基于两级字典与分频带字典的超分辨率算法研究
|
摘要
超分辨率作为图像处理领域的一个重要分支，已经广泛应用于计算机视觉、医学图像处理、遥感图像处理、公共安全等领域，其主要解决的问题是从一幅或多幅低分辨率图像中重构高分辨率图像。由于稀疏表示在图像超分辨率中的广泛应用，本文构造两级字典及分频带字典处理单幅图像的超分辨率问题。
首先，本文构造两级字典，恢复尽可能多的细节信息；同时利用图像的非局部自相似性，将其与迭代反向投影算法相结合，进行图像的后处理，进一步提高重构图像的质量。
其次，除了利用两级字典恢复细节信息外，本文构造联合低频字典、中频字典以及高频字典的分频带字典，利用图像低频、中频、高频三者之间的预测关系，重新预测图像的中高频部分信息；同时利用非局部迭代反向投影算法进行图像的后处理。实验结果表明了算法的有效性。
再次，传统基于学习的超分辨率算法存在图像的放大倍数由高低分辨率字典对决定的问题，为了克服以上不足，本文构造分频带字典，利用图像低中高三部分之间的预测关系重构图像。在假定插值图像与原始图像的低频信息基本相同的条件下，将中高频部分的稀疏表示作为限制约束条件，基于图像低中高频图像块稀疏表示相似性重构中高频图像块。同时将BM3D滤波与迭代反向投影算法相结合，进行图像的非局部处理。实验结果表明该算法在重构质量与速度方面达到一个更好的平衡。
最后，构造多尺度分频带字典进行超分辨率重构，利用自适应的加权平均算法将不同尺度字典重构的图像进行融合得到高分辨率图像。实验结果表明提出的算法具有更高的重构质量及速度。
As an active field in image processing, super-resolution has been widely appliedinto computer vision, medical imaging, image remote sensing and security detection,which aims to reconstruct high resolution image from one or multiple low resolutionimage(s). With the wide application of sparse representation in image super-resolution,two-stage and multi-frequency-band dictionaries are proposed for single imagesuper-resolution problem in this paper.
Firstly, two-stage dictionaries are explored into recovering as much detailinformation as possible. Considering that there are many repetitive structures in naturalimage, nonlocal self-similarity information is combined properly with iterativeback-projection to post-process the image, i.e nonlocal iterative back-projection tofurther improve the reconstruction quality.
Secondly, in addition to exploiting two-stage dictionaries to recover detailinformation, multi-frequency-band dictionaries consisting of low frequency (LF)dictionaries, middle frequency (MF) dictionaries and high frequency (HF) dictionariesare jointly learned to predict middle and high frequency information from low frequencycomponent by the prediction relation between LF\MF\HF components. Simultaneously,nonlocal iterative back-projection is applied into post-processing the image.Experimental results demonstrate the effectiveness of the proposed algorithm.
Thirdly, the magnification factor of the traditional super-resolution algorithms onsparse representation is determined by high resolution\low resolution dictionary pairs. Toovercome the drawback, multi-frequency-band dictionaries are proposed forsuper-resolution problem only exploiting the prediction relation between LF\MF\HFcomponents to reconstruct the image. Considering the LF components consistency of theinterpolator image and original image, with the sparse representation of MF\HF patchesas the regularization condition, MF\HF patches are reconstructed exploiting thecoefficients similarity of LF\MF\HF patches. Furthermore, block matching and3D(BM3D) filtering is incorporated into iterative back-projection to postprocess the image nonlocally. Compared with other popular learning-based algorithms, the proposedmethod keeps better balance in reconstruction quality and speed.
Finally, multiscale multiple-frequency-band dictionaries are constructed for SRproblem. The images reconstructed by dictionaries are fused by adaptive weightedaverage algorithm. Compared with other state-of-the-art algorithms, the proposed methodhas higher reconstruction quality and speed.
首先，本文构造两级字典，恢复尽可能多的细节信息；同时利用图像的非局部自相似性，将其与迭代反向投影算法相结合，进行图像的后处理，进一步提高重构图像的质量。
其次，除了利用两级字典恢复细节信息外，本文构造联合低频字典、中频字典以及高频字典的分频带字典，利用图像低频、中频、高频三者之间的预测关系，重新预测图像的中高频部分信息；同时利用非局部迭代反向投影算法进行图像的后处理。实验结果表明了算法的有效性。
再次，传统基于学习的超分辨率算法存在图像的放大倍数由高低分辨率字典对决定的问题，为了克服以上不足，本文构造分频带字典，利用图像低中高三部分之间的预测关系重构图像。在假定插值图像与原始图像的低频信息基本相同的条件下，将中高频部分的稀疏表示作为限制约束条件，基于图像低中高频图像块稀疏表示相似性重构中高频图像块。同时将BM3D滤波与迭代反向投影算法相结合，进行图像的非局部处理。实验结果表明该算法在重构质量与速度方面达到一个更好的平衡。
最后，构造多尺度分频带字典进行超分辨率重构，利用自适应的加权平均算法将不同尺度字典重构的图像进行融合得到高分辨率图像。实验结果表明提出的算法具有更高的重构质量及速度。
As an active field in image processing, super-resolution has been widely appliedinto computer vision, medical imaging, image remote sensing and security detection,which aims to reconstruct high resolution image from one or multiple low resolutionimage(s). With the wide application of sparse representation in image super-resolution,two-stage and multi-frequency-band dictionaries are proposed for single imagesuper-resolution problem in this paper.
Firstly, two-stage dictionaries are explored into recovering as much detailinformation as possible. Considering that there are many repetitive structures in naturalimage, nonlocal self-similarity information is combined properly with iterativeback-projection to post-process the image, i.e nonlocal iterative back-projection tofurther improve the reconstruction quality.
Secondly, in addition to exploiting two-stage dictionaries to recover detailinformation, multi-frequency-band dictionaries consisting of low frequency (LF)dictionaries, middle frequency (MF) dictionaries and high frequency (HF) dictionariesare jointly learned to predict middle and high frequency information from low frequencycomponent by the prediction relation between LF\MF\HF components. Simultaneously,nonlocal iterative back-projection is applied into post-processing the image.Experimental results demonstrate the effectiveness of the proposed algorithm.
Thirdly, the magnification factor of the traditional super-resolution algorithms onsparse representation is determined by high resolution\low resolution dictionary pairs. Toovercome the drawback, multi-frequency-band dictionaries are proposed forsuper-resolution problem only exploiting the prediction relation between LF\MF\HFcomponents to reconstruct the image. Considering the LF components consistency of theinterpolator image and original image, with the sparse representation of MF\HF patchesas the regularization condition, MF\HF patches are reconstructed exploiting thecoefficients similarity of LF\MF\HF patches. Furthermore, block matching and3D(BM3D) filtering is incorporated into iterative back-projection to postprocess the image nonlocally. Compared with other popular learning-based algorithms, the proposedmethod keeps better balance in reconstruction quality and speed.
Finally, multiscale multiple-frequency-band dictionaries are constructed for SRproblem. The images reconstructed by dictionaries are fused by adaptive weightedaverage algorithm. Compared with other state-of-the-art algorithms, the proposed methodhas higher reconstruction quality and speed.
引文
[1] Milanfar P. Super-Resolution Imaging[M]. Boca Raton, FL, USA: CRC Press,2011.
[2]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(1):27-32.
[3] Unser M, Aldroubi A, Eden M. Fast B-Spline Transforms for Continuous Image Representationaand Interpolation[J]. Transactions on Pattern Analysis and Machine Intelligence,1991,13(3):277-285.
[4] Michael T, Eldar Y C. A Hybrid Vector Wiener Filter Approach to TranslationalSuper-Resolution[R]. IEEE Transaction on Image Processing,2010:1-18.
[5] Liang S F, Chen H M, Liu Y C. Image Enlargement by Applying Coordinate Rotation andKernel Stretch to Interpolation Kernels[J]. Eurasip Journal on Advances in Signal Processing,2010,2010:1-18.
[6] Zhang X F, Ma S W, Zhang Y B, et al. Nonlocal Edge-Directed Interpolation[C]//Proceedings ofIEEE10th Pacific-Rim Conference on Multimedia. Bangkok, Thailand: IEEE,2009:1197-1207.
[7] Shi G M, Dong W S, Wu X L, et al. Context-based Adaptive Image Resolution Upconversion[J].Journal of Electronic Imaging,2010,19(1):1-9.
[8] Chen H C, Wang W J. Two Stage Interpolation Algorithm Based on Fuzzy Logics and EdgesFeatures for Image Zooming[J]. Eurasip Journal on Advances in Signal Processing,2009:121-128.
[9] Irani M, Peleg S. Motion Analysis for Image Enhancement: Resolution, Occlusion andTransparency[J]. Journal of Visual Communications and Image Representation,1993,12(4):324-335.
[10] Dai S Y, Han M, Wu Y, et al. Bilateral Back-projection for Single ImageSuper-Resolution[C]//Proceedings of IEEE International Conference on Multimedia and Expo.Beijing, China: IEEE,2007:1039-1042.
[11] Dong W S, Zhang L, Shi G M, et al. Nonlocal Back-projection for Adaptive ImageEnlargement[C]//Proceedings of IEEE International Conference on Image Processing. Cairo.Egypt: IEEE,2009:349-352.
[12] Sun J, Xu Z B, Shum H Y. Image Super-Resolution Using Gradient Projection Prior[J]. IEEETransactions on Image Processing,2011,6,20(6):1529-1542.
[13] Tai Y W, Liu S C, Brown M S, et al. Super Resolution Using Edge Prior and Single Image DetailSynthesis[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). San Francisco, America: IEEE,2010,1:2400-2407.
[14] Schultzr R R, Stevensonr R L. Improved Definition Video Frame Enhancement[C]//Proceedingsof the IEEE International Conference on Acoustics. Speech and Signal processing, Detroit, MI,USA: IEEE,1995:2169-2172.
[15] Schultzr R R, Stevensonr R L. Video Resolution Enhancement[C]//Proceedings of the Society ofPhoto-Optical Instrumentation Engineers. San Jose California, USA: SPIE,1995:23-24.
[16] Schultzr R R, Stevensonr R L. Montion-compensated Scan Conversion of Interlaced VideoSequences[C]//Proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE).San Jose California, USA: SPIE,1996:107-118.
[17] Schultzr R R, Stevensonr R L. Extraction of High-resolution Frames from Video Sequences[J].IEEE Transactions on Image Processing,1996,5(6):996-1011.
[18] Tian J, Ma K K. Stochastic Super-Resolution Image Reconstruction[J]. Journal of VisualCommunication and Image Representation,2010,21(3):232-244.
[19] Zhang L P, Zhang H Y, Shen H F. A Super Resolution Reconstruction Algorithm for SurveillanceImages[J]. Signal Processing,2009,90(3):848-859.
[20] Stark H, Oskoui P. High-Resolution Image Recovery from Image-Plane Arrays Using ConvexProjections[J]. Journal of the Optical Society of America,1989,6(11):1715-1726.
[21] Elad M, Feuer A. Restoration of a Single Superresolution Image from Several Bluerred, Noisy,and Undersampled Measured Images[J]. IEEE Transactions on Image Processing,1997,6(12):1646-1658.
[22] Elad M, Feuer A. Superrsolution Reconstruction of an Image[C]//Proceedings of the19th IEEEConference in Israel. Jerusalem, Israel: IEEE,1996:391-394.
[23] Freeman W T, Pasztor E C, Jones T R, et al. Learning Low-Level Vision[J]. International Journalof Computer Vision,2000,40(1):25-47.
[24] Freeman W T, Pasztor E C, Jones T R. Example-based Super-Resolution[J]. IEEE ComputerGraphics and Applications,2002,22(2):56-65.
[25] Sun J, Zheng N N, Tao H, et al. Image Hallucination with Primal Sketch Priors[C]//Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition. Monona TerraceConvention Center Madison. Wisconsin, USA: IEEE,2003:729-736.
[26] Chang H., Yeung D, Xiong Y M. Super-Resolution through NeighborEmbedding[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington. D. C, USA: IEEE,2004,2:275-282.
[27] Gupta M D. Hashing Image Patches for Zooming. Computer Vision and Pattern Recognition,2010,4.
[28] Yang J C, Wright J, Ma Y, et al. Image Super-Resolution as Sparse Sepresentation of Raw ImagePatches[C]//Proceedings of IEEE Computer Society Conference On Computer Vision and PatternRecognition. Anchorage, USA: IEEE,2008:1-8.
[29] Yang J C, Wright J, Ma Y. Image Super-Resolution via Sparse Representation[J]. IEEETransactions on Image Processing,2010,19(11):2861-2873.
[30] Zeyde R, Elad M, Protter M. On Single Image Scale-Up usingSparse-Representations[C]//Proceedings of the7th International Conference on Curves andSurfaces. Avignon, France: Springer,2010:1-20.
[31] Baker S, Kanade T. Limits on Super-Resolution and How to Break Them[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,2002,24(9):1167-1183.
[32] Sun J, Zhu J J, Tappen M F. Context-Constrained Hallucination for ImageSuperresolution[C]//Proceedings of IEEE Computer Society Conference on Computer Vision andPattern Recognition (CVPR). San Francisco, CA, USA: IEEE,2010:231-238.
[33] HaCohen Y, Fattal R, Lischinski D. Image Upsampling via TextureHallucination[C]//Proceedings of IEEE International Conference on Computational Photography.Cambridge MA, USA: IEEE,2010:1-8.
[34] Xiong Z W, Sun X Y, Wu F. Image Hallucination with Feature Enhancement[C]//Proceedings ofIEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Hefei,China: IEEE,2009:2074-2081.
[35] Adler A, Hei O Y, Elad M. Ashrinkage Learning Approach for Single Image Super Resolutionwith Overcomplete Representation[C]//Proceedings of the11th European Conference onComputer Vision. Heraklion. Crete, Greece: Springer,2010:622-635.
[36] Yu G S, Mallat S. Sparese Super Resolution with Space Matching Pursuits[C]//Signal Processingwith Adaptive Sparse Structured Representations. Saint-Malo, France,2009.
[37] Mallat S, Yu G S. Super Resolution with Sparse Mixing Estimators[J]. IEEE Transactions onImage Processing,2010,19(11):2889-2900.
[38] Yu G S, Sapiro G, Mallat S. Solving Inverse Problems with Piecewise Linear Estimator: fromGaussian Mixture Models to Structures Sparsity[J]. IEEE Transaction on Image Processing,2011:1-30.
[39]孙玉宝,韦志辉,肖亮.多形态稀疏性正则化的图像超分辨率算法[J].电子学报,2010,38(12):2898-2903.
[40]孙玉宝,费选,韦志辉,等.基于前向后向算子分裂的稀疏性正则化图像超分辨率算法[J].自动化学报,2010,36(9):1232-1238.
[41]李民,李世华,李小文,等.非局部联合稀疏近似的超分辨率算法[J].电子与信息学报,2011,33(6):1407-1412.
[42]浦剑,张军平.基于词典学习和稀疏表示的超分辨率方法[J].模式识别与人工智能,2010,23(3):335-340.
[43] Lee H, Battle A, Raina R, et al. Efficient Sparse Coding Algorithms[J]. In Advances in NeuralInformation Processing Systems,2007,19(2):801-808.
[44] Mairal J, Bach F, Ponce J. Online Dictionary Learning for Sparse Coding[C]//Proceedings of the26th International Conference on Machine Learning (ICML). Montreal, Canada: Omnipress,2009:689-696.
[45] Mairal J, Bach F, Ponce J, et al. Online Learning for Matrix Factorization and Sparse Coding[J].Journal of Machine Learning Research,2010,11:19-60.
[46] Engan K, Aase S O, Husoy J H. Multi-frame Compression: Theory and Design[J]. EURASIPSignal Process,2000,80(10):2121-2140.
[47] Aharon M, Elad M, Bruckstein A M. The K-SVD: An Algorithm for Designing of OvercompleteDictionaries for Sparse Representation[J]. IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[48] Buades A, Coll B, Morel J M. A Non-Local Algorithm for Image Denoising[C]//Proceedings ofthe2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition. SanDiego, USA: IEEE Computer Society,2005:60-65.
[49] Protter M, Elad M, Takeda H, et al, Generalizing the Nonlocal-Means to Super-ResolutionReconstruction[J]. IEEE Transactions on Image Processing,2009,18(1):36-51.
[50] Dong W S, Zhang L, Shi G M, et al. Image Deblurring and Super-resolution by Adaptive SparseDomain Selection and Adaptive Regularization[J]. IEEE Transactions on Image Processing,2011,20(7):1838-1857.
[51] Dabov K, Foi A, Katkovnik V, et al. Image Denosing by Sparse3D Transform-DomainCollaborative Filtering[J]. IEEE Transaction on Image Processing,2007,16(8):2080-2095.
[52] Danielyan A, Foi A, Katkovnik V, et al. Image Upsampling via Spatially AdaptiveBlock-Matching Filtering[C]//Proceedings of the16th European Signal Processing Conference.Lausanne, Switzerland: Springer,2008:1-5.
[53] Elad M. Sparse and Redundant Representations: From Theory to Applications in Signal andImage Processing[M]. New York, USA: Springer,2010:227-246.
[54] Mallat S, Zhang Z F. Matching Pursuits with Time-Frequency Dictionaries[J]. IEEE Transactionson Signal Processing,1993,41(12):3397-3415.
[55] Needell D, Vershynin R. Signal Recovery From Incomplete and Inaccurate Measurements viaRegularized Orthogonal Matching Pursuit[J]. IEEE Journal of Selected Topics in SignalProcessing,2010,4(2):310-316.
[56] Tibshirani R. Regression Shrinkage and Selection via the Lasso[J]. Journal of the RoyalStatistical Society Series B,1996,58(1):267-288.
[57] Efron B, Hastie T, Johnstone I, et al. Least Angle Regression[J]. The Annals of Statistics,2004,32(2):407-451.
[58] Starck J L, Fadili J, Murtagh F. The Undecimated Wavelet Decomposition and ItsReconstruction[J]. IEEE Transactions on Image Processing,2007,16(2):297-309.
[59] Jolliffe I. Principal Component Analysis[M]. New York: Springer-Verlag,1986.
[2]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(1):27-32.
[3] Unser M, Aldroubi A, Eden M. Fast B-Spline Transforms for Continuous Image Representationaand Interpolation[J]. Transactions on Pattern Analysis and Machine Intelligence,1991,13(3):277-285.
[4] Michael T, Eldar Y C. A Hybrid Vector Wiener Filter Approach to TranslationalSuper-Resolution[R]. IEEE Transaction on Image Processing,2010:1-18.
[5] Liang S F, Chen H M, Liu Y C. Image Enlargement by Applying Coordinate Rotation andKernel Stretch to Interpolation Kernels[J]. Eurasip Journal on Advances in Signal Processing,2010,2010:1-18.
[6] Zhang X F, Ma S W, Zhang Y B, et al. Nonlocal Edge-Directed Interpolation[C]//Proceedings ofIEEE10th Pacific-Rim Conference on Multimedia. Bangkok, Thailand: IEEE,2009:1197-1207.
[7] Shi G M, Dong W S, Wu X L, et al. Context-based Adaptive Image Resolution Upconversion[J].Journal of Electronic Imaging,2010,19(1):1-9.
[8] Chen H C, Wang W J. Two Stage Interpolation Algorithm Based on Fuzzy Logics and EdgesFeatures for Image Zooming[J]. Eurasip Journal on Advances in Signal Processing,2009:121-128.
[9] Irani M, Peleg S. Motion Analysis for Image Enhancement: Resolution, Occlusion andTransparency[J]. Journal of Visual Communications and Image Representation,1993,12(4):324-335.
[10] Dai S Y, Han M, Wu Y, et al. Bilateral Back-projection for Single ImageSuper-Resolution[C]//Proceedings of IEEE International Conference on Multimedia and Expo.Beijing, China: IEEE,2007:1039-1042.
[11] Dong W S, Zhang L, Shi G M, et al. Nonlocal Back-projection for Adaptive ImageEnlargement[C]//Proceedings of IEEE International Conference on Image Processing. Cairo.Egypt: IEEE,2009:349-352.
[12] Sun J, Xu Z B, Shum H Y. Image Super-Resolution Using Gradient Projection Prior[J]. IEEETransactions on Image Processing,2011,6,20(6):1529-1542.
[13] Tai Y W, Liu S C, Brown M S, et al. Super Resolution Using Edge Prior and Single Image DetailSynthesis[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). San Francisco, America: IEEE,2010,1:2400-2407.
[14] Schultzr R R, Stevensonr R L. Improved Definition Video Frame Enhancement[C]//Proceedingsof the IEEE International Conference on Acoustics. Speech and Signal processing, Detroit, MI,USA: IEEE,1995:2169-2172.
[15] Schultzr R R, Stevensonr R L. Video Resolution Enhancement[C]//Proceedings of the Society ofPhoto-Optical Instrumentation Engineers. San Jose California, USA: SPIE,1995:23-24.
[16] Schultzr R R, Stevensonr R L. Montion-compensated Scan Conversion of Interlaced VideoSequences[C]//Proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE).San Jose California, USA: SPIE,1996:107-118.
[17] Schultzr R R, Stevensonr R L. Extraction of High-resolution Frames from Video Sequences[J].IEEE Transactions on Image Processing,1996,5(6):996-1011.
[18] Tian J, Ma K K. Stochastic Super-Resolution Image Reconstruction[J]. Journal of VisualCommunication and Image Representation,2010,21(3):232-244.
[19] Zhang L P, Zhang H Y, Shen H F. A Super Resolution Reconstruction Algorithm for SurveillanceImages[J]. Signal Processing,2009,90(3):848-859.
[20] Stark H, Oskoui P. High-Resolution Image Recovery from Image-Plane Arrays Using ConvexProjections[J]. Journal of the Optical Society of America,1989,6(11):1715-1726.
[21] Elad M, Feuer A. Restoration of a Single Superresolution Image from Several Bluerred, Noisy,and Undersampled Measured Images[J]. IEEE Transactions on Image Processing,1997,6(12):1646-1658.
[22] Elad M, Feuer A. Superrsolution Reconstruction of an Image[C]//Proceedings of the19th IEEEConference in Israel. Jerusalem, Israel: IEEE,1996:391-394.
[23] Freeman W T, Pasztor E C, Jones T R, et al. Learning Low-Level Vision[J]. International Journalof Computer Vision,2000,40(1):25-47.
[24] Freeman W T, Pasztor E C, Jones T R. Example-based Super-Resolution[J]. IEEE ComputerGraphics and Applications,2002,22(2):56-65.
[25] Sun J, Zheng N N, Tao H, et al. Image Hallucination with Primal Sketch Priors[C]//Proceedingsof the IEEE Conference on Computer Vision and Pattern Recognition. Monona TerraceConvention Center Madison. Wisconsin, USA: IEEE,2003:729-736.
[26] Chang H., Yeung D, Xiong Y M. Super-Resolution through NeighborEmbedding[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington. D. C, USA: IEEE,2004,2:275-282.
[27] Gupta M D. Hashing Image Patches for Zooming. Computer Vision and Pattern Recognition,2010,4.
[28] Yang J C, Wright J, Ma Y, et al. Image Super-Resolution as Sparse Sepresentation of Raw ImagePatches[C]//Proceedings of IEEE Computer Society Conference On Computer Vision and PatternRecognition. Anchorage, USA: IEEE,2008:1-8.
[29] Yang J C, Wright J, Ma Y. Image Super-Resolution via Sparse Representation[J]. IEEETransactions on Image Processing,2010,19(11):2861-2873.
[30] Zeyde R, Elad M, Protter M. On Single Image Scale-Up usingSparse-Representations[C]//Proceedings of the7th International Conference on Curves andSurfaces. Avignon, France: Springer,2010:1-20.
[31] Baker S, Kanade T. Limits on Super-Resolution and How to Break Them[J]. IEEE Transactionson Pattern Analysis and Machine Intelligence,2002,24(9):1167-1183.
[32] Sun J, Zhu J J, Tappen M F. Context-Constrained Hallucination for ImageSuperresolution[C]//Proceedings of IEEE Computer Society Conference on Computer Vision andPattern Recognition (CVPR). San Francisco, CA, USA: IEEE,2010:231-238.
[33] HaCohen Y, Fattal R, Lischinski D. Image Upsampling via TextureHallucination[C]//Proceedings of IEEE International Conference on Computational Photography.Cambridge MA, USA: IEEE,2010:1-8.
[34] Xiong Z W, Sun X Y, Wu F. Image Hallucination with Feature Enhancement[C]//Proceedings ofIEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Hefei,China: IEEE,2009:2074-2081.
[35] Adler A, Hei O Y, Elad M. Ashrinkage Learning Approach for Single Image Super Resolutionwith Overcomplete Representation[C]//Proceedings of the11th European Conference onComputer Vision. Heraklion. Crete, Greece: Springer,2010:622-635.
[36] Yu G S, Mallat S. Sparese Super Resolution with Space Matching Pursuits[C]//Signal Processingwith Adaptive Sparse Structured Representations. Saint-Malo, France,2009.
[37] Mallat S, Yu G S. Super Resolution with Sparse Mixing Estimators[J]. IEEE Transactions onImage Processing,2010,19(11):2889-2900.
[38] Yu G S, Sapiro G, Mallat S. Solving Inverse Problems with Piecewise Linear Estimator: fromGaussian Mixture Models to Structures Sparsity[J]. IEEE Transaction on Image Processing,2011:1-30.
[39]孙玉宝,韦志辉,肖亮.多形态稀疏性正则化的图像超分辨率算法[J].电子学报,2010,38(12):2898-2903.
[40]孙玉宝,费选,韦志辉,等.基于前向后向算子分裂的稀疏性正则化图像超分辨率算法[J].自动化学报,2010,36(9):1232-1238.
[41]李民,李世华,李小文,等.非局部联合稀疏近似的超分辨率算法[J].电子与信息学报,2011,33(6):1407-1412.
[42]浦剑,张军平.基于词典学习和稀疏表示的超分辨率方法[J].模式识别与人工智能,2010,23(3):335-340.
[43] Lee H, Battle A, Raina R, et al. Efficient Sparse Coding Algorithms[J]. In Advances in NeuralInformation Processing Systems,2007,19(2):801-808.
[44] Mairal J, Bach F, Ponce J. Online Dictionary Learning for Sparse Coding[C]//Proceedings of the26th International Conference on Machine Learning (ICML). Montreal, Canada: Omnipress,2009:689-696.
[45] Mairal J, Bach F, Ponce J, et al. Online Learning for Matrix Factorization and Sparse Coding[J].Journal of Machine Learning Research,2010,11:19-60.
[46] Engan K, Aase S O, Husoy J H. Multi-frame Compression: Theory and Design[J]. EURASIPSignal Process,2000,80(10):2121-2140.
[47] Aharon M, Elad M, Bruckstein A M. The K-SVD: An Algorithm for Designing of OvercompleteDictionaries for Sparse Representation[J]. IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[48] Buades A, Coll B, Morel J M. A Non-Local Algorithm for Image Denoising[C]//Proceedings ofthe2005IEEE Computer Society Conference on Computer Vision and Pattern Recognition. SanDiego, USA: IEEE Computer Society,2005:60-65.
[49] Protter M, Elad M, Takeda H, et al, Generalizing the Nonlocal-Means to Super-ResolutionReconstruction[J]. IEEE Transactions on Image Processing,2009,18(1):36-51.
[50] Dong W S, Zhang L, Shi G M, et al. Image Deblurring and Super-resolution by Adaptive SparseDomain Selection and Adaptive Regularization[J]. IEEE Transactions on Image Processing,2011,20(7):1838-1857.
[51] Dabov K, Foi A, Katkovnik V, et al. Image Denosing by Sparse3D Transform-DomainCollaborative Filtering[J]. IEEE Transaction on Image Processing,2007,16(8):2080-2095.
[52] Danielyan A, Foi A, Katkovnik V, et al. Image Upsampling via Spatially AdaptiveBlock-Matching Filtering[C]//Proceedings of the16th European Signal Processing Conference.Lausanne, Switzerland: Springer,2008:1-5.
[53] Elad M. Sparse and Redundant Representations: From Theory to Applications in Signal andImage Processing[M]. New York, USA: Springer,2010:227-246.
[54] Mallat S, Zhang Z F. Matching Pursuits with Time-Frequency Dictionaries[J]. IEEE Transactionson Signal Processing,1993,41(12):3397-3415.
[55] Needell D, Vershynin R. Signal Recovery From Incomplete and Inaccurate Measurements viaRegularized Orthogonal Matching Pursuit[J]. IEEE Journal of Selected Topics in SignalProcessing,2010,4(2):310-316.
[56] Tibshirani R. Regression Shrinkage and Selection via the Lasso[J]. Journal of the RoyalStatistical Society Series B,1996,58(1):267-288.
[57] Efron B, Hastie T, Johnstone I, et al. Least Angle Regression[J]. The Annals of Statistics,2004,32(2):407-451.
[58] Starck J L, Fadili J, Murtagh F. The Undecimated Wavelet Decomposition and ItsReconstruction[J]. IEEE Transactions on Image Processing,2007,16(2):297-309.
[59] Jolliffe I. Principal Component Analysis[M]. New York: Springer-Verlag,1986.