[1]张健,黄德天,林炎明.采用稀疏表示和小波变换的超分辨率重建算法[J].华侨大学学报(自然科学版),2020,41(2):250-259.[doi:10.11830/ISSN.1000-5013.201908005]
　ZHANG Jian,HUANG Detian,LIN Yanming.Super-Resolution Reconstruction Algorithm Using Sparse Representation and Wavelet Transform[J].Journal of Huaqiao University(Natural Science),2020,41(2):250-259.[doi:10.11830/ISSN.1000-5013.201908005]
点击复制

采用稀疏表示和小波变换的超分辨率重建算法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第41卷
期数:
2020年第2期
页码:
250-259
栏目:
出版日期:
2020-03-20

文章信息/Info

Title:
Super-Resolution Reconstruction Algorithm Using Sparse Representation and Wavelet Transform
文章编号:
1000-5013(2020)02-0250-10
作者:
张健;  黄德天;  林炎明
华侨大学 工学院, 福建 泉州 362021
Author(s):
ZHANG Jian;  HUANG Detian;  LIN Yanming
College of Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
图像处理;  超分辨率;  稀疏表示;  局部线性嵌入;  小波变换
Keywords:
image processing;  super-resolution;  sparse representation;  locally linear embedding;  wavelet transform
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201908005
文献标志码:
A
摘要:
为了提高超分辨率重建图像的质量,提出一种基于稀疏表示和小波变换的超分辨率重建算法.首先,将小波变换的多尺度性、多方向性与稀疏表示的灵活性相结合,构建一种双稀疏编码(DSC)模型,提高稀疏系数的精度.然后,在双稀疏编码模型中引入局部线性嵌入正则化项(LLER),以更好地保留图像的结构;在重建过程中,对输入的低分辨率图像进行小波分解,得到3幅不同方向的高频子图,并采用提出的模型对其进行重建.最后,利用逆小波得到最终的高分辨率图像.实验结果表明:与多种主流的超分辨率算法相比,文中算法无论在主观视觉效果还是在峰值信噪比和结构相似度两个客观评价指标上,都取得了更好的效果.
Abstract:
To improve the quality of super-resolution reconstruction images, a super-resolution reconstruction algorithm based on sparse representation and wavelet transform is proposed. Firstly, combining the multi-scale and multi-directionality of wavelet transform with the flexibility of sparse representation, a dual sparse coding(DSC)model is constructed to improve the accuracy of sparse coefficients. Then, a locally linear embedding regularization(LLER)term is introduced to better preserve the structure of the image. In the process of image reconstruction, three high-frequency subbands with different directional characteristics, obtained by performing wavelet decomposition on the input LR image, are reconstructed by the proposed LLER-DSC model, respectively. Finally, the final high-resolution image is obtained by inverse wavelet transform. Experiments illustrate that the proposed approach outperforms several state-of-the-art super-resolution algorithms in terms of subjective visual quality and objective evaluation indices including peak signal-to-noise ratio and structural smilarity.

参考文献/References:

[1] YANG Jianchao,WRIGHT J,HUANG T,et al.Image super-resolution as sparse representation of raw image patches[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Anchorage:IEEE Press,2008:1-8.DOI:10.1109/CVPR.2008.4587647.
[2] ZEYDE R,ELAD M,PROTTER M.On single image scale-up using sparse-representations[C]//International Conference on Curves and Surfaces.Avignon:DBLP,2010:711-730.DOI:10.1007/978-3-642-27413-8_47.
[3] PATI Y C,REZAIIFAR R,KRISHNAPRASAD P S.Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition[C]//Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.Pacific Grove:IEEE Press,1993:40-44.DOI:10.1109/ACSSC.1993.342465.
[4] NAZZAL M,OZKARAMANLI H.Wavelet domain dictionary learning-based single image superresolution[J].Signal, Image and Video Processing,2015,9:1491-1501.DOI:10.1007/s11760-013-0602-7.
[5] CHANG Hong,YEUNG D,XIONG Yimin.Super-resolution through neighbor embedding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Washington D C:IEEE Press,2004:275-282.DOI:10.1109/CVPR.2004.1315043.
[6] DONG Weisheng,ZHANG Lei,SHI Guangming,et al.Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization[J].IEEE Transactions Image Processing,2011,20:1838-1857.DOI:10.1109/TIP.2011.2108306.
[7] EFROS A A,LEUNG T K.Texture synthesis by non-parametric sampling[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision.Kerkyra:IEEE Press,2002:1033-1038.DOI:10.1109/ICCV.1999.790383.
[8] CHEN Honggang,HE Xiaohai,TENG Qizhi,et al.Single image super resolution using local smoothness and nonlocal self-similarity priors[J].Signal Processing Image Communication,2016,43:68-81.DOI:10.1016/j.image.2016.01.007.
[9] DONG Weisheng,ZHANG Lei,LUKAC R,et al.Sparse representation based image interpolation with nonlocal autoregressive modeling[J].IEEE Transactions on Image Processing,2013,22(4):1382-1394.DOI:10.1109/TIP.2012.2231086.
[10] HUANG Detian,HUANG Weiqin,YUAN Zhenguo,et al.Image super-resolution algorithm based on an improved sparse autoencoder[J].Informtaion,2018,9(1):1-17.DOI:10.3390/info9010011.
[11] WU Xiaomin,FAN Jiulun,XU Jian,et al.Wavelet domain multidictionary learning for single image super-resolution[J].Journal of Electrical and Computer Engineering,2015,2015:1-12.DOI:10.1155/2015/526508.
[12] AYAS S,EKINCI M.Single image super resolution based on sparse representation using discrete wavelet transform[J].Multimedia Tools and Applications,2018,77:16685-16698.DOI:10.1007/s11042-017-5233-5.
[13] 王相海,赵晓阳,毕晓昀,等.小波域多角度轮廓模板变分模型的单幅图像超分辨率重建[J].电子学报,2018,46(9):2256-2262.DOI:10.3969/j.issn.0372-2112.2018.09.030.
[14] PLENGE E,POOT D H J,BERNSEN M,et al.Super-resolution methods in MRI: Can they improve the trade-off between resolution, signal-to-noise ratio, and acquisition time[J].Magnetic Resonance in Medicine,2012,68(6):1983-1993.DOI:10.1002/mrm.24187.
[15] FENG Shi,CHENG Jian,WANG Li,et al.LRTV: MR image super-resolution with low-rank and total variation regularizations[J].IEEE Transactions on Medical Imaging,2015,34(12):2459-2466.DOI:10.1109/TMI.2015.2437894.
[16] AHMADI K,SALARI E.Edge-preserving MRI super resolution using a high frequency regularization technique[C]//2015 IEEE Signal Processing in Medicine and Biology Symposium.Philadelphia:IEEE Press,2016:1-5.DOI:10.1109/SPMB.2015.7405429.
[17] ZHENG Hong,QU Xiaobo,BAI Zhengjian,et al.Multi-contrast brain magnetic resonance image super-resolution using the local weight similarity[J].BMC Medical Imaging,2017,17(1):1-13.DOI:10.1186/s12880-016-0176-2.
[18] LIANG Zifei,HE Xiaohai,TENG Qizhi,et al.3D MRI image super-resolution for brain combining rigid and large diffeomorphic registration[J].IET Image Processing,2017,11(12):1291-1301.DOI:10.1049/iet-ipr.2017.0517.
[19] ZHENG Hong,ZENG Kun,GUO Di,et al.Multi-contrast brain MRI image super-resolution with gradient-guided edge enhancement[J].IEEE Access,2018,6:57856-57867.DOI:10.1109/ACCESS.2018.2873484.
[20] ZHANG Yongqin,SHI Feng,CHENG Jian,et al.Longitudinally guided super-resolution of neonatal brain magnetic resonance images[J].IEEE Transactions on Cybernetics,2019,49(2):662-674.DOI:10.1109/TCYB.2017.27861 61.
[21] PHAM C H,AURELIEN D,RONAN F,et al.Brain MRI super-resolution using deep 3D convolutional networks[C]//14th IEEE International Symposium on Biomedical Imaging.Melbourne:IEEE Press,2017:197-200.DOI:10.1109/ISBI.2017.7950500.
[22] SHI Jun,LI Zheng,WANG Chaofeng,et al.MR image super-resolution via wide residual networks with fixed skip connection[J].IEEE Journal of Biomedical and Health Informatics,2019,23(3):1129-1140.DOI:10.1109/JBHI.2018.2843819.
[23] CAI Jianfeng,OSHER S,SHEN Zuowei.Split Bregman methods and frame based image restoration[J].Multiscale Modeling and Simulation,2009,8(2):337-369.DOI:10.1137/090753504.
[24] YANG Jianchao,WRIGHT J,HUANG T S,et al.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.DOI:10.1109/TIP.2010.2050625.
[25] TIMOFTE R,DE V,GOOL L V.Anchored neighborhood regression for fast example-based super-resolution[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision.Sydney:IEEE Press,2013:1920-1927.DOI:10.1109/ICCV.2013.241.
[26] TTIMOFTE R, DE V, GOOL L V.A+: Adjusted anchored neighborhood regression for fast super-resolution [C]//Asian Conference on Computer Vision.Cham:Springer,2015:111-126.DOI:10.1007/978-3-319-16817-3_8.
[27] BEVILACQUA M,ROUMY A,GUILLEMOT C,et al.Low-complexity single-image super-resolution based on nonnegative neighbor embedding[C]//BMVC 2012-Electronic Proceedings of the British Machine Vision Conference.Surrey:BMVA Press,2012:1-10.DOI:10.5244/C.26.135.
[28] MARTIN D,CHARLESS F,DORON T,et al.A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics[C]//Proceedings of the IEEE International Conference on Computer Vision.Vancouver:IEEE Press,2014:416-423.DOI:10.1109/ICCV.2001.937655.
[29] CLARK K,VENDT B,SIMTH K,et al.The cancer imaging archive(TCIA): Maintaining and operating a public information repository[J].Journal of Digital Imaging,2013,26(6):1045-1057.DOI:10.1007/s10278-013-9622-7.
[30] CHANG Hong,YEUNG D,XIONG Yimin.Super-resolution through neighbor embedding[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D C:IEEE Press,2004:275-282.DOI:10.1109/CVPR.2004.1315043.
[31] HUANG Detian,HUANG Weiqin,HUANG Hui,et al.Application of regularization technique in image super-resolution algorithm via sparse representation[J].Optoelectronics Letters,2017,13(6):439-443.DOI:10.1007/s118 01-017-7143-1.
[32] HUANG Detian,HUANG Weiqin,YUAN Zhenguo,et al.Image super-resolution algorithm based on an improved sparse autoencoder[J].Information,2018,9(1):1-17.DOI:10.3390/info9010011.
[33] HUANG Detian,HUANG Weiqin,GU Peiting,et al.Image super-resolution reconstruction based on regularization technique and guided filter[J].Infrared Physics and Technology,2017,83:103-113.DOI:10.1016/j.infrared.2017.04.006.
[34] 黄德天,黄炜钦,云海姣,等.正则化技术和低秩矩阵在稀疏表示超分辨率算法中的应用[J].计算机辅助设计与图形学学报,2018,30(5):868-877.DOI:10.3724/SP.J.1089.2018.16442.

相似文献/References:

[1]郑玉燕,何建农.软形态学的多结构加权均值形态滤波算法[J].华侨大学学报(自然科学版),2008,29(4):535.[doi:10.11830/ISSN.1000-5013.2008.04.0535]
　ZHENG Yu-yan,HE Jian-nong.Omnidirectional Weighted Combination Morphological Filter Based on Soft Morphology[J].Journal of Huaqiao University(Natural Science),2008,29(2):535.[doi:10.11830/ISSN.1000-5013.2008.04.0535]
[2]黄炜钦,黄德天,顾培婷,等.非局部相似和双边滤波的图像超分重建[J].华侨大学学报(自然科学版),2018,39(6):926.[doi:10.11830/ISSN.1000-5013.201702043]
　HUANG Weiqin,HUANG Detian,GU Peiting,et al.Image Super-Resolution Reconstruction Based on Non-Local Similarity and Bilateral Filter[J].Journal of Huaqiao University(Natural Science),2018,39(2):926.[doi:10.11830/ISSN.1000-5013.201702043]

备注/Memo

备注/Memo:
收稿日期: 2019-08-01
通信作者: 黄德天(1985-),男,副教授,博士,主要从事计算机视觉、机器学习和嵌入式系统的研究.E-mail:huangdetian@hqu.edu.cn.
基金项目: 国家自然科学基金青年科学基金资助项目(61901183); 福建省教育厅中青年教师教育科研项目(JAT170053); 福建省自然科学基金面上资助项目(2019J01083); 福建省泉州市高层次人才创新创业项目(2017G046)
更新日期/Last Update: 2020-03-20