基于马尔科夫网络的人脸图像超分辨率算法
|
摘要
超分辨率是一种从低分辨率观测结果中获得高分辨率图像或图像序列的技术。低分辨率等同低频信息,而高分辨率则包含了高、中、低各频带的信息。目前,超分辨率主要有基于重建的技术和基于学习的技术两种方式。现在研究的热点是人脸图像超分辨率合成,即从低分辨率脸部图像中获得高分辨率图像。人脸图像超分辨率合成由Baker和Kanade提出,人脸图像所隐含的高频部分必须被完全构造出来。人脸图像超分辨率合成极具挑战性,因为人们对于脸部非常熟悉。
高分辨率和超高分辨率在多媒体领域应用非常广泛,传统的方法是输入几个低分辨率的图像,然后合成出来一个高分辨率的图像,问题是我们很难获得足够数量的低分辨率图像,所以这种技术应用非常有限。基于学习的超分辨率是依靠先验知识从低分辨率图像中推断丢失细节的算法。最近,在马尔科夫网络领域出现了基于学习的算法,但是大多数的算法获得图像信息的水平仍然很低,最新的研究表明如何提高获取图像信息的水平非常重要,值得深入的研究。我们即从这一点出发,在一些获取图像的技术实例和马尔科夫网络的基础上,研究人脸图像超分辨率合成技术。
在本文中,我们研究的是人脸图像超分辨率技术,或者说基于样本图像和马尔科夫网络的人脸图像超分辨率合成技术。我们构造了一个高分辨率图像的统计模型,并说明如何通过该模型从一个低分辨率输入图像估计高分辨率图像。我们的目标是使超分辨率脸部图像算法更加简单、灵活和适合于实时处理。在标准的马尔科夫网络框架下,采用了一种新颖算法,即采用特定位置抑制算子来增加马尔科夫网络中观测函数的概率值;对于马尔科夫网络中的隐含节点,通过像素颜色特征匹配和特定位置抑制算子选择最接近的k个节点,在这些节点之间采用最一致的周边相容性检查技术,增加马尔科夫网络传递函数的值。在相关的训练使用样本图像并非很精确对齐的情况下,这些技术产生了良好效果。实际上,我们构造一种自适应马尔科夫网络,从而获得一种精确、快速并且较简单,灵活的算法,以适应输入图像的实时处理。本文提出的技术通过了几个实例测试,采用图像数据库进行了相关试验,演示了该算法,表明其有效性。
我们发现块位置的约束机制,能够增加观察函数的概率值。特别是,即使使用一个小的训练数据集,它也有良好的表现,能够寻找到最接近的高频图像块。
The term super-resolution (SR) is used to describe the process of obtaining a high-resolution (HR) image or a sequence of HR images from a set of low-resolution (LR) observations. Low-resolution is equivalent to low-frequency and high-resolution consists of high, middle and low frequency bands. There are in general two classes of super-resolution techniques: reconstruction-based (from input images alone) and learning-based (from other images). Of particular interest is face hallucination (which implies the high-frequency part of face image, must be purely fabricated), or learning high-resolution face images from low-resolution ones. Hallucinating faces is particularly challenging because people are so familiar with faces.
Many multimedia applications rely on high-resolution images. Conventional methods employed several input low-resolution images to reconstruct the output high-resolution image. Since it is difficult to obtain sufficient numbers of input images, the effect of such methods is limited. Learning-based algorithms are popular SR techniques that use application dependent prior to infer the missing details in low resolution images. Learning-based algorithm under the framework of Markov Random Fields is emerging recently and attracts many researchers. However, most of such algorithms learn low-level knowledge about images. Recent researches indicate that learning high-level knowledge is also important and should be investigated further more. We follow this line and study the face image super resolution techniques based on image examples and Markov Network (MN).
In this thesis, we investigate the face image super resolution technique or hallucination based on image examples and Markov Network (MN). We build a statistical model of high-resolution images and show how this model can be used to estimate a high-resolution image from a lower-resolution input image. Our goal is to make the algorithm of SR face images more simple, flexible and suitable for real-time applications. Under the framework of standard MN, we propose a novel algorithm that uses the location-restraint operation to increase the probability value of observation function in MN. For hidden nodes of MN, we use the most compatible neighbouring patches among k closest ones that are selected by combining the pixel colour feature matching and location restraint operation. This can increase the transition function of MN and works very well even under the condition where the alignment of the images in the training dataset is not accurate. By these measures, we generate an adaptive MN. Achieving accurate, fast and a simpler, flexible and suitable algorithm for realtime application of the input images is a critical step in super-resolution processing. Motivated by this basic requirement, the techniques presented in this thesis are tested in practical experiments. We carry out related experiments with the image database and demonstrate the effectiveness and performance of the proposed algorithms. Due to the simplicity of computing MN, our algorithm is practical and suitable for real-time applications. We find that location restraint mechanism can potentially increase the probability value of observation function in MN. Especially, with a small training dataset, it extremely improves the performance of searching the closest patches.
高分辨率和超高分辨率在多媒体领域应用非常广泛,传统的方法是输入几个低分辨率的图像,然后合成出来一个高分辨率的图像,问题是我们很难获得足够数量的低分辨率图像,所以这种技术应用非常有限。基于学习的超分辨率是依靠先验知识从低分辨率图像中推断丢失细节的算法。最近,在马尔科夫网络领域出现了基于学习的算法,但是大多数的算法获得图像信息的水平仍然很低,最新的研究表明如何提高获取图像信息的水平非常重要,值得深入的研究。我们即从这一点出发,在一些获取图像的技术实例和马尔科夫网络的基础上,研究人脸图像超分辨率合成技术。
在本文中,我们研究的是人脸图像超分辨率技术,或者说基于样本图像和马尔科夫网络的人脸图像超分辨率合成技术。我们构造了一个高分辨率图像的统计模型,并说明如何通过该模型从一个低分辨率输入图像估计高分辨率图像。我们的目标是使超分辨率脸部图像算法更加简单、灵活和适合于实时处理。在标准的马尔科夫网络框架下,采用了一种新颖算法,即采用特定位置抑制算子来增加马尔科夫网络中观测函数的概率值;对于马尔科夫网络中的隐含节点,通过像素颜色特征匹配和特定位置抑制算子选择最接近的k个节点,在这些节点之间采用最一致的周边相容性检查技术,增加马尔科夫网络传递函数的值。在相关的训练使用样本图像并非很精确对齐的情况下,这些技术产生了良好效果。实际上,我们构造一种自适应马尔科夫网络,从而获得一种精确、快速并且较简单,灵活的算法,以适应输入图像的实时处理。本文提出的技术通过了几个实例测试,采用图像数据库进行了相关试验,演示了该算法,表明其有效性。
我们发现块位置的约束机制,能够增加观察函数的概率值。特别是,即使使用一个小的训练数据集,它也有良好的表现,能够寻找到最接近的高频图像块。
The term super-resolution (SR) is used to describe the process of obtaining a high-resolution (HR) image or a sequence of HR images from a set of low-resolution (LR) observations. Low-resolution is equivalent to low-frequency and high-resolution consists of high, middle and low frequency bands. There are in general two classes of super-resolution techniques: reconstruction-based (from input images alone) and learning-based (from other images). Of particular interest is face hallucination (which implies the high-frequency part of face image, must be purely fabricated), or learning high-resolution face images from low-resolution ones. Hallucinating faces is particularly challenging because people are so familiar with faces.
Many multimedia applications rely on high-resolution images. Conventional methods employed several input low-resolution images to reconstruct the output high-resolution image. Since it is difficult to obtain sufficient numbers of input images, the effect of such methods is limited. Learning-based algorithms are popular SR techniques that use application dependent prior to infer the missing details in low resolution images. Learning-based algorithm under the framework of Markov Random Fields is emerging recently and attracts many researchers. However, most of such algorithms learn low-level knowledge about images. Recent researches indicate that learning high-level knowledge is also important and should be investigated further more. We follow this line and study the face image super resolution techniques based on image examples and Markov Network (MN).
In this thesis, we investigate the face image super resolution technique or hallucination based on image examples and Markov Network (MN). We build a statistical model of high-resolution images and show how this model can be used to estimate a high-resolution image from a lower-resolution input image. Our goal is to make the algorithm of SR face images more simple, flexible and suitable for real-time applications. Under the framework of standard MN, we propose a novel algorithm that uses the location-restraint operation to increase the probability value of observation function in MN. For hidden nodes of MN, we use the most compatible neighbouring patches among k closest ones that are selected by combining the pixel colour feature matching and location restraint operation. This can increase the transition function of MN and works very well even under the condition where the alignment of the images in the training dataset is not accurate. By these measures, we generate an adaptive MN. Achieving accurate, fast and a simpler, flexible and suitable algorithm for realtime application of the input images is a critical step in super-resolution processing. Motivated by this basic requirement, the techniques presented in this thesis are tested in practical experiments. We carry out related experiments with the image database and demonstrate the effectiveness and performance of the proposed algorithms. Due to the simplicity of computing MN, our algorithm is practical and suitable for real-time applications. We find that location restraint mechanism can potentially increase the probability value of observation function in MN. Especially, with a small training dataset, it extremely improves the performance of searching the closest patches.
引文
[1] A. Hertzmann, C.E. Jacobs, N. Oliver, B. Curless, and D.H. Salesin. "Image analogies". Proceedings of SIGGRAPH 2001, August 2001.
[2] A. J. Patti, M. I. Sezan, and A. M. Tekalp, "High resolution image reconstruction from a low-resolution image sequence in the presence of time-varying motion blur". Proc. of the IEEE International Conference on Image Processing, vol. I,1994.
[3] A. M. Tekalp, M. K. Ozkan, and M. I. Sezan, "High-resolution image reconstruction from lower-resolution image sequences and space-varying image restoration". Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, vol. III, 1992.
[4] A. N. Rajagopalan and S. Chaudhuri, "Space-variant approaches to recovery of depth from defocused images," Computer Vision and Image Understanding, vol.68, no. 3, pp. 309-329, Dec. 1997.
[5] C. Liu, H.-Y. Shum, and W. T. Freeman. Face hallucination: Theory and practice.International Journal of Computer Vision, in press, 2007.
[6] B. K. Gunturk, A. U. Batur, Y. Altunbasak, M. H. Hayes, and R. M. Mersereau,"Eigenface-domain super-resolution for face recognition," IEEE Trans. Image Process., vol. 12, pp. 597-606, 2003.
[7] D. A. Roark, S. E. Barrett, A. J. O'Toole, and H. Abdi. Learning the moves: The effect of familiarity and facial motion on person recognition across large changes in viewing format. Perception, 35:761-773, 2006.
[8] Brian C. Tom, Aggelos T. Katsaggelos, "Reconstruction of a high resolution image from multiple degraded mis-registered low resolution images". SPIE, vol.2308.
[9] C. L. Luengo Hendriks, L. J. van Vliet, "Improving resolution to reduce aliasing in an under-sampled image sequence". SPIE, vol. 3965, Jan. 2000.
[10] C. Liu, H. Y. Shum, and C. S. Zhang. "A two-step approach to hallucinating faces:Global parametric model and local nonparametric model". Proc. IEEE Conf.Computer Vision and Pattern Recognition, pages 192-198, 2001.
[11] D. M. Blackburn, J. M. Bone, and P. J. Phillips, FRVT 2000 Evaluation Report,February 2001.
[12]D.P.Capel and A.Zisserman,"Super-resolution enhancement of text image sequence," in Int.Conf.Pattern Recognit.,Barcelona,Spain,pp.600-605,2000.
[13]David Capel and Andrew Zisserman."Super-resolution from multiple views using learnt image models".In Proc.CVPR,2001.
[14]H.Derin and H.Elliot,"Modeling and segmentation of noisy and textured images using gibbs random fields," IEEE Trans.on Pattern Analysis and Machine Intelligence,vol.9,pp.3-55,1987.
[15]H.Stark and P.Oskoui,"High-resolution image recovery from plane-image arrys,using convex projections".Journal of the Optical Society of America A,vol.6,no.11,1989.
[16]High-resolution image reconstruction from digital video by exploitation of nonglobal motion".SPIE,vol.38,no.5,May 1999.
[17]J.Besag,"Spatial interaction and the statistical analysis of lattice systems,"Journal of Royal Statistical Society,Series B,vol.36,pp.192-236,1974.
[18]J.L.Marroquin,Probabilistic solution of inverse problems,Ph.D.thesis,MIT Al Lab,1985.
[19]H.R.Sheikh and A.C.Bovik.Image information and visual quality.IEEE Transactions on Image Processing,15(2):430-444,2006.
[20]J.P.Makinen,J.Aikio,V.P.Putila,K.Keranen,P.Karioja,T.Kolehmainen,and J.Haavisto.Prototyping of miniature plastic imaging lens.Telescopes and Instrumentation for Solar Astrophysics,Proceeding of SPIE,5178:89-100,2004.
[21]M.Ben-Ezra,A.Zomet,and S.Nayar.Jitter camera:High resolution video from a low resolution detector.In Proceedings of the International Conference on Computer Vision and Pattern Recognition,volume 2,pages 135-142,June 2004.
[22]M.V.Joshi,S.Chaudhuri,and R.Panuganti."A learning-based method for image super-resolution from zoomed observations".IEEE Transactions on Systems,Man,and Cybemetics,Part B,35(3),pp.527-537,2005.
[23]Marc Rumo,Patrick Vandewalle,"Superresolution in images using optical flow and irregular sampling".LCAV—School of Computer and Communication Sciences,2003.
[24]Michael Elad and Arie Feuer,"Restoration of a single super-resolution image from several blurred,noisy and undersampled measured images," IEEE Trans.on Image Processing,vol.6,no.12,pp.1646-1658,December 1997.
[25]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.
[26]Michael Elad,Arie Feuer,"Super-resolution reconstruction of image sequences".IEEE Trans.On Pattem Analysis and Machine Intelligence(PAMI),vol.21,no.9,September 1999.
[27]Michal Irani,Shmuel Peleg,"Improving resolution by image registration".CVGIP:Graphical Models and Image Processing,vol.53,no.3,May 1991.
[28]Michal Irani,Shmuel Peleg,"Motion analysis for image enhancement:resolution,occlusion,and transparency".Journal of Visual Communications and Image Representation,vol.4,Dec.1993.
[29]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.
[30]P.Sinha,B.J.Balas,Y.Ostrovsky,and R.Russell.Face Processing:Advanced Modeling and Methods,chapter Face recognition by humans,pages 257-291.Academic Press,December 2005.
[31]R.C.Hardie,K.J.Barnard,and E.Armstrong,"Joint MAP registration and highresolution image estimation using a sequence of undersampled images".IEEE Trans.on Image Processing,vol.6,no.12,Dec.1997.
[32]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.
[33]R.Kindermann and J.L.Snell,Markov Random Fields and their applications,American Mathematical Society,Providence,RI,1980.
[34]R.R.Schultz and R.L.Stevenson,"A Bayesian approach to image expansion for improved definition," IEEE Trans.on Image Processing,vol.3,no.3,pp.233-242,May 1994.
[35]R.Y.Tsai and T.S.Huang,"Multiple frame image restoration and registration",Advances in Computer Vision and Image Processing,Jai Press Inc.,1984,pp.317-339.
[36]Richard C.Dubes and Anil K.Jain,"Random field models in image analysis,"Journal of Applied Statistics,vol.16,no.2,pp.131-164,1989.
[37]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.
[38]S.Baker and T.Kanade,"Limits on super-resolution and how to break them,"IEEE Trans.Pattern Anal Machine Intell.,vol.24,pp.1167-1183,2002.
[39]S.Baker and T.Kanade.Hallucinating faces.In IEEE International Conference on Automatic Face and Gesture Recognition,March 2000.
[40]S.Borman and R.Stevenson,"Spatial resolution enhancement of low-resolution image sequences.A comprehensive review with directions for future research,"Technical report,Laboratory for Image and Signal Analysis(LISA),University of Notre Dame,Notre Dame,IN,USA,July 1998.
[41]S.Chaudhri,Ed.Super-Resolution Imaging,the Kluwer International Series in Engineering and Computer Science,2002.
[42]S.Chaudhuri and A.N.Rajagopalan,Depth from defocused images:A real aperture imaging approach,Springer-Verlag,New York,1999.
[43]S.Geman and D.Geman,"Stochastic relaxation,Gibbs distribution and the Bayesian restoration of image," IEEE Trans.on Pattem Analysis and Machine Intelligence,vol.6,no.6,pp.721-741,1984.
[44]K.Jia and S.Gong.Hallucinating multiple occluded face images of different resolutions.Pattern Recognition Letters,27:1768-1775,November 2006.
[45]S.Kleinfelder,S.Lim,X.Liu,and A.E.Gamal.A 10,000 frames/s CMOS digital pixel sensor.IEEE Journal of Solid-State Circuits,36(12):2049-2059,December 2001.
[46]S.Krishnamachari and Rama Chellappa,"Multiresolution gaussmarkov random field models for texture segmentation," IEEE Trans.on Image Processing,vol.6,no.2,pp.251-266,February 1997.
[47]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.
[48]S.P.Kim,N.K.Bose,H.M.Valenzuela,"Recursive total least squares algorithm for image reconstruction from noisy,undersampled multiframes".Multidimensional Systems and Signal Processing,vol.4,no.3,July 1993.
[49]R.Gross,I.Matthews,and S.Baker.Generic vs.person specific active appearance models.Image and Vision Computing,23(11):1080-1093,2005.
[50]S.Z.Li,Markov Random Field Modelling in Computer Vision,Springer-Verlag,Tokyo,1995.
[51]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.
[52]Sina Farsiu,M.Dirk Robinson,Michael Elad,and Peyman Milanfar,"Fast and robust multiframe super resolution".IEEE Trans.on Image Processing,vol.13,no.10,Oct.2004.
[53]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.
[54]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.
[55]Tasso R.M.Sales and G.M.Morris,"Fundamental limits of optical superresolution",Optics Letters,vol.22,Issue 9,pp.582-584.
[56]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.
[57]K.Jia and S.Gong.Multi-modal tensor face for simultaneous super-resolution and recognition.Proceedings of the IEEE International Conference on Computer Vision(ICCV),2:1683-1690,2005.ISSN 1550-5499.
[58]W.T.Freeman,E.C.Pasztor,and O.T.Carmichael."Learning low-level vision".International Journal on Computer Vision,40(1):25-47,2000.
[59]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.
[60]http://www.wisdom.weizmann.ac.il/～borise/hierarchies/images/faces/faces.htm
[61]M.Elad and Y.Hel-Or,"A fast super-resolution reconstruction algorithm for pure translational motion and common space invariant blur," IEEE Transactions on Image Processing,vol.10,no.8,pp.1187-1193,2001.
[62]C.M.Bishop,A.Blake,and B.Marthi.Super-resolution Enhancement of Video.In C.M.Bishop and B.Frey(Eds.),Proc.Artificial Intelligence and Statistics.Society for Artificial Intelligence and Statistics,2003.
[63] W. Liu, D. Lin, and X. Tang. Hallucinating Faces: TensorPatch Super-resolution and Coupled Residue Compensation. Proc. Computer Vision and Pattern Recognition, pp. II 478-484, 2005.
[64] L.C. Pickup, S.J. Roberts, and A. Zisserman. A Sample Texture Prior for Image Superresolution. Advances in Neural Information Processing Systems, pp. 1587-1594,2003.
[65] J. Sun, H. Tao, and H.-Y. Shum. Image Hallucination with Primal Sketch Priors, Proc. Computer Vision and Pattern Recognition, pp. II 729-736, 2003.
[66] V.N. Vapnik. Statistical Learning Theory. John Wiley & Sons, Inc., 1998.
[67] X. Wang and X. Tang. Hallucinating Face by Eigentransformation. IEEE Trans.Systems, Man, and Cybernetics, Part C, vol. 35, no. 3, pp. 425-434, 2005.
[68] J.S. De Bonet. Multiresolution sampling procedure for analysis and synthesis of texture images. In Computer Graphics Proceedings, Annual Conference Series,(SIGGRAPH '97), pages 361-368, 1997.
[69] X. Liu, P. H. Tu, and F. W. Wheeler. Face model fitting on low resolution images.In Proceedings of the British Machine Vision Conference (BMVC), 2006.
[70] P.J. Burt and E.H. Adelson. The Laplacian pyramid as a compact image code.IEEE Transactions on Communiations, 31(4):532-540, April 1983.
[71] Y.-L Tian, T. Kanade, and J. Conn. Facial expression analysis. In S. Z. Li and A.K. Jain, editors, Handbook of face recognition. Springer, 2005.
[72] Programming Windows, 5th edition, by Charles Petzold, Microsoft Press, 1998
[2] A. J. Patti, M. I. Sezan, and A. M. Tekalp, "High resolution image reconstruction from a low-resolution image sequence in the presence of time-varying motion blur". Proc. of the IEEE International Conference on Image Processing, vol. I,1994.
[3] A. M. Tekalp, M. K. Ozkan, and M. I. Sezan, "High-resolution image reconstruction from lower-resolution image sequences and space-varying image restoration". Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, vol. III, 1992.
[4] A. N. Rajagopalan and S. Chaudhuri, "Space-variant approaches to recovery of depth from defocused images," Computer Vision and Image Understanding, vol.68, no. 3, pp. 309-329, Dec. 1997.
[5] C. Liu, H.-Y. Shum, and W. T. Freeman. Face hallucination: Theory and practice.International Journal of Computer Vision, in press, 2007.
[6] B. K. Gunturk, A. U. Batur, Y. Altunbasak, M. H. Hayes, and R. M. Mersereau,"Eigenface-domain super-resolution for face recognition," IEEE Trans. Image Process., vol. 12, pp. 597-606, 2003.
[7] D. A. Roark, S. E. Barrett, A. J. O'Toole, and H. Abdi. Learning the moves: The effect of familiarity and facial motion on person recognition across large changes in viewing format. Perception, 35:761-773, 2006.
[8] Brian C. Tom, Aggelos T. Katsaggelos, "Reconstruction of a high resolution image from multiple degraded mis-registered low resolution images". SPIE, vol.2308.
[9] C. L. Luengo Hendriks, L. J. van Vliet, "Improving resolution to reduce aliasing in an under-sampled image sequence". SPIE, vol. 3965, Jan. 2000.
[10] C. Liu, H. Y. Shum, and C. S. Zhang. "A two-step approach to hallucinating faces:Global parametric model and local nonparametric model". Proc. IEEE Conf.Computer Vision and Pattern Recognition, pages 192-198, 2001.
[11] D. M. Blackburn, J. M. Bone, and P. J. Phillips, FRVT 2000 Evaluation Report,February 2001.
[12]D.P.Capel and A.Zisserman,"Super-resolution enhancement of text image sequence," in Int.Conf.Pattern Recognit.,Barcelona,Spain,pp.600-605,2000.
[13]David Capel and Andrew Zisserman."Super-resolution from multiple views using learnt image models".In Proc.CVPR,2001.
[14]H.Derin and H.Elliot,"Modeling and segmentation of noisy and textured images using gibbs random fields," IEEE Trans.on Pattern Analysis and Machine Intelligence,vol.9,pp.3-55,1987.
[15]H.Stark and P.Oskoui,"High-resolution image recovery from plane-image arrys,using convex projections".Journal of the Optical Society of America A,vol.6,no.11,1989.
[16]High-resolution image reconstruction from digital video by exploitation of nonglobal motion".SPIE,vol.38,no.5,May 1999.
[17]J.Besag,"Spatial interaction and the statistical analysis of lattice systems,"Journal of Royal Statistical Society,Series B,vol.36,pp.192-236,1974.
[18]J.L.Marroquin,Probabilistic solution of inverse problems,Ph.D.thesis,MIT Al Lab,1985.
[19]H.R.Sheikh and A.C.Bovik.Image information and visual quality.IEEE Transactions on Image Processing,15(2):430-444,2006.
[20]J.P.Makinen,J.Aikio,V.P.Putila,K.Keranen,P.Karioja,T.Kolehmainen,and J.Haavisto.Prototyping of miniature plastic imaging lens.Telescopes and Instrumentation for Solar Astrophysics,Proceeding of SPIE,5178:89-100,2004.
[21]M.Ben-Ezra,A.Zomet,and S.Nayar.Jitter camera:High resolution video from a low resolution detector.In Proceedings of the International Conference on Computer Vision and Pattern Recognition,volume 2,pages 135-142,June 2004.
[22]M.V.Joshi,S.Chaudhuri,and R.Panuganti."A learning-based method for image super-resolution from zoomed observations".IEEE Transactions on Systems,Man,and Cybemetics,Part B,35(3),pp.527-537,2005.
[23]Marc Rumo,Patrick Vandewalle,"Superresolution in images using optical flow and irregular sampling".LCAV—School of Computer and Communication Sciences,2003.
[24]Michael Elad and Arie Feuer,"Restoration of a single super-resolution image from several blurred,noisy and undersampled measured images," IEEE Trans.on Image Processing,vol.6,no.12,pp.1646-1658,December 1997.
[25]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.
[26]Michael Elad,Arie Feuer,"Super-resolution reconstruction of image sequences".IEEE Trans.On Pattem Analysis and Machine Intelligence(PAMI),vol.21,no.9,September 1999.
[27]Michal Irani,Shmuel Peleg,"Improving resolution by image registration".CVGIP:Graphical Models and Image Processing,vol.53,no.3,May 1991.
[28]Michal Irani,Shmuel Peleg,"Motion analysis for image enhancement:resolution,occlusion,and transparency".Journal of Visual Communications and Image Representation,vol.4,Dec.1993.
[29]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.
[30]P.Sinha,B.J.Balas,Y.Ostrovsky,and R.Russell.Face Processing:Advanced Modeling and Methods,chapter Face recognition by humans,pages 257-291.Academic Press,December 2005.
[31]R.C.Hardie,K.J.Barnard,and E.Armstrong,"Joint MAP registration and highresolution image estimation using a sequence of undersampled images".IEEE Trans.on Image Processing,vol.6,no.12,Dec.1997.
[32]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.
[33]R.Kindermann and J.L.Snell,Markov Random Fields and their applications,American Mathematical Society,Providence,RI,1980.
[34]R.R.Schultz and R.L.Stevenson,"A Bayesian approach to image expansion for improved definition," IEEE Trans.on Image Processing,vol.3,no.3,pp.233-242,May 1994.
[35]R.Y.Tsai and T.S.Huang,"Multiple frame image restoration and registration",Advances in Computer Vision and Image Processing,Jai Press Inc.,1984,pp.317-339.
[36]Richard C.Dubes and Anil K.Jain,"Random field models in image analysis,"Journal of Applied Statistics,vol.16,no.2,pp.131-164,1989.
[37]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.
[38]S.Baker and T.Kanade,"Limits on super-resolution and how to break them,"IEEE Trans.Pattern Anal Machine Intell.,vol.24,pp.1167-1183,2002.
[39]S.Baker and T.Kanade.Hallucinating faces.In IEEE International Conference on Automatic Face and Gesture Recognition,March 2000.
[40]S.Borman and R.Stevenson,"Spatial resolution enhancement of low-resolution image sequences.A comprehensive review with directions for future research,"Technical report,Laboratory for Image and Signal Analysis(LISA),University of Notre Dame,Notre Dame,IN,USA,July 1998.
[41]S.Chaudhri,Ed.Super-Resolution Imaging,the Kluwer International Series in Engineering and Computer Science,2002.
[42]S.Chaudhuri and A.N.Rajagopalan,Depth from defocused images:A real aperture imaging approach,Springer-Verlag,New York,1999.
[43]S.Geman and D.Geman,"Stochastic relaxation,Gibbs distribution and the Bayesian restoration of image," IEEE Trans.on Pattem Analysis and Machine Intelligence,vol.6,no.6,pp.721-741,1984.
[44]K.Jia and S.Gong.Hallucinating multiple occluded face images of different resolutions.Pattern Recognition Letters,27:1768-1775,November 2006.
[45]S.Kleinfelder,S.Lim,X.Liu,and A.E.Gamal.A 10,000 frames/s CMOS digital pixel sensor.IEEE Journal of Solid-State Circuits,36(12):2049-2059,December 2001.
[46]S.Krishnamachari and Rama Chellappa,"Multiresolution gaussmarkov random field models for texture segmentation," IEEE Trans.on Image Processing,vol.6,no.2,pp.251-266,February 1997.
[47]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.
[48]S.P.Kim,N.K.Bose,H.M.Valenzuela,"Recursive total least squares algorithm for image reconstruction from noisy,undersampled multiframes".Multidimensional Systems and Signal Processing,vol.4,no.3,July 1993.
[49]R.Gross,I.Matthews,and S.Baker.Generic vs.person specific active appearance models.Image and Vision Computing,23(11):1080-1093,2005.
[50]S.Z.Li,Markov Random Field Modelling in Computer Vision,Springer-Verlag,Tokyo,1995.
[51]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.
[52]Sina Farsiu,M.Dirk Robinson,Michael Elad,and Peyman Milanfar,"Fast and robust multiframe super resolution".IEEE Trans.on Image Processing,vol.13,no.10,Oct.2004.
[53]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.
[54]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.
[55]Tasso R.M.Sales and G.M.Morris,"Fundamental limits of optical superresolution",Optics Letters,vol.22,Issue 9,pp.582-584.
[56]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.
[57]K.Jia and S.Gong.Multi-modal tensor face for simultaneous super-resolution and recognition.Proceedings of the IEEE International Conference on Computer Vision(ICCV),2:1683-1690,2005.ISSN 1550-5499.
[58]W.T.Freeman,E.C.Pasztor,and O.T.Carmichael."Learning low-level vision".International Journal on Computer Vision,40(1):25-47,2000.
[59]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.
[60]http://www.wisdom.weizmann.ac.il/～borise/hierarchies/images/faces/faces.htm
[61]M.Elad and Y.Hel-Or,"A fast super-resolution reconstruction algorithm for pure translational motion and common space invariant blur," IEEE Transactions on Image Processing,vol.10,no.8,pp.1187-1193,2001.
[62]C.M.Bishop,A.Blake,and B.Marthi.Super-resolution Enhancement of Video.In C.M.Bishop and B.Frey(Eds.),Proc.Artificial Intelligence and Statistics.Society for Artificial Intelligence and Statistics,2003.
[63] W. Liu, D. Lin, and X. Tang. Hallucinating Faces: TensorPatch Super-resolution and Coupled Residue Compensation. Proc. Computer Vision and Pattern Recognition, pp. II 478-484, 2005.
[64] L.C. Pickup, S.J. Roberts, and A. Zisserman. A Sample Texture Prior for Image Superresolution. Advances in Neural Information Processing Systems, pp. 1587-1594,2003.
[65] J. Sun, H. Tao, and H.-Y. Shum. Image Hallucination with Primal Sketch Priors, Proc. Computer Vision and Pattern Recognition, pp. II 729-736, 2003.
[66] V.N. Vapnik. Statistical Learning Theory. John Wiley & Sons, Inc., 1998.
[67] X. Wang and X. Tang. Hallucinating Face by Eigentransformation. IEEE Trans.Systems, Man, and Cybernetics, Part C, vol. 35, no. 3, pp. 425-434, 2005.
[68] J.S. De Bonet. Multiresolution sampling procedure for analysis and synthesis of texture images. In Computer Graphics Proceedings, Annual Conference Series,(SIGGRAPH '97), pages 361-368, 1997.
[69] X. Liu, P. H. Tu, and F. W. Wheeler. Face model fitting on low resolution images.In Proceedings of the British Machine Vision Conference (BMVC), 2006.
[70] P.J. Burt and E.H. Adelson. The Laplacian pyramid as a compact image code.IEEE Transactions on Communiations, 31(4):532-540, April 1983.
[71] Y.-L Tian, T. Kanade, and J. Conn. Facial expression analysis. In S. Z. Li and A.K. Jain, editors, Handbook of face recognition. Springer, 2005.
[72] Programming Windows, 5th edition, by Charles Petzold, Microsoft Press, 1998