基于学习的图像超分辨率重建算法研究
|
摘要
图像超分辨率重建技术就是采用信号处理技术，从单帧或多帧低分辨率图像中估计出质量较好的高分辨率图像。其核心思想在于根据需要把相关性、互补性很强的多幅图像的有用信息综合在一起。由于超分辨率重建本身是个不适定的逆问题，该课题仍面临诸多挑战。
目前，图像超分辨率重建算法主要分为三大类：基于插值、基于多帧重构和基于学习的方法。论文围绕基于学习的超分辨率重建技术展开研究，重点包括基于流形学习的方法和基于稀疏表示的方法。主要研究内容与贡献包括：
1、将改进的基于流形学习的超分辨率重建与基于梯度约束的正则化重建结合起来，提出一种新的单帧图像超分辨率重建算法。该算法首先针对基于流形学习的超分辨率重建，提出新的特征提取方法，联合归一化亮度与平稳小波变换细节子带系数两个特征向量，提高重建性能；然后将学习得到的高分辨率图像作为初始估计，将其梯度作为目标梯度域，进行基于梯度约束的正则化重建。实验表明，该算法无论在视觉效果还是客观评价上都获得较好的重建性能。
2、针对基于局部线性嵌入的超分辨率重建算法中近邻保持率不高的问题，提出带约束的逐级放大策略，从而提高近邻保持率，改进重建效果。并且对各级放大的图像用迭代反向投影约束进行修正，减少学习过程中可能出现的误差，保证每一级的解向着正确的方向演化。此外，为了充分利用测试图像本身的信息，提出构建联合训练集的思想，进一步改进算法的性能。实验表明，与目前现有的一些算法相比，该算法获得更好的重建结果。
3、针对基于稀疏表示的超分辨率重建，提出基于双稀疏字典的图像超分辨率重建算法。双稀疏字典结合了解析字典和学习得到的字典的优势，同时具有自适应性和高效性。实验表明，该算法在保证重建质量的同时，显著提高了重建速度，适合对时间性能要求较高的应用。
4、提出基于小波系数稀疏表示的超分辨率重建算法。将训练图像的小波系数划分为三个部分：低频系数、中频系数和高频系数。首先利用中频-高频小波系数训练低分辨率-高分辨率字典对，由此推断测试低分辨率图像丢失的高频细节。然后通过小波逆变换获得高分辨率图像的初始估计。最后利用简单但是高效的迭代反向投影技术实施全局重构约束。实验表明，该算法无论在视觉效果还是客观评价上都获得较好的重建性能。
5、针对基于多类别字典的超分辨率重建，提出两种有监督的图像块分类方法，分别使用图像的相位一致性信息和梯度信息作为先验，引导图像块的聚类。相位一致性提供了对图像局部结构重要性的度量，梯度同样是表征图像特征的重要信息。将图像块划分为平滑块和不同方向的非平滑块，使得属于同一类别的图像块具有相似的模式。
6、将上述两种图像块分类方法应用到基于多类别字典的超分辨率重建中，重建质量和运行时间均取得了满意的效果，并且对噪声具有一定的鲁棒性。由于图像块和选择的子字典具有相似的模式，因而子字典能更好地对图像块进行稀疏表示和重建。最后，使用非局部自相似约束正则化超分辨率重建问题，进一步改进重建性能。与目前现有的一些先进算法的对比实验验证了文中算法的有效性和优越性。
Image super-resolution reconstruction technology is to estimate a high-resolution imagewith better quality from one or a sequence of low-resolution images, with the help of signalprocessing technology. The core idea is to integrate useful information with strongcorrelations and complementarities from multiple images as desired. As super-resolutionreconstruction itself is an ill-posed inverse problem, this subject is still facing manychallenges.
At present, image super-resolution reconstruction technology can be divided into threecategories: interpolation-based, multi-frame reconstruction-based and learning-based. Thelearning-based super-resolution reconstruction technology is studied in this thesis, amongwhich the focal points include the manifold learning based method and the sparserepresentation based method. Main contents and contributions include:
1. A novel single image super-resolution reconstruction algorithm is proposed, whichintegrates the improved manifold learning based super-resolution and gradient constraintbased regularized reconstruction. At first, a new feature extraction method is put forward formanifold learning based super-resolution reconstruction. The new method combines twofeature vectors: norm luminance and detail sub-band coefficients of stationary wavelettransform, to improve the reconstruction performance. Then the gradient constraint basedregularized reconstruction is implemented, with the learned high-resolution image as theinitial estimate and its gradient as the target gradient field. Experiments show that theproposed algorithm obtains better reconstruction performance both in visual effect and inobjective evaluation.
2. A constrained stepwise magnification strategy is put forward for locally linearembedding based image super-resolution reconstruction algorithm, to increase neighborhoodpreserving rate and improve reconstruction effect. Iterative back-projection constraint is usedto modify the magnified image in each step, which decreases errors that may occur during thelearning procedures and ensures the solution of each step to evolve towards correct direction.In addition, in order to take full advantage of the information of the test image, the idea ofbuilding a joint training set is proposed to further improve the performance of the algorithm.Experiments show that, compared with some existing algorithms, the proposed algorithmobtains better reconstruction results.
3. A novel image super-resolution algorithm based on the double sparsity dictionary is put forward for the sparse representation method. The double sparsity dictionary combines theadvantage of the analytic dictionary and the learning-based dictionary, and is both adaptiveand efficient. Experiments show that the algorithm significantly improves the reconstructionspeed when at the same time ensures the reconstruction quality, and is suitable forapplications with a high demand on time performance.
4. A novel super-resolution reconstruction algorithm based on sparse representation ofwavelet coefficients is proposed. The wavelet coefficients of the training images are separatedinto three parts: low-frequency (LF), median-frequency (MF) and high-frequency (HF)coefficients. The dictionary pairs are trained over the MF-HF wavelet coefficients. The HFdetails lost in the observed low-resolution image are inferred from the learned dictionary pairs,and the initial high-resolution estimate is obtained by inverse wavelet transform. Finally,iterative back-projection technology is used to enforce global reconstruction constraint, whichis simple but efficient. Experiments show that the proposed algorithm obtains betterreconstruction performance both in visual effect and in objective evaluation.
5. Two supervised image patch classification methods are put forward forsuper-resolution reconstruction with multi-class dictionaries. These two methods use thephase congruency information and the gradient information respectively as priors to guide theclustering of image patches. Phase congruency provides a measure of the significance of alocal structure, and the gradient is also important information to characterize the imagefeatures. Image patches are classified into smooth patches and non-smooth patches withdifferent orientations, and patches within the same category have similar patterns.
6. The two image patch classification methods mentioned above are applied to thesuper-resolution reconstruction with multi-class dictionaries, and satisfactory effects areobtained in both reconstruction quality and running time. And the algorithms are robust tonoise to some degree. Since the image patch has similar pattern with the selectedsub-dictionary, it can be better sparse represented and reconstructed. Finally, non-localself-similarity constraint is used to regularize the problem of super-resolution reconstruction,and to further improve the reconstruction performance. Comparative experiments with someexisting state-of-art algorithms verify the effectiveness and superiority of the proposedalgorithm.
目前，图像超分辨率重建算法主要分为三大类：基于插值、基于多帧重构和基于学习的方法。论文围绕基于学习的超分辨率重建技术展开研究，重点包括基于流形学习的方法和基于稀疏表示的方法。主要研究内容与贡献包括：
1、将改进的基于流形学习的超分辨率重建与基于梯度约束的正则化重建结合起来，提出一种新的单帧图像超分辨率重建算法。该算法首先针对基于流形学习的超分辨率重建，提出新的特征提取方法，联合归一化亮度与平稳小波变换细节子带系数两个特征向量，提高重建性能；然后将学习得到的高分辨率图像作为初始估计，将其梯度作为目标梯度域，进行基于梯度约束的正则化重建。实验表明，该算法无论在视觉效果还是客观评价上都获得较好的重建性能。
2、针对基于局部线性嵌入的超分辨率重建算法中近邻保持率不高的问题，提出带约束的逐级放大策略，从而提高近邻保持率，改进重建效果。并且对各级放大的图像用迭代反向投影约束进行修正，减少学习过程中可能出现的误差，保证每一级的解向着正确的方向演化。此外，为了充分利用测试图像本身的信息，提出构建联合训练集的思想，进一步改进算法的性能。实验表明，与目前现有的一些算法相比，该算法获得更好的重建结果。
3、针对基于稀疏表示的超分辨率重建，提出基于双稀疏字典的图像超分辨率重建算法。双稀疏字典结合了解析字典和学习得到的字典的优势，同时具有自适应性和高效性。实验表明，该算法在保证重建质量的同时，显著提高了重建速度，适合对时间性能要求较高的应用。
4、提出基于小波系数稀疏表示的超分辨率重建算法。将训练图像的小波系数划分为三个部分：低频系数、中频系数和高频系数。首先利用中频-高频小波系数训练低分辨率-高分辨率字典对，由此推断测试低分辨率图像丢失的高频细节。然后通过小波逆变换获得高分辨率图像的初始估计。最后利用简单但是高效的迭代反向投影技术实施全局重构约束。实验表明，该算法无论在视觉效果还是客观评价上都获得较好的重建性能。
5、针对基于多类别字典的超分辨率重建，提出两种有监督的图像块分类方法，分别使用图像的相位一致性信息和梯度信息作为先验，引导图像块的聚类。相位一致性提供了对图像局部结构重要性的度量，梯度同样是表征图像特征的重要信息。将图像块划分为平滑块和不同方向的非平滑块，使得属于同一类别的图像块具有相似的模式。
6、将上述两种图像块分类方法应用到基于多类别字典的超分辨率重建中，重建质量和运行时间均取得了满意的效果，并且对噪声具有一定的鲁棒性。由于图像块和选择的子字典具有相似的模式，因而子字典能更好地对图像块进行稀疏表示和重建。最后，使用非局部自相似约束正则化超分辨率重建问题，进一步改进重建性能。与目前现有的一些先进算法的对比实验验证了文中算法的有效性和优越性。
Image super-resolution reconstruction technology is to estimate a high-resolution imagewith better quality from one or a sequence of low-resolution images, with the help of signalprocessing technology. The core idea is to integrate useful information with strongcorrelations and complementarities from multiple images as desired. As super-resolutionreconstruction itself is an ill-posed inverse problem, this subject is still facing manychallenges.
At present, image super-resolution reconstruction technology can be divided into threecategories: interpolation-based, multi-frame reconstruction-based and learning-based. Thelearning-based super-resolution reconstruction technology is studied in this thesis, amongwhich the focal points include the manifold learning based method and the sparserepresentation based method. Main contents and contributions include:
1. A novel single image super-resolution reconstruction algorithm is proposed, whichintegrates the improved manifold learning based super-resolution and gradient constraintbased regularized reconstruction. At first, a new feature extraction method is put forward formanifold learning based super-resolution reconstruction. The new method combines twofeature vectors: norm luminance and detail sub-band coefficients of stationary wavelettransform, to improve the reconstruction performance. Then the gradient constraint basedregularized reconstruction is implemented, with the learned high-resolution image as theinitial estimate and its gradient as the target gradient field. Experiments show that theproposed algorithm obtains better reconstruction performance both in visual effect and inobjective evaluation.
2. A constrained stepwise magnification strategy is put forward for locally linearembedding based image super-resolution reconstruction algorithm, to increase neighborhoodpreserving rate and improve reconstruction effect. Iterative back-projection constraint is usedto modify the magnified image in each step, which decreases errors that may occur during thelearning procedures and ensures the solution of each step to evolve towards correct direction.In addition, in order to take full advantage of the information of the test image, the idea ofbuilding a joint training set is proposed to further improve the performance of the algorithm.Experiments show that, compared with some existing algorithms, the proposed algorithmobtains better reconstruction results.
3. A novel image super-resolution algorithm based on the double sparsity dictionary is put forward for the sparse representation method. The double sparsity dictionary combines theadvantage of the analytic dictionary and the learning-based dictionary, and is both adaptiveand efficient. Experiments show that the algorithm significantly improves the reconstructionspeed when at the same time ensures the reconstruction quality, and is suitable forapplications with a high demand on time performance.
4. A novel super-resolution reconstruction algorithm based on sparse representation ofwavelet coefficients is proposed. The wavelet coefficients of the training images are separatedinto three parts: low-frequency (LF), median-frequency (MF) and high-frequency (HF)coefficients. The dictionary pairs are trained over the MF-HF wavelet coefficients. The HFdetails lost in the observed low-resolution image are inferred from the learned dictionary pairs,and the initial high-resolution estimate is obtained by inverse wavelet transform. Finally,iterative back-projection technology is used to enforce global reconstruction constraint, whichis simple but efficient. Experiments show that the proposed algorithm obtains betterreconstruction performance both in visual effect and in objective evaluation.
5. Two supervised image patch classification methods are put forward forsuper-resolution reconstruction with multi-class dictionaries. These two methods use thephase congruency information and the gradient information respectively as priors to guide theclustering of image patches. Phase congruency provides a measure of the significance of alocal structure, and the gradient is also important information to characterize the imagefeatures. Image patches are classified into smooth patches and non-smooth patches withdifferent orientations, and patches within the same category have similar patterns.
6. The two image patch classification methods mentioned above are applied to thesuper-resolution reconstruction with multi-class dictionaries, and satisfactory effects areobtained in both reconstruction quality and running time. And the algorithms are robust tonoise to some degree. Since the image patch has similar pattern with the selectedsub-dictionary, it can be better sparse represented and reconstructed. Finally, non-localself-similarity constraint is used to regularize the problem of super-resolution reconstruction,and to further improve the reconstruction performance. Comparative experiments with someexisting state-of-art algorithms verify the effectiveness and superiority of the proposedalgorithm.
引文
[1] Park S C, Park M K, Kang M G. Super-resolution image reconstruction: A technicaloverview [J]. IEEE Signal Processing Magazine,2003,20(3):21-36.
[2] Harris J L. Diffraction and resolving power [J]. Journal of the Optical Society of America,1964,54(7):931-936.
[3] Ouwerkerk J D. Image super-resolution survey [J]. Image and Vision Computing,2006,24(10):1039-1052.
[4]肖宿,韩国强,沃焱.数字图像超分辨率重建技术综述[J].计算机科学,2009,36(12):8-13.
[5]沈焕锋,李平湘,张良培等.图像超分辨率重建技术与方法综述[J].光学技术,2009,35(2):194-203.
[6] Keys R G. Cubic convolution interpolation for digital image processing [J]. IEEETransactions on Acoustics, Speech, and Signal Processing,1981,29(6):1153-1160.
[7] Hou H S, Andrews H C. Cubic splines for image interpolation and digital filtering [J].IEEE Transactions on Acoustics, Speech, and Signal Processing,1978,29(6):508-517.
[8] Jensen K, Anastassiou D. Subpixel edge localization and the interpolation of still images[J]. IEEE Transactions on Image Processing,1995,4(3):285-295.
[9] Li X, Orchard M T. New edge-directed interpolation [J]. IEEE Transactions on ImageProcessing,2001,10(10):1521-1527.
[10] Muresan D D, Parks T W. Adaptively quadratic (aqua) image interpolation [J]. IEEETransactions on Image Processing,2004,13(5):690-698.
[11] Zhang L, Wu X. An edge-guided image interpolation algorithm via directional filteringand data fusion [J]. IEEE Transactions on Image Processing,2006,15(8):2226-2238.
[12] Zhang X, Wu X. Image interpolation by adaptive2-d autoregressive modeling andsoft-decision estimation [J]. IEEE Transactions on Image Processing,2008,17(6):887-896.
[13] Wang J, Gong Y. Fast image super-resolution using connected component enhancement[C]. IEEE International Conference on Multimedia and Expo,2008:157-160.
[14] Giachetti A, Asuni N. Real time artifact-free image upscaling [J]. IEEE Transactions onImage Processing,2011,20(10):2760-2768.
[15] Carey W K, Chuang D B, Hemami S S. Regularity-preserving image interpolation [J].IEEE Transactions on Image Processing,1999,8(9):1293-1297.
[16] Chang S G, Cvetkovi Z, Vetterli M. Locally adaptive wavelet-based image interpolation[J]. IEEE Transactions on Image Processing,2006,15(6):1471-1485.
[17] Tsai R Y, Huang T S. Multiframe image restoration and registration [C]. Advances inComputer Vision and Image Processing,1984:317-339.
[18] Kim S P, Bose N K, Valenzuela H M. Recursive reconstruction of high resolution imagefrom noisy undersampled multiframes [J]. IEEE Transactions on Acoustics, Speech, andSignal Processing,1990,38(6):1013-1027.
[19] Rhee S H, Kang M G. Discrete cosine transform based regularized high-resolution imagereconstruction algorithm [J].Optical Engineering,1999,38(8):1348-1356.
[20] Ur H, Gross D. Improved resolution from subpixel shifted pictures [J]. CVGIP:Graphical Models and Image Processing,1992,54(2):181-186.
[21] Alam M S, Bognar J G, Hardie R C, et al. Infrared image registration and high-resolution reconstruction using multiple translationally shifted aliased video frames [J].IEEE Transactions on Instrumentation and Measurement,2000,49(5):915-923.
[22] Shah N R, Zakhor A. Resolution enhancement of color video sequences [J]. IEEETransactions on Image Processing,1999,8(6):879-885.
[23] Irani M, Peleg S. Improving resolution by image registration [J]. CVGIP: GraphicalModels and Image Processing,1991,53(3):231-239.
[24] Irani M, Peleg S. Motion analysis for image enhancement resolution, occlusion, andtransparency [J]. Journal of Visual Communication and Image Representation,1993,4(4):324-335.
[25] Stark H, Oskoui P. High resolution image recovery from image-plane arrays, usingconvex projections [J]. Journal of the Optical Society of America A,1989,6(11):1715-1726.
[26] Patti A J, Sezan M I, Tekalp A M. Superresolution video reconstruction with arbitrarysampling lattices and nonzero aperture time [J]. IEEE Transactions on Image Processing,1997,6(8):1064-1076.
[27] Patti A J, Altunbasak Y. Artifact reduction for set theoretic super resolution imagereconstruction with edge adaptive constraints and higher-order interpolants [J]. IEEETransactions on Image Processing,2001,10(1):179-186.
[28] Schultz R R, Stevenson R L. A bayesian approach to image expansion for improveddefinition [J]. IEEE Transactions on Image Processing,1994,3(3):233-242.
[29] Schultz R R, Stevenson R L. Extraction of high-resolution frames from video sequences[J]. IEEE Transactions on Image Processing,1996,5(6):996-1011.
[30] Hardie R C, Barnard, Armstrong E E. Joint MAP registration and high-resolution imageestimation using a sequence of undersampled images [J]. IEEE Transactions on ImageProcessing,1997,6(12):1621-1633.
[31]苏秉华,金伟其.基于Poisson-Markov场的超分辨力图像复原算法[J].电子学报,2003,31(1):1-4.
[32]韩玉兵,吴乐南,张冬青.基于正则化处理的超分辨率重建[J].电子与信息学报,2007,29(7):1713-1716.
[33]肖创柏,禹晶,薛毅.一种基于MAP的超分辨率图像重建的快速算法[J].计算机研究与发展,2009,46(5):872-880.
[34] Elad M, Feuer A. Restoration of single super-resolution image from several blurred,noisy and down-sampled measured images [J]. IEEE Transactions on Image Processing,1997,6(12):1646-1658.
[35] Elad M, Feuer A. Superresolution restoration of an image sequence: adaptive filteringapproach [J]. IEEE Transactions on Image Process,1999,8(3):387-395.
[36] Elad M, Hel-Or Y. A fast super-resolution reconstruction algorithm for pure translationalmotion and common space-invariant blur [J]. IEEE Transactions on Image Process,2001,10(8):1187-1193.
[37]韩玉兵,吴乐南.基于自适应滤波的视频序列超分辨率重建[J].计算机学报,2006,29(4):642-647.
[38] Rajan D, Chaudhuri S. Simultaneous estimation of super-resolved scene and depth mapfrom low resolution defocused observations [J]. IEEE Transactions on Pattern andAnalysis and Machine Intelligence,2003,25(9):1102-1117.
[39] Sroubek F, Flusser J. Resolution enhancement via probabilistic deconvolution of multipledegraded images [J]. Pattern Recognition Letters,2006,27(4):287-293.
[40] Sroubek F, Cristobal G, Flusser J. A unified approach to superresolution and multichannelblind deconvolution [J]. IEEE Transactions on Image Processing,2007,16(9):2322-2332.
[41]乔建苹.超分辨率重建与图像增强技术研究[D].山东:山东大学博士学位论文,2008.
[42]杨怀栋,徐立,陈科新等.盲目反卷积光谱图超分辨复原算法[J].光谱学与光谱分析,2007,27(7):1249-1253.
[43]王素玉,沈兰荪,卓力等.一种基于权值矩阵的序列图像超分辨率盲复原算法[J].电子学报,2009,37(6):1198-1202.
[44]闫华,刘琚,孙建德等.基于误差-参数分析的超分辨率盲辨识和复原算法[J].通信学报,2009,30(8):62-68.
[45]闫华,刘琚.考虑亚像素配准误差的超分辨率图像复原[J].电子学报,2007,35(7):1409-1413.
[46] 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.
[47] Protter M, Elad M. Super resolution with probabilistic motion estimation [J]. IEEETransactions on Image Processing,2009,18(8):1899-1904.
[48] Cheng M H, Chen H Y, Leou J J. Video super-resolution reconstruction using a mobilesearch strategy and adaptive patch size [J]. Signal Processing,2011,91:1284-1297.
[49] Jiji C V, Joshi M V, Chaudhuri S. Single-frame image super-resolution using learnedwavelet coefficients [J]. International Journal of Imaging Systems and Technology,2004,14(3):105-112.
[50] Jiji C V, Chaudhuri S. Single-Frame image super-resolution through contourlet learning[J]. EURASIP Journal on Applied Signal Processing,2006,2006(1):1-11.
[51] Gajjar P P, Joshi M V. New learning based super-resolution: use of DWT and IGMRFprior [J]. IEEE Transactions on Image Processing,2010,19(5):1201-1213.
[52] Hui Z, Lam K M. Eigentransformation-based face super-resolution in the waveletdomain [J]. Pattern Recognition Letters,2012,33:718-727.
[53] Freeman W T, Pasztor E C, Carmichael O T. Learning low-level vision [J]. InternationalJournal of Computer Vision,2000,40(1):25-47.
[54] Freeman W T, Jones T R, Pasztor E C. Example-based super-resolution [J]. IEEEComputer Graphics and Applications,2002,22(2):56-65.
[55] Sun J, Zheng N, Tao H, et al. Image hallucination with primal sketch priors[C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2003,2:729-736.
[56] Baker S, Kanade T. Hallucinating faces [C]. IEEE International Conference onAutomatic Face and Gesture Recognition,2000:83-88.
[57] Baker S, Kanade T. Limits on super-resolution and how to break them [C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2000,2:2372-2379.
[58] Gunturk B K, Batur A U, Altunbasak Y, et al. Eigenface-based super-resolution for facerecognition [C]. IEEE International Conference on Image Processing,2002,2:845-848.
[59] Gunturk B K, Batur A U, Altunbasak Y, et al. Eigenface-domain super-resolution for facerecognition [J]. IEEE Transactions on Image Processing,2003,12(5):597-606.
[60] Liu C, Shum H Y, Zhang C S. A two-step approach to hallucinating faces: globalparametric model and local nonparametric model [C]. IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2001,1:192-198.
[61] Wang X, Tang X. Hallucinating face by eigentransformation [J]. IEEE Transactions onSystems, Man and Cybernetics,2005,35(3):425-434.
[62] Datsenko D, Elad M. Example-based single document image super-resolution: a globalMAP approach with outlier rejection [J]. Multidimentional Systems and SignalProcessing,2007,18:103-121.
[63] Elad M, Datsenko D. Example-based regularization deployed to super-resolutionreconstruction of a single image [J]. Computer Journal,2009,52(1):15-30.
[64] Ni K S, Nguyen T Q. An adaptable k-nearest neighbors algorithm for MMSE imageinterpolation [J]. IEEE Transactions on Image Processing,2009,18(9):1976-1987.
[65] Xiong Z, Sun X, Wu F. Image hallucination with feature enhancement [C]. IEEEConference on Computer Vision and Pattern Recognition,2009:2074-2081.
[66] Xiong Z, Sun X, Wu F. Robust web image/video super-resolution [J]. IEEE Transactionson Image Processing,2010,19(8):2017-2027.
[67] Hu Y, Lam K M, Qiu G, et al. From local pixel structure to global image super-resolution:A new face hallucination framework [J]. IEEE Transactions on Image Processing,2011,20(2):433-445.
[68] Glasner D, Bagon S, Irani M. Super-resolution from a single image [C]. IEEEInternational Conference on Computer Vision,2009:349-356.
[69] Freedman G, Fattal R. Image and video upscaling from local self-examples [J]. ACMTransactions on Graphics,2011,30(2):1-11.
[70] Chang H, Yeung D Y, Xiong Y. Super-resolution through neighbor embedding [C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2004,1:275-282.
[71] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science,2000,290(5500):2323-2326.
[72] 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.
[73] Chan T M, Zhang J. An improved super-resolution with manifold learning and histogrammatching [C]. Proceeding of IAPR International Conference on Biometrics,2006:756-762.
[74] Fan W, Yeung D Y. Image hallucination using neighbor embedding over visual primitivemanifolds [C]. IEEE Conference on Computer Vision and Pattern Recognition,2007:1-7.
[75] Park S W, Savvides M. Robust super-resolution of face images by iterative compensatingneighborhood relationships [J]. Biometrics Symposium,2007:1-5.
[76]吴炜,杨晓敏,陈默等.基于流形学习的人脸图像超分辨率技术研究[J].光学技术,2009,35(1):84-88.
[77]张雪松,江静,彭思龙.人脸图像超分辨率的自适应流形学习方法[J].计算机辅助设计与图形学学报,2008,20(7):856-863.
[78] Chan T M, Zhang J, Pu J, et al. Neighbor embedding based super-resolution algorithmthrough edge detection and feature selection [J]. Pattern Recognition Letters,2009,30(5):94–502.
[79] Li B, Chang H, Shan S, et al. Locality preserving constraints for super-resolution withneighbor embedding [C]. IEEE International Conference on Image Processing,2009:1189-1192.
[80] Zhang K, Gao X, Li X, et al. Partially supervised neighbor embedding for example-basedimage super-resolution [J]. IEEE Journal of Selected Topics in Signal Processing,2011,5(2):230-239.
[81] Gao X, Zhang K, Tao D, et al. Joint learning for single-image super-resolution via acoupled constraint [J]. IEEE Transactions on Image Processing,2012,21(2):469-480.
[82] Gao X, Zhang K, Tao D, et al. Image super-resolution with sparse neighbor embedding[J]. IEEE Transactions on Image Processing,2012,21(7):3194-3205.
[83] Takeda H, Farsiu S, Peyman Milanfar. Kernel Regression for image processing andreconstruction [J]. IEEE Transactions on Image Processing,2007,16(2):349-365.
[84] Kim K I, Kwon Y. Example-based learning for single-image super-resolution [C].30thDAGM Symposium Munich,2008:456-465.
[85] Kim K I, Kwon Y. Single-image super-resolution using sparse regression and naturalimage prior [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(6):1127-1133.
[86] Tang Y, Yan P, Yuan Y, et al. Single-image super resolution via local learning [J].International Journal of Machine Learning and Cybernetics,2011,2(1):15-23.
[87] Wu W, Liu Z, He X. Learning-based super resolution using kernel partial least squares [J].Image and Vision Computing,2011,29(6):394-406.
[88] Yang J, Wright J, Huang T, et al. Image super-resolution as sparse representation of rawimage patches [C]. IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[89] Candes E J, Wakin M. An introduction to compressive sampling [J]. IEEE SignalProcessing Magazine,2008,25(2):21-30.
[90] Yang J, Wright J, Huang T, et al. Image super-resolution via sparse representation [J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.
[91] Yang J, Wang Z, Lin Z, et al. Couple dictionary training for image super-resolution [J].IEEE Transactions on Image Processing,2012,21(8):3467-3478.
[92] Yang J, Wang Z, Lin Z, et al. Bilevel sparse coding for coupled feature spaces [C]. IEEEConference on Computer Vision and Pattern Recognition,2012:2360-2367.
[93] Wang J, Zhu S, Gong Y. Resolution enhancement based on learning the sparseassociation of image patches [J]. Pattern Recognition Letters,2010,31(1):1-10.
[94] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations [C].Proceedings of the7th International Conferences on Curves and Surfaces,2010:711-730.
[95] Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcompletedictionaries for sparse representation. IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[96] Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal matching pursuit: Recursivefunction approximation with applications to wavelet decomposition [C]. ConferenceRecord of27th Asilomar Conference on Signals, Systems and Computers,1993:40-44.
[97]浦剑,张军平.基于字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.
[98] Yang C Y, Huang J B, Yang M H. Exploiting self-similarities for single framesuper-resolution [C].10th Asian Conference on Computer Vision,2010:497-510.
[99] Lu J, Zhang Q, Xu Z, et al. Image super-resolution by dictionary concatenation andsparse representation with approximate L0norm minimization [J]. Computers andElectrical Engineering,2012,38(5):1336-1345.
[100] Mohimani G H, Badaie-Zadeh M, Jutten C. A fast approach for overcomplete sparsedecomposition based on smoothed L0norm [J]. IEEE Transactions on Signal Processing,2009,57(1):289-301.
[101] Yang S, Wang M, Sun Y, et al. Compressive sampling based single-imagesuper-resolution reconstruction by dual-sparsity and non-local similarity regularizer [J].Pattern Recognition Letters,2012,33:1049-1059.
[102] Lu X, Yuan H, Yan P, et al. Geometry constrained sparse coding for single imagesuper-resolution [C]. IEEE Conference on Computer Vision and Pattern Recognition,2012:1648-1655.
[103] Elad M, Yavneh I. A plurality of sparse representation is better than the sparsest onealone [J]. IEEE Transactions on Information Theory,2009,55(10):4701-4714.
[104] Protter M, Yavneh I, Elad M. Closed-form MMSE estimation for signal denoising undersparse representation modeling over a unitary dictionary [J]. IEEE Transactions onSignal Processing,2010,58(7):3471-3484.
[105] Mallat S, Yu G. Super-resolution with sparse mixing estimators [J]. IEEE Transactionson Image Processing,2010,19(11):2889-2900.
[106] Yin H, Li S, Hu J. Single image super resolution via texture constrained sparserepresentation [C]. IEEE Conference on Image Processing,2011:1161-1164.
[107] Yang S, Liu Z, Wang M, et al. Multitask dictionary learning and sparse representationbased single-image super-resolution reconstruction [J]. Neurocomputing,2011,74(17):3193-3203.
[108] Yang S, Wang M, Chen Y, et al. Single-image super-resolution reconstruction vialearned geometric dictionaries and clustered sparse coding [J]. IEEE Transactions onImage Processing,2012,21(9):4016-4028.
[109] Dong W, Zhang L, Shi G, et al. Image deblurring and super-resolution by adaptivesparse domain selection and adaptive regularization [J]. IEEE Transactions on ImageProcessing,2011,20(7):1838-1857.
[110] Dong W, Zhang L, Lukac R, et al. Sparse representation based image interpolation withnonlocal autoregressive modeling [J]. IEEE Transactions on Image Processing,2013,22(4):1382-1394.
[111] Li X, Lam K M, Qiu G, et al. Example-based image super-resolution with class-specificpredictors [J]. Journal of Visual Communication and Image Representation,2009,20(5):312-322.
[112] Sun J, Zhu J, Tappen M F. Context-constrained hallucination for image super-resolution[C]. IEEE Conference on Computer Vision and Pattern Recognition,2010:231-238.
[113] HaCohen Y, Fattal R, Lischinski D. Image upsampling via texture hallucination [C].IEEE International Conference on Computational Photography,2010:1-8.
[114] Sun J, Sun J, Xu Z, et al. Image super-resolution using gradient profile prior [C]. IEEEConference on Computer Vision and Pattern Recognition,2008:1-8.
[115] Tai Y, Liu S, Brown M, et al. Super resolution using edge prior and single image detailsynthesis [C]. IEEE Conference on Computer Vision and Pattern Recognition,2010:2400-2407.
[116] Zhang K, Gao X, Tao D, et al. Single image super-resolution with non-local means andsteering kernel regression [J]. IEEE Transactions on Image Processing,2012,21(11):4544-4556.
[117] Farsiu S, Robinson M D, Elad M, et al. Fast and robust multiframe super resolution [J].IEEE Transactions on Image Processing,2004,13(10):1327–1344.
[118] Zhang X, Lam E Y, Wu E X, et al. Application of Tikhonov regularization tosuper-resolution reconstruction of brain MRI image[J]. Lecture Notes in ComputerScience,2008,4987:51–56.
[119] Beck A, Teboulle M. Fast gradient-based algorithms for constrained total variationimage denoising and deblurring problems [J]. IEEE Transactions on Image Processing,2009,18(11):2419-2434.
[120] Zhu M, Wright S J, Chan T F. Duality-based algorithms for total-variation-regularizedimage restoration [J]. Computational Optimization and Applications,2010,47(3):377-400.
[121] Li X, Hu Y, Gao X, et al. A multi-frame image super-resolution method [J]. SignalProcessing,2010,90(2):405-414.
[122]张新明,沈兰荪.基于多尺度边缘保持正则化的超分辨率复原[J].软件学报,2003,14(6):1075-1081.
[123]邵文泽,韦志辉.基于广义Huber-MRF图像建模的超分辨率复原算法[J].软件学报,2007,18(10):2434-2444.
[124]张洪艳,沈焕峰,张良培等.一种保边缘影像超分辨率重建方法[J].中国图象图形学报,2009,14(11):2255-2261.
[125] Donoho D L. For most large underdetermined systems of linear equations the minimall1-norm solution is also the sparsest solution [J]. Communications on Pure and AppliedMathematics,2006,59(6):797-829.
[126] Bickel P J, Ritov Y, Tsybakov A B. Simultaneous analysis of Lasso and Dantzig selector[J]. The Annals of Statistics,2009,37(4):1705-1732.
[127] Lee H, Battle A, Raina R, et al. Efficient sparse coding algorithms [C]. In Proceedingsof the Neural Information Processing Systems (NIPS),2007.
[128]佟雨兵,胡薇薇,杨东凯等.视频质量评价方法综述[J].计算机辅助设计与图形学学报,2006,18(5):735-741.
[129] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibilityto structural similarity [J]. IEEE Transactions on Image Processing,2004,13(4):600-612.
[130] Wang Z, Bovik A C. Mean squared error: love it or leave it? A new look at signalfidelity measures [J]. IEEE Signal Processing Magazine,2009,26(1):98117.
[131] Liu Z, Lagani re. Phase congruence measurement for image similarity assessment [J].Pattern Recognition Letters,2007,28:166–172.
[132] Zhang L, Zhang L, Mou X, et al. FSIM: A Feature similarity index for image qualityassessment [J]. IEEE Transactions on Image Processing,2011,20(8):2378-2386.
[133] Hargrove L J, Scheme E J, Englehart K B, et al. Multiple binary classifications vialinear discriminant analysis for improved controllability of a powered prosthesis [J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2010,18(1):49-57.
[134] Lee D, Cognition S H. The manifold ways of perception [J]. Science,2000,290(5500):2268-2269.
[135] Tenenbaum J B, Silvam V D, Langford J C. A global geometric framework fornonlinear dimensionality reduction [J]. Science,2000,290(5500):2319-2323.
[136] Belkin M, Niyogi P. Laplacian eigenmaps for dimensionality reduction and datarepresentation [J]. Neural Computation,2003,15(6):1373-1396.
[137] Zhang Z, Zha H. Principal manifolds and nonlinear dimension reduction via localtangent space alignment [J]. SIAM Joumal of Scientific Computing,2004,26(l):313-338.
[138] Silva V, Tenenbaum J B. Global versus local methods in nonlinear dimensionalityreduction [J]. Advances in Neural Information Processing Systems,2002,15:705-712.
[139]黄启宏.流形学方法理论研究及图像中应用[D].成都:电子科技大学博士学位论文,2007.
[140] Demirel H, Anbarjafari G. Image resolution enhancement by using discrete andstationary wavelet decomposition [J]. IEEE Transactions on Image Processing,2011,20(5):1458-1460.
[141] Gao W, Cao B, Shan S, et al. The CAS-PEAL large-scale Chinese face database andbaseline evaluations [J]. IEEE Transactions on System Man, and Cybernetics (Part A),2008,38(1):149-161.
[142] Bruckstein A M, Donoho D L, Elad M. From sparse solutions of systems of equations tosparse modeling of signals and images [J]. SIAM Review,2009,51(1):34-81.
[143] Elad M, Starck J L, Querre P, et al. Simultaneous cartoon and texture image inpaintingusing morphological component analysis (MCA)[J]. Applied Computational HarmonicAnalysis,2005,19(3):340-358.
[144] Elad M, Aharon M. Image denoising via sparse and redundant representations overlearned dictionaries [J]. IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[145] Bryt O, Elad M. Compression of facial images using the K-SVD algorithm [J]. Journalof Visual Communication and Image Representation,2008,19(4):270-283.
[146] Rubinstein R, Bruckstein A M, Elad M. Dictionaries for sparse representation modeling[J]. Proceedings of the IEEE,2010,98(6):1045-1057.
[147] Selesnick I W, Baraniuk R G, Kingsbury N C. The dual-tree complex wavelet transform[J]. IEEE Signal Processing Magazine,2005,22(6):123-151.
[148] Do M N, Vetterli M. The contourlet transform: an efficient directional multiresolutionimage representation [J]. IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[149] Le Pennec E, Mallat S. Sparse geometric image representations with bandelets [J].IEEE Transactions on Image Processing,2005,14(4):423-438.
[150] Rubinstein R, Zibulevsky M, Elad M. Double sparsity: Learning sparse dictionaries forsparse signal approximation [J]. IEEE Transactions on Signal Processing,2010,58(3):1553-1564.
[151] Ophir B, Lustig M, Elad M. Multi-scale dictionary learning using wavelets [J]. IEEEJournal of Selected Topics in Signal Processing,2011,5(5):1014-1024.
[156] Mallat S G, Zhang Z. Matching pursuits with time-frequency dictionaries [J]. IEEETransactions on Signal Processing,1993,41(12):3397-3415.
[152] Morrone M C, Owens R A. Feature detection from local energy [J]. Pattern RecognitionLetters,1987,6(5):303-313.
[153] Kovesi P. Phase congruency: A low-level image invariant [J]. Psychological research,2000,64(2):136-148.
[154] Buades A, Coll B, Morel J M. A non-local algorithm for image denoising [C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2005,2:60-65.
[155] Wong A, Orchard J. A nonlocal-means approach to exemplar-based inpainting [C].IEEE International Conference on Image Processing,2008:2600-2603.
[156] Zhang X, Burger M, Bresson X, et al. Bregmanized nonlocal regularization fordeconvolution and sparse reconstruction [J]. SIAM Journal on Imaging Sciences,2010,3(3):253-276.
[157] Mairal J, Bach F, Ponce J, et al. Non-local sparse models for image restoration[C].IEEE12th International Conference on Computer Vision,2009:2272-2279.
[2] Harris J L. Diffraction and resolving power [J]. Journal of the Optical Society of America,1964,54(7):931-936.
[3] Ouwerkerk J D. Image super-resolution survey [J]. Image and Vision Computing,2006,24(10):1039-1052.
[4]肖宿,韩国强,沃焱.数字图像超分辨率重建技术综述[J].计算机科学,2009,36(12):8-13.
[5]沈焕锋,李平湘,张良培等.图像超分辨率重建技术与方法综述[J].光学技术,2009,35(2):194-203.
[6] Keys R G. Cubic convolution interpolation for digital image processing [J]. IEEETransactions on Acoustics, Speech, and Signal Processing,1981,29(6):1153-1160.
[7] Hou H S, Andrews H C. Cubic splines for image interpolation and digital filtering [J].IEEE Transactions on Acoustics, Speech, and Signal Processing,1978,29(6):508-517.
[8] Jensen K, Anastassiou D. Subpixel edge localization and the interpolation of still images[J]. IEEE Transactions on Image Processing,1995,4(3):285-295.
[9] Li X, Orchard M T. New edge-directed interpolation [J]. IEEE Transactions on ImageProcessing,2001,10(10):1521-1527.
[10] Muresan D D, Parks T W. Adaptively quadratic (aqua) image interpolation [J]. IEEETransactions on Image Processing,2004,13(5):690-698.
[11] Zhang L, Wu X. An edge-guided image interpolation algorithm via directional filteringand data fusion [J]. IEEE Transactions on Image Processing,2006,15(8):2226-2238.
[12] Zhang X, Wu X. Image interpolation by adaptive2-d autoregressive modeling andsoft-decision estimation [J]. IEEE Transactions on Image Processing,2008,17(6):887-896.
[13] Wang J, Gong Y. Fast image super-resolution using connected component enhancement[C]. IEEE International Conference on Multimedia and Expo,2008:157-160.
[14] Giachetti A, Asuni N. Real time artifact-free image upscaling [J]. IEEE Transactions onImage Processing,2011,20(10):2760-2768.
[15] Carey W K, Chuang D B, Hemami S S. Regularity-preserving image interpolation [J].IEEE Transactions on Image Processing,1999,8(9):1293-1297.
[16] Chang S G, Cvetkovi Z, Vetterli M. Locally adaptive wavelet-based image interpolation[J]. IEEE Transactions on Image Processing,2006,15(6):1471-1485.
[17] Tsai R Y, Huang T S. Multiframe image restoration and registration [C]. Advances inComputer Vision and Image Processing,1984:317-339.
[18] Kim S P, Bose N K, Valenzuela H M. Recursive reconstruction of high resolution imagefrom noisy undersampled multiframes [J]. IEEE Transactions on Acoustics, Speech, andSignal Processing,1990,38(6):1013-1027.
[19] Rhee S H, Kang M G. Discrete cosine transform based regularized high-resolution imagereconstruction algorithm [J].Optical Engineering,1999,38(8):1348-1356.
[20] Ur H, Gross D. Improved resolution from subpixel shifted pictures [J]. CVGIP:Graphical Models and Image Processing,1992,54(2):181-186.
[21] Alam M S, Bognar J G, Hardie R C, et al. Infrared image registration and high-resolution reconstruction using multiple translationally shifted aliased video frames [J].IEEE Transactions on Instrumentation and Measurement,2000,49(5):915-923.
[22] Shah N R, Zakhor A. Resolution enhancement of color video sequences [J]. IEEETransactions on Image Processing,1999,8(6):879-885.
[23] Irani M, Peleg S. Improving resolution by image registration [J]. CVGIP: GraphicalModels and Image Processing,1991,53(3):231-239.
[24] Irani M, Peleg S. Motion analysis for image enhancement resolution, occlusion, andtransparency [J]. Journal of Visual Communication and Image Representation,1993,4(4):324-335.
[25] Stark H, Oskoui P. High resolution image recovery from image-plane arrays, usingconvex projections [J]. Journal of the Optical Society of America A,1989,6(11):1715-1726.
[26] Patti A J, Sezan M I, Tekalp A M. Superresolution video reconstruction with arbitrarysampling lattices and nonzero aperture time [J]. IEEE Transactions on Image Processing,1997,6(8):1064-1076.
[27] Patti A J, Altunbasak Y. Artifact reduction for set theoretic super resolution imagereconstruction with edge adaptive constraints and higher-order interpolants [J]. IEEETransactions on Image Processing,2001,10(1):179-186.
[28] Schultz R R, Stevenson R L. A bayesian approach to image expansion for improveddefinition [J]. IEEE Transactions on Image Processing,1994,3(3):233-242.
[29] Schultz R R, Stevenson R L. Extraction of high-resolution frames from video sequences[J]. IEEE Transactions on Image Processing,1996,5(6):996-1011.
[30] Hardie R C, Barnard, Armstrong E E. Joint MAP registration and high-resolution imageestimation using a sequence of undersampled images [J]. IEEE Transactions on ImageProcessing,1997,6(12):1621-1633.
[31]苏秉华,金伟其.基于Poisson-Markov场的超分辨力图像复原算法[J].电子学报,2003,31(1):1-4.
[32]韩玉兵,吴乐南,张冬青.基于正则化处理的超分辨率重建[J].电子与信息学报,2007,29(7):1713-1716.
[33]肖创柏,禹晶,薛毅.一种基于MAP的超分辨率图像重建的快速算法[J].计算机研究与发展,2009,46(5):872-880.
[34] Elad M, Feuer A. Restoration of single super-resolution image from several blurred,noisy and down-sampled measured images [J]. IEEE Transactions on Image Processing,1997,6(12):1646-1658.
[35] Elad M, Feuer A. Superresolution restoration of an image sequence: adaptive filteringapproach [J]. IEEE Transactions on Image Process,1999,8(3):387-395.
[36] Elad M, Hel-Or Y. A fast super-resolution reconstruction algorithm for pure translationalmotion and common space-invariant blur [J]. IEEE Transactions on Image Process,2001,10(8):1187-1193.
[37]韩玉兵,吴乐南.基于自适应滤波的视频序列超分辨率重建[J].计算机学报,2006,29(4):642-647.
[38] Rajan D, Chaudhuri S. Simultaneous estimation of super-resolved scene and depth mapfrom low resolution defocused observations [J]. IEEE Transactions on Pattern andAnalysis and Machine Intelligence,2003,25(9):1102-1117.
[39] Sroubek F, Flusser J. Resolution enhancement via probabilistic deconvolution of multipledegraded images [J]. Pattern Recognition Letters,2006,27(4):287-293.
[40] Sroubek F, Cristobal G, Flusser J. A unified approach to superresolution and multichannelblind deconvolution [J]. IEEE Transactions on Image Processing,2007,16(9):2322-2332.
[41]乔建苹.超分辨率重建与图像增强技术研究[D].山东:山东大学博士学位论文,2008.
[42]杨怀栋,徐立,陈科新等.盲目反卷积光谱图超分辨复原算法[J].光谱学与光谱分析,2007,27(7):1249-1253.
[43]王素玉,沈兰荪,卓力等.一种基于权值矩阵的序列图像超分辨率盲复原算法[J].电子学报,2009,37(6):1198-1202.
[44]闫华,刘琚,孙建德等.基于误差-参数分析的超分辨率盲辨识和复原算法[J].通信学报,2009,30(8):62-68.
[45]闫华,刘琚.考虑亚像素配准误差的超分辨率图像复原[J].电子学报,2007,35(7):1409-1413.
[46] 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.
[47] Protter M, Elad M. Super resolution with probabilistic motion estimation [J]. IEEETransactions on Image Processing,2009,18(8):1899-1904.
[48] Cheng M H, Chen H Y, Leou J J. Video super-resolution reconstruction using a mobilesearch strategy and adaptive patch size [J]. Signal Processing,2011,91:1284-1297.
[49] Jiji C V, Joshi M V, Chaudhuri S. Single-frame image super-resolution using learnedwavelet coefficients [J]. International Journal of Imaging Systems and Technology,2004,14(3):105-112.
[50] Jiji C V, Chaudhuri S. Single-Frame image super-resolution through contourlet learning[J]. EURASIP Journal on Applied Signal Processing,2006,2006(1):1-11.
[51] Gajjar P P, Joshi M V. New learning based super-resolution: use of DWT and IGMRFprior [J]. IEEE Transactions on Image Processing,2010,19(5):1201-1213.
[52] Hui Z, Lam K M. Eigentransformation-based face super-resolution in the waveletdomain [J]. Pattern Recognition Letters,2012,33:718-727.
[53] Freeman W T, Pasztor E C, Carmichael O T. Learning low-level vision [J]. InternationalJournal of Computer Vision,2000,40(1):25-47.
[54] Freeman W T, Jones T R, Pasztor E C. Example-based super-resolution [J]. IEEEComputer Graphics and Applications,2002,22(2):56-65.
[55] Sun J, Zheng N, Tao H, et al. Image hallucination with primal sketch priors[C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2003,2:729-736.
[56] Baker S, Kanade T. Hallucinating faces [C]. IEEE International Conference onAutomatic Face and Gesture Recognition,2000:83-88.
[57] Baker S, Kanade T. Limits on super-resolution and how to break them [C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2000,2:2372-2379.
[58] Gunturk B K, Batur A U, Altunbasak Y, et al. Eigenface-based super-resolution for facerecognition [C]. IEEE International Conference on Image Processing,2002,2:845-848.
[59] Gunturk B K, Batur A U, Altunbasak Y, et al. Eigenface-domain super-resolution for facerecognition [J]. IEEE Transactions on Image Processing,2003,12(5):597-606.
[60] Liu C, Shum H Y, Zhang C S. A two-step approach to hallucinating faces: globalparametric model and local nonparametric model [C]. IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2001,1:192-198.
[61] Wang X, Tang X. Hallucinating face by eigentransformation [J]. IEEE Transactions onSystems, Man and Cybernetics,2005,35(3):425-434.
[62] Datsenko D, Elad M. Example-based single document image super-resolution: a globalMAP approach with outlier rejection [J]. Multidimentional Systems and SignalProcessing,2007,18:103-121.
[63] Elad M, Datsenko D. Example-based regularization deployed to super-resolutionreconstruction of a single image [J]. Computer Journal,2009,52(1):15-30.
[64] Ni K S, Nguyen T Q. An adaptable k-nearest neighbors algorithm for MMSE imageinterpolation [J]. IEEE Transactions on Image Processing,2009,18(9):1976-1987.
[65] Xiong Z, Sun X, Wu F. Image hallucination with feature enhancement [C]. IEEEConference on Computer Vision and Pattern Recognition,2009:2074-2081.
[66] Xiong Z, Sun X, Wu F. Robust web image/video super-resolution [J]. IEEE Transactionson Image Processing,2010,19(8):2017-2027.
[67] Hu Y, Lam K M, Qiu G, et al. From local pixel structure to global image super-resolution:A new face hallucination framework [J]. IEEE Transactions on Image Processing,2011,20(2):433-445.
[68] Glasner D, Bagon S, Irani M. Super-resolution from a single image [C]. IEEEInternational Conference on Computer Vision,2009:349-356.
[69] Freedman G, Fattal R. Image and video upscaling from local self-examples [J]. ACMTransactions on Graphics,2011,30(2):1-11.
[70] Chang H, Yeung D Y, Xiong Y. Super-resolution through neighbor embedding [C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2004,1:275-282.
[71] Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science,2000,290(5500):2323-2326.
[72] 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.
[73] Chan T M, Zhang J. An improved super-resolution with manifold learning and histogrammatching [C]. Proceeding of IAPR International Conference on Biometrics,2006:756-762.
[74] Fan W, Yeung D Y. Image hallucination using neighbor embedding over visual primitivemanifolds [C]. IEEE Conference on Computer Vision and Pattern Recognition,2007:1-7.
[75] Park S W, Savvides M. Robust super-resolution of face images by iterative compensatingneighborhood relationships [J]. Biometrics Symposium,2007:1-5.
[76]吴炜,杨晓敏,陈默等.基于流形学习的人脸图像超分辨率技术研究[J].光学技术,2009,35(1):84-88.
[77]张雪松,江静,彭思龙.人脸图像超分辨率的自适应流形学习方法[J].计算机辅助设计与图形学学报,2008,20(7):856-863.
[78] Chan T M, Zhang J, Pu J, et al. Neighbor embedding based super-resolution algorithmthrough edge detection and feature selection [J]. Pattern Recognition Letters,2009,30(5):94–502.
[79] Li B, Chang H, Shan S, et al. Locality preserving constraints for super-resolution withneighbor embedding [C]. IEEE International Conference on Image Processing,2009:1189-1192.
[80] Zhang K, Gao X, Li X, et al. Partially supervised neighbor embedding for example-basedimage super-resolution [J]. IEEE Journal of Selected Topics in Signal Processing,2011,5(2):230-239.
[81] Gao X, Zhang K, Tao D, et al. Joint learning for single-image super-resolution via acoupled constraint [J]. IEEE Transactions on Image Processing,2012,21(2):469-480.
[82] Gao X, Zhang K, Tao D, et al. Image super-resolution with sparse neighbor embedding[J]. IEEE Transactions on Image Processing,2012,21(7):3194-3205.
[83] Takeda H, Farsiu S, Peyman Milanfar. Kernel Regression for image processing andreconstruction [J]. IEEE Transactions on Image Processing,2007,16(2):349-365.
[84] Kim K I, Kwon Y. Example-based learning for single-image super-resolution [C].30thDAGM Symposium Munich,2008:456-465.
[85] Kim K I, Kwon Y. Single-image super-resolution using sparse regression and naturalimage prior [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(6):1127-1133.
[86] Tang Y, Yan P, Yuan Y, et al. Single-image super resolution via local learning [J].International Journal of Machine Learning and Cybernetics,2011,2(1):15-23.
[87] Wu W, Liu Z, He X. Learning-based super resolution using kernel partial least squares [J].Image and Vision Computing,2011,29(6):394-406.
[88] Yang J, Wright J, Huang T, et al. Image super-resolution as sparse representation of rawimage patches [C]. IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[89] Candes E J, Wakin M. An introduction to compressive sampling [J]. IEEE SignalProcessing Magazine,2008,25(2):21-30.
[90] Yang J, Wright J, Huang T, et al. Image super-resolution via sparse representation [J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.
[91] Yang J, Wang Z, Lin Z, et al. Couple dictionary training for image super-resolution [J].IEEE Transactions on Image Processing,2012,21(8):3467-3478.
[92] Yang J, Wang Z, Lin Z, et al. Bilevel sparse coding for coupled feature spaces [C]. IEEEConference on Computer Vision and Pattern Recognition,2012:2360-2367.
[93] Wang J, Zhu S, Gong Y. Resolution enhancement based on learning the sparseassociation of image patches [J]. Pattern Recognition Letters,2010,31(1):1-10.
[94] Zeyde R, Elad M, Protter M. On single image scale-up using sparse-representations [C].Proceedings of the7th International Conferences on Curves and Surfaces,2010:711-730.
[95] Aharon M, Elad M, Bruckstein A. K-SVD: An algorithm for designing overcompletedictionaries for sparse representation. IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[96] Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal matching pursuit: Recursivefunction approximation with applications to wavelet decomposition [C]. ConferenceRecord of27th Asilomar Conference on Signals, Systems and Computers,1993:40-44.
[97]浦剑,张军平.基于字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.
[98] Yang C Y, Huang J B, Yang M H. Exploiting self-similarities for single framesuper-resolution [C].10th Asian Conference on Computer Vision,2010:497-510.
[99] Lu J, Zhang Q, Xu Z, et al. Image super-resolution by dictionary concatenation andsparse representation with approximate L0norm minimization [J]. Computers andElectrical Engineering,2012,38(5):1336-1345.
[100] Mohimani G H, Badaie-Zadeh M, Jutten C. A fast approach for overcomplete sparsedecomposition based on smoothed L0norm [J]. IEEE Transactions on Signal Processing,2009,57(1):289-301.
[101] Yang S, Wang M, Sun Y, et al. Compressive sampling based single-imagesuper-resolution reconstruction by dual-sparsity and non-local similarity regularizer [J].Pattern Recognition Letters,2012,33:1049-1059.
[102] Lu X, Yuan H, Yan P, et al. Geometry constrained sparse coding for single imagesuper-resolution [C]. IEEE Conference on Computer Vision and Pattern Recognition,2012:1648-1655.
[103] Elad M, Yavneh I. A plurality of sparse representation is better than the sparsest onealone [J]. IEEE Transactions on Information Theory,2009,55(10):4701-4714.
[104] Protter M, Yavneh I, Elad M. Closed-form MMSE estimation for signal denoising undersparse representation modeling over a unitary dictionary [J]. IEEE Transactions onSignal Processing,2010,58(7):3471-3484.
[105] Mallat S, Yu G. Super-resolution with sparse mixing estimators [J]. IEEE Transactionson Image Processing,2010,19(11):2889-2900.
[106] Yin H, Li S, Hu J. Single image super resolution via texture constrained sparserepresentation [C]. IEEE Conference on Image Processing,2011:1161-1164.
[107] Yang S, Liu Z, Wang M, et al. Multitask dictionary learning and sparse representationbased single-image super-resolution reconstruction [J]. Neurocomputing,2011,74(17):3193-3203.
[108] Yang S, Wang M, Chen Y, et al. Single-image super-resolution reconstruction vialearned geometric dictionaries and clustered sparse coding [J]. IEEE Transactions onImage Processing,2012,21(9):4016-4028.
[109] Dong W, Zhang L, Shi G, et al. Image deblurring and super-resolution by adaptivesparse domain selection and adaptive regularization [J]. IEEE Transactions on ImageProcessing,2011,20(7):1838-1857.
[110] Dong W, Zhang L, Lukac R, et al. Sparse representation based image interpolation withnonlocal autoregressive modeling [J]. IEEE Transactions on Image Processing,2013,22(4):1382-1394.
[111] Li X, Lam K M, Qiu G, et al. Example-based image super-resolution with class-specificpredictors [J]. Journal of Visual Communication and Image Representation,2009,20(5):312-322.
[112] Sun J, Zhu J, Tappen M F. Context-constrained hallucination for image super-resolution[C]. IEEE Conference on Computer Vision and Pattern Recognition,2010:231-238.
[113] HaCohen Y, Fattal R, Lischinski D. Image upsampling via texture hallucination [C].IEEE International Conference on Computational Photography,2010:1-8.
[114] Sun J, Sun J, Xu Z, et al. Image super-resolution using gradient profile prior [C]. IEEEConference on Computer Vision and Pattern Recognition,2008:1-8.
[115] Tai Y, Liu S, Brown M, et al. Super resolution using edge prior and single image detailsynthesis [C]. IEEE Conference on Computer Vision and Pattern Recognition,2010:2400-2407.
[116] Zhang K, Gao X, Tao D, et al. Single image super-resolution with non-local means andsteering kernel regression [J]. IEEE Transactions on Image Processing,2012,21(11):4544-4556.
[117] Farsiu S, Robinson M D, Elad M, et al. Fast and robust multiframe super resolution [J].IEEE Transactions on Image Processing,2004,13(10):1327–1344.
[118] Zhang X, Lam E Y, Wu E X, et al. Application of Tikhonov regularization tosuper-resolution reconstruction of brain MRI image[J]. Lecture Notes in ComputerScience,2008,4987:51–56.
[119] Beck A, Teboulle M. Fast gradient-based algorithms for constrained total variationimage denoising and deblurring problems [J]. IEEE Transactions on Image Processing,2009,18(11):2419-2434.
[120] Zhu M, Wright S J, Chan T F. Duality-based algorithms for total-variation-regularizedimage restoration [J]. Computational Optimization and Applications,2010,47(3):377-400.
[121] Li X, Hu Y, Gao X, et al. A multi-frame image super-resolution method [J]. SignalProcessing,2010,90(2):405-414.
[122]张新明,沈兰荪.基于多尺度边缘保持正则化的超分辨率复原[J].软件学报,2003,14(6):1075-1081.
[123]邵文泽,韦志辉.基于广义Huber-MRF图像建模的超分辨率复原算法[J].软件学报,2007,18(10):2434-2444.
[124]张洪艳,沈焕峰,张良培等.一种保边缘影像超分辨率重建方法[J].中国图象图形学报,2009,14(11):2255-2261.
[125] Donoho D L. For most large underdetermined systems of linear equations the minimall1-norm solution is also the sparsest solution [J]. Communications on Pure and AppliedMathematics,2006,59(6):797-829.
[126] Bickel P J, Ritov Y, Tsybakov A B. Simultaneous analysis of Lasso and Dantzig selector[J]. The Annals of Statistics,2009,37(4):1705-1732.
[127] Lee H, Battle A, Raina R, et al. Efficient sparse coding algorithms [C]. In Proceedingsof the Neural Information Processing Systems (NIPS),2007.
[128]佟雨兵,胡薇薇,杨东凯等.视频质量评价方法综述[J].计算机辅助设计与图形学学报,2006,18(5):735-741.
[129] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibilityto structural similarity [J]. IEEE Transactions on Image Processing,2004,13(4):600-612.
[130] Wang Z, Bovik A C. Mean squared error: love it or leave it? A new look at signalfidelity measures [J]. IEEE Signal Processing Magazine,2009,26(1):98117.
[131] Liu Z, Lagani re. Phase congruence measurement for image similarity assessment [J].Pattern Recognition Letters,2007,28:166–172.
[132] Zhang L, Zhang L, Mou X, et al. FSIM: A Feature similarity index for image qualityassessment [J]. IEEE Transactions on Image Processing,2011,20(8):2378-2386.
[133] Hargrove L J, Scheme E J, Englehart K B, et al. Multiple binary classifications vialinear discriminant analysis for improved controllability of a powered prosthesis [J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2010,18(1):49-57.
[134] Lee D, Cognition S H. The manifold ways of perception [J]. Science,2000,290(5500):2268-2269.
[135] Tenenbaum J B, Silvam V D, Langford J C. A global geometric framework fornonlinear dimensionality reduction [J]. Science,2000,290(5500):2319-2323.
[136] Belkin M, Niyogi P. Laplacian eigenmaps for dimensionality reduction and datarepresentation [J]. Neural Computation,2003,15(6):1373-1396.
[137] Zhang Z, Zha H. Principal manifolds and nonlinear dimension reduction via localtangent space alignment [J]. SIAM Joumal of Scientific Computing,2004,26(l):313-338.
[138] Silva V, Tenenbaum J B. Global versus local methods in nonlinear dimensionalityreduction [J]. Advances in Neural Information Processing Systems,2002,15:705-712.
[139]黄启宏.流形学方法理论研究及图像中应用[D].成都:电子科技大学博士学位论文,2007.
[140] Demirel H, Anbarjafari G. Image resolution enhancement by using discrete andstationary wavelet decomposition [J]. IEEE Transactions on Image Processing,2011,20(5):1458-1460.
[141] Gao W, Cao B, Shan S, et al. The CAS-PEAL large-scale Chinese face database andbaseline evaluations [J]. IEEE Transactions on System Man, and Cybernetics (Part A),2008,38(1):149-161.
[142] Bruckstein A M, Donoho D L, Elad M. From sparse solutions of systems of equations tosparse modeling of signals and images [J]. SIAM Review,2009,51(1):34-81.
[143] Elad M, Starck J L, Querre P, et al. Simultaneous cartoon and texture image inpaintingusing morphological component analysis (MCA)[J]. Applied Computational HarmonicAnalysis,2005,19(3):340-358.
[144] Elad M, Aharon M. Image denoising via sparse and redundant representations overlearned dictionaries [J]. IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[145] Bryt O, Elad M. Compression of facial images using the K-SVD algorithm [J]. Journalof Visual Communication and Image Representation,2008,19(4):270-283.
[146] Rubinstein R, Bruckstein A M, Elad M. Dictionaries for sparse representation modeling[J]. Proceedings of the IEEE,2010,98(6):1045-1057.
[147] Selesnick I W, Baraniuk R G, Kingsbury N C. The dual-tree complex wavelet transform[J]. IEEE Signal Processing Magazine,2005,22(6):123-151.
[148] Do M N, Vetterli M. The contourlet transform: an efficient directional multiresolutionimage representation [J]. IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[149] Le Pennec E, Mallat S. Sparse geometric image representations with bandelets [J].IEEE Transactions on Image Processing,2005,14(4):423-438.
[150] Rubinstein R, Zibulevsky M, Elad M. Double sparsity: Learning sparse dictionaries forsparse signal approximation [J]. IEEE Transactions on Signal Processing,2010,58(3):1553-1564.
[151] Ophir B, Lustig M, Elad M. Multi-scale dictionary learning using wavelets [J]. IEEEJournal of Selected Topics in Signal Processing,2011,5(5):1014-1024.
[156] Mallat S G, Zhang Z. Matching pursuits with time-frequency dictionaries [J]. IEEETransactions on Signal Processing,1993,41(12):3397-3415.
[152] Morrone M C, Owens R A. Feature detection from local energy [J]. Pattern RecognitionLetters,1987,6(5):303-313.
[153] Kovesi P. Phase congruency: A low-level image invariant [J]. Psychological research,2000,64(2):136-148.
[154] Buades A, Coll B, Morel J M. A non-local algorithm for image denoising [C]. IEEEComputer Society Conference on Computer Vision and Pattern Recognition,2005,2:60-65.
[155] Wong A, Orchard J. A nonlocal-means approach to exemplar-based inpainting [C].IEEE International Conference on Image Processing,2008:2600-2603.
[156] Zhang X, Burger M, Bresson X, et al. Bregmanized nonlocal regularization fordeconvolution and sparse reconstruction [J]. SIAM Journal on Imaging Sciences,2010,3(3):253-276.
[157] Mairal J, Bach F, Ponce J, et al. Non-local sparse models for image restoration[C].IEEE12th International Conference on Computer Vision,2009:2272-2279.