基于二阶广义方向性全变分的图像超分辨率重建方法

doi:10.3969/j.issn.0372-2112.2017.11.008

电子学报 ›› 2017, Vol. 45 ›› Issue (11): 2625-2632.DOI: 10.3969/j.issn.0372-2112.2017.11.008

基于二阶广义方向性全变分的图像超分辨率重建方法

伍政华¹, 孙明健², 顾宗山¹, 范明意¹

1. 中国电子科技集团公司第三十八研究所, 安徽合肥 230088;
2. 哈尔滨工业大学(威海)控制科学与工程系, 山东威海 264209

收稿日期:2016-06-12 修回日期:2017-03-27 出版日期:2017-11-25
- 通讯作者:
- 孙明健
- 作者简介:
- 伍政华,男,1987年生于重庆市万州区,2015年获哈尔滨工业大学控制科学与工程系博士学位.现为中国电子科技集团公司第三十八研究所工程师,主要研究方向为稀疏优化算法、雷达信号处理、生物医学图像重建等.E-mail:zhenghuahitchina@gmail.com
- 基金资助:
- 国家自然科学基金 (No.61371045）; 山东省重点研发计划项目 (No.2016JMRH0217，No.2016GGX103032）

Second-Order Directional Total Generalized Variation Regularization for Image Super-resolution

WU Zheng-hua¹, SUN Ming-jian², GU Zong-shan¹, FAN Ming-yi¹

1. No. 38 Research Institute of China Electronics Technology Group Corporation, Hefei, Anhui 230088, China;
2. Control Science and Engineering, Harbin Institute of Technology at Weihai, Weihai, Shandong 264209, China

Received:2016-06-12 Revised:2017-03-27 Online:2017-11-25 Published:2017-11-25

摘要/Abstract

摘要： 超分辨率图像重建是增强那些低成本成像传感器系统图像分辨率的有效措施.得益于先验知识的学习，低分辨率图像可有效地被超分辨率增强.针对带有明显边缘结构的图像，现有方法没有有效利用高阶信息从而会出现一些光滑的图像细节.本文针对这种特殊的图像结构，研究一种基于二阶广义方向性全变分的重建方法来挖掘那些隐含的高阶可利用信息.二阶广义方向性全变分不仅可以作为先验知识，还能作为稀疏正则项抑制伪影和噪声.实验结果表明，本文方法可有效超分辨率重建结构边缘图像，并可获得高分辨率图像细节和纹理特征.

关键词: 超分辨率重建, 广义方向性全变分, 优化算法, 正则约束

Abstract: Super-resolution (SR) image reconstruction has developed into a powerful tool to enhance the image resolution for the systems with low-cost imaging sensors.A direct but efficient approach to super-resolve a low-resolution image is based on prior knowledge learning.But the existing methods do not consider matched high-level features in the images with structured edges,resulting in some smooth image artifacts.A second-order directional total generalized variation (DTGV) regularization based method is proposed to explore the underlying high-level information of the data in this paper.More specifically,second-order DTGV acts as not only an additional prior but also an effective constraint to reduce the image artifacts and remove the noise.Results from several texture images demonstrate that the proposed approach can generate high-resolution image details and tend to produce high-frequency textures.

Key words: super-resolution, directional total generalization variation, optimization algorithm, regularization constrains

中图分类号:

TN919.8

伍政华, 孙明健, 顾宗山, 范明意. 基于二阶广义方向性全变分的图像超分辨率重建方法[J]. 电子学报, 2017, 45(11): 2625-2632.

WU Zheng-hua, SUN Ming-jian, GU Zong-shan, FAN Ming-yi. Second-Order Directional Total Generalized Variation Regularization for Image Super-resolution[J]. Acta Electronica Sinica, 2017, 45(11): 2625-2632.

参考文献

[1] Yang J C,Wright J,Huang T S,Ma Y.Image super-resolution via sparse representation[J].IEEE Trans.Image Processing,2010,19(11):2861-2873.
[2] Shan Q,Li Z R,Jia J Y,Tang C K.Fast Image/Video Upsampling[J].ACM Trans.Graphics,2008,27(5):153.
[3] Granda C F,Candés E J.Super-resolution via transform-invariant group-sparse regularization[A].IEEE International Conference on Computer Vision Proceedings[C].Sydney,NSW,Australia:IEEE,2013,3336-3343.
[4] Dong W,Zhang L,Wu X.Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization[J].IEEE Trans.Image Processing,2011,20(7):1838-1857.
[5] Tang Y,Pan X,Yuan Y,Yan P,et al.Local semi supervised regression for single-image super-resolution[A].IEEE International Workshop on Multimedia Signal Processing Proceedings[C].Hangzhou,China:IEEE,2011,52-56.
[6] Hu J,Luo Y P.Single-image super resolution based on local regression and nonlocal self-similarity[J].Journal of Electronic Imaging,2014,23(3):033014.
[7] Reeth E V,Tham I W K,Tan C H,Poh C L.Super-resolution in magnetic resonance imaging:a review[J].Concepts in Magnetic Resonance Part A,2012,40(6):306-325.
[8] Joshi S H,Marquina A,Osher S J,Dinov I,et al.MRI resolution enhancement using total variation regularization[A].IEEE International Symposium on Biomedical Imaging:From Nano to Macro[C].Boston,MA,United States:IEEE,2009,161-164.
[9] Hou H S,Andrews H C.Cubic spline for image interpolation and digital filtering[J].IEEE Trans.Signal Processing,1978,26(6):508-517.
[10] Sun J,Xu Z,Shum H.Image super-resolution using gradient profile prior[A].IEEE Computer Society Conference on Computer Vision and Pattern Recognition Proceedings[C].Anchorage,AK,United States:IEEE,2008,1-8.
[11] 任福全,邱天爽,韩军,金声.基于二阶广义全变差的多帧图像超分辨率重建[J].电子学报,2015,43(7):1275-1280. Ren F Q,Qiu T S,Han J,Jin S.Multiframe image super resolution based on second order total generalized variation[J].Acta Electronica Sinica,2015,43(7):1275-1280.(in Chinese)
[12] Sun J,Zheng N N,Tao H,Shum H.Image hallucination with primal sketch priors[A].IEEE Computer Society Conference on Computer Vision and Pattern Recognition Proceedings[C].Madison,WI,United States:IEEE,2003.729-736.
[13] 潘宗序,禹晶,肖剑柏,孙卫东.基于自适应多字典学习的单幅图像超分辨率算法[J].电子学报,2015,43(2):209-216. Pan Z X,Yu J,Xiao C B,Sun W D.Single image super resolution based on adaptive multi-dictionary learning[J].Acta Electronica Sinica,2015,43(2):209-216.(in Chinese)
[14] Liu W,Lin D,Tang X.Hallucinating faces:Tensor patch super resolution and coupled residue compensation[A].IEEE Computer Society Conference on Computer Vision and Pattern Recognition Proceedings[C].San Diego,CA,United States:IEEE,2005,478-484.
[15] Zhang K,Gao X,Li X,Tao D.Partially supervised neighbor embedding for example learning-based image super-resolution[J].IEEE Journal of Selected Topics in Signal Processing,2011,5(2):230-239.
[16] Gao X,Zhang K,Li X,Tao D.Joint learning for single-image super-resolution via a coupled constraint[J].IEEE Trans.Image Processing,2012,21(2):469-480.
[17] Zhang K B,Gao X B,Tao D C,Li X L.Single image super-resolution with multiscale similarity learning[J].IEEE Trans.Neural Networks Learning System,2013,24(10):1648-1659.
[18] Glasner D,Bagon S,Irani M.Super-resolution from a single image[A].IEEE International Conference on Computer Vision[C].Kyoto,Japan:IEEE,2009.
[19] Kim K I,Kwon Y.Single-image super-resolution using sparse regression and natural image prior[J].IEEE Trans.Pattern Analysis Machine Intelligence,2010,32(6):1127-1133.
[20] 詹曙,方琪,杨福猛,常乐乐,闫婷.基于耦合特征空间下改进字典学习的图像超分辨率重建[J].电子学报,2016,44(5):1189-1195. Zhan S,Fang Q,Yang F M,Chang L L,et al.Image super-resolution reconstruction via improved dictionary learning based on coupled feature space[J].Acta Electronica Sinica,2016,44(5):1189-1195.(in Chinese)
[21] Farsiu S,Robinson M D,Elad M,Milanfar P.Fast and robust multi frame super resolution[J].IEEE Trans.Image Processing,2004,13(10):1327-1344.
[22] Hardie R C,Barnard K J,Armstrong E A.Joint map registration and high-resolution image estimation using a sequence of undersampled images[J].IEEE Trans.Image Processing,1997,6(12):1621-1633.
[23] Zhang K,Gao X,Tao D,Li X.Single image super-resolution with non-local means and steering kernel regression[J].IEEE Trans.Image Processing,2012,21(11):4544-4556.
[24] Marquina A,Osher S J.Image super-resolution by TV-regularization and Bergman iteration[J].Journal of Scientific Computing,2008,37(3):367-382.
[25] Tai Y W,Liu S,Brown M S,Lin S.Super resolution using edge prior and single image detail synthesis[A].IEEE Computer Society Conference on Computer Vision and Pattern Recognition Proceedings[C].San Francisco,CA,United States:IEEE,2010,2400-2407.
[26] Yang J,Wright J,Ma Y,Huang T.Image super-resolution as sparse representation of raw image patches[A].IEEE Computer Society Conference on Computer Vision and Pattern Recognition Proceedings[C].Anchorage,AK,United States:IEEE,2008.1-8.
[27] Bayram I,Kamasak M E.Directional total variation[J]. IEEE Signal Processing Letters,2012,19(12):781-784.
[28] Wang Q,Wu Z H,Sun M J,Liu T,et al.Single-image super-resolution using directional total variation regularization and alternating direction method of multiplier solver[J].Journal of Electronic Imaging,2015,24(2):023026.
[29] Guo W,Qin J,Yin W.A new detail-preserving regularity scheme[R].UCLA CAM Report,2013,13-04.
[30] He B,Liao L,Han D,Yang H.A new inexact alternating directions method for monotone variational inequalities[J].Mathematical Programming,2002,92(1):103-118.
[31] Bredies K,Kunisch K,Pock T.Total generalized variation[J].SIAM Journal on Imaging Sciences,2010,3(3):492-526.
[32] Knoll F,Bredies K,Pock T,Stollberger R.Second order total generalized variation (TGV) for MRI[J].Magnetic Resonance in Medicine,2011,65(2):480-491.
[33] Wu Z H,Lam F,Ma C,Liang Z P.Improved image reconstruction for subspace-based spectroscopic imaging using non-quadratic regularization[A].Annual International Conference of the IEEE Engineering in Medicine and Biology Society[C].Chicago,IL,United States:IEEE,2014,2432-2435.
[34] Wang Z,Bovik A C,Sheikh H R,Simoncelli E P.Image quality assessment:From error visibility to structural similarity[J].IEEE Trans.Image Processing,2004,13(4):600-612.

基于二阶广义方向性全变分的图像超分辨率重建方法

Second-Order Directional Total Generalized Variation Regularization for Image Super-resolution

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[2]	穆磊, 王鹏. 量子启发式优化算法的尺度动态调速机制[J]. 电子学报, 2022, 50(7): 1664-1673.
[3]	王相海, 赵晓阳, 王鑫莹, 赵克云, 宋传鸣. 非抽取小波边缘学习深度残差网络的单幅图像超分辨率重建[J]. 电子学报, 2022, 50(7): 1753-1765.
[4]	董明, 李敬, 索永录, 唐恩贤, 马宏伟, 陈渊, 张广明, 万翔. 基于改进果蝇优化算法正交匹配追踪的超声信号降噪方法[J]. 电子学报, 2022, 50(2): 493-501.
[5]	孟超, 周倩, 郭林, 王攀, 孙知信. 基于相关性传输模型的无线链路质量估计方法及路由优化算法[J]. 电子学报, 2022, 50(10): 2409-2424.
[6]	蒋伟进, 张婉清, 陈萍萍, 陈君鹏, 孙永霞, 刘权. 基于IWOA群智感知中数量敏感的任务分配方法[J]. 电子学报, 2022, 50(10): 2489-2502.
[7]	刘景森, 马义想, 李煜. 改进蝴蝶算法求解多维复杂函数优化问题[J]. 电子学报, 2021, 49(6): 1068-1076.
[8]	韩红桂, 阿音嘎, 张璐, 乔俊飞. 自适应分解式多目标粒子群优化算法[J]. 电子学报, 2020, 48(7): 1245-1254.
[9]	孙辉, 邓志诚, 赵嘉, 王晖, 谢海华. 混合均值中心反向学习粒子群优化算法[J]. 电子学报, 2019, 47(9): 1809-1818.
[10]	何杰光, 彭志平, 林伟豪, 崔得龙. 一种矩形邻域结构的教学优化算法[J]. 电子学报, 2019, 47(8): 1768-1775.
[11]	周岩, 王鹏, 辛罡, 李波, 王德志. MQHOA优化算法能级稳定过程及判据研究[J]. 电子学报, 2019, 47(6): 1337-1343.
[12]	刘月峰, 赵光权, 彭喜元. 多核相关向量机优化模型的锂电池剩余寿命预测方法[J]. 电子学报, 2019, 47(6): 1285-1292.
[13]	褚鼎立, 陈红, 王旭光. 基于自适应权重和模拟退火的鲸鱼优化算法[J]. 电子学报, 2019, 47(5): 992-999.
[14]	黄锦旺, 吕善翔, 李广明, 袁华强. 基于增殖系数的混沌信号提取算法[J]. 电子学报, 2019, 47(4): 855-861.
[15]	郑威迪, 李志刚, 贾涵中, 高闯. 基于改进型鲸鱼优化算法和最小二乘支持向量机的炼钢终点预测模型研究[J]. 电子学报, 2019, 47(3): 700-706.