
 SUN Jun-ding,ZHAO Hui-hui.Sparse Representation and Applications in Image Processing[J].Infrared Technology,2014,36(九):533.[doi:10.11846/j.issn.1001_8891.201407004]
[5]王志社,杨风暴,彭智浩.基于NSST和稀疏表示的多源异类图像融合方法[J].红外技术,2015,37(三):210.[doi:10.11846/j.issn.1001_8891.201503008]
 WANG Zhi-she,YANG Feng-bao,PENG Zhi-hao.Multi-source Heterogeneous Image Fusion Based on NSST and Sparse Presentation[J].Infrared Technology,2015,37(九):210.[doi:10.11846/j.issn.1001_8891.201503008]
[6]周琳,杨娜.基于离线双字典学习算法的图像超分辨率重建研究[J].红外技术,2015,37(四):277.[doi:10.11846/j.issn.1001_8891.201504003]
 ZHOU Lin,YANG Na.Image Super Resolution Reconstruction Based on Offline Double Dictionary Learning Algorithm[J].Infrared Technology,2015,37(九):277.[doi:10.11846/j.issn.1001_8891.201504003]
[7]莫建文,曾儿孟,张 彤,等.基于几何字典学习和耦合约束的超分辨率重建[J].红外技术,2015,37(八):664.[doi:10.11846/j.issn.1001_8891.201508007]
 MO Jian-wen,ZENG Er-meng,ZHANG Tong,et al.Super-resolution Reconstruction Based on Geometric Dictionary Learning and Coupled Regularization[J].Infrared Technology,2015,37(九):664.[doi:10.11846/j.issn.1001_8891.201508007]
[8]梅家诚,王 瑞,叶汉民.结合稀疏表示与图像压缩融合的目标检测[J].红外技术,2016,38(3):218.[doi:10.11846/j.issn.1001_8891.201603008]
 MEI Jiacheng,WANG Rui,YE Hanmin.Compressive Fusion and Target Detection Based on Sparse Representation[J].Infrared Technology,2016,38(九):218.[doi:10.11846/j.issn.1001_8891.201603008]
[9]杨春伟,王仕成,廖守亿,等.基于协方差描述子稀疏表示的前视红外建筑物目标跟踪锁定[J].红外技术,2016,38(5):389.[doi:10.11846/j.issn.1001_8891.201605006]
 YANG Chunwei,WANG Shicheng,LIAO Shouyi,et al.Forward-looking-infrared Building Object Tracking Based on Sparse Representation of Covariance Descriptor [J].Infrared Technology,2016,38(九):389.[doi:10.11846/j.issn.1001_8891.201605006]
[10]林玉明,赵勋杰,沈琪琪.一种参数自适应正则化超分辨率图像重建算法[J].红外技术,2016,38(7):592.[doi:10.11846/j.issn.1001_8891.201607011]
 LIN Yuming,ZHAO Xunjie,SHEN Qiqi.A Regularization Super-resolution Image Reconstruction Algorithmwith Adaptive Parameters [J].Infrared Technology,2016,38(九):592.[doi:10.11846/j.issn.1001_8891.201607011]

备注/Memo

备注/Memo:
收稿日期:2015-06-10;修订日期:2015-07-30.
作者简介:张强(1991-),男,硕士研究生,主要从事图形图像处理的研究。E-mail:zqs359@163.com。
通讯作者:张爱梅(1964-),女,教授,硕士研究生导师,主要研究方向为图形图像处理与模式识别。
更新日期/Last Update: 2015-09-23