计算机视觉中的二分光问题研究
|
摘要
光照的变化能够明显改变物体的外观。人们通过对光反射模型的研究,知道物体表面的反射光主要由镜面反射光和漫反射光两部分组成。其中镜面反射光和观测方向密切相关,漫反射光与物体表面材质相关,与观测方向无关。在计算机视觉领域,许多研究人员通过对这两个反射光成分的分析,获取物体的三维信息、物体所处环境的光照等等隐含信息。在许多具体应用中,如物体分割,识别,跟踪等,镜面反射光与漫反射光的混杂使得算法的鲁棒性和准确性大大降低。鉴于以上原因,人们开始研究利用镜面反射光与漫反射光各自不同的特性,希望能够将这两个成分分离,即二分光问题的研究。
本文的研究工作正是围绕如何利用单张图像中的视觉信息,在物体儿何参数、表面材质以及环境光照条件等未知的情况下,将这两个成分光分离这一问题展开的。因为在数学上,该问题是病态的,不可能一蹴而就的解决所有的情况,所以,本文将研究重点集中于透明光滑介质表面(人眼角膜,玻璃面)图像的二分光问题。此时来自于介质后方的透射光可以看作是漫反射成分,与介质前方的镜面反射成分一起,在介质表面的反射光图像中,非常清晰的反映着介质两侧的信息。由于该问题中的两成分光通常较为复杂,前人的二分光算法并不能很好解决。所以,本文提出了三种新的二分光算法:对于角膜,本文提山了利用角膜物理特征的二分光算法:对于普通介质(如玻璃面等),本文提出了利用局部交叉点特征的二分光算法:由于局部特征对全局约束不够,本文又提出了利用两成分光所形成的图层的语义信息进行约束的二分光算法。实验证明本文提出的二分光算法较前人的算法效果更好,更为准确鲁棒,能处理更为复杂的情况。
本文首先介绍了二分光研究的背景及意义,回顾了前人二分光算法的成果,分类对前人方法进行分析和比较,指出其优点和不足之处,并给出研究的难点。
然后,本文针对二分光问题中较为困难的透明介质单幅图像的二分光问题,提出了三种新的分离算法。
对于人眼角膜图像,虹膜的纹理被看作是漫反射成分,此时的角膜图像虽然包含了外界环境的光照信息,但由于纹理的影响非常不准确。而对于具有复杂纹理的漫反射成分和变化较多的镜面反射成分的分离,前人的二分光算法是无法处理的。所以,本文提出了利用人眼角膜的物理特征(虹膜颜色,虹膜纹理的放射状分布,左右角膜的立体视觉对应)的二分光算法,利用求解能量函数,将角膜的镜面反射光成分分离出来。实验证明经过二分光之后的镜面反射成分更为准确的反映了环境光照的信息。
对于普通透明介质表面的反射光图像(如玻璃表面),基于人眼角膜物理特征的二分光算法不再适用。此时的二分光问题更为复杂。两成分光分别反映了介质两侧的场景信息,形成了两个透明图层。本文提出了通过求解两透明图层梯度,对两成分光进行分离的思想,分析了反射光图像中的局部交叉点特征,建立交叉点区域的概率模型,对交叉点进行分类,并用线性变换对各种不同类型交叉点进行分离,然后利用这些交叉点区域约束其它非交叉点的分离,从而得到整幅反射光图像的梯度分离结果,经过梯度重建得到与成分光对应的两分离图层。
由于局部特征对于全图的分离过程约束不足,本文又提出了基于语义信息的二分光方法,并仍然采用梯度描述。本章算法将图像用面片表示,通过对样本数据的学习,建立语义与面片之间的关系,即SOLDA概率模型。在反射光图像进行分离时,利用两图层的语义信息约束图层中的面片分布,从而控制面片的分离过程。本章采用了Gibbs采样的方法,对图层语义给定与不给定两种情况进行求解。在不知道图层语义时,能够在分离图层的同时,给出图层的语义。
Changes in illumination can induce significant variations in the appearance of an object. With the research on illumination reflectance, people realize that reflection of light from surfaces can be classified into two broad categories: specular and diffuse. The specular component is highly dependent on the viewing direction, while the diffuse component is closely related to the material of the object but changes little when observing direction varies. In computer vision field, many researchers acquire useful information through the analysis of these two components, such as the information about the object shape and the illumination environment, etc. On the other hand, the mixture of specular and diffuse reflections can result in significant inaccuracy in a vast majority of techniques in areas such object recognition, segmentation, etc. Due to the reasons above, people began to pay efforts to separate these two components by making use of their inherent properties, which is so called dichromatic reflection separation problem.
This thesis focuses on how to separate these two reflection components, based on the visual information in a single static image without any knowledge of objects' geometric parameters, surface material information or environmental lighting conditions. Because mathematically the separation process is ill-posed, it is impossible to accomplish this problem analytically in one action. Thus, in this thesis, the effort is focused on solving the dichromatic reflection separation problem on transparent surfaces (cornea of human eyes, glass, etc.). In this case, the transmitted light could be considered as diffuse, and reveals the environment details behind the surface, while the surface specular reflections shows the details of the frontal scene. Since the two components are usually very complex, previous separation methods are not applicable. So, in this thesis, three new methods are proposed: for corneal, a method uses physical properties of irises is proposed; for transparent material like glass, a local method based on junction features is proposed; due to the inefficiency of local features in global control, a semantic information based method is proposed. Experiment results show that these methods have good performance and could deal with more complex situations than the previous ones.
In this thesis, the background and the motivation of the dichromatic reflection separation problem is explained firstly. And previous methods are discussed and compared briefly by pointing out their advantages and disadvantages. The challenge of this problem is also mentioned as an important part.
Then, for the problem of transparent surface reflection separation, the thesis proposes three algorithms.
For human corneal image, iris textures are considered as diffuse, and the environment illumination information contained in the specular component is significantly obscured by the iris textures. Because of the intricate textures and complicated illumination environment, previous methods could not applicable to corneal image dichromatic separation. So, in chapter 3, a method utilizes the physical characteristics of human irises (iris chromaticity, radial autocorrelation of iris texture, illumination correspondence between two irises) is proposed. Experiments show that after the separation, the specular component could give the illumination information more accurately.
For ordinary transparent material image (e.g. glass), the corneal image separation method is not suitable any longer. The separation problem is more complicated. The two components reflect the scene information of the material surface's two sides, and form two transparent layers. In chapter 4, the dichromatic separation process is transformed into the gradient separation of two layers, and the local junction features are analyzed. A probability model is proposed to classify the junctions, and these junctions are first separated using linear transform, then, they are used as the other areas' constraints. After the gradient reconstruction step, the two separated gradient maps could be transformed back into the two layers.
Because of the inefficiency of local features in global control, in chapter 5, a semantic information based method is proposed, in which the gradient description is still used. This method divides the image into patches, and by learning from the training data, SOLDA probability model is constructed to describe the relationship between different semantic categories and patches. When doing the separation, the semantic information of the two separated layers are used to globally constrain the patch distribution within the layers. Gibbs sampling is adopted to give the solutions when the layers' semantic information is known, or undetermined, in which case the layers' sementic categories are the bonus of the separation process.
本文的研究工作正是围绕如何利用单张图像中的视觉信息,在物体儿何参数、表面材质以及环境光照条件等未知的情况下,将这两个成分光分离这一问题展开的。因为在数学上,该问题是病态的,不可能一蹴而就的解决所有的情况,所以,本文将研究重点集中于透明光滑介质表面(人眼角膜,玻璃面)图像的二分光问题。此时来自于介质后方的透射光可以看作是漫反射成分,与介质前方的镜面反射成分一起,在介质表面的反射光图像中,非常清晰的反映着介质两侧的信息。由于该问题中的两成分光通常较为复杂,前人的二分光算法并不能很好解决。所以,本文提出了三种新的二分光算法:对于角膜,本文提山了利用角膜物理特征的二分光算法:对于普通介质(如玻璃面等),本文提出了利用局部交叉点特征的二分光算法:由于局部特征对全局约束不够,本文又提出了利用两成分光所形成的图层的语义信息进行约束的二分光算法。实验证明本文提出的二分光算法较前人的算法效果更好,更为准确鲁棒,能处理更为复杂的情况。
本文首先介绍了二分光研究的背景及意义,回顾了前人二分光算法的成果,分类对前人方法进行分析和比较,指出其优点和不足之处,并给出研究的难点。
然后,本文针对二分光问题中较为困难的透明介质单幅图像的二分光问题,提出了三种新的分离算法。
对于人眼角膜图像,虹膜的纹理被看作是漫反射成分,此时的角膜图像虽然包含了外界环境的光照信息,但由于纹理的影响非常不准确。而对于具有复杂纹理的漫反射成分和变化较多的镜面反射成分的分离,前人的二分光算法是无法处理的。所以,本文提出了利用人眼角膜的物理特征(虹膜颜色,虹膜纹理的放射状分布,左右角膜的立体视觉对应)的二分光算法,利用求解能量函数,将角膜的镜面反射光成分分离出来。实验证明经过二分光之后的镜面反射成分更为准确的反映了环境光照的信息。
对于普通透明介质表面的反射光图像(如玻璃表面),基于人眼角膜物理特征的二分光算法不再适用。此时的二分光问题更为复杂。两成分光分别反映了介质两侧的场景信息,形成了两个透明图层。本文提出了通过求解两透明图层梯度,对两成分光进行分离的思想,分析了反射光图像中的局部交叉点特征,建立交叉点区域的概率模型,对交叉点进行分类,并用线性变换对各种不同类型交叉点进行分离,然后利用这些交叉点区域约束其它非交叉点的分离,从而得到整幅反射光图像的梯度分离结果,经过梯度重建得到与成分光对应的两分离图层。
由于局部特征对于全图的分离过程约束不足,本文又提出了基于语义信息的二分光方法,并仍然采用梯度描述。本章算法将图像用面片表示,通过对样本数据的学习,建立语义与面片之间的关系,即SOLDA概率模型。在反射光图像进行分离时,利用两图层的语义信息约束图层中的面片分布,从而控制面片的分离过程。本章采用了Gibbs采样的方法,对图层语义给定与不给定两种情况进行求解。在不知道图层语义时,能够在分离图层的同时,给出图层的语义。
Changes in illumination can induce significant variations in the appearance of an object. With the research on illumination reflectance, people realize that reflection of light from surfaces can be classified into two broad categories: specular and diffuse. The specular component is highly dependent on the viewing direction, while the diffuse component is closely related to the material of the object but changes little when observing direction varies. In computer vision field, many researchers acquire useful information through the analysis of these two components, such as the information about the object shape and the illumination environment, etc. On the other hand, the mixture of specular and diffuse reflections can result in significant inaccuracy in a vast majority of techniques in areas such object recognition, segmentation, etc. Due to the reasons above, people began to pay efforts to separate these two components by making use of their inherent properties, which is so called dichromatic reflection separation problem.
This thesis focuses on how to separate these two reflection components, based on the visual information in a single static image without any knowledge of objects' geometric parameters, surface material information or environmental lighting conditions. Because mathematically the separation process is ill-posed, it is impossible to accomplish this problem analytically in one action. Thus, in this thesis, the effort is focused on solving the dichromatic reflection separation problem on transparent surfaces (cornea of human eyes, glass, etc.). In this case, the transmitted light could be considered as diffuse, and reveals the environment details behind the surface, while the surface specular reflections shows the details of the frontal scene. Since the two components are usually very complex, previous separation methods are not applicable. So, in this thesis, three new methods are proposed: for corneal, a method uses physical properties of irises is proposed; for transparent material like glass, a local method based on junction features is proposed; due to the inefficiency of local features in global control, a semantic information based method is proposed. Experiment results show that these methods have good performance and could deal with more complex situations than the previous ones.
In this thesis, the background and the motivation of the dichromatic reflection separation problem is explained firstly. And previous methods are discussed and compared briefly by pointing out their advantages and disadvantages. The challenge of this problem is also mentioned as an important part.
Then, for the problem of transparent surface reflection separation, the thesis proposes three algorithms.
For human corneal image, iris textures are considered as diffuse, and the environment illumination information contained in the specular component is significantly obscured by the iris textures. Because of the intricate textures and complicated illumination environment, previous methods could not applicable to corneal image dichromatic separation. So, in chapter 3, a method utilizes the physical characteristics of human irises (iris chromaticity, radial autocorrelation of iris texture, illumination correspondence between two irises) is proposed. Experiments show that after the separation, the specular component could give the illumination information more accurately.
For ordinary transparent material image (e.g. glass), the corneal image separation method is not suitable any longer. The separation problem is more complicated. The two components reflect the scene information of the material surface's two sides, and form two transparent layers. In chapter 4, the dichromatic separation process is transformed into the gradient separation of two layers, and the local junction features are analyzed. A probability model is proposed to classify the junctions, and these junctions are first separated using linear transform, then, they are used as the other areas' constraints. After the gradient reconstruction step, the two separated gradient maps could be transformed back into the two layers.
Because of the inefficiency of local features in global control, in chapter 5, a semantic information based method is proposed, in which the gradient description is still used. This method divides the image into patches, and by learning from the training data, SOLDA probability model is constructed to describe the relationship between different semantic categories and patches. When doing the separation, the semantic information of the two separated layers are used to globally constrain the patch distribution within the layers. Gibbs sampling is adopted to give the solutions when the layers' semantic information is known, or undetermined, in which case the layers' sementic categories are the bonus of the separation process.
引文
[1]彭群生,鲍虎军,金小刚,计算机真实感图形的算法研究,科学出版社,1999.
[2]Andrew Glassner,ed.An Introduction to Ray Tracing.Academic Press Limited,1989.
[3]S.Shafer,"Using Color to Separate Reflection Components," Color Research Application,vol.10,pp.210-218,1985.
[4]R.T.Tan and K.Ikeuchi,"Separating Reflection Components of Textured Surfaces using a Single Image," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.27,no.2,pp.178-193,2005.
[5]T.Gevers,"Adaptive Image Segmentation by Combining Photometric Invariant Region and Edge Information," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.24,pp.848-852,2002.
[6]V.Kravtchenko and J.J.Little,"Efficient Color Object Segmentation Using the Dichromatic Reflection Model," Proceedings of IEEE Pacific Rim Conference on Comnication,Computer and Signal Processing,pp.90-94,1999.
[7]T.Gevers,"Robust Segmentation and Tracking of Colored Objects in Video," IEEE Transactions on Circuits and Systems for Video Technology,vol.14,no.6,pp.776-781,2004.
[8]J.C.Glas,F.V.Heijden,"The Use of Separated Reflection Components in Estimating Geometrical Parameters of Curved Surface Elements," Proceedings of International Conference on Image Processing and lts Applications,pp.340-344,1995.
[9]J.-S.Park and J.T.Tou,"Highlight Separation and Surface Orientations for 3-D Specular Objects," Proceedings of International Conference on Pattern Recognition,vol.1,pp.331-335,1990.
[10]S.Lin,Y.Li,S.B.Kang,X.Tong and H.Shum,"Diffuse-Specular Separation and Depth Recovery from Image Sequences," Proceedings of the 7~(th)European Conference on Computer Vision-Part Ⅲ,pp.210-224,2002
[11]D.N.Brat and S.K.Nayar,"Stereo in the Presence of Specular Reflection," Proceedings of International Conference on Computer Vision,pp.1086-1092,1995.
[12]S.G.Narasimhan,V.Ramesh and S.K.Nayar,"A Class of Photometric Invariants Separating Material from Shape and Illumination," Proceedings of International Conference on Computer Vision,vol.2,pp.1387-1394,Nice,France,2003.
[13]R.W.Fleming and H.H.Bulthoff,"Low-Level Image Cues in the Perception of Translucent Materials," ACM Transactions on Applied Perception,vol.2,no.3,pp.346-382,2005.
[14]J.Ho,B.V.Funt and M.S.Drew,"Separating a Color Signal into Illumination and Surface Reflectance Components:Theoy and Application," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.12,no.10,pp.966-977,1990.
[15]R.Lenz and P.Meer,"Color Image Normalization through Illumination Recovery,"Proceedings of International Conference on Acoustics,Speech,and Signal Processing,vol.4,pp.3141-3144,Munich,Germany,1997.
[16]S.Nadimi and B.Bhanu,"Moving Shadow Detection Using a Physics-based Approach,"Proceedings of International Conference on Pattern Recognition,vol.2,pp.701-704,2002.
[17]Y.Y.Schechner,J.Shamir and N.Kiryati,"Polarization-based Decorrelation of Transparent Layers:The Inclination Angle of an Invisible Surface," Proceedings of International Conference on Computer Vision,pp.814-819,1999.
[18]H.Wang,S.Lin,X.Liu,S.B.Kang."Separating Reflection in Human Iris Image for Illumination Estimation," Proceedings of International Conference on Computer Vision,vol.2,pp.1691-1698,Beijing,China,2005.
[19]T.Shibata,T.Takahashi,D.Miyasaki,Y.Sato and K.Ikeuchi,"Creating Photorealistic Virtual Model with Polarization-based Vision System," Proceedings of SPIE(Polorization Science and Remote Sensing Ⅱ,Part of SPIE's International Symposium on Optics and Photonics 2005),vol.5888,pp.25-35,San Diego,CA,USA,2005.
[20]J.Dong and M.Chantler,"Estimating Parameters of an Illumination model for the Synthesis of Specular Surface Textures," Proceedings of International Conference on Computer and Information Technology,pp.716-721,2004.
[21]G.J.Klinker,S.A.Shafer and T.Kanade,"The Measurement of highlights in color images,"International Journal of Computer Vision,vol.2,pp.7-32,1990.
[22]F.Tong and B.V.Funt,"Specularity Removal for Shape from Shading," Vision Interface,pp.98-103,1988.
[23]P.Tan,S.Lin,L.Quan and H.Shum,"Highlight Removel by Illumination-Constrained Inpainting," Proceedings of International Conference on Computer Vision,pp.164-169,2003.
[24]S.P.Mallick,T.Zickler,P.N.Belhumeur and D.Kriegman,"Specularity Removal in Images and Videos:A PDE Approach," Proceedings of European Conference on Computer Vision,Part Ⅰ,pp.550-563,2006.
[25]L.B.Wolff,"Using Polarization to Separate Reflection Components," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.363-369,1989.
[26]S.K.Nayar,X.S.Fang and T.Boult,"Separation of Reflection Components Using Color and Polarization," International Journal of Computer Vision,vol.21,no.3,pp.163-186,1997.
[27]H.Farid and E.H.Adelson,"Separating Reflections and Lighting Using Independent Components Analysis," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.262-267,1999.
[28]S.Lin and S.W.Lee,"Estimation of Diffuse and Specular Appearance," Proceedings of International Conference on Computer Vision,vol.2,pp.855-860,1999.
[29]K.I.Diamantaras,T.Papadmitriou,"Blind Separation of Reflections Using the Image Mixture Ratio," Proceedings of International Conference on Image Processing,vol.2,pp.1034-137,2005.
[30]I.Stainvas and D.Lowe,"A Generative Model for Separating Illumination and Reflectance form Images," Journal of Machine Learning Research,vol.4,pp.1499-1519,2003.
[31]M.Yamazaki,Y.-W.Chen and G.Xu,"Separating Reflections from Images Using Kernel Independent Component Analysis," International Conference on Pattern Recognition,vol.3,194-197,Hong Kong,China,2006.
[32]B.Sarel and M.Irani,"Separating Transparent Layers through Layer Information Exchange,"Proceedings of European Conference on Computer Vision,Part 4,pp.328-341,Prague,Czech,2004.
[33]J.Toro,R.Medina and D.Ziou,"Recovery of Two Transparent Primitive Images from Two Frams," Proceedings of International Conference on Acoustics,Speech and Signal Processing,vol.3,pp.225-228,Montreal,Canada,2004.
[34]A.Levin,A.Zomet and Y.Weiss,"Learning to Perceive Transparency from the Statistics of Natural Scenes," Advances in Neurai Information Processing Systems,pp.1247-1254,2002.
[35]A.Levin,A.Zomet and Y.Weiss,"Separating Reflections from a Single Image Using Local Features," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.1,pp.306-313,2004.
[36]A.Levin and Y.Weiss,"User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior," Proceedings of European Conference on Computer Vision,pp.602-613,2004.
[37]M.Singh and X.Huang,"Computing Layered Surface Representations:An Algorithm for Detecting and Separating Transparent Overlays," Proceedings of IEEE Conference on Computer Vision and Pattem Recognition,vol.2,pp.11-18,Toronto,Canada,2003.
[38]R.S.Hunter,The Measurement of Appearance,John Wiley and Sons,New-York,1975.
[39]D.B.Judd and G.Wyszecki,Color in Business,Science and Industry,John Wiley and Sons,New York,1975.
[40]G.Healey and T.O.Binford,"The Role and Use of Color in a General Vision System,"DARPA-Image Understanding(IUS)workshop,pp.599-613,1987.
[41]G.J.Klinker,S.A.Shafer and T.Kanade,"Measurement of Gloss from Color Images,"Inter-Society Color Council(ISCC)87 Conference on Appearance,pp.9-12,1987.
[42]G.J.Klinker,S.A.Shafer and T.Kanade,"Using a Color Reflection Model to Separate Highlights from Object Color," Proceedings of the First International Conference on Computer Vision,pp.145-150,1987.
[43]B.T.Phong,Illumination for Computer Generated Images,PhD Dissertation,University of Utah,July,1973.
[44]R.L.Cook and K.E.Torrance,"A Reflectance Model for Computer Graphics," Computer Graphics,vol.15,no.3,pp.307-316,1981.
[45]D.A.Forsyth and J.Ponce,Computer Vision:A Modern Approach,Prentice Hall,2003.
[46]P.Moon,"A Table of Fresnel Reflection," Journal of Mathematical Physics,vol.19,no.1,pp.1-33,1940.
[47]R.M.Johnston,"Geometric Metamerism," Color Engineering,vol.5,no.3,pp.42,1967.
[48]J.F.Blinn,"Models of Light Reflection for Computer Synthesized Pictures," Computer Graphics,vol.11,no.2,pp.192-198,1977.
[49]F.Metelli,"The Perception of Transparency," Scientific American,vol.230,no.4,pp.90-98,1974.
[50]R.Gershon,The Use of Color in Computational Vision,PhD thesis,University of Toronto,1987.
[51]I.T.Jolliffe,Principal Component Analysis,Series:Springer Series in Statistics,2nd ed.,Springer,NY,2002
[52]F.S.Acton,Analysis of Straight-Line Data,New York,Dover,1966.
[53]R.Bajcsy,S.W.Lee and A.Leonardis,"Color Image Segmentation with Detection of Highlights and Local Illumination Induced by Interreflections," Proceedings of International Conference on Pattern Recognition,vol.1,pp.785-790,Atlantic City,N J,USA,1990.
[54]C.Novak and S.Shafer,"Anatomy of Color Histogram," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,Champaign,IL,USA,pp.599-605,1992.
[55]R.T.Tan,K.Nishino and K.Ikeuchi,"Separating Reflection Components Based on Chromaticity and Noise Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.26,no.10,pp.1373-1379,2004.
[56]R.T.Tan and K.Ikeuchi,"Reflection Components Decomposition of Textured Surfaces Using Linear Basis Functions," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.1,pp.125-131,San Diego,CA,USA,2005.
[57]K.-J.Yoon,Y.Choi and I.S.Kweon,"Fast Separation of Reflection Components Using A Specular-Invariant Image Representation," Proceedings of International Conference on Image Processing,pp.973-980,Atlanta,GA,USA,2006.
[58]M.Bertalmio,G.Sapiro,C.Ballester and V.Caselles,"Image Inpainting," Proceedings of ACM SIGGRAPH,pp.417-424,New Orleans,USA,2000.
[59]T.F.Chan and J.Shen,"Mathematical Models for Local Nontexture Inpintings," SIAM Journal of Applied Mathematics,voL 62,no.3,pp.1019-1043,2001.
[60]T.F.Chan,J.Shen and L.Vese,"Variational PDE Models in Image Processing," Notices of American Mathematical Society,vol.50,no.1,pp.14-26,2002.
[61]P.Tan,S.Lin and L.Quan,"Separation of Highlight Reflections on Textured Surfaces,"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.vol.2,pp.1855-1860,New York,NY,USA,2006.
[62]钟锡华,现代光学基础,北京大学出版社,2003.
[63]M.Born and E.Wolff,Principles of Optics,London:Pergamon,1965.
[64]L.B.Wolff and T.E.Boult,"Constraining Object Features Using a Polarization Reflectance Model," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.13,no.7,pp.635-657,1991.
[65]L.B.Wolff,"Surface Orientation From Polarization Images," Optics,Illumination,and Image Sensing For Machine Vision Ⅲ,Proceedings of SPIE,vol.850,pp.110-121,1987.
[66]S.Umeyama and G.Godin,"Separation of Diffuse and Specular Components of Surface Reflection by Use of Polarization and Statistical Analysis of Images," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.26,no.5,pp.639-647,2004.
[67]A.Hyvarinen and E.Oja,"Independent Component Analysis:Algorithms and Applications,"Neural Networks,vol.13,pp.411-430,2000.
[68]G.-J.Jang and T.-W.Lee,"A Maximum Likelihood Approach to Single-Channel Source Separation," Journal of Machine Learning Research,vol.4,pp.1365-1392,2003.
[69]A.J.Bell and T.J.Sejnowski,"An Information-Maximization Approach to Blind Separation and Blind Deconvolution," Neural Computation,vol.7,pp.1129-1159,1995.
[70]S.Umeyama,"Blind Deconvolution of Images Using Gabor Filters and Independent Component Analysis," Proceedings of International Symposium on Independent Component Analysis and Blind Signal Separation,pp.319-324,Nara,Japan,2003.
[71]M.S.Bartlett,Pace Image Analysis by Unsupervised Learning.Kluwer Academic,2001.
[72]S.Makeig,A.J.Bell,T.-P.Jung and T.J.Sejnovsld,"Independent Component Analysis of Electroencephalographic Data," Advances in Neural Information Processing Systems 8,MIT Presss,pp.145-151,1996.
[73]Y.Sato and K.Ikeuchi,"Temporal-Color Space Analysis of Reflection," Technical Report,CMU-CS-92-207,Computer Science Department,Carnegie Mellon University,1992.
[74]S.Lin,"Generation of Diffuse and Specular Appearance from Photometric Images,"Proceedings of Workshop on Photometric Modeling for Computer Vision and Graphics,pp.39-46,Fort Collins,CO,USA,1999.
[75]S.Lin and S.W.Lee,"An Appearance Representation for Multiple Reflection Components,"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.1105-1110,Hilton Head Island,SC,USA,2000.
[76]E.P.F.Lafortune,S.Foo,K.E.Torrance and D.P.Greenberg,"Non-Linear Approximation of Reflectance Functions," Proceedings ofA CM SIGGRAPH,pp.117-126,Los Angeles,CA,USA,1997.
[77]S.W.Lee and R.Bajcsy,"Detection of Specularity Using Color and Multiple Views,"Image and Vision Computing,vol.10,pp.643-653,1992.
[78]Y.Y.Schechner,N.Kiryati,R.Basri,"Separation of Transparent Layers Using Focus,"Proceedings of International Conference on Computer Vision,pp.1061-1066,Bombay,India,1998.
[79]E.H.Adelson and P.Anandan,"Ordinal Characteristics of Transparency," AAAI Workshop on Qualitative Vision,pp.77-81,1990.
[80]S.Nakauchi,S.Usui,J.Parkkinen and P.Silfsten,"Computational Explanations for Color Transparency," Proceedings of International Joint Conference on Neural Networks,vol.1,pp.170-173,Washington DC,USA,1999.
[81]B.A.Olshausen and D.J.Field,"Field Emergence of Simple-Cell Receptive Field Properties by Learning a Sparse Code for Natural Images," Nature,vol.381,pp.607-609,1996.
[82]E.P.Simoncelli,"Statistical Models for Images:Compression Restoration and Synthesis,"Proceedings of Asilomar Conference on Signals,Systems and Computers,pp.673-678,1997.
[83]W.T.Freeman and E.C.Pasztor,"Learning to Estimate Scenes from Images," Advance Neural Information Processing Systems 11,MIT Press,1999.
[84]B.J.Frey,R.Koetter and N.Petrovic,"Very Loopy Belief Propagation for Unwrapping Phase Images," Advance Neural Information Processing 14,2001.
[85]J.Daugman,"Iris Recognition," American Scientist,vol.89,pp.326-333,2001.
[86]J.Daugman,"High Confidence Visual Recognition of Persons by A Test of Statistical Independence," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.15,pp.1148-1161,1993.
[87]T.Hutchinson,K.White,K.Reichert and L.Frey,"Human-Computer Interaction Using Eye-Gaze Input," IEEE Transactions on Systems,Man and Cybernetics,vol.19,pp.1527-1534,1989.
[88]R.Jacob,"What You Look at Is What You Get:Eye Movement-Based Interaction Techniques," Proceedings of ACM Computer-Human Interaction,pp.11-18,1990.
[89]A.Lefohn,R.Caruso,E.Reihard,B.Budge and P.Shirley,"An Ocularist's Approach to Human Iris Synthesis," IEEE Computer Graphics and Applications,vol.23,pp.70-75,2003.
[90]P.Debevec,"Virtual Cinematography:Relighting Through Computation," Computer,vol.39,no.8,pp.57-65,2006.
[91]P.Debevec,"Rendering Synthetic Objects into Real Scenes:Bridging Traditional and Image-based Graphics with Global Illumination and High Dynamic Range Photography,"Proceedings of ACM SIGGRAPH,pp.189-198,Orlando,FL,USA,1998.
[92]D.R.Hougen and N.Ahuja,"Estimation of the Light Source Distribution and Its Use in Integrated Shape Recovery from Stereo and Shading," Proceedings of International Conference on Computer Vision,pp.148-155,Berlin,Germany,1993.
[93]Q.Zheng and R.Chellappa,"Estimation of Illuminant Direction,Albedo and Shape from Shading," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.13,pp.680-702,1991.
[94]Y.Wang and D.Samaras,"Estimation of Multiple Illuminants from A Single Image of Arbitrary Known Geometry," Proceedings of European Conference on Computer Vision,Part 1,pp.272-288,2002.
[95]Y.Zhang and Y.-H.Yang,"Multiple Illuminant Direction Detection with Application to Image Synthesis," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.23,no.8,pp.915-920,2001.
[96]I.Sato,Y.Sato and K.Ikeuchi,"Illumination Distribution from Brightness in Shadows:Adaptive Estimation of Illumiuation Distribution with Unknown Reflectance Properties in Shadow Regions," Proceedings of International Conference on Computer Vision,pp.875-883,Kerkyra,Corfu,Greece,1999.
[97]I.Sato,Y.Sato,and K.Ikeuchi,"Illumination Distribution from Shadows," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.306-312,Collins,CO,USA,1999.
[98]I.Sato,Y.Sato,and K.Ikeuchi,"Stability Issues in Recovering Illumination Distribution from Brightness in Shadows," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.400-407,Kauai,HI,USA,2001.
[99]N.Tsumura,M.Dang,T.Makino and Y.Miyake,"Estimation the Directions to Light Sources Using Images of Eye for Reconstructing 3D Human Face," Proceedings of IS&T/SID's Color Image Conference,pp.77-81,2003.
[100]K.Nishino and S.K.Nayar,"The World in An Eye," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.444-451,2004.
[101]K.Nishino and S.K.Nayar,"Corneal Imaging System:Environment from Eyes,"International Journal of Computer Vision,vol.70,no.1,pp.23-40,2006.
[102]K.Nishino and S.K.Nayar,"Eyes for Relighting," ACM Transactions on Graphics,vol.23,pp.704-711,2004.
[103]K.Nishino,P.N.Belhumeur and S.K.Nayar,"Using Eye Reflections for Face Recognition Under Varying Illumination," Proceedings of International Conference on Computer Vision,vol.1,pp.519-526,2005.
[104]M.Lam and G.Baranoski,"A Predictive Light Transport Model for the Human Iris,"Proceedings of EUROGRAPHICS,pp.359-368,2006.
[105]P.D.Imesch,I.H.L.Wallow and D.M.Albert,"The Color of the Human Eye:A Review of Morphologic Correlates and of Some Conditions that Affect Iridial Pigmentation," Survey of Ophthalmology,vol.41,pp.117-123,1997.
[106]S.J.Preece and E.Claridge,"Monte Carlo Modeling of The Spectral Reflectance of The Human Eye," Physics in Medicine and Biology,vol.47,pp.2863-2877,2002.
[107]S.Fan,C.R.Dyer and L.Hubbard,"Quantification and Correction of Iris Color," Technical Report 1945,University of Wisconsin-Madison,2003.
[108]E.H.Land,"Recent Advances in Retinex Theory," Vision Research,vol.26,pp.7-21,1986.
[109]G.D.Finlayson,S.D.Hordley and M.S.Drew,"Removing Shadows from Images,"Proceedings of European Conference on Computer Vision,pp.823-836,2002.
[110]P.L.Kaufman and A.Aim,editors.Adler's Physiology of the Eye:Clinical Application.Mosby,10~(th)edition,2003.
[111]H.V.Helmholtz.Physiologic Optics,volume 1 and 2.Voss,Hamburg,Germany,third edition,1909.
[112]D.W.Hansen and A.Pecc,"Eye Typing Off the Shelf," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.159-164,Washington DC,USA,2004.
[113]C.P.Stein,"Accurate Internal Camera Calibration Using Rotation,with Analysis of Sources of Errors," Proceedings of International Conference on Computer Vision,pp.230-236,Cambrigde,MA,USA,1995.
[114]J.-G.Wang,E.Sung and R.Venkateswarlu,"Eye Gaze Estimation from a Single Image of One Eye," Proceedings of International Conference on Computer Vision,pp.136-143,2003.
[115]S.K.Nayar,"Sphereo:Recovering Depth Using a Single Camera and Two Specular Spheres," SPIE:Optics,Illumination and Image Sensing for Machine Vision Ⅱ,1988.
[116]S.A.Nene and S.K.Nayar,"Stereo Using Mirrors," Proceedings of International Conference on Computer Vision,pp.1087-1094,1998.
[117]W.H.Press,S.A.Teukolsky,W.T.Vettedmg and B.P.Flannery,Numerical Recipes in C++:The Art of Scientific Computing,Cambridge University Press,2~(nd)edtion,2002.
[118]Y.-Yu.Chuang,B.Curless,D.H.Salesin and R.Szeliski,"A Bayesian Approach to Digital Matting," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,264-271,2001.
[119]J.Sun,J.Jia,C.-K,Tang and H.-Y.Shum,"Poisson Matting," A CM Transactions on Graphics,vol.23,no.3,pp.315-321,2004.
[120]C.B.Atkins,Classification-Based Methods in Optimal Image Interpolation,PhD Dissertation,Purdue University,December,1998.
[121]L.Parida,D.Geiger and R.Hummel,"Kona:A Multi-Junction Detector Using Minimum Description Length Principle," Proceedings of the First International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition,pp.51-65,1997.
[122]W.Yu,K.Daniilidis and G.Sommer,"Approximate Orientation Steerability Based on Angular Gaussians," IEEE Transactions on Image Processing,vol.10,no.2,pp.193-205,2001.
[123]T.Lmdeberg,"Junction Detection with Automatic Selection of Detection Scales and Localization Scales," Proceedings of International Conference on Image Processing,vol.1,pp.924-928,Austin,TA,USA,1994.
[124]V.Caselles,B.Coil and J.-M.Morel,"Junction Detection and Filtering:A Morphological Approach," Proceedings of International Conference on Image Processing,vol.1,pp.493-496,1996.
[125]A.P.Dempster,N.M.Laird and D.B.Rubin,"Maximum Likelihood from Incomplete Data Via the EM Algorithm," Journal of the Royal Statistical Society,Series B,vol.39,no.1,pp.1-38,1997.
[126]C.Tomasi,"Estimating Gaussian Mixture Densities with EM-A Tutorial," Technical Report,Duke University,2004.
[127]J.Bilmes,"A Gentle Tutorial of the EM Algorithm and Its Application to Parameter Estimation for Ganssian Mixture and Hidden Markov Models," Technical Report TR-97-021,International Computer Science Institute,Berkeley CA,1998.
[128]Raanan Fattal,Dani Lischinski,Michael Werman,"Gradient Domain High Dynamic Range Compression," Proceedings of ACM SIGGRAPH,pp.249-256,2002.
[129]P.Perez,M.Gangnet,A.Blake."Possion Image Editing," ACM Transactions on Graphics,vol.22,no.3,pp.313-318,San Diego,CA,USA,2003.
[130]朱云芳,基于图像拼接的视频编辑,浙江大学博士论文,2006.
[131]Y.Yu,K.Zhou,D.Xu,X.Ski,H.Bao and H.-Y.Sham,"Mesh Editing with Poisson-Based Gradient Field Manipulation," ACM Transactions on Graphics,vol.23,no.3,pp.641-648,Los Angeles,CA,USA,2003.
[132]D.M.Blei,A.Y.Ng and M.I.Jordan,"Latent Dirichlet Allocation," Journal of Machine Learning Research,vol.3,pp.993-1022,2003.
[133]T.Hofmann,"Probabilistic Latent Semantic Indexing," Proceeding of the SIGIR,pp.50-57,Berkely,CA,USA,1999.
[134]K.Nigam,A.McCallum,S.Thrum and T.Mitchell,"Text Classification From Labeled and Unlabeled Documents Using EM," Machine Learning,vol.39,no.2/3,pp.103-134,2000.
[135]王惠锋,孙正兴,王箭,“语义图像检索研究进展,”计算机研究与发展,vol.39,no.5,pp.513-523,2002.
[136]X.Wang and E.Grimson,"Spatial Latent Dirichlet Allocation," Proceedings of Neural Information Processing System Conference 20,pp.1577-1584,MIT Press,Cambrigdge,MA,2008.
[137]L.Cao and L.Fei-Fei,"Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes," Proceedings of International Conference on Computer Vision,vol.1,pp.1-8,Rio de Janeiro,Brazil,2007.
[138]R.Fergus,P.Perona and A.Zisserman,"Object Class Recognition by Unsupervised Scale-Invariant Learning," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.264-271,Madison,Vii,USA,2003.
[139]B.C.Russell,A.A.Efros,J.Sivic,W.T.Freeman and A.Zisserman,"Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.1605-1614,New York,NY,USA,2006.
[140]J.Sivic,B.C.Russell,A.A.Effros,A.Zisserman and W.T.Freeman,"Discovering Object Categories in Image Collections," Technical Report,MIT-CSAIL-TR-2005-012,2005.
[141]M.-E.Nilsback and A.Zisserman,"A Visual Vocabulary for Flower Classification,"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.1447-1454,New York,NY,USA,2006.
[142]L.Fei-Fei and P.Perona,"A Bayesian Hierarchical Model for Learning Natural Scene Categories," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.1,pp.524-531,San Diego,CA,USA,2005.
[143]R.Fergus,L.Fei-Fei,P.Perona and A.Zisserman,"Learning Object Categories from Google's Image Search," Proceedings of lnternational Conference on Computer Vision,vol.2,pp.1816-1823,,Beijing,China,2005.
[144]J.Vogel and B.Schiele,"Semantic Modeling of Natural Scenes for Content-Based Image Retrievel," International Journal of Computer Vision,vol.72,no.2,pp.133-157,2007.
[145]D.Lowe,"Object Recognition From Local Scale-lnvariant Features," Proceedings of International Conference on Computer Vision,pp.1150-1157,Kerkyra,Corfu,Greece,1999.
[146]T.Hofrnann,"Unsupervised Learning by Probabilistic Latent Semantic Analysis," Machine Learning,vol.42,pp.177-196,2001.
[147]A.Gelman,J.B.Carlin,Stern H.S.and Rubin D.B.,Bayesian Data Analysis,Chapman Hall/CRC,1995.
[148]M.Jordan,Z.Ghahramani,T.Jaakkola and L.Saul,"An Introduction to Variational Methods for Graphical Models," Machine Learning,vol.37,no.2,pp.183-233,1999.
[149]J.Winn and C.Bishop,"Variational Message Passing," Journal of Machine Learning Research,vol.6,pp.661-694,2005.
[150]T.Griffths,"Gibbs Sampling in the Generative Model of Latent Dirichlet Allocation,"Technical Report,University of California,Berkerley,2002.
[151]B.Walsh,"Markov Chain Monte Carlo and Gibbs Sampling," Technical Report,MIT,2004.
[2]Andrew Glassner,ed.An Introduction to Ray Tracing.Academic Press Limited,1989.
[3]S.Shafer,"Using Color to Separate Reflection Components," Color Research Application,vol.10,pp.210-218,1985.
[4]R.T.Tan and K.Ikeuchi,"Separating Reflection Components of Textured Surfaces using a Single Image," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.27,no.2,pp.178-193,2005.
[5]T.Gevers,"Adaptive Image Segmentation by Combining Photometric Invariant Region and Edge Information," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.24,pp.848-852,2002.
[6]V.Kravtchenko and J.J.Little,"Efficient Color Object Segmentation Using the Dichromatic Reflection Model," Proceedings of IEEE Pacific Rim Conference on Comnication,Computer and Signal Processing,pp.90-94,1999.
[7]T.Gevers,"Robust Segmentation and Tracking of Colored Objects in Video," IEEE Transactions on Circuits and Systems for Video Technology,vol.14,no.6,pp.776-781,2004.
[8]J.C.Glas,F.V.Heijden,"The Use of Separated Reflection Components in Estimating Geometrical Parameters of Curved Surface Elements," Proceedings of International Conference on Image Processing and lts Applications,pp.340-344,1995.
[9]J.-S.Park and J.T.Tou,"Highlight Separation and Surface Orientations for 3-D Specular Objects," Proceedings of International Conference on Pattern Recognition,vol.1,pp.331-335,1990.
[10]S.Lin,Y.Li,S.B.Kang,X.Tong and H.Shum,"Diffuse-Specular Separation and Depth Recovery from Image Sequences," Proceedings of the 7~(th)European Conference on Computer Vision-Part Ⅲ,pp.210-224,2002
[11]D.N.Brat and S.K.Nayar,"Stereo in the Presence of Specular Reflection," Proceedings of International Conference on Computer Vision,pp.1086-1092,1995.
[12]S.G.Narasimhan,V.Ramesh and S.K.Nayar,"A Class of Photometric Invariants Separating Material from Shape and Illumination," Proceedings of International Conference on Computer Vision,vol.2,pp.1387-1394,Nice,France,2003.
[13]R.W.Fleming and H.H.Bulthoff,"Low-Level Image Cues in the Perception of Translucent Materials," ACM Transactions on Applied Perception,vol.2,no.3,pp.346-382,2005.
[14]J.Ho,B.V.Funt and M.S.Drew,"Separating a Color Signal into Illumination and Surface Reflectance Components:Theoy and Application," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.12,no.10,pp.966-977,1990.
[15]R.Lenz and P.Meer,"Color Image Normalization through Illumination Recovery,"Proceedings of International Conference on Acoustics,Speech,and Signal Processing,vol.4,pp.3141-3144,Munich,Germany,1997.
[16]S.Nadimi and B.Bhanu,"Moving Shadow Detection Using a Physics-based Approach,"Proceedings of International Conference on Pattern Recognition,vol.2,pp.701-704,2002.
[17]Y.Y.Schechner,J.Shamir and N.Kiryati,"Polarization-based Decorrelation of Transparent Layers:The Inclination Angle of an Invisible Surface," Proceedings of International Conference on Computer Vision,pp.814-819,1999.
[18]H.Wang,S.Lin,X.Liu,S.B.Kang."Separating Reflection in Human Iris Image for Illumination Estimation," Proceedings of International Conference on Computer Vision,vol.2,pp.1691-1698,Beijing,China,2005.
[19]T.Shibata,T.Takahashi,D.Miyasaki,Y.Sato and K.Ikeuchi,"Creating Photorealistic Virtual Model with Polarization-based Vision System," Proceedings of SPIE(Polorization Science and Remote Sensing Ⅱ,Part of SPIE's International Symposium on Optics and Photonics 2005),vol.5888,pp.25-35,San Diego,CA,USA,2005.
[20]J.Dong and M.Chantler,"Estimating Parameters of an Illumination model for the Synthesis of Specular Surface Textures," Proceedings of International Conference on Computer and Information Technology,pp.716-721,2004.
[21]G.J.Klinker,S.A.Shafer and T.Kanade,"The Measurement of highlights in color images,"International Journal of Computer Vision,vol.2,pp.7-32,1990.
[22]F.Tong and B.V.Funt,"Specularity Removal for Shape from Shading," Vision Interface,pp.98-103,1988.
[23]P.Tan,S.Lin,L.Quan and H.Shum,"Highlight Removel by Illumination-Constrained Inpainting," Proceedings of International Conference on Computer Vision,pp.164-169,2003.
[24]S.P.Mallick,T.Zickler,P.N.Belhumeur and D.Kriegman,"Specularity Removal in Images and Videos:A PDE Approach," Proceedings of European Conference on Computer Vision,Part Ⅰ,pp.550-563,2006.
[25]L.B.Wolff,"Using Polarization to Separate Reflection Components," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.363-369,1989.
[26]S.K.Nayar,X.S.Fang and T.Boult,"Separation of Reflection Components Using Color and Polarization," International Journal of Computer Vision,vol.21,no.3,pp.163-186,1997.
[27]H.Farid and E.H.Adelson,"Separating Reflections and Lighting Using Independent Components Analysis," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.262-267,1999.
[28]S.Lin and S.W.Lee,"Estimation of Diffuse and Specular Appearance," Proceedings of International Conference on Computer Vision,vol.2,pp.855-860,1999.
[29]K.I.Diamantaras,T.Papadmitriou,"Blind Separation of Reflections Using the Image Mixture Ratio," Proceedings of International Conference on Image Processing,vol.2,pp.1034-137,2005.
[30]I.Stainvas and D.Lowe,"A Generative Model for Separating Illumination and Reflectance form Images," Journal of Machine Learning Research,vol.4,pp.1499-1519,2003.
[31]M.Yamazaki,Y.-W.Chen and G.Xu,"Separating Reflections from Images Using Kernel Independent Component Analysis," International Conference on Pattern Recognition,vol.3,194-197,Hong Kong,China,2006.
[32]B.Sarel and M.Irani,"Separating Transparent Layers through Layer Information Exchange,"Proceedings of European Conference on Computer Vision,Part 4,pp.328-341,Prague,Czech,2004.
[33]J.Toro,R.Medina and D.Ziou,"Recovery of Two Transparent Primitive Images from Two Frams," Proceedings of International Conference on Acoustics,Speech and Signal Processing,vol.3,pp.225-228,Montreal,Canada,2004.
[34]A.Levin,A.Zomet and Y.Weiss,"Learning to Perceive Transparency from the Statistics of Natural Scenes," Advances in Neurai Information Processing Systems,pp.1247-1254,2002.
[35]A.Levin,A.Zomet and Y.Weiss,"Separating Reflections from a Single Image Using Local Features," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.1,pp.306-313,2004.
[36]A.Levin and Y.Weiss,"User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior," Proceedings of European Conference on Computer Vision,pp.602-613,2004.
[37]M.Singh and X.Huang,"Computing Layered Surface Representations:An Algorithm for Detecting and Separating Transparent Overlays," Proceedings of IEEE Conference on Computer Vision and Pattem Recognition,vol.2,pp.11-18,Toronto,Canada,2003.
[38]R.S.Hunter,The Measurement of Appearance,John Wiley and Sons,New-York,1975.
[39]D.B.Judd and G.Wyszecki,Color in Business,Science and Industry,John Wiley and Sons,New York,1975.
[40]G.Healey and T.O.Binford,"The Role and Use of Color in a General Vision System,"DARPA-Image Understanding(IUS)workshop,pp.599-613,1987.
[41]G.J.Klinker,S.A.Shafer and T.Kanade,"Measurement of Gloss from Color Images,"Inter-Society Color Council(ISCC)87 Conference on Appearance,pp.9-12,1987.
[42]G.J.Klinker,S.A.Shafer and T.Kanade,"Using a Color Reflection Model to Separate Highlights from Object Color," Proceedings of the First International Conference on Computer Vision,pp.145-150,1987.
[43]B.T.Phong,Illumination for Computer Generated Images,PhD Dissertation,University of Utah,July,1973.
[44]R.L.Cook and K.E.Torrance,"A Reflectance Model for Computer Graphics," Computer Graphics,vol.15,no.3,pp.307-316,1981.
[45]D.A.Forsyth and J.Ponce,Computer Vision:A Modern Approach,Prentice Hall,2003.
[46]P.Moon,"A Table of Fresnel Reflection," Journal of Mathematical Physics,vol.19,no.1,pp.1-33,1940.
[47]R.M.Johnston,"Geometric Metamerism," Color Engineering,vol.5,no.3,pp.42,1967.
[48]J.F.Blinn,"Models of Light Reflection for Computer Synthesized Pictures," Computer Graphics,vol.11,no.2,pp.192-198,1977.
[49]F.Metelli,"The Perception of Transparency," Scientific American,vol.230,no.4,pp.90-98,1974.
[50]R.Gershon,The Use of Color in Computational Vision,PhD thesis,University of Toronto,1987.
[51]I.T.Jolliffe,Principal Component Analysis,Series:Springer Series in Statistics,2nd ed.,Springer,NY,2002
[52]F.S.Acton,Analysis of Straight-Line Data,New York,Dover,1966.
[53]R.Bajcsy,S.W.Lee and A.Leonardis,"Color Image Segmentation with Detection of Highlights and Local Illumination Induced by Interreflections," Proceedings of International Conference on Pattern Recognition,vol.1,pp.785-790,Atlantic City,N J,USA,1990.
[54]C.Novak and S.Shafer,"Anatomy of Color Histogram," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,Champaign,IL,USA,pp.599-605,1992.
[55]R.T.Tan,K.Nishino and K.Ikeuchi,"Separating Reflection Components Based on Chromaticity and Noise Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.26,no.10,pp.1373-1379,2004.
[56]R.T.Tan and K.Ikeuchi,"Reflection Components Decomposition of Textured Surfaces Using Linear Basis Functions," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.1,pp.125-131,San Diego,CA,USA,2005.
[57]K.-J.Yoon,Y.Choi and I.S.Kweon,"Fast Separation of Reflection Components Using A Specular-Invariant Image Representation," Proceedings of International Conference on Image Processing,pp.973-980,Atlanta,GA,USA,2006.
[58]M.Bertalmio,G.Sapiro,C.Ballester and V.Caselles,"Image Inpainting," Proceedings of ACM SIGGRAPH,pp.417-424,New Orleans,USA,2000.
[59]T.F.Chan and J.Shen,"Mathematical Models for Local Nontexture Inpintings," SIAM Journal of Applied Mathematics,voL 62,no.3,pp.1019-1043,2001.
[60]T.F.Chan,J.Shen and L.Vese,"Variational PDE Models in Image Processing," Notices of American Mathematical Society,vol.50,no.1,pp.14-26,2002.
[61]P.Tan,S.Lin and L.Quan,"Separation of Highlight Reflections on Textured Surfaces,"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.vol.2,pp.1855-1860,New York,NY,USA,2006.
[62]钟锡华,现代光学基础,北京大学出版社,2003.
[63]M.Born and E.Wolff,Principles of Optics,London:Pergamon,1965.
[64]L.B.Wolff and T.E.Boult,"Constraining Object Features Using a Polarization Reflectance Model," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.13,no.7,pp.635-657,1991.
[65]L.B.Wolff,"Surface Orientation From Polarization Images," Optics,Illumination,and Image Sensing For Machine Vision Ⅲ,Proceedings of SPIE,vol.850,pp.110-121,1987.
[66]S.Umeyama and G.Godin,"Separation of Diffuse and Specular Components of Surface Reflection by Use of Polarization and Statistical Analysis of Images," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.26,no.5,pp.639-647,2004.
[67]A.Hyvarinen and E.Oja,"Independent Component Analysis:Algorithms and Applications,"Neural Networks,vol.13,pp.411-430,2000.
[68]G.-J.Jang and T.-W.Lee,"A Maximum Likelihood Approach to Single-Channel Source Separation," Journal of Machine Learning Research,vol.4,pp.1365-1392,2003.
[69]A.J.Bell and T.J.Sejnowski,"An Information-Maximization Approach to Blind Separation and Blind Deconvolution," Neural Computation,vol.7,pp.1129-1159,1995.
[70]S.Umeyama,"Blind Deconvolution of Images Using Gabor Filters and Independent Component Analysis," Proceedings of International Symposium on Independent Component Analysis and Blind Signal Separation,pp.319-324,Nara,Japan,2003.
[71]M.S.Bartlett,Pace Image Analysis by Unsupervised Learning.Kluwer Academic,2001.
[72]S.Makeig,A.J.Bell,T.-P.Jung and T.J.Sejnovsld,"Independent Component Analysis of Electroencephalographic Data," Advances in Neural Information Processing Systems 8,MIT Presss,pp.145-151,1996.
[73]Y.Sato and K.Ikeuchi,"Temporal-Color Space Analysis of Reflection," Technical Report,CMU-CS-92-207,Computer Science Department,Carnegie Mellon University,1992.
[74]S.Lin,"Generation of Diffuse and Specular Appearance from Photometric Images,"Proceedings of Workshop on Photometric Modeling for Computer Vision and Graphics,pp.39-46,Fort Collins,CO,USA,1999.
[75]S.Lin and S.W.Lee,"An Appearance Representation for Multiple Reflection Components,"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.1105-1110,Hilton Head Island,SC,USA,2000.
[76]E.P.F.Lafortune,S.Foo,K.E.Torrance and D.P.Greenberg,"Non-Linear Approximation of Reflectance Functions," Proceedings ofA CM SIGGRAPH,pp.117-126,Los Angeles,CA,USA,1997.
[77]S.W.Lee and R.Bajcsy,"Detection of Specularity Using Color and Multiple Views,"Image and Vision Computing,vol.10,pp.643-653,1992.
[78]Y.Y.Schechner,N.Kiryati,R.Basri,"Separation of Transparent Layers Using Focus,"Proceedings of International Conference on Computer Vision,pp.1061-1066,Bombay,India,1998.
[79]E.H.Adelson and P.Anandan,"Ordinal Characteristics of Transparency," AAAI Workshop on Qualitative Vision,pp.77-81,1990.
[80]S.Nakauchi,S.Usui,J.Parkkinen and P.Silfsten,"Computational Explanations for Color Transparency," Proceedings of International Joint Conference on Neural Networks,vol.1,pp.170-173,Washington DC,USA,1999.
[81]B.A.Olshausen and D.J.Field,"Field Emergence of Simple-Cell Receptive Field Properties by Learning a Sparse Code for Natural Images," Nature,vol.381,pp.607-609,1996.
[82]E.P.Simoncelli,"Statistical Models for Images:Compression Restoration and Synthesis,"Proceedings of Asilomar Conference on Signals,Systems and Computers,pp.673-678,1997.
[83]W.T.Freeman and E.C.Pasztor,"Learning to Estimate Scenes from Images," Advance Neural Information Processing Systems 11,MIT Press,1999.
[84]B.J.Frey,R.Koetter and N.Petrovic,"Very Loopy Belief Propagation for Unwrapping Phase Images," Advance Neural Information Processing 14,2001.
[85]J.Daugman,"Iris Recognition," American Scientist,vol.89,pp.326-333,2001.
[86]J.Daugman,"High Confidence Visual Recognition of Persons by A Test of Statistical Independence," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.15,pp.1148-1161,1993.
[87]T.Hutchinson,K.White,K.Reichert and L.Frey,"Human-Computer Interaction Using Eye-Gaze Input," IEEE Transactions on Systems,Man and Cybernetics,vol.19,pp.1527-1534,1989.
[88]R.Jacob,"What You Look at Is What You Get:Eye Movement-Based Interaction Techniques," Proceedings of ACM Computer-Human Interaction,pp.11-18,1990.
[89]A.Lefohn,R.Caruso,E.Reihard,B.Budge and P.Shirley,"An Ocularist's Approach to Human Iris Synthesis," IEEE Computer Graphics and Applications,vol.23,pp.70-75,2003.
[90]P.Debevec,"Virtual Cinematography:Relighting Through Computation," Computer,vol.39,no.8,pp.57-65,2006.
[91]P.Debevec,"Rendering Synthetic Objects into Real Scenes:Bridging Traditional and Image-based Graphics with Global Illumination and High Dynamic Range Photography,"Proceedings of ACM SIGGRAPH,pp.189-198,Orlando,FL,USA,1998.
[92]D.R.Hougen and N.Ahuja,"Estimation of the Light Source Distribution and Its Use in Integrated Shape Recovery from Stereo and Shading," Proceedings of International Conference on Computer Vision,pp.148-155,Berlin,Germany,1993.
[93]Q.Zheng and R.Chellappa,"Estimation of Illuminant Direction,Albedo and Shape from Shading," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.13,pp.680-702,1991.
[94]Y.Wang and D.Samaras,"Estimation of Multiple Illuminants from A Single Image of Arbitrary Known Geometry," Proceedings of European Conference on Computer Vision,Part 1,pp.272-288,2002.
[95]Y.Zhang and Y.-H.Yang,"Multiple Illuminant Direction Detection with Application to Image Synthesis," IEEE Transactions on Pattern Analysis and Machine Intelligence,vol.23,no.8,pp.915-920,2001.
[96]I.Sato,Y.Sato and K.Ikeuchi,"Illumination Distribution from Brightness in Shadows:Adaptive Estimation of Illumiuation Distribution with Unknown Reflectance Properties in Shadow Regions," Proceedings of International Conference on Computer Vision,pp.875-883,Kerkyra,Corfu,Greece,1999.
[97]I.Sato,Y.Sato,and K.Ikeuchi,"Illumination Distribution from Shadows," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.306-312,Collins,CO,USA,1999.
[98]I.Sato,Y.Sato,and K.Ikeuchi,"Stability Issues in Recovering Illumination Distribution from Brightness in Shadows," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.400-407,Kauai,HI,USA,2001.
[99]N.Tsumura,M.Dang,T.Makino and Y.Miyake,"Estimation the Directions to Light Sources Using Images of Eye for Reconstructing 3D Human Face," Proceedings of IS&T/SID's Color Image Conference,pp.77-81,2003.
[100]K.Nishino and S.K.Nayar,"The World in An Eye," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.444-451,2004.
[101]K.Nishino and S.K.Nayar,"Corneal Imaging System:Environment from Eyes,"International Journal of Computer Vision,vol.70,no.1,pp.23-40,2006.
[102]K.Nishino and S.K.Nayar,"Eyes for Relighting," ACM Transactions on Graphics,vol.23,pp.704-711,2004.
[103]K.Nishino,P.N.Belhumeur and S.K.Nayar,"Using Eye Reflections for Face Recognition Under Varying Illumination," Proceedings of International Conference on Computer Vision,vol.1,pp.519-526,2005.
[104]M.Lam and G.Baranoski,"A Predictive Light Transport Model for the Human Iris,"Proceedings of EUROGRAPHICS,pp.359-368,2006.
[105]P.D.Imesch,I.H.L.Wallow and D.M.Albert,"The Color of the Human Eye:A Review of Morphologic Correlates and of Some Conditions that Affect Iridial Pigmentation," Survey of Ophthalmology,vol.41,pp.117-123,1997.
[106]S.J.Preece and E.Claridge,"Monte Carlo Modeling of The Spectral Reflectance of The Human Eye," Physics in Medicine and Biology,vol.47,pp.2863-2877,2002.
[107]S.Fan,C.R.Dyer and L.Hubbard,"Quantification and Correction of Iris Color," Technical Report 1945,University of Wisconsin-Madison,2003.
[108]E.H.Land,"Recent Advances in Retinex Theory," Vision Research,vol.26,pp.7-21,1986.
[109]G.D.Finlayson,S.D.Hordley and M.S.Drew,"Removing Shadows from Images,"Proceedings of European Conference on Computer Vision,pp.823-836,2002.
[110]P.L.Kaufman and A.Aim,editors.Adler's Physiology of the Eye:Clinical Application.Mosby,10~(th)edition,2003.
[111]H.V.Helmholtz.Physiologic Optics,volume 1 and 2.Voss,Hamburg,Germany,third edition,1909.
[112]D.W.Hansen and A.Pecc,"Eye Typing Off the Shelf," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,pp.159-164,Washington DC,USA,2004.
[113]C.P.Stein,"Accurate Internal Camera Calibration Using Rotation,with Analysis of Sources of Errors," Proceedings of International Conference on Computer Vision,pp.230-236,Cambrigde,MA,USA,1995.
[114]J.-G.Wang,E.Sung and R.Venkateswarlu,"Eye Gaze Estimation from a Single Image of One Eye," Proceedings of International Conference on Computer Vision,pp.136-143,2003.
[115]S.K.Nayar,"Sphereo:Recovering Depth Using a Single Camera and Two Specular Spheres," SPIE:Optics,Illumination and Image Sensing for Machine Vision Ⅱ,1988.
[116]S.A.Nene and S.K.Nayar,"Stereo Using Mirrors," Proceedings of International Conference on Computer Vision,pp.1087-1094,1998.
[117]W.H.Press,S.A.Teukolsky,W.T.Vettedmg and B.P.Flannery,Numerical Recipes in C++:The Art of Scientific Computing,Cambridge University Press,2~(nd)edtion,2002.
[118]Y.-Yu.Chuang,B.Curless,D.H.Salesin and R.Szeliski,"A Bayesian Approach to Digital Matting," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,264-271,2001.
[119]J.Sun,J.Jia,C.-K,Tang and H.-Y.Shum,"Poisson Matting," A CM Transactions on Graphics,vol.23,no.3,pp.315-321,2004.
[120]C.B.Atkins,Classification-Based Methods in Optimal Image Interpolation,PhD Dissertation,Purdue University,December,1998.
[121]L.Parida,D.Geiger and R.Hummel,"Kona:A Multi-Junction Detector Using Minimum Description Length Principle," Proceedings of the First International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition,pp.51-65,1997.
[122]W.Yu,K.Daniilidis and G.Sommer,"Approximate Orientation Steerability Based on Angular Gaussians," IEEE Transactions on Image Processing,vol.10,no.2,pp.193-205,2001.
[123]T.Lmdeberg,"Junction Detection with Automatic Selection of Detection Scales and Localization Scales," Proceedings of International Conference on Image Processing,vol.1,pp.924-928,Austin,TA,USA,1994.
[124]V.Caselles,B.Coil and J.-M.Morel,"Junction Detection and Filtering:A Morphological Approach," Proceedings of International Conference on Image Processing,vol.1,pp.493-496,1996.
[125]A.P.Dempster,N.M.Laird and D.B.Rubin,"Maximum Likelihood from Incomplete Data Via the EM Algorithm," Journal of the Royal Statistical Society,Series B,vol.39,no.1,pp.1-38,1997.
[126]C.Tomasi,"Estimating Gaussian Mixture Densities with EM-A Tutorial," Technical Report,Duke University,2004.
[127]J.Bilmes,"A Gentle Tutorial of the EM Algorithm and Its Application to Parameter Estimation for Ganssian Mixture and Hidden Markov Models," Technical Report TR-97-021,International Computer Science Institute,Berkeley CA,1998.
[128]Raanan Fattal,Dani Lischinski,Michael Werman,"Gradient Domain High Dynamic Range Compression," Proceedings of ACM SIGGRAPH,pp.249-256,2002.
[129]P.Perez,M.Gangnet,A.Blake."Possion Image Editing," ACM Transactions on Graphics,vol.22,no.3,pp.313-318,San Diego,CA,USA,2003.
[130]朱云芳,基于图像拼接的视频编辑,浙江大学博士论文,2006.
[131]Y.Yu,K.Zhou,D.Xu,X.Ski,H.Bao and H.-Y.Sham,"Mesh Editing with Poisson-Based Gradient Field Manipulation," ACM Transactions on Graphics,vol.23,no.3,pp.641-648,Los Angeles,CA,USA,2003.
[132]D.M.Blei,A.Y.Ng and M.I.Jordan,"Latent Dirichlet Allocation," Journal of Machine Learning Research,vol.3,pp.993-1022,2003.
[133]T.Hofmann,"Probabilistic Latent Semantic Indexing," Proceeding of the SIGIR,pp.50-57,Berkely,CA,USA,1999.
[134]K.Nigam,A.McCallum,S.Thrum and T.Mitchell,"Text Classification From Labeled and Unlabeled Documents Using EM," Machine Learning,vol.39,no.2/3,pp.103-134,2000.
[135]王惠锋,孙正兴,王箭,“语义图像检索研究进展,”计算机研究与发展,vol.39,no.5,pp.513-523,2002.
[136]X.Wang and E.Grimson,"Spatial Latent Dirichlet Allocation," Proceedings of Neural Information Processing System Conference 20,pp.1577-1584,MIT Press,Cambrigdge,MA,2008.
[137]L.Cao and L.Fei-Fei,"Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes," Proceedings of International Conference on Computer Vision,vol.1,pp.1-8,Rio de Janeiro,Brazil,2007.
[138]R.Fergus,P.Perona and A.Zisserman,"Object Class Recognition by Unsupervised Scale-Invariant Learning," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.264-271,Madison,Vii,USA,2003.
[139]B.C.Russell,A.A.Efros,J.Sivic,W.T.Freeman and A.Zisserman,"Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.1605-1614,New York,NY,USA,2006.
[140]J.Sivic,B.C.Russell,A.A.Effros,A.Zisserman and W.T.Freeman,"Discovering Object Categories in Image Collections," Technical Report,MIT-CSAIL-TR-2005-012,2005.
[141]M.-E.Nilsback and A.Zisserman,"A Visual Vocabulary for Flower Classification,"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.2,pp.1447-1454,New York,NY,USA,2006.
[142]L.Fei-Fei and P.Perona,"A Bayesian Hierarchical Model for Learning Natural Scene Categories," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,vol.1,pp.524-531,San Diego,CA,USA,2005.
[143]R.Fergus,L.Fei-Fei,P.Perona and A.Zisserman,"Learning Object Categories from Google's Image Search," Proceedings of lnternational Conference on Computer Vision,vol.2,pp.1816-1823,,Beijing,China,2005.
[144]J.Vogel and B.Schiele,"Semantic Modeling of Natural Scenes for Content-Based Image Retrievel," International Journal of Computer Vision,vol.72,no.2,pp.133-157,2007.
[145]D.Lowe,"Object Recognition From Local Scale-lnvariant Features," Proceedings of International Conference on Computer Vision,pp.1150-1157,Kerkyra,Corfu,Greece,1999.
[146]T.Hofrnann,"Unsupervised Learning by Probabilistic Latent Semantic Analysis," Machine Learning,vol.42,pp.177-196,2001.
[147]A.Gelman,J.B.Carlin,Stern H.S.and Rubin D.B.,Bayesian Data Analysis,Chapman Hall/CRC,1995.
[148]M.Jordan,Z.Ghahramani,T.Jaakkola and L.Saul,"An Introduction to Variational Methods for Graphical Models," Machine Learning,vol.37,no.2,pp.183-233,1999.
[149]J.Winn and C.Bishop,"Variational Message Passing," Journal of Machine Learning Research,vol.6,pp.661-694,2005.
[150]T.Griffths,"Gibbs Sampling in the Generative Model of Latent Dirichlet Allocation,"Technical Report,University of California,Berkerley,2002.
[151]B.Walsh,"Markov Chain Monte Carlo and Gibbs Sampling," Technical Report,MIT,2004.