基于学习的人脸图像超分辨率重构算法的研究
|
摘要
人脸研究一直是计算机视觉、模式识别和计算机图形学领域中的热点研究问题之一。目前,通过监视器得到的人脸图像分辨率不高,以至于给人脸识别和跟踪等后续应用带来很大的困难。超分辨率图像重构(Super Resolution,SR)技术是一种基于信号处理技术来获得高分辨率图像的方法。SR技术的基本思想是,以若干模糊、有噪、频谱混叠的低分辨率(Low Resolution,LR)图像为输入,通过信号处理技术融合成一幅高分辨率(High Resolution,HR)图像。超分辨率图像重构技术在人脸或对象识别、遥感图像、视频监控、医学图像处理等领域都有着广泛的应用。
本文主要研究单幅人脸图像的超分辨率重构技术,目标是提出一种更有效、实时性更好的算法来获得高分辨率图像。首先,本文全面回顾和评述了超分辨率图像重构技术的概念,基本方法和SR算法。在此基础上重点研究基于学习的图像SR算法。本文采用马尔可夫网络(MN)模型提出了一个新的框架描述重构机制。本文提出的算法采用对图像块搜索操作进行位置限制和检查图像分块间重叠区域水平兼容性的思想,降低了搜索的复杂度,提高了匹配相关性,加快了马尔可夫网络收敛,简化了隐层节点的计算。最后采用样本拼镶技术直接输出超分辨率图像。实验平台由VC++编程实现,实验中所用的人脸图像训练集采用24位灰度图像。实验结果证实本文提出的算法具有输出质量好、效率更高等特点,有一定的的实用价值。
本文试图发展性能更好、更智能化的学习算法为以人脸图像为主的应用带来新机遇,并推动超分辨率技术自身的发展。
Research efforts in face processing always is one of a hot spot research questions which in the computer vision, the pattern recognition and in computer graphics domain. Nowadays, the human face image resolution which obtains through the monitoring device is not high, the human face recognition and the track and so on the following application brings the very great difficulty for the human. The Supper Resolution (SR)technology is one kind method obtains the high resolution(HR)image based on the signal processing technology . The basic idea behind SR is the fusion of a sequence of low-resolution noisy blurred images to produce a higher-resolution image based on the signal processing technology. The SR in human face research, long-distance image remote sensing, video frequency monitoring, and medicine domains and so on has the very good application.
We mainly study the single face image super resolution techniques with the goal aiming at an algorithm which is more simple, practical and suitable for real-time applications. First, this article comprehensively reviewed and narrated and commented the SR technology concept, essential method and SR algorithm. In this foundation key research based on study image SR algorithm. This article used Markov network (MN) model to propose a new Baye (MAP) frame description restructuring mechanism. We propose a novel algorithm that uses the location-restraint operation and uses the most compatible neighboring patches along horizontal dimension of the face to directly mosaic the high-resolution patches into the outcome. This can reduce the search order of complexity, enhance the match relevance, speed up Markov network restraining, and simplify the implicit strata node computation. The tests platform by the VC++ programming developmented, the human face image training sets which in the experiment uses 24 gradation images. The experimental result confirmed this article proposed the algorithm has the output quality well, an efficiency more higher characteristic, has certain practical value.
本文主要研究单幅人脸图像的超分辨率重构技术,目标是提出一种更有效、实时性更好的算法来获得高分辨率图像。首先,本文全面回顾和评述了超分辨率图像重构技术的概念,基本方法和SR算法。在此基础上重点研究基于学习的图像SR算法。本文采用马尔可夫网络(MN)模型提出了一个新的框架描述重构机制。本文提出的算法采用对图像块搜索操作进行位置限制和检查图像分块间重叠区域水平兼容性的思想,降低了搜索的复杂度,提高了匹配相关性,加快了马尔可夫网络收敛,简化了隐层节点的计算。最后采用样本拼镶技术直接输出超分辨率图像。实验平台由VC++编程实现,实验中所用的人脸图像训练集采用24位灰度图像。实验结果证实本文提出的算法具有输出质量好、效率更高等特点,有一定的的实用价值。
本文试图发展性能更好、更智能化的学习算法为以人脸图像为主的应用带来新机遇,并推动超分辨率技术自身的发展。
Research efforts in face processing always is one of a hot spot research questions which in the computer vision, the pattern recognition and in computer graphics domain. Nowadays, the human face image resolution which obtains through the monitoring device is not high, the human face recognition and the track and so on the following application brings the very great difficulty for the human. The Supper Resolution (SR)technology is one kind method obtains the high resolution(HR)image based on the signal processing technology . The basic idea behind SR is the fusion of a sequence of low-resolution noisy blurred images to produce a higher-resolution image based on the signal processing technology. The SR in human face research, long-distance image remote sensing, video frequency monitoring, and medicine domains and so on has the very good application.
We mainly study the single face image super resolution techniques with the goal aiming at an algorithm which is more simple, practical and suitable for real-time applications. First, this article comprehensively reviewed and narrated and commented the SR technology concept, essential method and SR algorithm. In this foundation key research based on study image SR algorithm. This article used Markov network (MN) model to propose a new Baye (MAP) frame description restructuring mechanism. We propose a novel algorithm that uses the location-restraint operation and uses the most compatible neighboring patches along horizontal dimension of the face to directly mosaic the high-resolution patches into the outcome. This can reduce the search order of complexity, enhance the match relevance, speed up Markov network restraining, and simplify the implicit strata node computation. The tests platform by the VC++ programming developmented, the human face image training sets which in the experiment uses 24 gradation images. The experimental result confirmed this article proposed the algorithm has the output quality well, an efficiency more higher characteristic, has certain practical value.
引文
[1]Sung Cheol Park,Min Kyu Park,and Moon Gi Kang."Super-Resolution Image Reconstruction:A Technical Overview".IEEE Signal Processing Magazine,pp:21-36,May 2003
[2]Sina Farsiu,Dirk Robinson,Michael Elad,Peyman Milanfar."Advances and Challenges in Super-Resolution".International Journal of Imaging Systems and Technology,vol.14,no.2,pp.47-57,July 2004
[3]Sung Cheol Park,Min Kyu Park,and Moon Gi Kang."Super-Resolution Image Reconstruction:A Technical Overview".IEEE Signal Processing Magazine,pp:21-36,May 2003
[4]张新明,沈兰荪.超分辨率复原技术的发展.测控技术,2002,21(5):33-35
[5]R.Y.Tsai and T.S.Huang,"Multipleframe image restoration and registration[C],"T.S.Huang and R.Tsai."Multi-Frame Image Restoration and Registration".Advances in Computer Vision and Image Processing,vol.1,pp.317-339,1984
[6]P.Kim,N.K.Bose,and H.M.Valenzuela,"Recursive reconstruction of high Resolution image from noisy undersampled multiframes[J],"Trans.on Acoust.,Speech,Singal Processing,vol.38,pp.1013-1027,June1990
[7]P.Kim and W.Y.Su,"Recursive high-resolution reconstruction of blurred multiframe images[J],"IEEE Trans.on Image Processing,vol.2,pp.534-539,Oct.1993
[8]Simon Baker and Takeo Kanade."Limits on Super-Resolution and How to Break Them".IEEE Transactions on Pattern Analysis and Machine Intelligence,Vol.24,NO.9,pp.1167-1183,September 2002
[9]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.软件学报,2003,14(6):1075-1081
[10]Sina Farsiu,M.Dirk Robinson,Michael Elad and Peyman Milanfar,Fast and Robust Multi-frame Super Resolution,IEEE Transaction on Image Processing,2004,Vol.13,NO.10:1327-1344
[11]孟庆武.预估计混叠度的MAP超分辨率处理算法.软件学报,2004,15(2):207-214
[12]Michael Elad and Dmitry Datsenko."Example-Based Regularization Deployed to Super-Resolution Reconstruction of a Single Image".The Computer Journal, Access published online on April 20,2007
[13]William T.Freeman,Thouis R.Jones and Egon C.Pasztor."Example-Based Super-Resolution".IEEE Computer Graphics and Applications,pp.56-65,March/April 2002.
[14]黄丽.基于学习的图像超分辨率技术:[硕士学位论文].杭州:浙江大学,2004
[15]苏从勇.人脸感知:基于学习的人脸跟踪与合成:[博士学位论文].杭州:浙江大学,2005
[16]William T.Freeman,Thouis R.Jones and Egon C.Pasztor."Example-Based Super-Resolution".IEEE Computer Graphics and Applications,pp.56-65,March/April 2002.
[17]Michael Elad and Dmitry Datsenko."Example-Based Regularization Deployed to Super-Resolution Reconstruction of a Single Image".The Computer Journal,Access published online on April 20,2007.
[18]M.V.Joshi,S.Chaudhuri,and R.Panuganti."A learning-based method for image superresolution from zoomed observations".IEEE Transactions on Systems,Man,and Cybernetics,Part B,35(3),pp.527-537,2005.
[19]A.Hertzmann,C.E.Jacobs,N.Oliver,B.Curless,and D.H.Salesin."Image analogies".Proceedings of SIGGRAPH 2001,August 2001.
[20]刘欢喜.图像人脸检测及超分辨率处理:[硕士学位论文].上海:上海交通大学,2008
[21]A.J.den Dekker,A.van den Bos,Resolution:a survey[J],Journal of the Optical Society of America A.Vol.14(3):547-557.
[22]Tasso R.M.Sales and G.M.Morris,"Fundamental limits of optical superresolution",Optics Letters,vol.22,Issue 9,pp.582-584.
[23]S.Borman and R.L.Stevenson."Spatial Resolution Enhancement of Low-Resolution Image Sequences:A Comprehensive Review with Directions for Future Research".Technical report,Univ.of Notre Dame,1998.
[24]S.P.Kim,N.K.Bose,H.M.Valenzuela,"Recursive reconstruction of high resolution image from noisy undersampled multiframes".IEEE Trans.on Acoustics,Speech,and Signal Processing,vol.38,no.6,1990.
[25]Richard R.Schultz,Robert L.Stevenson,"Extraction of high-resolution frames from video sequences".IEEE Trans.on Image Processing,vol.5,no.6,June 1996.
[26]R.C.Hardie,K.J.Barnard,and E.Armstrong,"Joint MAP registration and high-resolution image estimation using a sequence of undersampled images".IEEE Trans.on Image Processing,vol.6,no.12,Dec.1997.
[27]R.C.Hardie,T.R.Tuinstra,J.Bognar,K.J.Barnard,and E.Armstrong,"High resolution image reconstruction from digital video with global and non-global scene motion".Proc.of the IEEE International Conference on Image Processing,vol.Ⅰ,Oct.1997.
[28]Michael Elad,Arie Feuer,"Super-resolution reconstruction of image sequences".IEEE Trans.On Pattern Analysis and Machine Intelligence(PAMI),vol.21,no.9,September 1999
[29]Michal Irani,Shmuel Peleg,"Improving resolution by image registration".CVGIP:Graphical Models and Image Processing,vol.53,no.3,May 1991.
[30]Michal Irani,Shmuel Peleg,"Motion analysis for image enhancement:resolution,occlusion,and transparency".Journal of Visual Communications and Image Representation,vol.4,Dec.1993.
[31]N.R.Shah and A.Zakhor,"Multiframe spatial resolution enhancement of color video".Proc.of the IEEE Intl.Conference on Image Processing,vol.I,Sep.1996.
[32]M.Irani and S.Peleg,"Motion analysis for image enhancement resolution,occlusion,and transparency[J]," J.Visual Commun.Image Represent,vol.4,pp.324-335,Dec.1993.
[33]MannandR.W.Pieard,"Vitual bellows from video[C]," in Proc.Int.Conf.on Image Processing,Austin,TX,1994,pp.13-16
[34]洪功义,姜昱明等.超分辨率图像重构算法的研究.微电子学与计算机,2004,21(4):84-87
[35]N.Nguyen and P.Milanfar,"An efficient wavelet-based algorithm for image superresolution[C],".in Proc.Int.Conf.on Image Processing,vol.2,2000,pp.351-354
[36]M.S.Alam,J.G.Bognar,R.C.Hardie,and B.J.Yasuda,"Infrared image registration and high-resolution reconstruction using multiple translationally shifted aliased video frames[J]," IEEE Trans.on Instrum.Meas.,vol.49,pp.915-923,Oct.2000.
[37]B.C.Tom and A.K.Katsaggelos "An iterative algorithm for improving the resolution of video sequences[C]," in Proc.1996 SPIE Conf.on Visual Communications and Image Processing,Orlando,FL,pp.1430-1438,Mar.1996.
[38]A.J. Patti, M.I. Sezan, and A.M. Tekalp, "Super resolution video reconstruction with arbitrary sampling lattices and nonzero aperture time [J]," IEEE Trans. on Image Processing, vol. 6, no. 8, pp. 1064-1076, Aug. 1997.
[39]P.E. Eren, M.I. Sezan, and A.M. Tekalp, "Robust, object-based high- resolution image reconstruction from low-resolution video [J]," IEEE Trans. on Image Processing, vol. 6, no. 10, pp. 1446-1451,Oct. 1997.
[40] A.J. Patti and Y. Altunbasak, "Artifact reduction for set theoretic super resolution image reconstruction with edge adaptive constraints and higher-order interpolants [J],"IEEE Trans. on Image Processing, vol. 10, no. 1, pp.179-186, Jan. 2001
[41]R.R. Schulz and R.L. Stevenson, "Extraction of high-resolution frames from video sequences [J]," IEEE Trans. on Image Processing, vol. 5, pp. 996-1011,1996.
[42]R.C. Hardie, K.J. Barnard, and E.E. Armstrong, "Joint MAP registration and high-resolution image estimation using a sequence of undersampled images [J],"IEEE Traps. on Image Processing, vol. 6, up. 1621-1633,1997.
[43]M. Elad and A. Feuer, "Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images [J]," IEEE Trans. on Image Processing, vol. 6, no. 12, pp. 1646-1658, 1997.
[44]M. Elad and A. Feuer, "Superresolution restoration of an image sequence:adaptive filtering approach [J],". IEEE Trans. on Image Processing, vol. 8, pp.387-395, 1999.
[45]M. Elad and A. Feuer, "Super-resolution reconstruction of image sequences[J],"IEEE Trans. on Pattern Anal. Machine Inteli, vol. 21, no. 9, pp. 817- 834, 1999.
[46]M.C.Hong, M.G. Kang, and A.K. Katsaggelos, "An iterative weighted regularized algorithm for improving the resolution of video sequences [C]," in Proc. Int. Conf.on Image Processing, vol. 2, pp. 474-477,1997.
[47]M.G. Kang,"Generalized multichannel image deconvolution approach and its applications[J]," Opt. Eng., vol. 37, no. 11, pp. 2953-2964, 1998
[48]N.K. Bose, S. Lertrattanapanich, and J. Koo, "Advances in superresolution using L-curve [C]," in Proc. Int. on Symp. Circuits and Systems, vol.2, pp.433-436,2001
[49]M.K. Ng, N.K. Bose and J. Koo, "Constrained Total Least Squares Computations for High-Resolution Image Reconstruction With Multisensors," Journal of Imaging Science and Technology, John Wiley and Sons, Inc., vol. 12, no. 1, pp. 35-42,2002
[50]S.Baker and T.Kanade,"Hallucinating Faces[R]," CMU-RI-TR-99-32,Robotics Institute,Carnegie Melton University,Tech.Rep 1999
[51]W.T.Freeman,E.C.Pasztor,and O.T.Carmichael."Learning low-level vision".International Journal on Computer Vision,40(1):25-47,2000
[52]A.Hertzmann,C.E.Jacobs,N.Oliver,B.Curless,and D.H.Salesin."Image analogies".Proceedings of SIGGRAPH 2001,August 2001
[53]C.Liu,H.Y.Shum,and C.S.Zhang,"A two-step approach to hallucinating faces:Global parametric model and local nonparametric model[C]," In Computer Vision and Pattern Recognition,vol.1,pp.192-198,2001
[54]B.K.Gunturk,A.U.Batur,Y.Altunbasak,M.H.Ⅲ Hayes,and R.M.Mersereau,"Eigenface-based super-resolution for face recognition[C]," in Proc.2002 Int.Conf.on Image Processing,vol.2,pp.845-848,2002
[55]B.K.Gunturk,A.U.Batur,Y.Altunbasak,M.H.,Ⅲ Hayes,and R.M.Mersereau,"Eigenface-domain super-resolution for face recognition[J]," IEEE Trans.an Image Processing,vol.12,no.5,pp.597-606,2003
[56]X.G.Wang,X.O.Tang,"Hallucinating face by eigentransformation[J]",IEEE Trans.on Systems,Man and Cybernetics Part C:Applications and Reviews,vol.35,no.3,pp.425-34,2005
[57]David Capel and Andrew Zisserman."Super-resolution from multiple views using learnt image models".In Proc.CVPR,2001
[58]Todd A.Stephenson and Tsuhan Chen."Adaptive Markov Random Fields for Example-Based Super-resolution of faces".EURASIP Journal on Applied Signal Processing,vol.2006,Article ID 31062,11 pages,doi:10.1155/ASP/2006/31062,2006
[59]Yueting Zhuang,Congyong Su,Li Huang,Fei Wu."Subdivision Feedback Based 3D Facial Modeling for E-Learning" Lecture Notes in computer science.Vol:2783/2003,pp.218-229,Aug.,2003
[60]Min Chen,Guoping Qiu and Kin-Man Lam,Example Selective and Order Independent Learning-based Image Super-resolution,Processing of 2005International Symposium on Intelligent Signal Processing and Communication Systems,Dec.2005,Hong Kong:77-80
[61]黄华,樊鑫等.基于识别的凸集投影人脸图像超分辨率重建.计算机研究与发展,2005,42(10):1718-1725
[62]Geman S.,Geman D. "Stochastic Relax ation,Gibbs Distributions,and the Bayesian Restoration of Images [J] ".IEEE Trans on PAMI,1984,6(6):721-741.
[63]Besag J. "On the statistical analysis of dirty pictures [J] ". J R Statist Soc B, 1986,48(3):259-302.
[64]Chambolle A., "Nonlinear Wavelet Image Processing: Variational Problems,Compression, and Noise Removal Through Wavelet Shrinkage[J] ". IEEE Trans on Image Processing, 1998,(7):319-335.
[2]Sina Farsiu,Dirk Robinson,Michael Elad,Peyman Milanfar."Advances and Challenges in Super-Resolution".International Journal of Imaging Systems and Technology,vol.14,no.2,pp.47-57,July 2004
[3]Sung Cheol Park,Min Kyu Park,and Moon Gi Kang."Super-Resolution Image Reconstruction:A Technical Overview".IEEE Signal Processing Magazine,pp:21-36,May 2003
[4]张新明,沈兰荪.超分辨率复原技术的发展.测控技术,2002,21(5):33-35
[5]R.Y.Tsai and T.S.Huang,"Multipleframe image restoration and registration[C],"T.S.Huang and R.Tsai."Multi-Frame Image Restoration and Registration".Advances in Computer Vision and Image Processing,vol.1,pp.317-339,1984
[6]P.Kim,N.K.Bose,and H.M.Valenzuela,"Recursive reconstruction of high Resolution image from noisy undersampled multiframes[J],"Trans.on Acoust.,Speech,Singal Processing,vol.38,pp.1013-1027,June1990
[7]P.Kim and W.Y.Su,"Recursive high-resolution reconstruction of blurred multiframe images[J],"IEEE Trans.on Image Processing,vol.2,pp.534-539,Oct.1993
[8]Simon Baker and Takeo Kanade."Limits on Super-Resolution and How to Break Them".IEEE Transactions on Pattern Analysis and Machine Intelligence,Vol.24,NO.9,pp.1167-1183,September 2002
[9]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.软件学报,2003,14(6):1075-1081
[10]Sina Farsiu,M.Dirk Robinson,Michael Elad and Peyman Milanfar,Fast and Robust Multi-frame Super Resolution,IEEE Transaction on Image Processing,2004,Vol.13,NO.10:1327-1344
[11]孟庆武.预估计混叠度的MAP超分辨率处理算法.软件学报,2004,15(2):207-214
[12]Michael Elad and Dmitry Datsenko."Example-Based Regularization Deployed to Super-Resolution Reconstruction of a Single Image".The Computer Journal, Access published online on April 20,2007
[13]William T.Freeman,Thouis R.Jones and Egon C.Pasztor."Example-Based Super-Resolution".IEEE Computer Graphics and Applications,pp.56-65,March/April 2002.
[14]黄丽.基于学习的图像超分辨率技术:[硕士学位论文].杭州:浙江大学,2004
[15]苏从勇.人脸感知:基于学习的人脸跟踪与合成:[博士学位论文].杭州:浙江大学,2005
[16]William T.Freeman,Thouis R.Jones and Egon C.Pasztor."Example-Based Super-Resolution".IEEE Computer Graphics and Applications,pp.56-65,March/April 2002.
[17]Michael Elad and Dmitry Datsenko."Example-Based Regularization Deployed to Super-Resolution Reconstruction of a Single Image".The Computer Journal,Access published online on April 20,2007.
[18]M.V.Joshi,S.Chaudhuri,and R.Panuganti."A learning-based method for image superresolution from zoomed observations".IEEE Transactions on Systems,Man,and Cybernetics,Part B,35(3),pp.527-537,2005.
[19]A.Hertzmann,C.E.Jacobs,N.Oliver,B.Curless,and D.H.Salesin."Image analogies".Proceedings of SIGGRAPH 2001,August 2001.
[20]刘欢喜.图像人脸检测及超分辨率处理:[硕士学位论文].上海:上海交通大学,2008
[21]A.J.den Dekker,A.van den Bos,Resolution:a survey[J],Journal of the Optical Society of America A.Vol.14(3):547-557.
[22]Tasso R.M.Sales and G.M.Morris,"Fundamental limits of optical superresolution",Optics Letters,vol.22,Issue 9,pp.582-584.
[23]S.Borman and R.L.Stevenson."Spatial Resolution Enhancement of Low-Resolution Image Sequences:A Comprehensive Review with Directions for Future Research".Technical report,Univ.of Notre Dame,1998.
[24]S.P.Kim,N.K.Bose,H.M.Valenzuela,"Recursive reconstruction of high resolution image from noisy undersampled multiframes".IEEE Trans.on Acoustics,Speech,and Signal Processing,vol.38,no.6,1990.
[25]Richard R.Schultz,Robert L.Stevenson,"Extraction of high-resolution frames from video sequences".IEEE Trans.on Image Processing,vol.5,no.6,June 1996.
[26]R.C.Hardie,K.J.Barnard,and E.Armstrong,"Joint MAP registration and high-resolution image estimation using a sequence of undersampled images".IEEE Trans.on Image Processing,vol.6,no.12,Dec.1997.
[27]R.C.Hardie,T.R.Tuinstra,J.Bognar,K.J.Barnard,and E.Armstrong,"High resolution image reconstruction from digital video with global and non-global scene motion".Proc.of the IEEE International Conference on Image Processing,vol.Ⅰ,Oct.1997.
[28]Michael Elad,Arie Feuer,"Super-resolution reconstruction of image sequences".IEEE Trans.On Pattern Analysis and Machine Intelligence(PAMI),vol.21,no.9,September 1999
[29]Michal Irani,Shmuel Peleg,"Improving resolution by image registration".CVGIP:Graphical Models and Image Processing,vol.53,no.3,May 1991.
[30]Michal Irani,Shmuel Peleg,"Motion analysis for image enhancement:resolution,occlusion,and transparency".Journal of Visual Communications and Image Representation,vol.4,Dec.1993.
[31]N.R.Shah and A.Zakhor,"Multiframe spatial resolution enhancement of color video".Proc.of the IEEE Intl.Conference on Image Processing,vol.I,Sep.1996.
[32]M.Irani and S.Peleg,"Motion analysis for image enhancement resolution,occlusion,and transparency[J]," J.Visual Commun.Image Represent,vol.4,pp.324-335,Dec.1993.
[33]MannandR.W.Pieard,"Vitual bellows from video[C]," in Proc.Int.Conf.on Image Processing,Austin,TX,1994,pp.13-16
[34]洪功义,姜昱明等.超分辨率图像重构算法的研究.微电子学与计算机,2004,21(4):84-87
[35]N.Nguyen and P.Milanfar,"An efficient wavelet-based algorithm for image superresolution[C],".in Proc.Int.Conf.on Image Processing,vol.2,2000,pp.351-354
[36]M.S.Alam,J.G.Bognar,R.C.Hardie,and B.J.Yasuda,"Infrared image registration and high-resolution reconstruction using multiple translationally shifted aliased video frames[J]," IEEE Trans.on Instrum.Meas.,vol.49,pp.915-923,Oct.2000.
[37]B.C.Tom and A.K.Katsaggelos "An iterative algorithm for improving the resolution of video sequences[C]," in Proc.1996 SPIE Conf.on Visual Communications and Image Processing,Orlando,FL,pp.1430-1438,Mar.1996.
[38]A.J. Patti, M.I. Sezan, and A.M. Tekalp, "Super resolution video reconstruction with arbitrary sampling lattices and nonzero aperture time [J]," IEEE Trans. on Image Processing, vol. 6, no. 8, pp. 1064-1076, Aug. 1997.
[39]P.E. Eren, M.I. Sezan, and A.M. Tekalp, "Robust, object-based high- resolution image reconstruction from low-resolution video [J]," IEEE Trans. on Image Processing, vol. 6, no. 10, pp. 1446-1451,Oct. 1997.
[40] A.J. Patti and Y. Altunbasak, "Artifact reduction for set theoretic super resolution image reconstruction with edge adaptive constraints and higher-order interpolants [J],"IEEE Trans. on Image Processing, vol. 10, no. 1, pp.179-186, Jan. 2001
[41]R.R. Schulz and R.L. Stevenson, "Extraction of high-resolution frames from video sequences [J]," IEEE Trans. on Image Processing, vol. 5, pp. 996-1011,1996.
[42]R.C. Hardie, K.J. Barnard, and E.E. Armstrong, "Joint MAP registration and high-resolution image estimation using a sequence of undersampled images [J],"IEEE Traps. on Image Processing, vol. 6, up. 1621-1633,1997.
[43]M. Elad and A. Feuer, "Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images [J]," IEEE Trans. on Image Processing, vol. 6, no. 12, pp. 1646-1658, 1997.
[44]M. Elad and A. Feuer, "Superresolution restoration of an image sequence:adaptive filtering approach [J],". IEEE Trans. on Image Processing, vol. 8, pp.387-395, 1999.
[45]M. Elad and A. Feuer, "Super-resolution reconstruction of image sequences[J],"IEEE Trans. on Pattern Anal. Machine Inteli, vol. 21, no. 9, pp. 817- 834, 1999.
[46]M.C.Hong, M.G. Kang, and A.K. Katsaggelos, "An iterative weighted regularized algorithm for improving the resolution of video sequences [C]," in Proc. Int. Conf.on Image Processing, vol. 2, pp. 474-477,1997.
[47]M.G. Kang,"Generalized multichannel image deconvolution approach and its applications[J]," Opt. Eng., vol. 37, no. 11, pp. 2953-2964, 1998
[48]N.K. Bose, S. Lertrattanapanich, and J. Koo, "Advances in superresolution using L-curve [C]," in Proc. Int. on Symp. Circuits and Systems, vol.2, pp.433-436,2001
[49]M.K. Ng, N.K. Bose and J. Koo, "Constrained Total Least Squares Computations for High-Resolution Image Reconstruction With Multisensors," Journal of Imaging Science and Technology, John Wiley and Sons, Inc., vol. 12, no. 1, pp. 35-42,2002
[50]S.Baker and T.Kanade,"Hallucinating Faces[R]," CMU-RI-TR-99-32,Robotics Institute,Carnegie Melton University,Tech.Rep 1999
[51]W.T.Freeman,E.C.Pasztor,and O.T.Carmichael."Learning low-level vision".International Journal on Computer Vision,40(1):25-47,2000
[52]A.Hertzmann,C.E.Jacobs,N.Oliver,B.Curless,and D.H.Salesin."Image analogies".Proceedings of SIGGRAPH 2001,August 2001
[53]C.Liu,H.Y.Shum,and C.S.Zhang,"A two-step approach to hallucinating faces:Global parametric model and local nonparametric model[C]," In Computer Vision and Pattern Recognition,vol.1,pp.192-198,2001
[54]B.K.Gunturk,A.U.Batur,Y.Altunbasak,M.H.Ⅲ Hayes,and R.M.Mersereau,"Eigenface-based super-resolution for face recognition[C]," in Proc.2002 Int.Conf.on Image Processing,vol.2,pp.845-848,2002
[55]B.K.Gunturk,A.U.Batur,Y.Altunbasak,M.H.,Ⅲ Hayes,and R.M.Mersereau,"Eigenface-domain super-resolution for face recognition[J]," IEEE Trans.an Image Processing,vol.12,no.5,pp.597-606,2003
[56]X.G.Wang,X.O.Tang,"Hallucinating face by eigentransformation[J]",IEEE Trans.on Systems,Man and Cybernetics Part C:Applications and Reviews,vol.35,no.3,pp.425-34,2005
[57]David Capel and Andrew Zisserman."Super-resolution from multiple views using learnt image models".In Proc.CVPR,2001
[58]Todd A.Stephenson and Tsuhan Chen."Adaptive Markov Random Fields for Example-Based Super-resolution of faces".EURASIP Journal on Applied Signal Processing,vol.2006,Article ID 31062,11 pages,doi:10.1155/ASP/2006/31062,2006
[59]Yueting Zhuang,Congyong Su,Li Huang,Fei Wu."Subdivision Feedback Based 3D Facial Modeling for E-Learning" Lecture Notes in computer science.Vol:2783/2003,pp.218-229,Aug.,2003
[60]Min Chen,Guoping Qiu and Kin-Man Lam,Example Selective and Order Independent Learning-based Image Super-resolution,Processing of 2005International Symposium on Intelligent Signal Processing and Communication Systems,Dec.2005,Hong Kong:77-80
[61]黄华,樊鑫等.基于识别的凸集投影人脸图像超分辨率重建.计算机研究与发展,2005,42(10):1718-1725
[62]Geman S.,Geman D. "Stochastic Relax ation,Gibbs Distributions,and the Bayesian Restoration of Images [J] ".IEEE Trans on PAMI,1984,6(6):721-741.
[63]Besag J. "On the statistical analysis of dirty pictures [J] ". J R Statist Soc B, 1986,48(3):259-302.
[64]Chambolle A., "Nonlinear Wavelet Image Processing: Variational Problems,Compression, and Noise Removal Through Wavelet Shrinkage[J] ". IEEE Trans on Image Processing, 1998,(7):319-335.