基于语义的图像显示适配技术研究
摘要
图像适配问题是计算机图形学和图像处理领域的重要研究方向。传统适配方法通过直接缩放图像尺寸以适应目标屏幕，会导致适配过程中图像主要内容的扭曲变形，或丢弃了图像中大量的重要信息，无法将图像的真实内容高效、准确、全面的传递给用户。基于语义的图像显示适配技术通过对图像内容进行理解识别，可以有效避免传统方法的弊端，成为近来热门的研究课题之一。
本文在系统论述图像适配问题的理论基础、技术特点、国内外研究现状、研究难点、应用的基础上，提出了对图像进行分类的方法，并就三种图像类型：纹理图像，一般自然图像和具有对称特性的图像，分别提出了三种图像适配方法。
首先对于自然图像，设计一种可逆的显示适配方法。该方法针对自然图像多次适配操作过程中出现的误差累计问题，提出由正向和逆向两部分能量函数组成的可逆能量函数，以解决自然图像的可逆显示适配问题。同时，针对现有方法在图像放大过程中出现的走样问题，构建了适合图像放大过程的“虚拟点”数据结构，用以预测在图像放大过程中填充像素点对整个图像适配过程的影响，从而大大提高了图像放大质量。
其次对于纹理图像，基于纹理图像纹理单元尺度性强且结构性脆弱的特点，本文提出利用纹理合成的方法，实现纹理图像基于语义的适配过程，以灵活得到不同目标尺度的纹理图像。鉴于纹理合成时间和速度之间的矛盾，提出了基于小波多分辨率金字塔的纹理合成方法，在保证纹理合成质量的同时，大大提高了纹理合成的速度。同时提出了改进的纹理邻域匹配策略，并采用IMED距离进行邻域相似度的度量。最终在多种图像上进行实验，该方法可以取得比较满意的效果。
再次，具有对称性质的图像是日常生活中常见的一类图像。通过分析现有四类典型方法，本文分别提出了针对平移对称图像和旋转对称图像的基于语义的对称图像显示适配方法。通过对对称单元的分析识别，采用图像概要的方式，将图像中的对称单元进行增减，从而实现整个对称区域的显示适配。同时，对于适配后的对称与非对称临界区域，利用Deghosting方法进行边界融合，使得最终结果视觉自然无明显形变。
最后，总结了本文的工作，从研究内容，研究方法和研究结果三方面进行阐述，并对未来工作方向进行预测。
Image retargeting is an important research area of computer graphics and imageprocessing. Previous methods scale images into target size, but fail to keep the imagein a semantic way. Images maybe shrink badly and main parts of images will bedistorted during the resizing process. At the other hands, some approaches only retainthe important parts and discards the surrounding to fit the display resolution, thisusually discard large number of background information. The retargeting methodswithout semantic feature usually lead to user’s misunderstanding. Image retargetingbased on semantic recognizing considers image content in the process of imageresizing, which is now one of the research focuses.
This thesis first surveys the existing works on image retargeting. The surveyincludes theoretical basis, technical characteristics, related work, difficulties,development and applications. Based on three kinds of specific images (texture,nature image and image with symmetry), the thesis proposes different retargetingmethods.
For natural images, seam carving is an effective operator supportingcontent-aware resizing for both image reduction and expansion. However, repeatedseam removing and inserting processes lead to excessively distortion image whenimposed on seam insertion and removal operations or the other way around. Byconsidering the relationship between seams removing and inserting processes, wepresent an ameliorated energy function to minimize aliasing.“Forward Energy” isonly an effective improvement to image reduction. Moreover, the thesis propose anovel”Visual Points” structure which distinguishes the “Forward Energy” of seaminsertion from that of seam removal, and improves seam insertion operations greatly.
The thesis introduces texture synthesis method to texture image retargeting.Time consumption and quality are two main concerns to texture synthesis algorithm.A wavelet based texture optimization approach is proposed in this paper. Twomulti-resolution texture pyramids are used: an input pyramid built by the wavelettransform of the exemplars and an output pyramid reconstruction from the inversewavelet transform. In the step of nearest neighborhood searching, wavelet coefficientis integrated to estimate neighborhoods' distance, instead of RGB and other channels.Because the wavelet transform is reversible and nondestructive, this strategy does notdebase quality.
Images with symmetry exist everywhere. Symmetry summarization can resize atranslational symmetric image while maintaining the semantics quite well. The thesispresents a novel retargeting method that allows arbitrarily resizing the ratio ofrotational symmetric images as well as preserving their symmetric structure andseamlessness. First, we detect the rotational symmetric area, and convert the area intolinearly translation symmetric form. Then, we construct a texture feature map andextract potential symmetric cells through symmetry group analysis. The resizingprocess is finally achieved by increasing or removing proper-measured symmetriccells. Both the experimental results and user study demonstrate superior performanceof our algorithm compared with other existing methods.
At last, some examples are illustrated applying the proposed algorithm ondifferent kinds of images, which concludes the thesis with discussions of the digitalresults and limitations of the presented method.
本文在系统论述图像适配问题的理论基础、技术特点、国内外研究现状、研究难点、应用的基础上，提出了对图像进行分类的方法，并就三种图像类型：纹理图像，一般自然图像和具有对称特性的图像，分别提出了三种图像适配方法。
首先对于自然图像，设计一种可逆的显示适配方法。该方法针对自然图像多次适配操作过程中出现的误差累计问题，提出由正向和逆向两部分能量函数组成的可逆能量函数，以解决自然图像的可逆显示适配问题。同时，针对现有方法在图像放大过程中出现的走样问题，构建了适合图像放大过程的“虚拟点”数据结构，用以预测在图像放大过程中填充像素点对整个图像适配过程的影响，从而大大提高了图像放大质量。
其次对于纹理图像，基于纹理图像纹理单元尺度性强且结构性脆弱的特点，本文提出利用纹理合成的方法，实现纹理图像基于语义的适配过程，以灵活得到不同目标尺度的纹理图像。鉴于纹理合成时间和速度之间的矛盾，提出了基于小波多分辨率金字塔的纹理合成方法，在保证纹理合成质量的同时，大大提高了纹理合成的速度。同时提出了改进的纹理邻域匹配策略，并采用IMED距离进行邻域相似度的度量。最终在多种图像上进行实验，该方法可以取得比较满意的效果。
再次，具有对称性质的图像是日常生活中常见的一类图像。通过分析现有四类典型方法，本文分别提出了针对平移对称图像和旋转对称图像的基于语义的对称图像显示适配方法。通过对对称单元的分析识别，采用图像概要的方式，将图像中的对称单元进行增减，从而实现整个对称区域的显示适配。同时，对于适配后的对称与非对称临界区域，利用Deghosting方法进行边界融合，使得最终结果视觉自然无明显形变。
最后，总结了本文的工作，从研究内容，研究方法和研究结果三方面进行阐述，并对未来工作方向进行预测。
Image retargeting is an important research area of computer graphics and imageprocessing. Previous methods scale images into target size, but fail to keep the imagein a semantic way. Images maybe shrink badly and main parts of images will bedistorted during the resizing process. At the other hands, some approaches only retainthe important parts and discards the surrounding to fit the display resolution, thisusually discard large number of background information. The retargeting methodswithout semantic feature usually lead to user’s misunderstanding. Image retargetingbased on semantic recognizing considers image content in the process of imageresizing, which is now one of the research focuses.
This thesis first surveys the existing works on image retargeting. The surveyincludes theoretical basis, technical characteristics, related work, difficulties,development and applications. Based on three kinds of specific images (texture,nature image and image with symmetry), the thesis proposes different retargetingmethods.
For natural images, seam carving is an effective operator supportingcontent-aware resizing for both image reduction and expansion. However, repeatedseam removing and inserting processes lead to excessively distortion image whenimposed on seam insertion and removal operations or the other way around. Byconsidering the relationship between seams removing and inserting processes, wepresent an ameliorated energy function to minimize aliasing.“Forward Energy” isonly an effective improvement to image reduction. Moreover, the thesis propose anovel”Visual Points” structure which distinguishes the “Forward Energy” of seaminsertion from that of seam removal, and improves seam insertion operations greatly.
The thesis introduces texture synthesis method to texture image retargeting.Time consumption and quality are two main concerns to texture synthesis algorithm.A wavelet based texture optimization approach is proposed in this paper. Twomulti-resolution texture pyramids are used: an input pyramid built by the wavelettransform of the exemplars and an output pyramid reconstruction from the inversewavelet transform. In the step of nearest neighborhood searching, wavelet coefficientis integrated to estimate neighborhoods' distance, instead of RGB and other channels.Because the wavelet transform is reversible and nondestructive, this strategy does notdebase quality.
Images with symmetry exist everywhere. Symmetry summarization can resize atranslational symmetric image while maintaining the semantics quite well. The thesispresents a novel retargeting method that allows arbitrarily resizing the ratio ofrotational symmetric images as well as preserving their symmetric structure andseamlessness. First, we detect the rotational symmetric area, and convert the area intolinearly translation symmetric form. Then, we construct a texture feature map andextract potential symmetric cells through symmetry group analysis. The resizingprocess is finally achieved by increasing or removing proper-measured symmetriccells. Both the experimental results and user study demonstrate superior performanceof our algorithm compared with other existing methods.
At last, some examples are illustrated applying the proposed algorithm ondifferent kinds of images, which concludes the thesis with discussions of the digitalresults and limitations of the presented method.
引文
[1]Jain A.K., Fundamentals of digital image processing, New Jersey:Prentice Hall,1989.
[2]彭群生，鲍虎军，金小刚，计算机真实感图形的算法基础，北京：科学出版社，1999.
[3]Suh, B., Ling, H., Bederson, B. B., and Jacobs, D. W. Automaticthumbnail cropping and its electiveness, Proceedings of UIST,2003,95~104.
[4]A. Santella, M. Agrawala, D. DeCarlo, D. Salesin, and M. Cohen,Gaze-based interaction for semi-automatic photo cropping, Proceedings ofthe SIGCHI conference on Human Factors in computing systems, New York,NY,2006, pp.771~780.
[5]S. Avidan and A. Shamir, Seam carving for content-aware image resizing,ACM Trans. Graph., vol.26, no.3, pp.10,2007.
[6]M. Rubinstein, A. Shamir, and S. Avidan, Improved seam carving forvideo retargeting, ACM Transactions on Graphics,2008, vol.27, no.3,pp.1~9.
[7]H. Wu, Y.S. Wang, K.C. Feng, T.T. Wong, T.Y. Lee, and P. A. Heng,Resizing by symmetry summarization, ACM Transaction on Graphics,2010,vol.29, no.159.
[8]W. Dong, N. Zhou, J.C. Paul, and X. Zhang, Optimized image resizingusing seam carving and scaling, ACM SIGGRAPH Asia2009, New York, NY, USA:ACM,2009, pp.125:1~125:10.
[9]M. Rubinstein, A. Shamir, and S. Avidan, Multi-operator mediaretargeting, ACM Trans. Graph.,2009, vol.28, pp.23:1–23:11.
[10]Y. Pritch, E. Kav-Venaki, and S. Peleg, Shift-map image editing,ICCV’09, Kyoto,2009, pp.151~158.
[11]Zhang, G.X., Cheng, M.M., Hu, S.M., and Martin, R, A shape-preservingapproach to image resizing, Computer Graphics Forum,2009, vol.28, no.7,1897~1906.
[12]D.S. Hwang and S.Y. Chien, Content-aware image resizing usingperceptual seam carving with human attention model, IEEE InternationalConference on Multimedia and Expo,2008, pp.1029~1032.
[13]O. S. Yu-Shuen Wang, Chiew-Lan Tai and T.Y. Lee, Optimizedscale-and-stretch for image resizing, Proceedings of ACM SIGGRAPH ASIA,2008, vol.27, no.5.
[14]H. Huang, T. Fu, P. Rosin, and C. Qi, Real-time content aware imageresizing, Science in China Series F: Information Sciences,2009, vol.52,no.2, pp.172~182.
[15]G. Pan, W. Li, W. Bai, Reverse seam carving, Proceedings of the SixthInternational Conference on Image and Graphics,2011, pp.50~55.
[16]Barnes, C., Shechtman, E., Finkelstein, A., and Goldman, D. B.PatchMatch: A randomized correspondence algorithm for structural imageediting, ACM Trans. On Graph,28,3.
[17]C. Harris and M. Stephens, A combined corner and edge detector, inProceedings of the4th Alvey Vision Conference,1988, pp.147~151
[18]P. Viola and M. Jones, Rapid object detection using a boosted cascadeof simple features, Computer Vision and Pattern Recognition,2001, vol.1, pp.511~518.
[19]L. Itti, C. Koch, and E. Niebur, A model of saliency-based visualattention for rapid scene analysis, Pattern Analysis and MachineIntelligence, IEEE Transactions on,1998, vol.20, no.11, pp.1254~1259.
[20]D. Hoiem, A. Efros, and M. Hebert, Geometric context from a singleimage, Tenth IEEE International Conference on Computer Vision,2005, vol.1, pp.654~661.
[21]L. Wolf, M. Guttmann, and D. Cohen-Or, Non-homogeneous content-drivenvideo-retargeting, IEEE11th International Conference on Computer Vision,2007, pp.1~6.
[22]V. Kraevoy, A. Sheffer, A. Shamir, and D. Cohen-Or, Nonhomogeneousresizing of complex models, ACM Trans. Graph.,2008, vol.27, pp.111:1~111:9.
[23]Jinjie Lin, Daniel Cohen-Or, Hao Zhang, Cheng Liang, Andrei Sharf,Oliver Deussen, Baoquan Chen, Structure-preserving retargeting ofirregular3D architecture, ACM Transactions on Graphics,2011, vol.30,no.6.
[24]Wang, Y.S., Lin, H.C., Sorkine, O., and Lee, T.Y, Motionbased videoretargeting with optimized crop-and-warp, ACM Transaction on Graphics,2010, vol.29, no.3.
[25]Wang, Y.S., Fu, H., Sorkine, O., Lee, T.Y., and Seidel, H.P.,Motion-aware temporal coherence for video resizing, ACM Transaction onGraphics,2009, vol.28, no.5.
[26]Zhang, Y.F., Hu, S.M., and Martin, R. R., Shrinkability maps forcontent-aware video resizing, Pacific Graphics,2008.
[27]Alexei Efros, Thomas Leung, Texture synthesis by non-parametricsampling [C], ICCV '99: Proceedings of the International Conference onComputer Vision,1999,2:1033~1038.
[28]Li-Yi Wei, Marc Levoy, Fast texture synthesis using tree-structuredvector quantization, Computer Graphics Proceedings, New York, NY,2000,479~488.
[29]Michael Ashikhmin, Synthesizing natural textures, Proceedings of the2001symposium on Interactive3D graphics, New York, NY, USA: ACM Press,2001,217~216.
[30]Alexei Efros, W T Freeman, Image quilting for texture synthesis andtransfer, Eugene Fiume, SIGGRAPH2001, Computer Graphics Proceedings,2001,341~347.
[31]E.Simoncelli, J. Portilla, Texture characterization via jointstatistics of wavelet coefficient magnitudes, In Fifth InternationalConference on Image Processing, Chicago: IEEE ComputerSociety,1998,62~66.
[32]X. Tong, J. Zhang, L. Liu et al, Synthesis of Bidirectional TextureFunctions on Arbitrary Surfaces, ACM Trans. Graph,2002,21(3):665~672.
[33]Vivek Kwatra, Irfan E A, Texture Optimization for Example-basedSynthesis, ACM Transactions on Graphics,2005,24(3),795~802.
[34]Simakov, D., Caspi, Y., Shechtman, E., and Irani, M., Summarizingvisual data using bidirectional similarity, CVPR,2008.
[35]Cho, T. S., Butman, M., Avidan, S., and Freeman, W. T. The patchtransform and its applications to image editing, CVPR,2008.
[36]D. A. Clausi and M. E. Jernigan, Designing gabor filters for optimaltexture separability, Pattern Recognition,2000, vol.33, no.11, pp.1835~1849.
[37]J. Zhang, T. Tan, and L. Ma, Invariant texture segmentation viacircular gabor filters, Proceedings of16th International Conference onPattern Recognition,2002, vol.2, pp.901~904.
[38]V. Levesque, Texture segmentation using gabor filters, Ceter ForIntelligent,2000.
[39]A.K. Jain, F. Farrokhnia, Unsupervised texture segmentation usingGabor filters, Pattern Recognition,1991, vol.24, no.12, pp.1167~1186.
[40]Canada B, Thomas G K, Cheng K C, Towards efficient automatedharacterization of irregular histology images via transformation tofrieze like patterns, In Proceedings of the2008internationalconferenceon Content-based image and video retrieval,2008, pp.581~590.
[41]Vivek Kwatra, SCH DL A., Essa I, Turk G., Bobick, A, Graph cut textures:Image and video synthesis using graph cuts, ACM Transactions on Graphics,2003,22(3):277~286.
[42]V. S. N. Prasad, L. S. Davis, Detecting rotational symmetries,Proceedings of the Tenth IEEE International Conference on Computer Vision,2005, vol.2, pp.954~961.
[43]Y. Liu, J. Hays, Y.Q. Xu, and H.Y. Shum, Digital papercutting, ACMSIGGRAPH2005Sketches,2005.
[44]H. Cornelius, G. Loy, Detecting rotational symmetry under affineprojection, Proceedings International Conference on Pattern Recognition,2006, pp.292~295.
[45]G. Loy and J. olof Eklundh, Detecting symmetry and symmetricconstellations of features, ECCV,2006, pp.508~521.
[46]Y. Keller, Y. Shkolnisky, A signal processing approach to symmetrydetection, IEEE Transaction on Image Processing,2006, vol.15, no.8,pp.2198~2207.
[47]S. Lee, R. Collins, and Y. Liu, Rotation symmetry group detection viafrequency analysis of frieze-expansions, IEEE Conference on ComputerVision and Pattern Recognition,2008, pp.1~8.
[48]LEE S., LIU Y., Skewed rotation symmetry group detection, IEEETransactions on Pattern Analysis and Machine Intelligence,2010, vol.32,no.9, pp.1659~672.
[49]T. N. Pappas and R. J. Safranek, Perceptual criteria for image qualityevaluation, in Handbook of Image and Video Processing. Academic Press,2000, pp.669~684.
[50]Z. Wang and A. Bovik, Modern Image Quality Assessment, SynthesisLectures on Image, Video&Multimedia Processing,2006.
[51]Y.J. Liu, X. Luo, Y.M. Xuan, W.F. Chen, and X.L. Fu, Image retargetingquality assessment, Computer Graphics Forum,2011.
[52]Levy B., Constrained texture mapping for polygonal meshes.Proceedings of SIGGRAPH,2001,417~424.
[53]Catmull E, Subdivision algorithm for computer display of curvedsurfaces, Ph.D. Thesis, Department of Computer Science, University ofUtah, Salt Lake City, Utah,1974.
[54]Pedersen H.K, Decorating implicit surfaces. Computer Graphics,Proceedings of Annual Conference Series,1995,291~300.
[55]Soler C., Cani M., Angelidis A., Hierarchical pattern mapping.Computer Graphics Proceedings, Annual Conference Series,2002,673~680.
[56]Andrew Witkin, Michael Kass, Reaction-diffusion textures, ComputerGraphics,1991,25(4):299~308.
[57]Dorsey J., Edelman A., Legakis J., Jensen H.W, Pedersen H.K, Modelingand rendering of weathered stone. Proceedings of SIGGRAPH1999.1999,225~234.
[58]Perlin K, An image synthesizer, Computer Graphics(SIGGRAPH1985).July1985,19(3):287~296.
[59]Darwyn R. P, Solid texturing of complex surfaces, Computer Graphics(SIGGRAPH1985),1985,19(3):279~286.
[60]Ebert D. S. et al. Texturing and modeling: a procedural approach.2ndedition, San Diego, USA: Academic Press.1998.
[61]Worley S., A cellular texture basis function, Computer GraphicsProceedings, Annual Conference Series(SIGGRAPH1996),1996,291~294.
[62]Neyret F, Cani M, Pattern-based texturing revisited, SIGGRAPH1999,Computer Graphics Proceedings,1999,235~242.
[63]Turk G, Generating textures on arbitrary surfaces usingreaction-diffusion, Computer Graphics (SIGGRAPH1991),1991,25(4):289~298.
[64]Fleischer K, Laidlaw D, Currin B, Barr A, Cellular texture generation,Proceedings of SIGGRAPH1995,1995,239~248.
[65]M Walter, A Fournier, Clonal mosaic model for the synthesis ofmammalian coat patterns, In Proceeding of Graphics Interface,1998,82~91.
[66]David J. Heeger, James R. Bergen, Pyramid-Based Texture AnalysisSynthesis, Proceedings of the1995International Conference on ImageProcessing,1995,229~238.
[67]Jeremy S. De Bonet, Multi-resolution sampling procedure for analysisand synthesis of texture images, Computer Graphics,1997,31:361~368.
[68]Chen J, Zeng B. Patch-Based Multi-Resolution Real-Time TextureSynthesis in Wavelet Domain, International Conference on Communications,Circuits and Systems,2004,2:788~791.
[69]Leandro Tonietto, Marcelo Walter, Claudio Rosito Jung, Patch-basedtexture synthesis using wavelets, Proceedings of the XVIII BrazilianSymposium on Computer Graphics and Image Processing, Washington, DC, USA:IEEE Computer Society,2005,383.
[70]Gallagher, C., Kokaram, A. Nonparametric wavelet based texturesynthesis, IEEE international Conference on Image Processing2005,2005,9,2:462~465.
[71]Praun E, Finkelstein A, Hoppe H, Lapped texture, Computer GraphicsProceedings,2000,55~64.
[72]Hays, J., Leordeanu, M., Efros, A. A., and Liu, Y. Discovering textureregularity as a higher-order correspondence problem, ECCV,2006,522~535.
[73]林福宗，小波与小波变换，清华大学计算机科学与技术系智能技术与系统国家重点实验室，2001.
[74]Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing imagesusing the Hausdorff distance, IEEE Transactions on PAMI,1993,15(9):850~863.
[75]Liwei Wang, Yan Zhang, Jufu Feng, On the Euclidean Distance of Images,IEEE Transactions on Pattern Analysis and Machine Intelligence,2005, vol.27no.8, pp.334~1339.
[76]Bertalmio M, Vese L, SapiroG, et al. Simultaneous texture andstructure image inpainting, IEEE Transactions on Image Processing,2003,12(8):882～889.
[77]Criminisi A, Perez P, Tpyama K, Region Filling and Object Removal byexample based image inpaiting, IEEE Transactions on Image Processing,2004,13(9):1200~1212.
[78]Sun J, Lu Y, Jia JY, Shum HY, Image completion with structurepropagation, Proc. of the ACM SIGGRAPH2005,2005,861~868.
[79]Ahuja, N., and Todorovic, S. Extracting texels in2.1d naturaltextures, In ICCV,2007,1~8.
[80]Liu, H., Xie, X., Ma, W.Y., and Zhang, H.J. Automatic browsing of largepictures on mobile devices, Proceedings of ACM International Conferenceon Multimedia,2003,148~155.
[81]Canny, F. J. A Computational Approach to Edge Detection, IEEE Trans.PAMI,1986,679-698.
[82]Chen, L. Q., Xie, X., Fan, X., Ma, W. Y., Zhang, H. J., and Zhou, H.Q. A visual attention model for adapting images on small displays, ACMMultimedia Systems Journal,2003, vol.9, no.4,353~364.
[83]Shi, J., and Tomasi, C. Good features to track. IEEE Conference onComputer Vision and Pattern Recognition,1994,593~600.
[84]Y. Keller and Y. Shkolnisky, A signal processing approach to symmetrydetection, IEEE Transactions on Image Processing,2006, vol.15,pp.2198~2207.
[85]Gal, R., Sorkine, O., and Cohen-Or, D. Feature-aware texturing, EGSR,2006,297~303.
[86]D. Shen, H.H. Ip, K.T. Eam, Robust detection of skewed symmetries,Pattern Recognition,2000, vol.3, pp.1010~1013.
[87]Gr¨unbaum, B., and Shephard, G. C. Tilings and patterns. W. H.Freeman&Co., New York, NY, USA.1986.
[88]Kwatra, V., Sch¨odl, A., Essa, I. A., Turk, G., and Bobick, A. F.,Graphcut textures: Image and video synthesis using graph cuts, ACMTransactions on Graphics,2003, vol.22, no.3,277~286.
[89]Leung, T. K., and Malik, J. Detecting, localizing and groupingrepeated scene elements from an image, ECCV,1996,546~555.
[90]Lin, W.C., and Liu, Y. A lattice-based MRF model for dynamicnear-regular texture tracking, IEEE Trans. Pattern Anal. Mach. Intell.,2007, vol.29, no.5,777~792.
[91]Liu, Y., Collins, R. T., and Tsin, Y. A computational model forperiodic pattern perception based on frieze and wallpaper groups, IEEETrans. Pattern Anal. Mach. Intell.,2004, vol.26, no.3,354~371.
[92]Lowe, D. G., Distinctive image features from scale-invariantkeypoints, International Journal of Computer Vision,2004, vol.60, no.2,91~110.
[93]Park, M., Brocklehurst, K., Collins, R. T., and Liu, Y. Deformedlattice detection in real-world images using mean-shift beliefpropagation, IEEE Trans. Pattern Anal. Mach. Intell.,2009, vol.31, no.10,1804~1816.
[94]Schattschneider, D, The plane symmetry groups: Their recognition andnotation, The American Mathematical Monthly,1978. Vol.85, no.6,439~450.
[95]Matas, J., Chum, O., Urban, M., and Pajdla, T. Robust wide baselinestereo from maximally stable extremal regions, British Machine VisionConference,2002,384~393.
[96]Cheng, M.M., Zhang, F.L., Mitra, N. J., Huang, X., and Hu, S.M.Rep_finder: Finding approximately repeated scene elements for imageediting, ACM Transaction on Graphics,2010,29,3.
[97]Comaniciu, D, Meer, P, Mean shift: A robust approach toward featurespace analysis, IEEE Trans. Pattern Anal. Mach. Intell.2002, vol.24, no.5,603~619.
[98]B. A. Canada, G. K. Thomas, K. C. Cheng, J. Z. Wang, and Y. Liu, Towardsefficient automated characterization of irregular histology images viatransformation to frieze-like patterns, Proceedings of the internationalconference on Content-based image and video retrieval,2008, pp.581~590.
[99]B. A. Canada, G. K. Thomas, K. C. Cheng, and J. Z. Wang, Shiraz: anautomated histology image annotation system for zebrafish phenomics,Multimedia Tools Appl.,2011, vol.51, no.2, pp.401~440.
[100]R. Szeliski and H. Shum. Deghosting method and apparatus forconstruction of image mosaics. US Patent No.5,986,668, November1999.
[2]彭群生，鲍虎军，金小刚，计算机真实感图形的算法基础，北京：科学出版社，1999.
[3]Suh, B., Ling, H., Bederson, B. B., and Jacobs, D. W. Automaticthumbnail cropping and its electiveness, Proceedings of UIST,2003,95~104.
[4]A. Santella, M. Agrawala, D. DeCarlo, D. Salesin, and M. Cohen,Gaze-based interaction for semi-automatic photo cropping, Proceedings ofthe SIGCHI conference on Human Factors in computing systems, New York,NY,2006, pp.771~780.
[5]S. Avidan and A. Shamir, Seam carving for content-aware image resizing,ACM Trans. Graph., vol.26, no.3, pp.10,2007.
[6]M. Rubinstein, A. Shamir, and S. Avidan, Improved seam carving forvideo retargeting, ACM Transactions on Graphics,2008, vol.27, no.3,pp.1~9.
[7]H. Wu, Y.S. Wang, K.C. Feng, T.T. Wong, T.Y. Lee, and P. A. Heng,Resizing by symmetry summarization, ACM Transaction on Graphics,2010,vol.29, no.159.
[8]W. Dong, N. Zhou, J.C. Paul, and X. Zhang, Optimized image resizingusing seam carving and scaling, ACM SIGGRAPH Asia2009, New York, NY, USA:ACM,2009, pp.125:1~125:10.
[9]M. Rubinstein, A. Shamir, and S. Avidan, Multi-operator mediaretargeting, ACM Trans. Graph.,2009, vol.28, pp.23:1–23:11.
[10]Y. Pritch, E. Kav-Venaki, and S. Peleg, Shift-map image editing,ICCV’09, Kyoto,2009, pp.151~158.
[11]Zhang, G.X., Cheng, M.M., Hu, S.M., and Martin, R, A shape-preservingapproach to image resizing, Computer Graphics Forum,2009, vol.28, no.7,1897~1906.
[12]D.S. Hwang and S.Y. Chien, Content-aware image resizing usingperceptual seam carving with human attention model, IEEE InternationalConference on Multimedia and Expo,2008, pp.1029~1032.
[13]O. S. Yu-Shuen Wang, Chiew-Lan Tai and T.Y. Lee, Optimizedscale-and-stretch for image resizing, Proceedings of ACM SIGGRAPH ASIA,2008, vol.27, no.5.
[14]H. Huang, T. Fu, P. Rosin, and C. Qi, Real-time content aware imageresizing, Science in China Series F: Information Sciences,2009, vol.52,no.2, pp.172~182.
[15]G. Pan, W. Li, W. Bai, Reverse seam carving, Proceedings of the SixthInternational Conference on Image and Graphics,2011, pp.50~55.
[16]Barnes, C., Shechtman, E., Finkelstein, A., and Goldman, D. B.PatchMatch: A randomized correspondence algorithm for structural imageediting, ACM Trans. On Graph,28,3.
[17]C. Harris and M. Stephens, A combined corner and edge detector, inProceedings of the4th Alvey Vision Conference,1988, pp.147~151
[18]P. Viola and M. Jones, Rapid object detection using a boosted cascadeof simple features, Computer Vision and Pattern Recognition,2001, vol.1, pp.511~518.
[19]L. Itti, C. Koch, and E. Niebur, A model of saliency-based visualattention for rapid scene analysis, Pattern Analysis and MachineIntelligence, IEEE Transactions on,1998, vol.20, no.11, pp.1254~1259.
[20]D. Hoiem, A. Efros, and M. Hebert, Geometric context from a singleimage, Tenth IEEE International Conference on Computer Vision,2005, vol.1, pp.654~661.
[21]L. Wolf, M. Guttmann, and D. Cohen-Or, Non-homogeneous content-drivenvideo-retargeting, IEEE11th International Conference on Computer Vision,2007, pp.1~6.
[22]V. Kraevoy, A. Sheffer, A. Shamir, and D. Cohen-Or, Nonhomogeneousresizing of complex models, ACM Trans. Graph.,2008, vol.27, pp.111:1~111:9.
[23]Jinjie Lin, Daniel Cohen-Or, Hao Zhang, Cheng Liang, Andrei Sharf,Oliver Deussen, Baoquan Chen, Structure-preserving retargeting ofirregular3D architecture, ACM Transactions on Graphics,2011, vol.30,no.6.
[24]Wang, Y.S., Lin, H.C., Sorkine, O., and Lee, T.Y, Motionbased videoretargeting with optimized crop-and-warp, ACM Transaction on Graphics,2010, vol.29, no.3.
[25]Wang, Y.S., Fu, H., Sorkine, O., Lee, T.Y., and Seidel, H.P.,Motion-aware temporal coherence for video resizing, ACM Transaction onGraphics,2009, vol.28, no.5.
[26]Zhang, Y.F., Hu, S.M., and Martin, R. R., Shrinkability maps forcontent-aware video resizing, Pacific Graphics,2008.
[27]Alexei Efros, Thomas Leung, Texture synthesis by non-parametricsampling [C], ICCV '99: Proceedings of the International Conference onComputer Vision,1999,2:1033~1038.
[28]Li-Yi Wei, Marc Levoy, Fast texture synthesis using tree-structuredvector quantization, Computer Graphics Proceedings, New York, NY,2000,479~488.
[29]Michael Ashikhmin, Synthesizing natural textures, Proceedings of the2001symposium on Interactive3D graphics, New York, NY, USA: ACM Press,2001,217~216.
[30]Alexei Efros, W T Freeman, Image quilting for texture synthesis andtransfer, Eugene Fiume, SIGGRAPH2001, Computer Graphics Proceedings,2001,341~347.
[31]E.Simoncelli, J. Portilla, Texture characterization via jointstatistics of wavelet coefficient magnitudes, In Fifth InternationalConference on Image Processing, Chicago: IEEE ComputerSociety,1998,62~66.
[32]X. Tong, J. Zhang, L. Liu et al, Synthesis of Bidirectional TextureFunctions on Arbitrary Surfaces, ACM Trans. Graph,2002,21(3):665~672.
[33]Vivek Kwatra, Irfan E A, Texture Optimization for Example-basedSynthesis, ACM Transactions on Graphics,2005,24(3),795~802.
[34]Simakov, D., Caspi, Y., Shechtman, E., and Irani, M., Summarizingvisual data using bidirectional similarity, CVPR,2008.
[35]Cho, T. S., Butman, M., Avidan, S., and Freeman, W. T. The patchtransform and its applications to image editing, CVPR,2008.
[36]D. A. Clausi and M. E. Jernigan, Designing gabor filters for optimaltexture separability, Pattern Recognition,2000, vol.33, no.11, pp.1835~1849.
[37]J. Zhang, T. Tan, and L. Ma, Invariant texture segmentation viacircular gabor filters, Proceedings of16th International Conference onPattern Recognition,2002, vol.2, pp.901~904.
[38]V. Levesque, Texture segmentation using gabor filters, Ceter ForIntelligent,2000.
[39]A.K. Jain, F. Farrokhnia, Unsupervised texture segmentation usingGabor filters, Pattern Recognition,1991, vol.24, no.12, pp.1167~1186.
[40]Canada B, Thomas G K, Cheng K C, Towards efficient automatedharacterization of irregular histology images via transformation tofrieze like patterns, In Proceedings of the2008internationalconferenceon Content-based image and video retrieval,2008, pp.581~590.
[41]Vivek Kwatra, SCH DL A., Essa I, Turk G., Bobick, A, Graph cut textures:Image and video synthesis using graph cuts, ACM Transactions on Graphics,2003,22(3):277~286.
[42]V. S. N. Prasad, L. S. Davis, Detecting rotational symmetries,Proceedings of the Tenth IEEE International Conference on Computer Vision,2005, vol.2, pp.954~961.
[43]Y. Liu, J. Hays, Y.Q. Xu, and H.Y. Shum, Digital papercutting, ACMSIGGRAPH2005Sketches,2005.
[44]H. Cornelius, G. Loy, Detecting rotational symmetry under affineprojection, Proceedings International Conference on Pattern Recognition,2006, pp.292~295.
[45]G. Loy and J. olof Eklundh, Detecting symmetry and symmetricconstellations of features, ECCV,2006, pp.508~521.
[46]Y. Keller, Y. Shkolnisky, A signal processing approach to symmetrydetection, IEEE Transaction on Image Processing,2006, vol.15, no.8,pp.2198~2207.
[47]S. Lee, R. Collins, and Y. Liu, Rotation symmetry group detection viafrequency analysis of frieze-expansions, IEEE Conference on ComputerVision and Pattern Recognition,2008, pp.1~8.
[48]LEE S., LIU Y., Skewed rotation symmetry group detection, IEEETransactions on Pattern Analysis and Machine Intelligence,2010, vol.32,no.9, pp.1659~672.
[49]T. N. Pappas and R. J. Safranek, Perceptual criteria for image qualityevaluation, in Handbook of Image and Video Processing. Academic Press,2000, pp.669~684.
[50]Z. Wang and A. Bovik, Modern Image Quality Assessment, SynthesisLectures on Image, Video&Multimedia Processing,2006.
[51]Y.J. Liu, X. Luo, Y.M. Xuan, W.F. Chen, and X.L. Fu, Image retargetingquality assessment, Computer Graphics Forum,2011.
[52]Levy B., Constrained texture mapping for polygonal meshes.Proceedings of SIGGRAPH,2001,417~424.
[53]Catmull E, Subdivision algorithm for computer display of curvedsurfaces, Ph.D. Thesis, Department of Computer Science, University ofUtah, Salt Lake City, Utah,1974.
[54]Pedersen H.K, Decorating implicit surfaces. Computer Graphics,Proceedings of Annual Conference Series,1995,291~300.
[55]Soler C., Cani M., Angelidis A., Hierarchical pattern mapping.Computer Graphics Proceedings, Annual Conference Series,2002,673~680.
[56]Andrew Witkin, Michael Kass, Reaction-diffusion textures, ComputerGraphics,1991,25(4):299~308.
[57]Dorsey J., Edelman A., Legakis J., Jensen H.W, Pedersen H.K, Modelingand rendering of weathered stone. Proceedings of SIGGRAPH1999.1999,225~234.
[58]Perlin K, An image synthesizer, Computer Graphics(SIGGRAPH1985).July1985,19(3):287~296.
[59]Darwyn R. P, Solid texturing of complex surfaces, Computer Graphics(SIGGRAPH1985),1985,19(3):279~286.
[60]Ebert D. S. et al. Texturing and modeling: a procedural approach.2ndedition, San Diego, USA: Academic Press.1998.
[61]Worley S., A cellular texture basis function, Computer GraphicsProceedings, Annual Conference Series(SIGGRAPH1996),1996,291~294.
[62]Neyret F, Cani M, Pattern-based texturing revisited, SIGGRAPH1999,Computer Graphics Proceedings,1999,235~242.
[63]Turk G, Generating textures on arbitrary surfaces usingreaction-diffusion, Computer Graphics (SIGGRAPH1991),1991,25(4):289~298.
[64]Fleischer K, Laidlaw D, Currin B, Barr A, Cellular texture generation,Proceedings of SIGGRAPH1995,1995,239~248.
[65]M Walter, A Fournier, Clonal mosaic model for the synthesis ofmammalian coat patterns, In Proceeding of Graphics Interface,1998,82~91.
[66]David J. Heeger, James R. Bergen, Pyramid-Based Texture AnalysisSynthesis, Proceedings of the1995International Conference on ImageProcessing,1995,229~238.
[67]Jeremy S. De Bonet, Multi-resolution sampling procedure for analysisand synthesis of texture images, Computer Graphics,1997,31:361~368.
[68]Chen J, Zeng B. Patch-Based Multi-Resolution Real-Time TextureSynthesis in Wavelet Domain, International Conference on Communications,Circuits and Systems,2004,2:788~791.
[69]Leandro Tonietto, Marcelo Walter, Claudio Rosito Jung, Patch-basedtexture synthesis using wavelets, Proceedings of the XVIII BrazilianSymposium on Computer Graphics and Image Processing, Washington, DC, USA:IEEE Computer Society,2005,383.
[70]Gallagher, C., Kokaram, A. Nonparametric wavelet based texturesynthesis, IEEE international Conference on Image Processing2005,2005,9,2:462~465.
[71]Praun E, Finkelstein A, Hoppe H, Lapped texture, Computer GraphicsProceedings,2000,55~64.
[72]Hays, J., Leordeanu, M., Efros, A. A., and Liu, Y. Discovering textureregularity as a higher-order correspondence problem, ECCV,2006,522~535.
[73]林福宗，小波与小波变换，清华大学计算机科学与技术系智能技术与系统国家重点实验室，2001.
[74]Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing imagesusing the Hausdorff distance, IEEE Transactions on PAMI,1993,15(9):850~863.
[75]Liwei Wang, Yan Zhang, Jufu Feng, On the Euclidean Distance of Images,IEEE Transactions on Pattern Analysis and Machine Intelligence,2005, vol.27no.8, pp.334~1339.
[76]Bertalmio M, Vese L, SapiroG, et al. Simultaneous texture andstructure image inpainting, IEEE Transactions on Image Processing,2003,12(8):882～889.
[77]Criminisi A, Perez P, Tpyama K, Region Filling and Object Removal byexample based image inpaiting, IEEE Transactions on Image Processing,2004,13(9):1200~1212.
[78]Sun J, Lu Y, Jia JY, Shum HY, Image completion with structurepropagation, Proc. of the ACM SIGGRAPH2005,2005,861~868.
[79]Ahuja, N., and Todorovic, S. Extracting texels in2.1d naturaltextures, In ICCV,2007,1~8.
[80]Liu, H., Xie, X., Ma, W.Y., and Zhang, H.J. Automatic browsing of largepictures on mobile devices, Proceedings of ACM International Conferenceon Multimedia,2003,148~155.
[81]Canny, F. J. A Computational Approach to Edge Detection, IEEE Trans.PAMI,1986,679-698.
[82]Chen, L. Q., Xie, X., Fan, X., Ma, W. Y., Zhang, H. J., and Zhou, H.Q. A visual attention model for adapting images on small displays, ACMMultimedia Systems Journal,2003, vol.9, no.4,353~364.
[83]Shi, J., and Tomasi, C. Good features to track. IEEE Conference onComputer Vision and Pattern Recognition,1994,593~600.
[84]Y. Keller and Y. Shkolnisky, A signal processing approach to symmetrydetection, IEEE Transactions on Image Processing,2006, vol.15,pp.2198~2207.
[85]Gal, R., Sorkine, O., and Cohen-Or, D. Feature-aware texturing, EGSR,2006,297~303.
[86]D. Shen, H.H. Ip, K.T. Eam, Robust detection of skewed symmetries,Pattern Recognition,2000, vol.3, pp.1010~1013.
[87]Gr¨unbaum, B., and Shephard, G. C. Tilings and patterns. W. H.Freeman&Co., New York, NY, USA.1986.
[88]Kwatra, V., Sch¨odl, A., Essa, I. A., Turk, G., and Bobick, A. F.,Graphcut textures: Image and video synthesis using graph cuts, ACMTransactions on Graphics,2003, vol.22, no.3,277~286.
[89]Leung, T. K., and Malik, J. Detecting, localizing and groupingrepeated scene elements from an image, ECCV,1996,546~555.
[90]Lin, W.C., and Liu, Y. A lattice-based MRF model for dynamicnear-regular texture tracking, IEEE Trans. Pattern Anal. Mach. Intell.,2007, vol.29, no.5,777~792.
[91]Liu, Y., Collins, R. T., and Tsin, Y. A computational model forperiodic pattern perception based on frieze and wallpaper groups, IEEETrans. Pattern Anal. Mach. Intell.,2004, vol.26, no.3,354~371.
[92]Lowe, D. G., Distinctive image features from scale-invariantkeypoints, International Journal of Computer Vision,2004, vol.60, no.2,91~110.
[93]Park, M., Brocklehurst, K., Collins, R. T., and Liu, Y. Deformedlattice detection in real-world images using mean-shift beliefpropagation, IEEE Trans. Pattern Anal. Mach. Intell.,2009, vol.31, no.10,1804~1816.
[94]Schattschneider, D, The plane symmetry groups: Their recognition andnotation, The American Mathematical Monthly,1978. Vol.85, no.6,439~450.
[95]Matas, J., Chum, O., Urban, M., and Pajdla, T. Robust wide baselinestereo from maximally stable extremal regions, British Machine VisionConference,2002,384~393.
[96]Cheng, M.M., Zhang, F.L., Mitra, N. J., Huang, X., and Hu, S.M.Rep_finder: Finding approximately repeated scene elements for imageediting, ACM Transaction on Graphics,2010,29,3.
[97]Comaniciu, D, Meer, P, Mean shift: A robust approach toward featurespace analysis, IEEE Trans. Pattern Anal. Mach. Intell.2002, vol.24, no.5,603~619.
[98]B. A. Canada, G. K. Thomas, K. C. Cheng, J. Z. Wang, and Y. Liu, Towardsefficient automated characterization of irregular histology images viatransformation to frieze-like patterns, Proceedings of the internationalconference on Content-based image and video retrieval,2008, pp.581~590.
[99]B. A. Canada, G. K. Thomas, K. C. Cheng, and J. Z. Wang, Shiraz: anautomated histology image annotation system for zebrafish phenomics,Multimedia Tools Appl.,2011, vol.51, no.2, pp.401~440.
[100]R. Szeliski and H. Shum. Deghosting method and apparatus forconstruction of image mosaics. US Patent No.5,986,668, November1999.