摘要
现代多媒体信息处理要求计算机能够模拟人脑的功能实现对海量图像和视频数据的检索、分类、识别、编辑、交互和存储。而形状作为物体识别的关键特征，对于上述应用起着不可或缺的作用。因此，如何准确而高效地实现形状的计算和存储，成为本文研究的重点。
现实物体姿态和视角的变化，使得形状的外观千变万化。人眼对形状的区域选择性和多尺度特性，极易导致实际形状度量与视觉感知之间的差异。更不用说由形状获取导致的量化和分割噪声。这些都给形状的计算和存储带来了极大的挑战。
为迎接上述挑战，本文深入研究了基于部分和轮廓的形状表示理论及应用。提出了形状部分的视觉显著度，改进了可操作率失真轮廓编码框架的失真度量和编码结构，并通过双重失真规则化优化了原有的框架。上述成果应用于形状解析、指尖检测和手势识别，均取得了良好的效果。下面给出具体的研究成果。
1、提出了形状部分的视觉显著度。首先，将形状部分的视觉显著度简化成三角形的视觉显著度。然后，将三角形的视觉显著度建模成三角形的两邻边长度和、长度比和转角的函数。再利用这三个因素之间的完备性、独立性和直观性，推导出三角形的视觉显著度。实验结果表明，该度量优于现有度量，能显著提升形状解析和手势识别的准确度。
2、提出了基于解析法的精确失真度量。首先，将该度量定义为原始轮廓点到参数曲线的最短距离。接着，利用最短距离线段与参数曲线段垂直这一几何关系，给出对应的参数方程。然后，通过解析法求解参数空间，获得最终的距离。为减少执行时间，提出了混合允许失真检验算法。实验结果表明，该度量能精确度量实际失真，且计算复杂度与现有度量的最低计算复杂度持平。
3、提出了两种任意方向边编码结构。首先，将数字平面分成八个或者十六个扇区，然后用扇区序号、短分量和长分量表示近似边。实验结果表明，该编码结构能有效地节省近似多边形的顶点数目，在提高编码效率的同时，使得形状描述更加简洁。
4、提出了基于失真双重规则化的可操作率失真形状编码方法。将基于2-范数的失真规则项引入原有的目标函数，以期在边码率与边失真之间寻求更好的平衡。为避免噪声干扰，给出了规则化参数的取值范围。并将该组合优化问题转化为带权重的有向无环图中的最短路径问题求解。实验结果表明，该方法不仅能够在保持编码效率不变的情况下减少近似边失真，同时对噪声也具有很好的鲁棒性，因而非常适用指尖检测和手势识别等应用。
本文的贡献主要有两点：第一，形状部分的视觉显著度使得物体形状部分之间的视觉显著性比较成为可能，第二，基于解析法的精确失真度量、任意方向编码结构，以及双重失真规则化策略使得可操作率失真轮廓编码结果更准确、简洁而高效。这些都为基于形状的物体识别奠定了良好的基础。
Modern multimedia information processing requires that computers can stimulate thefunctions of the human brain, including mass image and video data retrieval, classification,recognition, edit, interaction and storage. The shape, served as the key feature in objectrecognition, plays an indispensible role in these applications. Thus, how to make the shapecomputing and storage accurately and efficiently becomes the focus of this dissertation.
The diversity of object poses and the changes of viewpoints result in the myriadchanges of shape appearances. Moreover, the human eyes’ regioselectivity and multi-scalecharacteristics can easily lead to the difference between the shape measure and the visualexperiences. Not to mention that the shape acquisitions often introduce quantification andsegmentation noise. These all brings great challenges of the shape computing and storage.
To meet these challenges, the part-based and the contour-based shape representationtheory and applications are investigated in this dissertation. The visual salience of shapeparts are measured, the distortion measurement and the encoding structure of the opera-tional rate-distortion (ORD) shape coding framework are improved, and the dual distortionregularization strategy of this framework is presented. These proposals are applied to shapeparsing, fingertip detection and hand gesture recognition, which lead to promising results.The detailed works of this dissertation are provided as follows.
1) A visual salience measure of shape parts is proposed. Firstly, measuring the visualsalience of shape parts is simplified into measuring the visual salience of triangles. Then,the triangle salience is modeled as a function with respect to the total length, length ratioand turning angle. Using the completeness, independence and visualization of these threefactors, the final metric of the triangle salience are derived. Experiments show that thismeasure outperforms the existing ones, and can significantly improve the accuracy of shapeparsing and hand gesture recognition.
2) An accurate distortion measurement using the analytical method is proposed. First-ly, the contour point distortion is defined as the shortest distance from the parametric curveto that contour point. Then, the parametric equation is derived using the perpendicular rela- tionship between the shortest distance line segment and the tangent line, and this equationis resolved using the analytical method. In order to reduce the execution time, a hybridadmissible distortion checking algorithm is proposed. Experiments show that this measurecan accurately measure the actual distortion with the computational complexity the same asthe lowest among the existing measurements.
3) Two arbitrary directional edge encoding structures are proposed. Firstly, the digitalplane is partitioned into eight or sixteen sectors. Then, the approximate edge is representedby a sector number, a short component and a long component. Experiments show that thesestructures can save a host of polygon vertices, so they can improve the coding efficiency aswell as make the approximate polygon more compact.
4) A dual distortion regularization-based ORD shape coding method is proposed. An2-norm distortion regularization term is added to the original ORD framework, in order tofind a better tradeoff between the edge rate and the edge distortion. The range of regular-ization parameter is provided to avoid the boundary noise influence, and the final solutionto this combinatorial optimization problem is obtained using a shortest path algorithm fora weighted directed acyclic graph. Experiments show that this method can not only reduceedge distortions without loss of coding efficiency, but also be robust against boundary noiseand therefore applicable to fingertip detection and hand gesture recognition.
The main contributions of this dissertation are twofold. Firstly, the visual saliencemeasure of shape parts make it possible to compare the visual saliences among differentshape parts. Secondly, the accurate distortion measurement using the analytical method,two arbitrary direction edge encoding structures and the dual distortion regularizationstrategy make the ORD shape coding results more accurate, compact and efficient. Theseall lay a good foundation for further shape-based object recognition.
引文
[1] J. De Winter, J. Wagemans. Contour-based object identification and segmentation: S-timuli, norms and data, and software tools. Behavior Research Methods, Instruments,and Computers,2004,36(4):604～624.
[2] J. Wagemans, W. Notebaert, T. Beckers, et al. Picture identification of everydayobjects: Silhouettes, outlines, and contour fragments. in: Proceedings of the38thAnnual the meeting of the Psychonomic Society,1997,71.
[3] A. Ploeger, J. Wagemans, T. Beckers, et al. Are silhouettes easier to recognize thanoutlines? Perception-Proceedings of the20th European Conference on Visual Per-ception,1998,27:123b.
[4] J. Wagemans, J. De Winter, H. Op de Beeck, et al. Identification of silhouette and con-tour versions of line drawings of everyday objects. Perception,2008,37(2):207～244.
[5] D. D. Hoffman. Representing shapes for visual recognition:[PhD Dissertation].Cambridge, MA: Massachusetts Institute of Technology,1983.
[6] D. D. Hoffman, W. A. Richards. Parts of recognition. Cognition,1984,18(1～3):65～96.
[7] D. D. Hoffman, M. Singh. Salience of visual parts. Cognition,1997,63(1):29～78.
[8] G. Kova′cs, G. Sa′ry, K. Ko¨teles, et al. Effects of surface cues on macaque inferiortemporal cortical responses. Cerebral Cortex,2003,13(2):178～188.
[9] S. E. Palmer. Explorations in Cognition. San Francisco, CA: Miller Freeman Tech-nical Ltd.,1975, chapter Visual perception and world knowledge: Notes on a modelof sensory cognitive interaction, page279～307.
[10] S. E. Palmer. Hierarchical structure in perceptual representation. Cognitive Psychol-ogy,1978,9(4):441～474.
[11] D. Marr. Analysis of occluding contour. Proceedings of the Royal Society of London,Series B,1977,197(1129):441～475.
[12] D. Marr, H. K. Nishihara. Representation and recognition of the spatial organizationof three-dimensional shapes. Proceedings of the Royal Society of London, Series B,1978,200(1140):269～294.
[13] D. Marr. Vision: A computational investigation into human representation and pro-cessing of visual information. New York, NY: W.H. Freeman and Company,1982.
[14] D. D. Hoffman. The interpretation of visual illusions. Scientific American,1983,249(6):154～162.
[15] B. Tversky, K. Hemenway. Objects, parts, and categories. Journal of ExperimentalPsychology: General,1984,113(2):169～193.
[16] B. M. Bennett, D. D. Hoffman. Image Understanding. Norwood, NJ: Ablex Pub-lishing Corp.,1987, chapter Shape decompositions for visual shape recognition: Therole of transversality, page215～256.
[17] J. Beusmans, D. D. Hoffman, B. M. Bennett. Description of solid shape and itsinference from occluding contours. Journal of the Optical Society of America A:Optics, Image Science, and Vision,1987,4(7):1155～1167.
[18] K. A. Stevens, A. Brookes. The concave cusp as a determiner of figure-ground.Perception,1988,17(1):35～42.
[19] M. L. Braunstein, D. D. Hoffman, A. Saidpour. Parts of visual objects: An experi-mental test of the minima rule. Perception,1989,18(6):817～826.
[20] I. Biederman. Recognition-by-components: A theory of human image understanding.Psychological Review,1987,94(2):115～147.
[21] I. Biederman, E. E. Cooper. Priming contour-deleted images: Evidence for inter-mediate representations in visual object recognition. Cognitive Psychology,1991,23(3):393～419.
[22] M. A. Kurbat. Structural description theories: Is RBC/JIM a general-purpose theoryof human entry-level object recognition? Perception,1994,23(11):1339～1368.
[23] G. C. Baylis, J. Driver. One-sided edge assignment in vision:1. Figure–groundsegmentation and attention to objects. Current Directions in Psychological Science,1995,4(5):140～146.
[24] G. C. Baylis, J. Driver. Obligatory edge assignment in vision: The role of figureand part segmentation in symmetry detection. Journal of Experimental Psychology:Human Perception and Performance,1995,21(6):1323～1342.
[25] J. Driver, G. C. Baylis. One-sided edge assignment in vision:2. Part decomposi-tion, shape description, and attention to objects. Current Directions in PsychologicalScience,1995,4(6):201～206.
[26] K. Siddiqi, K. Tresness, B. B. Kimia. Parts of visual form: Psychophysical aspects.Perception,1996,25(4):399～424.
[27] J. T. Todd, J. J. Koenderink, A. J. van Doorn, et al. Effects of changing viewing condi-tions on the perceived structure of smoothly curved surfaces. Journal of ExperimentalPsychology: Human Perception and Performance,1996,22(3):695～706.
[28] K. Lamberts, R. P. J. Freeman. Building object representations from parts: Tests of astochastic sampling model. Journal of Experimental Psychology: Human Perceptionand Performance,1999,25(4):904～926.
[29] C. Lamote, J. Wagemans. Rapid integration of contour fragments: From simplefilling-in to parts-based shape description. Visual Cognition,1999,6(3～4):345～361.
[30] B. J. Scholl. Objects and attention: The state of the art. Cognition,2001,80(1～2):1～46.
[31] M. Singh, D. Hoffman. From Fragments to Objects: Segmentation and Grouping inVision. Amsterdam, Holland: Elsevier Science,2001, chapter Part-based representa-tions of visual shape and implications for visual cognition, page401～459.
[32] A. Hayden, R. S. Bhatt, A. Kangas, et al. Parts, cavities, and object representation ininfancy. Journal of Experimental Psychology: Human Perception and Performance,2011,37(1):314～317.
[33] C. B. Cave, S. M. Kosslyn. The role of parts and spatial relations in object identifica-tion. Perception,1993,22(2):229～248.
[34] T. O. Binford. Visual perception by computer. in: Proceedings of IEEE SystemsScience and Cybernetics Conference,1971.
[35] A. Guzman. Machine Intelligence, volume6. Edinburgh, UK: Edinburgh Univer-sity Press,1971, chapter Analysis of curved line drawings using context and globalinformation, page325～376.
[36] P. A. Winston. The psychology of Computer Vision. New York, NY: McGraw-Hill,1975, chapter Learning structural descriptions from examples, page157～209.
[37] R. A. Brooks. Symbolic reasoning among3-D models and2-D images. ArtificialIntelligence,1981,17(1～3):285～348.
[38] A. P. Pentland. Perceptual organization and the representation of natural form. Arti-ficial Intelligence,1986,28(3):293～331.
[39] D. Terzopoulos, A. Witkin, M. Kass. Symmetry-seeking models and3D object re-construction. International Journal of Computer Vision,1987,1(3):211～221.
[40] S. J. Dickinson, A. P. Pentland, A. Rosenfeld. From volumes to views: An approachto3D object recognition. Computer Vision, Graphics, and Image Processing: ImageUnderstanding,1992,55(2):130～154.
[41] K. Siddiqi, B. B. Kimia. Parts of visual form: Computational aspects. IEEE Trans-actions on Pattern Analysis and Machine Intelligence,1995,17(3):239～251.
[42] L. G. Roberts. Optical and Electro-Optical Information Processing. Cambridge,MA: MIT Press,1965, chapter Machine perception of three-dimensional solids, page11～277.
[43] D. Waltz. The Psychology of Computer Vision. New York, NY: McGraw-Hill,1975,chapter Generating semantic descriptions from drawings of scenes with shadows,page19～91.
[44] Kinect for Xbox360. Microsoft Corporation, Redmond WA,2010.
[45] A. N. Netravali, B. Haskell. Digital Pictures: Representation and Compression. NewYork, NY: Plenum Press,1988.
[46] International Telecommunication Union, Telecommunication Standardization Sector,Geneva, Switzerland. Recommendation T.6: Facsimile coding schemes and codingcontrol functions for Group4facsimile apparatus, November,1994.
[47] International Telecommunication Union, Telecommunication Standardization Sector,Geneva, Switzerland. T.82: Information technology-Coded representation of pictureand audio information-Progressive bi-level image compression, March,1993.
[48] S. M. Aghito, S. Forchhammer. Context-based coding of bilevel images enhancedby digital straight line analysis. IEEE Transactions on Image Processing,2006,15(8):2020～2130.
[49] N. Brady, F. Bossen, N. Murphy. Context-based arithmetic encoding of2D shapesequences. in: Proceedings of the4th IEEE International Conference on Image Pro-cessing, Special Issue on Shape Coding,1997, I-29～I-32.
[50] N. Brady, F. Bossen. Shape compression of moving objects using context-based arithmetic encoding. Signal Processing: Image Communication,2000,15(7～8):601～617.
[51] L. Y. Wang, C. H. Lai, K. R. Pan. Quad-tree-based image shape coding with blockcompensation. in: Proceedings of the3rd International Conference on InformationTechnology and Applications,2005,716～719.
[52] Z. Shen, M. R. Frater, J. F. Arnold. Optimal pruning quad-tree block-based binaryshape coding. in: Proceedings of the14th IEEE International Conference on ImageProcessing,2007, VI-437～VI-440.
[53] Z. Shen, M. R. Frater, J. F. Arnold. Quad-tree block-based binary shape coding. IEEETransactions on Circuits and Systems for Video Technology,2008,18(6):845～850.
[54] H. Freeman. On the encoding of arbitrary geometric configurations. IRE Transactionson Electronic Computers,1961, EC-10(2):260～268.
[55] J. Saghri, H. Freeman. Analysis of the precision of generalized chain codes for therepresentation of planar curves. IEEE Transactions on Pattern Analysis and MachineIntelligence,1981, PAMI-3(5):533～539.
[56] T. Kaneko, M. Okudaira. Encoding of arbitrary curves based on the chain code rep-resentation. IEEE Transactions on Communications,1985, COM-33(7):697～707.
[57] R. Prasad, J. W. Vieveen, J. H. Bons, et al. Relative vector probabilities in differentialchain coded linedrawings. in: Proceedings of the1st IEEE Pacific Rim Conferenceon Communications, Computers and Signal Processing,1989,138～142.
[58] J. Koplowitz. On the performance of chain codes for quantization of line draw-ings. IEEE Transactions on Pattern Analysis and Machine Intelligence,1981, PAMI-3(2):180～185.
[59] D. L. Neuhoff, K. G. Castor. A rate and distortion analysis of chain codes for linedrawings. IEEE Transactions on Information Theory,1985, IT-31(1):53～68.
[60] M. Ho¨tter. Object-oriented analysis-synthesis coding based on moving two-dimensional objects. Special Issue on64kbit/s Coding, Part I, Signal Processing:Image Communication,1990,2(4):409～428.
[61] P. Gerken. Object-based analysis-synthesis coding of image sequences at very lowbit rates. IEEE Transactions on Circuits and Systems for Video Technology,1994,4(3):228～235.
[62] C.-M. Kuo, C.-H. Hsieh, Y.-R. Huang. A new adaptive vertex-based binary shapecoding technique. Image and Vision Computing,2007,25(1):863～872.
[63] R. Bellman. On the approximation of curves by line segments using dynamic pro-gramming. Communications of the ACM,1961,4(6):284.
[64] J. Sklansky, V. Gonzalez. Fast polygonal approximation of digitized curves. PatternRecognition,1980,12(5):327～331.
[65] J. G. Dunham. Optimum uniform piecewise linear approximation of planar curves.IEEE Transactions on Pattern Analysis and Machine Intelligence,1986, PAMI-8(1):67～75.
[66] D. Saupe. Optimal piecewise linear image coding. in: Proceedings of SPIE Interna-tional Conference on Visual Communications and Image Processing,1998,747～760.
[67] G. M. Schuster, A. K. Katsaggelos. Optimal lossy segmentation encoding scheme. in:Proceedings of SPIE International Conference on Visual Communications and ImageProcessing,1996,1050～1061.
[68] G. M. Schuster, A. K. Katsaggelos. An optimal segmentation encoding scheme in therate distortion sense. in: Proceedings of IEEE International Symposium on Circuitsand Systems,1996,640～643.
[69] G. M. Schuster, A. K. Katsaggelos. An efficient boundary encoding scheme whichis optimal in the rate distortion sense. in: Proceedings of the3rd IEEE InternationalConference on Image Processing,1996, II-77～II-80.
[70] G. M. Schuster, A. K. Katsaggelos. An optimal polygonal boundary encodingscheme in the rate distortion sense. IEEE Transactions on Image Processing,1998,7(1):13～26.
[71] A. K. Jain. Fundamentals of Digital Image Processing. Englewood Cliffs, NJ: Pren-tice Hall,1989.
[72] F. W. Meier, G. M. Schuster, A. K. Katsaggelos. An efficient boundary encodingscheme using B-spline curves which is optimal in the rate-distortion sense. in: Pro-ceedings of the2nd Erlangen Symposium on Advances in Digital Image Communi-cation,1997,75～84.
[73] F. W. Meier, G. M. Schuster, A. K. Katsaggelos. An efficient boundary encodingscheme which is optimal in the rate distortion sense. in: Proceedings of the4th IEEEInternational Conference on Image Processing,1997, II-9～II-12.
[74] F. W. Meier, G. M. Schuster, A. K. Katsaggelos. A mathematical model for shapecoding with B-splines. Special Issue on Shape Coding for Emerging MultimediaApplications, Signal Processing: Image Communication,2000,15(7～8):685～701.
[75] F. A. Sohel, L. S. Dooley, G. C. Karmakar. A novel half-way shifting Bezier curvemodel. in: Proceedings of IEEE Region10International Conference on TENCON,2005,1～6.
[76] F. A. Sohel, G. C. Karmakar, L. S. Dooley. Enhanced Bezier curve models incorpo-rating local information. in: Proceedings of the30th IEEE International Conferenceon Acoustics, Speech, and Signal Processing,2005,253～256.
[77] F. A. Sohel, G. C. Karmakar, L. S. Dooley, et al. Quasi-Bezier curves integratinglocalised information. Pattern Recognition,2008,41(2):531～542.
[78] F. A. Sohel, L. S. Dooley, G. C. Karmakar. A dynamic Bezier curve model. in:Proceedings of the12th IEEE International Conference on Image Processing,2005,II-474～II-477.
[79] F. A. Sohel, G. C. Karmakar, L. S. Dooley. Dynamic Bezier curves for variable rate-distortion. Pattern Recognition,2008,41(10):3153～3165.
[80] A. K. Katsaggelos, L. P. Kondi, F. W. Meier, et al. MPEG-4and rate-distortion-based shape-coding techniques. Special Issue on Multimeia Signal Procissing, PartII, Proceedings of the IEEE,1998,86(6):1126～1154.
[81] D. A. Forsyth, J. Ponce. Computer Vision: A Modern Approach. London, UK:Prentice Hall,2011.
[82] Q. Cai, D. Gallup, C. Zhang, et al.3D deformable face tracking with a commoditydepth camera. in: Proceedings of the11th European Conference on Computer Vision,2010,229～242.
[83] J. Shotton, A. Fitzgibbon, M. Cook, et al. Real-time human pose recognition inparts from single depth images. in: Proceedings of the24th IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2011,1297～1304.
[84] W. Shen, K. Deng, X. Bai, et al. Exemplar-based human action pose correction andtagging. in: Proceedings of the25th IEEE Computer Society Conference on Com-puter Vision and Pattern Recognition,2012,1784～1791.
[85] J. P. Wachs, M. Ko¨lsch, H. Stern, et al. Vision-based hand-gesture applications. Com-munications of the ACM,2011,54(2):60～71.
[86] J. L. Raheja, A. Chaudhary, K. Singal. Tracking of fingertips and centres of palmusing kinect. in: Proceedings of the3rd International Conference on ComputationalIntelligence, Modelling and Simulation,2010,248～252.
[87] Z. Ren, J. Yuan, C. Li, et al. Minimum near-convex decomposition for robust shaperepresentationrobust shape representation. in: Proceedings of the13th IEEE Interna-tional Conference on Computer Vision,2011,303～310.
[88] Z. Ren, J. Yuan, Z. Zhang. Robust hand gesture recognition based on finger-earthmover’s distance with a commodity depth camera. in: Proceedings of the19th ACMInternational Conference on Multimedia,2011,1093～1096.
[89] Z. Ren, J. Yuan, W. Liu. Minimum near-convex shape decomposition. IEEE Trans-actions on Pattern Analysis and Machine Intelligence,2013.
[90] Z. Ren, J. Meng, J. Yuan, et al. Robust hand gesture recognition with Kinect sensor.in: Proceedings of the19th ACM International Conference on Multimedia,2011,759～760.
[91] Z. Ren, J. Meng, J. Yuan. Depth camera based hand gesture recognition and its appli-cations in human-computer-interaction. in: Proceedings of the8th IEEE InternationalConference on Information, Communications and Signal Processing,2011,1～5.
[92] Z. Ren, J. Yuan, J. Meng, et al. Robust part-based hand gesture recognition based onfinger-earth mover’s distance. IEEE Transactions on Multimedia,2013.
[93] H. Liang, J. Yuan, D. Thalmann.3D fingertip and palm tracking in depth image se-quences. in: Proceedings of the20th ACM International Conference on Multimedia,2012,785～788.
[94] H. Liang, J. Yuan, D. Thalmann. Hand pose estimation by combining fingertip track-ing and articulated ICP. in: Proceedings of the11th ACM SIGGRAPH Internation-al Conference on Virtual-Reality Continuum and its Applications in Industry,2012,87～90.
[95] H. Liang, J. Yuan, D. Thalmann, et al. Model-based hand pose estimation via spatial-temporal hand parsing and3D fingertip localization. in: Proceedings of the30thComputer Graphics International,2013.
[96] H. Liang, J. Yuan, D. Thalmann, et al. Model-based hand pose estimation via spatial-temporal hand parsing and3D fingertip localization. The Visual Computer,2013.
[97] I. Oikonomidis, N. Kyriazis, A. A. Argyros. Markerless and efficient26-DOF handpose recovery. in: Proceedings of the10th Asian Conference on Computer Vision,2010,744～757.
[98] I. Oikonomidis, N. Kyriazis, A. A. Argyros. Full DOF tracking of a hand interactingwith an object by modeling occlusions and physical constraints. in: Proceedings ofthe13th IEEE International Conference on Computer Vision,2011,2088～2095.
[99] I. Oikonomidis, N. Kyriazis, A. A. Argyros. Efficient model-based3D tracking ofhand articulations using Kinect. in: Proceedings of the22nd British Machine VisionConference,2011,101.1～101.11.
[100] I. Oikonomidis, N. Kyriazis, A. A. Argyros. Tracking the articulated motion of t-wo strongly interacting hands. in: Proceedings of the25th IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2012,1862～1869.
[101] N. Kyriazis, I. Oikonomidis, A. A. Argyros. A GPU-powered computational frame-work for efficient3D model-based vision. Technical Report420, Institute of Com-puter Science, Foundation for Research and Technology-Hellas,2011.
[102] S. K. Reed. Structural descriptions and the limitations of visual images. Memory andCognition,1974,2(2):329～336.
[103] L. J. Latecki, R. Lakaemper. Convexity rule for shape decomposition based ondiscrete contour evolution. Computer Vision and Image Understanding,1999,73(3):441～454.
[104] X. Bai, L. J. Latecki, W. Liu. Skeleton pruning by contour partitioning with discretecurve evolution. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(3):449～462.
[105] E. Rubin. Readings in Perception. Princeton, NJ: Van Nostrand,1958, chapter Figureand ground, page194～203.
[106] J. De Winter, S. Panis, J. Wagemans. Perceptual saliency of points along the contourof everyday objects: A large-scale study. Journal of Vision-Proceedings of the2ndAnnual Meeting of Vision Sciences Society,2002,2(7):487.
[107] J. D. Winter, J. Wagemans. Perceptual saliency of points along the contour of every-day objects: A large-scale study. Perception and Psychophysics,2008,70(1):50～64.
[108] J. De Winter, J. Wagemans. Segmentation of object outlines into parts: A large-scaleintegrative study. Cognition,2006,99(3):275～325.
[109] M. Brady, H. Asada. Smoothed local symmetries and their implementation. Interna-tional Journal of Robotics Research,1984,3(3):36～61.
[110] J. J. Koenderink, A. Brookes. The structure of images. Biological Cybernetics,1984,50(5):363～370.
[111] A. P. Witkin. From Pixels to Predicates: Recent Advances in Computational andRobotic Vision. Norwood, NJ: Ablex Publishing Corp.,1986, chapter Scale-spacefiltering, page5～19.
[112] H. R. Wilson, W. A. Richards. Discrimination of contour curvature: Data and theory.Journal of the Optical Society of America, A,1985,2(7):1191～1198.
[113] E. H. Cohen, M. Singh. Geometric determinants of shape segmentation: Tests usingsegment identification. Vision Research,2007,47(22):2825～2840.
[114] J. De Winter, J. Wagemans. Visual segmentation of88outlines of everyday objects:Bottom-up versus top-down and contours versus shapes. Perception-Proceedings ofthe22nd European Conference on Visual Perception,1999,28:129a.
[115] J. De Winter, J. Wagemans. Segmentation of object outlines into parts: From a large-scale normative study to a tentative model. Journal of Vision-Proceedings of the1stAnnual Meeting of Vision Sciences Society,2001,1(3):421.
[116] J. De Winter, J. Wagemans. Segmentation of object outlines into parts: A scale-space analysis. Perception-Proceedings of the26th European Conference on VisualPerception,2003,32:119c.
[117] F. Attneave. Some informational aspects of visual perception. Psychological Review,1954,61(3):183～193.
[118] H. Liu, L. J. Latecki, W. Liu, et al. Visual curvature. in: Proceedings of the20thIEEE Computer Society Conference on Computer Vision and Pattern Recognition,2007,1～8.
[119] H. Liu, L. J. Latecki, W. Liu. A unified curvature definition for regular, polyg-onal, and digital planar curves. International Journal of Computer Vision,2008,80(1):104～124.
[120] P. L. Rosin. Shape partitioning by convexity. IEEE Transactions on Systems, Man,and Cybernetics-Part A: Systems and Humans,2000,30(2):202～210.
[121] A. Pasupathy, C. E. Connor. Responses to contour features in macaque area V4.Journal of Neurophysiology,1999,82(2):2490～2502.
[122] H. Blum. Biological shape and visual science (part I). Journal of Theoretical Biology,1973,38(2):205～287.
[123] H. Blum, R. N. Nagel. Shape description using weighted symmetric axis features.Pattem Recognition,1978,10(3):167～180.
[124] M. Singh, G. D. Seyranian, D. D. Hoffman. Parsing silhouettes: The short-cut rule.Perception and Psychophysics,1999,61(4):636～660.
[125] R. S. Bhatt, A. Hayden, A. Kangas, et al. Part perception in infancy: Sensitivity to theshort-cut rule. Attention, Perception and Psychophysics,2010,72(4):1070～1078.
[126] J. G. Snodgrass, M. Vanderwart. A standardized set of260pictures: Norms forname agreement, image agreement, familiarity, and visual complexity. Journal ofExperimental Psychology: Human Learning and Memory,1980,6(2):174～215.
[127] H. Blum. Models for the Perception of Speech and Visual Form. Amsterdam, Hol-land: MIT Press,1967, chapter A transformation for extracting new descriptors ofshape, page363～380.
[128] H. Choi, S. Choi, H. Moon. Mathematical theory of medial axis transform. PacificJournal of Mathematics,1997,181(1):57～88.
[129] J. Zeng, R. Lakaemper, X. Yang, et al.2D Shape Decomposition Based on Com-bined Skeleton-Boundary Features. in: G. Bebis, R. Boyle, B. Parvin, et al., editors,Proceedings of Advances in Visual Computing, volume5359of Lecture Notes inComputer Science, page682～691. Springer Berlin Heidelberg,2008.
[130] W. P. Choi, K. M. Lam, W. C. Siu. Extraction of the Euclidean skeleton based on aconnectivity criterion. Pattern Recognition,2003,36(3):721～729.
[131] R. L. Ogniewicz, O. Kubler. Hierarchic Voronoi skeletons. Pattern Recognition,1995,28(3):343～359.
[132] M. Couprie, R. Zrour. Discrete bisector function and Euclidean skeleton in2D and3D. Image and Vision Computing,2007,25(10):1543～1556.
[133] X. Bai, L. J. Latecki, W. Liu. Skeleton pruning by contour partitioning. in: Pro-ceedings of the13th International Conference on Discrete Geometry for ComputerImagery,2006,567～579.
[134] W. Shen, X. Bai, R. Hu, et al. Skeleton growing and pruning with bending potentialratio. Pattern Recognition,2011,44(2):196～209.
[135] L. J. Latecki, R. Lakaemper, U. Eckhardt. Shape descriptors for non-rigid shapeswith a single closed contour. in: Proceedings of the13th IEEE Computer SocietyConference on Computer Vision and Pattern Recognition,2000,424～429.
[136] X. Bai, L. J. Latecki. Path similarity skeleton graph matching. IEEE Transactions onPattern Analysis and Machine Intelligence,2008,30(7):1282～1292.
[137] X. Bai, W. Liu, Z. Tu. Integrating contour and skeleton for shape classification.in: Proceedings of the11th IEEE International Conference on Computer VisionWorkshop on Non-Rigid Shape Analysis and Deformable Image Alignment,2009,360～367.
[138] A. Rosenfeld, E. Johnston. Angle detection on digital curves. IEEE Transactions onComputers,1973, C-22(9):875～878.
[139] A. Rosenfeld, E. Johnston. An improved method of angle detection on digital curves.IEEE Transactions on Computers,1975, C-24(9):940～941.
[140] H. Freeman, L. S. Davis. A corner-finding algorithm for chain-coded curves. IEEETransactions on Computers,1977, C-26(3):297～303.
[141] H. Freeman, L. S. Davis. An improved corner detection algorithm based on chain-coded plane curves. Pattern Recognition,1987,20(3):291～296.
[142] D. Chetverikov, Z. Szabo. A simple and efficient algorithm for detection of high cur-vature points in planar curves. in: Proceedings of the23rd Workshop of the AustrianPattern Recognition Group,1999,175～184.
[143] A. Erol, G. Bebis, M. Nicolescu, et al. Vision-based hand pose estimation: A review.Computer Vision and Image Understanding,2007,108(1～2):52～73.
[144] J. Lien, N. Amato. Approximate convex decomposition of polygons. in: Proceedingsof the20th Annual ACM Symposium on Computational Geometry,2004,17～26.
[145] J. Lien, N. Amato. Approximate convex decomposition of polygons. ComputationalGeometry: Theory and Applications,2006,35(1):291～296.
[146] G. M. Schuster, A. K. Katsaggelos. Rate-distortion Based Video Compression: Opti-mal Video Frame Compression and Object Boundary Encoding. Amsterdam, Nether-lands: Kluwer Academic Publishers,1996.
[147] G. M. Schuster, G. Melnikov, A. K. Katsaggelos. Operationally optimal vertex-basedshape coding. IEEE Signal Processing Magazine,1998,15(6):91～108.
[148] J. Ostermann, A. Vetro. Document and Image Compression. Boca Raton, FL: CRCPress Inc., Taylor&Francis Ltd.,2006, chapter Two-dimensional shape coding, page299～321.
[149] F. A. Sohel, L. S. Dooley, G. C. Karmakar. Variable width admissible control pointband for vertex based operational-rate-distortion optimal shape coding algorithms. in:Proceedings of the13th IEEE International Conference on Image Processing,2006,2461～2464.
[150] F. A. Sohel, L. S. Dooley, G. C. Karmakar. New dynamic enhancements to the vertex-based rate-distortion optimal shape coding algorithm. IEEE Transactions on Circuitsand Systems for Video Technology,2007,17(10):1408～1413.
[151] F. A. Sohel, G. C. Dooley, L. S.and Karmakar. Accurate distortion measurement forgeneric shape coding. Pattern Recognition Letters,2006,27(27):133～142.
[152] L. P. Kondi, F. W. Meier, G. M. Schuster, et al. Joint optimal object shape estimationand encoding. in: Proceedings of SPIE International Conference on Visual Commu-nications and Image Processing,1998,14～25.
[153] K. J. Kim, C. W. Lim, M. G. Kang, et al. Adaptive approximation bounds forvertex based contour encoding. IEEE Transactions on Image Processing,1999,8(8):1142～1147.
[154] L. P. Kondi, G. Melnikov, A. K. Katsaggelos. Jointly optimal coding of texture andshape. in: Proceedings of the8th IEEE International Conference on Image Process-ing,2001, III-94～III-97.
[155] L. P. Kondi, G. Melnikov, A. K. Katsaggelos. Joint optimal object shape estimationand encoding. IEEE Transactions on Circuits and Systems for Video Technology,2004,14(4):528～533.
[156] F. A. Sohel, G. C. Karmakar, L. S. Dooley. Fast distortion measurement using chord-length parameterization within the vertex-based rate-distortion optimal shape codingframework. IEEE Signal Processing Letters,2007,14(2):121～124.
[157] F. A. Sohel, M. Bennamoun. Distortion measurement using arc-length parameter-isation within a vertex-based shape coding framework. in: Proceedings of the11thInternational Conference on Computer and Information Technology,2008,329～334.
[158] F. A. Sohel, G. C. Karmakar, L. S. Dooley, et al. Geometric distortion measure-ment for shape coding: A contemporary review. ACM Computing Surveys,2011,43(4):29:1～29:22.
[159] Z. Lai, W. Liu, Y. Zhang. Perceptual relevance measure for generic shape coding. in:Proceedings of the19th IEEE Data Compression Conference,2009,453.
[160] Z. Lai, W. Liu, F. Zhang, et al. Perceptual distortion measure for polygon-based shapecoding. IEICE Transactions on Information and Systems,2013, E96-D(3).
[161] Z. Lai, Z. Zuo, Z. Wang, et al. A hybrid admissible distortion checking algorithm forthe B-spline-based operational rate-distortion optimal shape coding. in: Proceedingsof the21st IEEE Data Compression Conference,2011,464.
[162] Z. Lai, Z. Zuo, Z. Wang, et al. Accurate distortion measurement using analyticalmodel for the B-spline-based shape coding. in: Proceedings of the21st IEEE DataCompression Conference,2011,465.
[163] Z. Lai, Z. Zuo, Z. Wang, et al. Accurate distortion measurement for B-spline basedshape coding. in: Proceedings of the18th IEEE International Conference on ImageProcessing,2011,229～232.
[164] Z. Lai, Z. Zuo, Z. Wang, et al. A hybrid admissible distortion checking algorithmwithin the vertex-based operational rate-distortion optimal shape coding framework.Journal of Computational Information Systems,2013,9(8).
[165] Z. Lai, J. Zhu, Z. Ren, et al. Arbitrary directional edge encoding schemes for theoperational rate-distortion optimal shape coding framework. in: Proceedings of the20th IEEE Data Compression Conference,2010,20～29.
[166] J. D. Foley, A. van Dam, S. K. Feiner, et al. Computer Graphics: Principles andPractice. Reading, MA: Addison-Wesley,1990.
[167] G. M. Schuster, A. K. Katsaggelos. The minimum-average and minimum-maximumcriteria in lossy compression. Vistas in Astronomy,1997,41(3):427～431.
[168] G. M. Schuster, G. Melnikov, A. K. Katsaggelos. A review of the minimum maximumcriterion for optimal bit allocation among dependent quantizers. IEEE Transactionson Multimedia,1999,1(1):3～17.
[169] M. Ho¨tter. Predictive contour coding for an object–oriented analysis–synthesiscoder. in: Proceedings of IEEE International Symposium on Information Theory,1990,75.
[170] P. Gerken, W. M., S. Schultz. Polygon/spline approximation of arbitrary image re-gions as proposal for MPEG-4tool evaluation-Technical Description. ISO/IECJTC1/SC29WG11MPEG95/M360, Dallas, TX, November,1995.
[171] J. Ostermann. Coding of binary shape in MPEG-4. in: Proceedings of the14thPicture Coding Symposium,1997,659～662.
[172] J. Ostermann, E. Jang, S.-S. Shin, et al. Coding of arbitrarily shaped video objectsin MPEG-4. in: Proceedings of the4th IEEE International Conference on ImageProcessing,1997, I-496～I-499.
[173] J. Ostermann. Methodologies used for evaluation of video tools and algorithms inMPEG-4. Special Issue on MPEG-4, Signal Processing: Image Communication,1997,9(4):343～365.
[174] K. J. O’Connell. Object-adaptive vertex-based shape coding method. IEEE Transac-tions on Circuits Systems for Video Technology,1997,7(1):252～255.
[175] J. Chung, J. Lee, J. Moon, et al. A new vertex-based binary shape coder for codingefficiency. Special Issue on Shape Coding for Emerging Multimedia Applications,Signal Processing: Image Communication,2000,15(7～8):665～684.
[176] S. D. Lin, C.-C. Lin, S.-C. Shie. A technique of object-adaptive vertex-based shapecoding for MPEG-4videos. International Journal of Imaging Systems and Technolo-gy,2001,11(5):277～282.
[177] S. D. Lin, C.-C. Lin, S.-C. Shie. A vertex-based shape coding technique for videoobjects. IEICE Transactions on Information and Systems,2001, E84-D(7):918～922.
[178] B. J. Yun, J. S. Cho, Y. H. Ko. A new vertex adjustment method for polygon-based shape coding. IEICE Transactions on Information and Systems,2006, E89-D(10):2693～2695.
[179] C. L. B. Jordan, T. Ebrahimi. Progressive polygon encoding of shape contours. in:Proceedings of the6th International Conference on Image Processing and Its Appli-cations,1997,17～21.
[180] C. L. B. Jordan, T. Ebrahimi, M. Kunt. Progressive content-based shape compressionfor retrieval of binary images. Computer Vision and Image Understanding,1998,71(2):198～212.
[181] J. I. Kim, B. L. Evans. Predictive shape coding using generic polygon approximation.in: Proceedings of IEEE International Symposium on Circuits and Systems,1998,277～280.
[182] J. I. Kim, A. C. Bovik, B. L. Evans. Generalized predictive binary shape coding usingpolygon approximation. Special Issue on Shape Coding for Emerging MultimediaApplications, Signal Processing: Image Communication,2000,15(7～8):643～663.
[183] K. J. Kim, J.-Y. Suh,, et al. Generalized interframe vertex-based shape encod-ing scheme for video sequence. IEEE Transactions on Image Processing,2000,9(10):1667～1676.
[184] L. J. Karam, T. Ebrahimi, S. Hemami, et al. Introduction to the special issue on visualmedia quality assessment. Special Issue on Visual Media Quality Assessment, IEEEJournal on Special Topics in Signal Processing,2009,3(2):189～192.
[185] M. Abramowitz, I. A. Stegun. Handbook of Mathematical Functions with Formulas,Graphs, and Mathematical Tables. New York, NY: Dover Publications,1972.
[186] T. Adamek, N. E. O’Connor. A multiscale representation method for nonrigid shapeswith a single closed contour. IEEE Transactions on Circuits Systems for Video Tech-nology,2004,14(5):742～753.
[187] E. Attalla, P. Siy. Robust shape similarity retrieval based on contour segmenta-tion polygonal multiresolution and elastic matching. Pattern Recognition,2005,38(12):2229～2241.
[188] C. Xu, J. Liu, X. Tang.2D shape matching by contour flexibility. IEEE Transactionson Pattern Analysis and Machine Intelligence,2009,31(1):180～186.
[189] F. A. Sohel, G. C. Karmakar, L. S. Dooley. A generic shape descriptor using Beziercurves. in: Proceedings of International Conference on Information Technology:Coding and Computing,2005,95～100.
[190] G. Melnikov, P. V. Karunaratne, G. M. Schuster, et al. Rate-distortion optional bound-ary encoding using an area distortion measure. in: Proceedings of IEEE InternationalSymposium on Circuits and Systems,1998,289～292.
[191] G. M. Melnikov, G.and Schuster, A. K. Katsaggelos. Simultaneous optimal bound-ary encoding and variable-length code selection. in: Proceedings of the5th IEEEInternational Conference on Image Processing,1998, I-256～I-260.
[192] G. Melnikov, G. M. Schuster, A. K. Katsaggelos. Inter mode vertex-based optimalshape coding. in: Proceedings of the24th IEEE International Conference on Acous-tics, Speech, and Signal Processing,1999,3125～3128.
[193] G. Melnikov, G. M. Schuster, A. K. Katsaggelos. Context based optimal shape cod-ing. in: Proceedings of IEEE3rd Workshop on Multimedia Signal Processing,1999,303～308.
[194] G. M. Melnikov, G.and Schuster, A. K. Katsaggelos. Shape coding using temporalcorrelation and joint VLC optimization. IEEE Transactions on Circuits Systems forVideo Technology,2000,10(5):744～754.
[195] G. Melnikov, G. M. Schuster, A. K. Katsaggelos. A rate-distortion optimal scalablevertex based shape coding algorithm. in: Proceedings of the25th IEEE InternationalConference on Acoustics, Speech and Signal Processing,2000,1947～1950.
[196] L. Gao, G. Zhang, Y. Lai. Lpshape deformation. Science China Information Sciences,2012,55(5):983～993.
[197] T. Cormen, C. Leiserson, R. Rivest. Introduction to Algorithms. New York, NY:McGraw-Hill,1991.
[198] L. Latecki, R. Lakamper. Shape similarity measure based on correspondence of vi-sual parts. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1185～1190.
[199] L. Latecki, R. Lakamper. Application of planar shape comparison to object retrievalin image databases. Pattern Recognition,2002,35(1):15～29.
[200] C. Wang, W. Liu, Z. Lai, et al. Perceptually friendly shape decomposition by resolv-ing segmentation points with minimum cost. Journal of Visual Communication andImage Representation,2013,24(3):270～282.
[201] B. Curless, M. Levoy. A volumetric method for building complex models from rangeimages. in: Proceedings of the23rd Annual Conference on Computer Graphics andInteractive Techniques,1996,303～312.
[202] V. Krishnamurthy, M. Levoy. Fitting smooth surfaces to dense polygon meshes. in:Proceedings of the23rd Annual Conference on Computer Graphics and InteractiveTechniques,1996,313～324.
[203] G. Turk, L. M. Zippered polygon meshes from range images. in: Proceedings of the21rd Annual Conference on Computer Graphics and Interactive Techniques,1994,311～318.
[204] K. Siddiqi, J. Zhang, D. Macrini, et al. Retrieving articulated3D models using medialsurfaces. Machine Vision and Applications,2008,19(4):261～274.
[205] K. Verfaillie, L. Boutsen. A corpus of714full-color images of depth-rotated objects.Perception and Psychophysics,1995,57(7):925～961.
[206] L. Boutsen, K. Lamberts, K. Verfaillie. Recognition times of different views of56depth-rotated objects: A note concerning Verfaillie and Boutsen. Perception andPsychophysics,1998,60(5):900～907.
[207] C. H. Lee, A. Varshney, D. W. Jacobs. Mesh Saliency. ACM Transactions on Graphics-Proceedings of the32nd Annual Conference on Computer Graphics and InteractiveTechniques,2005,24(3):659～666.
[208] S. K. Bandyopadhyay, L. P. Kondi. Joint rate distortion optimal shape and texturecoding. in: Proceedings of the17th Canadian Conference on Electrical and ComputerEngineering,2004,841～844.
[209] S. K. Bandyopadhyay, L. P. Kondi. Optimal bit allocation for joint contour-basedshape coding and shape adaptive texture coding. in: Proceedings of the12th IEEEInternational Conference on Image Processing,2005, I-589～I-592.
[210] S. K. Bandyopadhyay, L. P. Kondi. Optimal bit allocation for joint texture-awarecontour-based shape coding and shape-adaptive texture coding. IEEE Transactionson Circuits and Systems for Video Technology,2008,18(6):840～844.
