基于骨架的图像中物体表示与识别研究
|
摘要
制造出具有人工智能的机器人一直是科学家们的梦想。要实现这一目标关键的一步是识别图像中的物体。物体的骨架不仅包含了物体的形状特征,还具有拓扑结构,所以它在物体识别及相关应用领域,例如基于内容的图像检索、字符识别、生物医学图像分析和监控系统中,是一种有用而且重要的描述符。最近几年,鉴于骨架能方便地描述有关节的物体,所以在人机交互系统和体感游戏中,骨架被广泛用于模拟人体运动姿势。总而言之,研究基于骨架的物体表示和识别能加速计算机视觉领域的发展。
本文的工作主要集中在解决基于骨架的识别问题上,包括骨架剪枝,形状分类与聚类和人体姿势修正。本文的主要贡献包括如下几个方面：
1.提出一种新的叫做弯曲潜能比率的重要性度量,将其用于骨架剪枝。根据这种重要性度量,一段骨架枝是否该去除取决于它所对应的轮廓段对整个形状的贡献。而同样一段轮廓段处于整个轮廓上不同位置时所表现出的重要程度可能会有所不同,所以判断轮廓段对整个形状的贡献还需考虑其所处位置。同时,通过在骨架生长中结合该重要性度量进行剪枝,以保证剪枝骨架的连通性。实验结果表明,该剪枝算法能去除冗余的骨架枝,并得到适用于形状匹配的精确骨架。
2.提出一种新的骨架剪枝算法,它与传统的方法有着本质的不同。它将骨架剪枝问题通过贝叶斯模型抽象成一个骨架简单性和形状重建误差之间的开关问题。形状重建误差通过重建形状与原始形状的面积覆盖程度度量,而形状简单性则反比于骨架长度。一个简单的贪心算法被用来去逼近最大的贝叶斯后验概率,由此定义了一个剪枝顺序,从而得到最终的剪枝骨架。实验表明,在不调节任何参数的情况下,该算法得到的骨架对于物体轮廓变形及类内形状变化依旧是稳定的。
3.提出一种基于骨架的形状分类方法。通过有监督学习得到同类形状的骨架联合树,树中的节点包含了样例骨架的接合点以及它们的统计分布。随后,根据贝叶斯准则,这些信息会被用来对新的形状进行分类。在两个知名的形状数据集上的分类精度都要好于其他最先进的形状分类方法,说明了该算法的有效性。
4.提出一种基于骨架的方法去解决形状聚类的问题。该方法发掘出一种能表示同类物体固有内在信息的共同结构。一般聚类方法仅仅考虑成对的相似性度量,与之不同,本文提出的聚类方法采用合并型多层次框架,在聚类的同时更新共同结构,并将之用于下一次合并迭代以改进形状间相似度。实验结果表明,该方法能发掘出同类形状的共同结构,同时能自动检测出异常骨架节点,并对参数设置不敏感,且在四个形状数据集上都取得了最好的聚类效果。
5.提出一种基于从Kinect深度图像中估计得到的初始人体骨架的姿势修正算法。它显示了基于样例的方法是解决姿势修正问题的一个有效途径,而通过随机森林回归去学习非齐次的系统化误差则是解决问题的关键。采用级联回归和增加运动一致性约束也可以帮助提高姿势修正的结果。实验结果表明,该姿势修正算法,确实可以极大程度地提高姿势识别的精度,并且远好于当前Kinect系统所采用的姿势修正算法的效果。
本文所要解决的问题都是计算机视觉领域中的基础问题,所以本文所提出的模型和算法对其他的视觉任务和应用也有积极的推动作用。
The manufacture of artificial intelligence robots has been a dream of scientists for a long time. An essential step to achieve this goal is recognizing objects in images. The objec-t's skeleton contains not only the shape feature but also the topological structure, therefore it is a useful and essential descriptor for object recognition and many related applications, such as content-based image retrieval systems, character recognition systems, analysis of biomed-ical images and surveillance systems. In recent years, due to ease of capturing the articulated objects, the skeleton is widely applied to model human pose motion for human computer interaction and somatosensory gaming. Consequently, the research on skeleton-based object representation and recognition will lead to the rapid progress of computer vision.
The works of this dissertation concentrate on addressing the skeleton-based recogni-tion tasks, including skeleton pruning, shape classification and clustering and human pose correction. The main contributions of this dissertation are summarized as follow:
1. A novel significance measure, called bending potential ratio (BPR), is proposed for skeleton pruning, in which the pruning decision for a skeletal branch is determined by the contribution of its corresponding contour segment to the overall shape. Such the contribution depends on the particular location of the segment within the whole contour based on the fact that a segment may be considered to be insignificant in one place on the contour while it may be considered as feature elsewhere. The BPR measurement is integrated in a skeleton growing scheme to obtain the pruned skeleton, which meanwhile ensures the connectivity of the skeleton. Our experi-ments demonstrate that the proposed algorithm can remove the redundant skeleton branches and generate accurate skeletons which are useful for shape matching.
2. A novel skeleton pruning approach is proposed, which differs from the traditional ones fundamentally. It casts skeleton pruning as a tradeoff between skeleton sim-plicity and shape reconstruction error, formulated within a Bayesian framework. Shape reconstruction error is measured as the area overlap between the reconstruct-ed and original shapes. Skeleton simplicity is measured to be inversely related to skeleton length. A simple greedy algorithm is applied to approximate the maxi-mum of the Baycsian posterior probability which defines an order for iteratively removing the end branches to obtain the pruned skeleton. Presented experimental results obtained without any parameter tuning clearly demonstrate that the resulting skeletons are stable to boundary deformations and intra class shape variability.
3. A skeleton-based approach to shape classification is proposed. It models a shape class by a supervised learned tree-union. Each node in the tree-union stores not only the examples of skeletal junctions but also their statistic distributions. These information are then used to classify new shapes according to Bayesian rule. The classification accuracies on two well known shape data sets are higher than the state-of-the-art approach which shows the effectiveness of the proposed approach.
4. A skeleton-based approach is proposed to address the problem of shape clustering by discovering the common structure which captures the intrinsic structural infor-mation of shapes belonging to the same cluster. Unlike the traditional clustering algorithms only consider the pairwise similarity, the proposed approach adopts ag-glomerative hierarchical framework, in which the common structure is updated dur-ing clustering and used to improve the similarity between shapes in next merging iteration. The experimental results show that the proposed approach can discover the common structure of shapes of the same cluster, detect the outlier node automat-ically, be not sensitive to parameter setting, and achieve the best clustering results on four shape data sets.
5. A new algorithm for pose correction from the initially estimated skeletons from Kinect depth images is present. It shows that exemplar-based approach serves a promising direction for pose correction and learning the inhomogeneous systemat-ic bias by random forest regression is the essential key. Cascaded regression and motion consistency are also applied to improve pose correction. The experimental results show that the proposed pose correction algorithm indeed significantly im-proves the accuracy of pose recognition and is much better than the one employed in the Kinect system.
All the problems addressed in this dissertation are fundamental in computer vision, so other vision tasks and applications can benefit from the models and the algorithms proposed in this dissertation.
本文的工作主要集中在解决基于骨架的识别问题上,包括骨架剪枝,形状分类与聚类和人体姿势修正。本文的主要贡献包括如下几个方面：
1.提出一种新的叫做弯曲潜能比率的重要性度量,将其用于骨架剪枝。根据这种重要性度量,一段骨架枝是否该去除取决于它所对应的轮廓段对整个形状的贡献。而同样一段轮廓段处于整个轮廓上不同位置时所表现出的重要程度可能会有所不同,所以判断轮廓段对整个形状的贡献还需考虑其所处位置。同时,通过在骨架生长中结合该重要性度量进行剪枝,以保证剪枝骨架的连通性。实验结果表明,该剪枝算法能去除冗余的骨架枝,并得到适用于形状匹配的精确骨架。
2.提出一种新的骨架剪枝算法,它与传统的方法有着本质的不同。它将骨架剪枝问题通过贝叶斯模型抽象成一个骨架简单性和形状重建误差之间的开关问题。形状重建误差通过重建形状与原始形状的面积覆盖程度度量,而形状简单性则反比于骨架长度。一个简单的贪心算法被用来去逼近最大的贝叶斯后验概率,由此定义了一个剪枝顺序,从而得到最终的剪枝骨架。实验表明,在不调节任何参数的情况下,该算法得到的骨架对于物体轮廓变形及类内形状变化依旧是稳定的。
3.提出一种基于骨架的形状分类方法。通过有监督学习得到同类形状的骨架联合树,树中的节点包含了样例骨架的接合点以及它们的统计分布。随后,根据贝叶斯准则,这些信息会被用来对新的形状进行分类。在两个知名的形状数据集上的分类精度都要好于其他最先进的形状分类方法,说明了该算法的有效性。
4.提出一种基于骨架的方法去解决形状聚类的问题。该方法发掘出一种能表示同类物体固有内在信息的共同结构。一般聚类方法仅仅考虑成对的相似性度量,与之不同,本文提出的聚类方法采用合并型多层次框架,在聚类的同时更新共同结构,并将之用于下一次合并迭代以改进形状间相似度。实验结果表明,该方法能发掘出同类形状的共同结构,同时能自动检测出异常骨架节点,并对参数设置不敏感,且在四个形状数据集上都取得了最好的聚类效果。
5.提出一种基于从Kinect深度图像中估计得到的初始人体骨架的姿势修正算法。它显示了基于样例的方法是解决姿势修正问题的一个有效途径,而通过随机森林回归去学习非齐次的系统化误差则是解决问题的关键。采用级联回归和增加运动一致性约束也可以帮助提高姿势修正的结果。实验结果表明,该姿势修正算法,确实可以极大程度地提高姿势识别的精度,并且远好于当前Kinect系统所采用的姿势修正算法的效果。
本文所要解决的问题都是计算机视觉领域中的基础问题,所以本文所提出的模型和算法对其他的视觉任务和应用也有积极的推动作用。
The manufacture of artificial intelligence robots has been a dream of scientists for a long time. An essential step to achieve this goal is recognizing objects in images. The objec-t's skeleton contains not only the shape feature but also the topological structure, therefore it is a useful and essential descriptor for object recognition and many related applications, such as content-based image retrieval systems, character recognition systems, analysis of biomed-ical images and surveillance systems. In recent years, due to ease of capturing the articulated objects, the skeleton is widely applied to model human pose motion for human computer interaction and somatosensory gaming. Consequently, the research on skeleton-based object representation and recognition will lead to the rapid progress of computer vision.
The works of this dissertation concentrate on addressing the skeleton-based recogni-tion tasks, including skeleton pruning, shape classification and clustering and human pose correction. The main contributions of this dissertation are summarized as follow:
1. A novel significance measure, called bending potential ratio (BPR), is proposed for skeleton pruning, in which the pruning decision for a skeletal branch is determined by the contribution of its corresponding contour segment to the overall shape. Such the contribution depends on the particular location of the segment within the whole contour based on the fact that a segment may be considered to be insignificant in one place on the contour while it may be considered as feature elsewhere. The BPR measurement is integrated in a skeleton growing scheme to obtain the pruned skeleton, which meanwhile ensures the connectivity of the skeleton. Our experi-ments demonstrate that the proposed algorithm can remove the redundant skeleton branches and generate accurate skeletons which are useful for shape matching.
2. A novel skeleton pruning approach is proposed, which differs from the traditional ones fundamentally. It casts skeleton pruning as a tradeoff between skeleton sim-plicity and shape reconstruction error, formulated within a Bayesian framework. Shape reconstruction error is measured as the area overlap between the reconstruct-ed and original shapes. Skeleton simplicity is measured to be inversely related to skeleton length. A simple greedy algorithm is applied to approximate the maxi-mum of the Baycsian posterior probability which defines an order for iteratively removing the end branches to obtain the pruned skeleton. Presented experimental results obtained without any parameter tuning clearly demonstrate that the resulting skeletons are stable to boundary deformations and intra class shape variability.
3. A skeleton-based approach to shape classification is proposed. It models a shape class by a supervised learned tree-union. Each node in the tree-union stores not only the examples of skeletal junctions but also their statistic distributions. These information are then used to classify new shapes according to Bayesian rule. The classification accuracies on two well known shape data sets are higher than the state-of-the-art approach which shows the effectiveness of the proposed approach.
4. A skeleton-based approach is proposed to address the problem of shape clustering by discovering the common structure which captures the intrinsic structural infor-mation of shapes belonging to the same cluster. Unlike the traditional clustering algorithms only consider the pairwise similarity, the proposed approach adopts ag-glomerative hierarchical framework, in which the common structure is updated dur-ing clustering and used to improve the similarity between shapes in next merging iteration. The experimental results show that the proposed approach can discover the common structure of shapes of the same cluster, detect the outlier node automat-ically, be not sensitive to parameter setting, and achieve the best clustering results on four shape data sets.
5. A new algorithm for pose correction from the initially estimated skeletons from Kinect depth images is present. It shows that exemplar-based approach serves a promising direction for pose correction and learning the inhomogeneous systemat-ic bias by random forest regression is the essential key. Cascaded regression and motion consistency are also applied to improve pose correction. The experimental results show that the proposed pose correction algorithm indeed significantly im-proves the accuracy of pose recognition and is much better than the one employed in the Kinect system.
All the problems addressed in this dissertation are fundamental in computer vision, so other vision tasks and applications can benefit from the models and the algorithms proposed in this dissertation.
引文
[1]Sebastian T B, Klein P N, Kimia B B. Recognition of shapes by editing their shock graphs. IEEE Trans. Pattern Analysis and Machine Intelligence,2004,26(5):550-571.
[2]Epshtein B, Ofek E, Wexler Y. Detecting text in natural scenes with stroke width transform. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2010.
[3]Ma L, Tan T, Wang Y, et al. Personal identification based on iris texture analysis. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(12):1519-1533.
[4]Jain A K, Hong L, Pankanti S, ct al. An identity verification system using fingerprints. IEEE Proceedings,1999,85(9):1365-1388.
[5]D Marr. Vision:a computational investigation into human representation and processing of visual information. Inc. New York, USA,:Henry Holt and Co.,1982.
[6]Wang C, Li Z, Zhang L. MindFinder:image search by interactive sketching and tagging. in: Proceedings of International World Wide Web Conference (WWW),2010.
[7]Cao Y, Wang C, Zhang L, et al. Edgel inverted index for large-scale sketch-based image search. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[8]Wang C, Li Z, Zhang L. Sketch-Based Image Search Patent 20120054177, march,2012.
[9]Blum H. Biological shape and visual science. J. Theor. Biol.,1973,38:205-287.
[10]Blum H. A Transformation for extracting new descriptors of shape, in:models for the perception of speech and visual form. MIT Press,1967, pages 363-380.
[11]Canny J. A computational approach to edge detection. IEEE Trans. Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[12]Martin D, Fowlkes C, Malik J. Learning to detect natural image boundaries using local brightness, color and texture cues. IEEE Trans. Pattern Analysis and Machine Intelligence,2004,26(5):530-549.
[13]Dollar P, Tu Z, Belongie S. Supervised learning of edges and object boundaries. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2006.
[14]Yao C, Shen W, Bai X, et al. Class-specific object contour detection by iteratively combining context information. in:Proceedings of IEEE International Conference on Information, Commu-nications, and Signal Processing (ICICS),2011.
[15]Bai X, Wang X, Latecki L J, et al. Active skeleton for non-rigid object detection. in:Proceedings of IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan,2009.
[16]Trinh N H, Kimia B B. Category-specific object recognition and segmentation using a skeletal shape model. in:Proceedings of British Machine Vision Conference (BMVC),2009.
[17]Sorantin E, Halmai C, Erdoelyi B, et al. Spiral-CT-based assessment of tracheal stenoses using 3D-skeletonization. IEEE Trans. Medical Imaging,2002,21(3):263-273.
[18]Grau V, Mewes A U J, Alcanz M, et al. Improved watershed transform for medical image segmen-tation using prior information. IEEE Trans. Medical Imaging,2004,23(4):447^458.
[19]Jiang H, Liu W, Wang D, et al. CASE:connectivity-based skeleton extraction in wireless sensor networks. in:Proceedings of IEEE Conference on Computer Communications (INFOCOM), 2009,2916-2920.
[20]Jiang H, Liu W, Wang D, et al. Connectivity-based skeleton extraction in wireless sensor networks. IEEE Trans. on Parallel and Distributed Systems,2010,21 (5):710-721.
[21]August J, Siddiqi K, Zucker S. Ligature instabilities and the perceptual organization of shape. Computer Vision and Image Understanding,1999,76(3):231-243.
[22]Aslan C, Erdem A, Erdem E, et al. Disconnected skeleton:shape at its absolute scale. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(12):2188-2203.
[23]Ruberto C D. Recognition of shapes by attributed skeletal graphs. Pattern Recognition,2004, 37(1):21-31.
[24]Zhu S, Yuille A L. FORMS:a flexible object recognition and modeling system. International Journal of Computer Vision,1996,20(3):187-212.
[25]Siddiqi K, Shkoufandeh A, Dickinson S, et al. Shock graphs and shape matching. in:Proceedings of IEEE International Conference on Computer Vision (ICCV),1998,222-229.
[26]A. Shokoufandeh K S, Dickinson S, Zucker S. Shock graphs and shape matching. International Journal of Computer Vision,1999,35(1):13-32.
[27]Macrini D, Siddiqi K, Dickinson S. From skeletons to bone graphs:medial abstraction for object recognition. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2008.
[28]Microsoft Corp. Kinect for XBOX 360. Redmond WA.
[29]Lai K, Bo L, Ren X, et al. A large-scale hierarchical multi-view RGB-D object dataset. in: Proceedings of IEEE International Conference on Robotics and Automation (ICRA),2011,1817-1824.
[30]Shotton J, Fitzgibbon A, Cook M, et al. Real-time human pose recognition in parts from a single depth image. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[31]Liu H, Latccki L J, Liu W. A Unified Curvature Definition for Regular, Polygonal, and Digital Planar Curves. International Journal of Computer Vision,2008,80:104-124.
[32]Lam L, Lee S W, Suen C Y. Thinning methodologies-a comprehensive survey. IEEE Trans. Pattern Analysis and Machine Intelligence,1996,14(9):869-885.
[33]Leymarie F, Levine M. Simulating the grassfire transaction form using an active contour model. IEEE Trans. Pattern Analysis and Machine Intelligence,1992,14(1):56-75.
[34]Arcelli C, Baja G S. A width-independent fast thinning algorithm. IEEE Trans. Pattern Analysis and Machine Intelligence,1985,7(4):463-474.
[35]Ogniewicz R, Ilg M. Voronoi skeletons:theory and applications. in:Proceedings of IEEE Inter-national Conference on Computer Vision and Pattern Recognition (CVPR),1992,63-69.
[36]Brandt J W, Algazi V R. Continuous skeleton computation by Voronoi diagram. CVGIP:Image Understanding,1999,55(3):329-338.
[37]Mayya N, Rajan V T. Voronoi diagrams of polygons:a framework for shape representation. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),1994,638-643.
[38]Niblack C W, Gibbons P B, Capson D W. Generating skeletons and centerlines from the distance transform. CVGIP:Image Understanding,1992,54(5):420-437.
[39]Ge Y, Fitzpatrick J M. On the generation of skeletons from discrete Euclidean distance maps. IEEE Trans. Pattern Analysis and Machine Intelligence,1996,18(11):1055-1066.
[40]Choi W P, Lam K M, Siu W C. Extraction of the Euclidean skeleton based on a connectivity criterion. Pattern Recognition,2003,36:721-729.
[41]Arcelli C, Baja G S. A one-pass two-operations process to detect the skeletal pixels on the 4-distance transform. IEEE Trans. Pattern Analysis and Machine Intelligence,1989,11(4):411-414.
[42]Baja G S. Well-shaped, stable and reversible skeletons from the (3,4)-distance transform. Journal of Visual Communication and Image Representation,1994,5:107-115.
[43]Baja G S, Thiel E. Skeletonization algorithm running on path-based distance maps. Image and Vision Computing,1996,14(1):47-57.
[44]Arcelli C, Baja G S. Euclidean skeleton via center-of-maximal-disc extraction. Image and Vision Computing,1993,11 (3):163-173.
[45]Yu Z Y, Bajaj C. A segmentation-free approach for skeletonization of gray-scale images via anisotropic vector diffusion. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2000,415-420.
[46]Krinidis S, Chatzis V. A skeleton family generator via physics-based deformable models. IEEE Trans. Image Processing,2009,18(1):1-11.
[47]Gorelick L, Galun M, Sharon E, et al. Simulating the grassfire transaction form using an active contour model. IEEE Trans. Pattern Analysis and Machine Intelligence,2006,28(12):1991-2005.
[48]Dimitrov P, Damon J N, Siddiqi K. Flux invariants for shape, in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2003,835-841.
[49]Golland P, Grimson E. Fixed topology skeletons. in:Proceedings of IEEE International Confer-ence on Computer Vision and Pattern Recognition (CVPR),2000.
[50]Dimitrov P, Phillips C, Siddiqi K. Robust and efficient skeletal graphs, in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2000.
[51]Siddiqi K, Bouix S, Tannenbaum A, et al. Hamilton-jacobi skeletons. International Journal of Computer Vision,2002,48(3):215-231.
[52]Siddiqi K, Kimia B B, Shu C. Geometric shock-capturing ENO schemes for subpixel interpolation, computation, and curve evolution. in:Proceedings of ISCV,1995.
[53]Bai X, Latecki L, Liu W. Skeleton pruning by contour partitioning with discrete curve evolution. IEEE Trans. Pattern Analysis and Machine Intelligence,2007,29(3):449-462.
[54]Ogniewicz R, Kubler O. Hierarchic voronoi skeletons. Pattern Recognition,1995,28(3):343-359.
[55]Shaked D, Bruckstein A. Pruning medial axes. Computer Vision and Image Understanding,1998, 69(2):156-169.
[56]Couprie M, Zrour R. Discrete bisector function and Euclidean skeleton in 2D and 3D. Image and Vision Computing,2007,25(10):1543-1556.
[57]Latecki L J, Lakamper R. Polygon evolution by vertex deletion. in:Proceedings of Int'l Conf. Scale-Space,1999.
[58]Latecki L J, Lakamper R. Convexity rule for shape decompostion based on discrete curve evolu-tion. Computer Vision and Image Understanding,1999,73:441-454.
[59]Latecki L J, Lakamper R. Shape similarity measure based on correspondence of visual parts. EEEE Trans. Pattern Analysis and Machine Intelligence,2000,22(10):1185-1190.
[60]Choi H, Choi S, Moon H. Mathematical theory of medial axis transform. Pacific Journal of Math., 1997,181(1):57-88.
[61]Xu C J, Liu J Z, Tang X O.2D shape matching by contour flexibility. IEEE Trans. Pattern Analysis and Machine Intelligence,2009,31 (10):180-186.
[62]Leyton M. A process-grammar for shape. Artificial Intelligence,1988,34(2):213-247.
[63]Bai X, Latecki L. Path similarity skeleton graph matching. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(7):1282-1292.
[64]Bai X, Yang X W, Yu D, et al. Skeleton-based shape classification using path similarity. Int. Journal of Pattern Recognition and Art. Intell.,2008,22(4):733-746.
[65]Bai X, Liu W Y, Tu Z. Integrating contour and skeleton for shape classification. in:Proceedings of IEEE Workshop on NORDIA,2009.
[66]Latecki L J, Lakamper R, Eckhardt U. Shape descriptors for non-rigid shapes with a single closed contour. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2000,1424-1429.
[67]Bai X, Latecki L J. Discrete skeleton evolution. in:Proceedings of EMMCVPR,2007.
[68]Telea A, Wijk J. An augmented fast marching method for computing skeletons and centerlines. IEEE TCVG Symposium on Visualization,2002, pages 251-259.
[69]Pelillo M, Siddiqi K, Zucker S. Matching hierarchical structure using association graphs. IEEE Trans. Pattern Analysis and Machine Intelligence,1999,21(11):1105-1120.
[70]Siddiqi K, Kimia B B. A shock grammar for recognition. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),1996,507-513.
[71]Aslan C, Tari S. An axis-based representation for recognition. in:Proceedings of IEEE Interna-tional Conference on Computer Vision (ICCV),2005.
[72]Lin H, Jacobs D W. Shape classification using the inner-distance. IEEE Trans. Pattern Analysis and Machine Intelligence,2007,29(2):286-299.
[73]Siddiqi K, Pizer S. Medial representations:Mathematics, algorithms and applications. Springer, 2011.
[74]Torsello A, Hancock E. Correcting curvature-density effects in the Hamilton-Jacobi skeleton. IEEE Trans. Image Processing,2006,15(4):887-891.
[75]Borgefors G, Ramella G, Baja G S. Hierarchical decomposition of multiscale skeleton. IEEE Trans. Pattern Analysis and Machine Intelligence,2001,13(11):1296-1312.
[76]Katz R, Pizer S. Untangling the blum medial axis transform. International Journal of Computer Vision,2003,55:139-153.
[77]Eede M, Macrini D, Telea A, et al. Canonical skeletons for shape matching. in:Proceedings of International Conference on Pattern Recognition (ICPR),2006.
[78]Ward A, Hamarneh G. Gmat:the groupwise medial axis transform for fuzzy skeletonization and intelligent pruning. Technical report, School of Computing Science, Simon Fraser University, 2008.
[79]Ward A, Hamarneh G. The groupwise medial axis transform for fuzzy skeletonization and pruning. IEEE Trans. Pattern Analysis and Machine Intelligence,2010,32(6):1084-1096.
[80]Levinshtein A, Sminchisescu C, Dickinson S. Multiscale symmetric part detection and grouping, in:Proceedings of IEEE International Conference on Computer Vision (ICCV),2009.
[81]Adluru N, Latecki L J, Lakamper R, et al. Contour grouping based on local symmetry. in:Pro-ceedings of IEEE International Conference on Computer Vision (ICCV),2007.
[82]Feldman J, Singh M. Bayesian estimation of the shape skeleton. Proceeding of National Academy of Sciences of the United States of America,2006,103(47):18014-18019.
[83]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,24(4):509-522.
[84]Cootes T, Taylor C, Cooper D, et al. Active shape models — their training and application. Com-puter Vision and Image Understanding,1995,61(1):38-59.
[85]Davies R, Twining C, Cootes T, et al. A minimum description length approach to statistical shape modeling. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,21(5):525-537.
[86]Ghebreab S, Smeulders A. Strings:variational deformable models of multivariate continuous boundary features. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(11):1399-1410.
[87]Grigorescu C, Petkov N. Distance sets for shape filters and shape recognition. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,12(10):1274-1286.
[88]Sebastian T, Klein P, Kimia B. Shock-based indexing into large shape databases. in:Proceedings of Europeon Conference on Computer Vision (ECCV),2002,731-746.
[89]Rissanen J. Modelling by shortest data description. Automatica,1978,14:465-471.
[90]Sun K B, Super B J. Classification of contour shapes using class segment sets. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2005, 727-733.
[91]Latecki L, Megalooikonomou V, Wang Q, et al. Partial elastic matching of time series. in:Pro-ceedings of IEEE International Conference on Data Mining (ICDM),2005.
[92]Felzenszwalb P F, Schwartz J. Hierarchical matching of deformable shapes. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2007.
[93]Daliri M R, Torre V. Robust symbolic representation for shape recognition and retrieval. Pattern Recognition,2008,41(5):1799-1815.
[94]Geiger D, Liu T L, Kohn R V. Representation and self-similarity of shapes. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(1):86-99.
[95]Torsello A, ER E R H. A skeletal measure of 2D shape similarity. Computer Vision and Image Understanding,2004,95(1):1-29.
[96]Xie J, Heng P, Shah M. Shape matching and modeling using skeletal context. Pattern Recognition, 2008,41 (5):1756-1767.
[97]Goh W. Strategies for shape matching using skeletons. Computer Vision and Image Understand-ing,2008,110(3):326-345.
[98]Sebastian T B, Kimia B B. Curves vs skeletons in object recognition. in:Proceedings of IEEE International Conference on Image Processing (ICIP),2001.
[99]Basri R, Costa L, Geiger D, et al. Determining the similarity of deformable shapes. Vision Research,1998,38:2365-2385.
[100]Siddiqi K, Kimia B, Tannenbaum A, et al. Shocks, shapes, and wiggles. Image and Vision Computing,1999,17:365-373.
[101]Sebastian T, Klein P, Kimia B. Recognition of shapes by editing shock graphs. in:Proceedings of IEEE International Conference on Computer Vision (ICCV),2001.
[102]Liu T, Geiger D. Approximate Tree Matching and Shape Similarity. in:Proceedings of IEEE International Conference on Computer Vision (ICCV),1999,456-462.
[103]Demirci M, Shokoufandeh A, Keselman Y, et al. Object recognition as many-to-many feature matching. International Journal of Computer Vision,2006,69(2):203-222.
[104]Baseski E, Erdem A, Tari S. Dissimilarity between two skeletal trees in a context. Pattern Recog-nition,2009,42(3):370-385.
[105]Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. New York:Springer, 2009.
[106]Spath H. Cluster analysis algorithms. Chichester:Ellis Horwood,1980.
[107]Sokal R, Michener C. A statistical method for evaluating systematic relationships. University of Kansas Science Bulletin,38:1409-1438.
[108]Lakaemper R, Zeng J. A context dependent distance measure for shape clustering. in:Proceedings of IS VC,2008.
[109]Srivastava A, Joshi S, Mio W, et al. Statistical shape analysis:clustering, learning, and testing. IEEE Trans. Pattern Analysis and Machine Intelligence,2005,27(4):590-602.
[110]Yankov D, Keogh E. Manifold clustering of shapes. in:Proceedings of IEEE International Con-ference on Data Mining (ICDM),2006.
[111]Mio W, Srivastava A, Joshi S. On shape of plane elastic curves. International Journal of Computer Vision,2007,73(3):307-324.
[112]Demirci M, Shokoufandeh A, Dickinson S. Skeletal shape abstraction from examples. IEEE Trans. Pattern Analysis and Machine Intelligence,2009,31(5):944-952.
[113]Torsello A, Hancock E. Learning shape-classes using a mixture of tree-unions. IEEE Trans. Pattern Analysis and Machine Intelligence,2006,28(6):954-967.
[114]Kuhn H W. The Hungarian method for the assignment problem. Naval Research Logistics Quar-terly,1955,2:83-97.
[115]Shi J, Malik J. Normalized cuts and image segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[116]Tan P N, Steinbach M, Kumar V. Introduction to Data Mining. Addison Wesley,2005.
[117]Girshick R, Shotton J, Kohli P, et al. Real-time human pose recognition in parts from a single depth image, in:Proceedings of IEEE International Conference on Computer Vision (ICCV),2011.
[118]Isard M, Blake A. CONDENSATION-Conditional density propagation for visual tracking. In-ternational Journal of Computer Vision,1998,29(1):5-28.
[119]Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(5):564-575.
[120]Dollar P, Rabaud V, Cottrell G, et al. Behavior recognition via sparse spatio-temporal features. in: Proceedings of ICCV VS-PETS,2005.
[121]Bourdev L D, Malik J. Poselets:body part detectors trained using 3D human pose annotations. in: Proceedings of IEEE International Conference on Computer Vision (ICCV),2009.
[122]Niebles J C, Chen C W, Fei-Fei L. Modeling temporal structure of decomposable motion segments for activity classification. in:Proceedings of Europeon Conference on Computer Vision (ECCV), 2010.
[123]Moeslund T, Hilton A, Kruger V. A survey of advances invision-based human motion capture and analysis. Computer Vision and Image Understanding,2006.
[124]Poppe R. Vision-based human motion analysis:An overview. Computer Vision and Image Un-derstanding,2007,108.
[125]Grest D, Woetzel J,, et al. Nonlinear body pose estimation from depth images. in:Proceedings of DAGM,2005.
[126]Knoop S, Vacek S, Dillmann R. Sensor fusion for 3D human body tracking with an articulated 3D body model. in:Proceedings of IEEE International Conference on Robotics and Automation (ICRA),2006.
[127]Siddiqui M, Medioni G. Human pose estimation from a single view point, real-time range sensor, in:Proceedings of CVPR-CVCG,2010.
[128]Christian P R, Casella G. Monte Carlo statistical methods. New York:Springer,2004.
[129]Fanelli G, Gall J, Gool L V. Real Time Head Pose Estimation with Random Regression Forests. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[130]Breiman L. Random forests. Machine learning,2001,45(1):5-32.
[131]Lepetit V, Lagger P, Fua P. Randomized trees for real-time keypoint recognition. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2005, 775-781.
[132]Quinlan J R. Induction of decision trees. Machine Learning,1986.
[133]Comaniciu D, Meer P. Mean shift:a robust approach toward feature space analysis. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[134]Birnbaum A. A unified theory of estimation. The Annals of Mathematical Statistics,1961,32(1).
[135]Tak S, Ko H S. Physically-based motion retargeting filter. ACM Transactions on Graphics,2005, 24(1).
[136]Lee J, Shin S Y. Motion fairing. in:Proceedings of Computer Animation,1996,136-143.
[137]Lou H, Chai J. Example-based human motion denoising. IEEE Trans. Visualization and Computer Graphics,2010,16(5).
[138]Duda R, Hart P, Stork D. Pattern classification and scene analysis. John Wiley and Sons,2000.
[139]Rasmussen C E, Williams C. Gaussian processes for machine learning. MIT Press,2006.
[140]Scholkopf B, Smola A, Williamson R, et al. New support vector algorithms. Neural Computation, 2000,12:1207-1245.
[141]Peduzzi P, Concato J, Kemper E, et al. A simulation study of the number of events per variable in logistic regression analysis. J Clin Epidemiol,1996,49(12):1373-1379.
[142]Wang J M, Fleet D J, Hertzmann A. Gaussian process dynamical models for human motion. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(2):283-298.
[143]Wang J M, Fleet D J, Hertzmann A. Gaussian process dynamical models. in:Proceedings of Neural Information Processing Systems,2005,1441-1448.
[144]Breiman L. Random forests. Machine learning,2001,45(1):5-32.
[145]Liaw A, Wiener M. Classification and regression by random forest,2002.
[146]Dollar P, Welinder P, Perona P. Cascaded pose regression. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2010.
[147]Tu Z. Auto-context and its application to high-level vision tasks. in:Proceedings of IEEE Inter-national Conference on Computer Vision and Pattern Recognition (CVPR),2008.
[148]Tu Z, Bai X. Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence,2010,32(10):1744-1757.
[149]Gelfand A E, Smith A F M. Sampling-based approaches to calculating marginal densities. Jounal of the American Statistical Association,1990,85(410):398-409.
[150]Rasmussen C E, Nickisch H. Gaussian processes for machine learning (GPML) toolbox. Jour-nal of Machine Learning Research,2010,11:3011-3015. Software available at http://www. gaussianprocess.org/gpml.
[151]Chang C C, Lin C J. LIBSVM:A library for support vector machines. ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27. Software available at http://www.csie.ntu. edu.tw/-cjlin/libsvm.
[152]Stahl J S, Wang S. Globally optimal grouping for symmetric boundaries. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2006.
[153]Ferrari V, Fevrier L, Jurie F, et al. Groups of Adjacent Contour Segments for Object Detection. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(1):36-51.
[154]Stahl J S, Wang S. Edge Grouping Combining Boundary and Region Information. IEEE Trans. Image Processing,2007,16(10):2590-2606.
[155]Sundar H, Silver D, Gagvani N, et al. Skeleton based shape matching and retrieval. in:Proceedings of International Conference on Shape Modeling and Applications (SMI),2003.
[156]Cornea N D, Demirci M, Silver D, et al.3D object retrieval using many-to-many matching of curve skeletons. in:Proceedings of International Conference on Shape Modeling and Applications (SMI),2005.
[157]Wagg D K, Nixon M S. On automated model-based extraction and analysis of gait. in:Proceedings of International Conference Automatic Face and Gesture Recognition (FG),2004.
[158]Tanawongsuwan R, Bobick A. Gait recognition from time-normalized joint-angle trajectories in the walking plane. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2001.
[2]Epshtein B, Ofek E, Wexler Y. Detecting text in natural scenes with stroke width transform. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2010.
[3]Ma L, Tan T, Wang Y, et al. Personal identification based on iris texture analysis. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(12):1519-1533.
[4]Jain A K, Hong L, Pankanti S, ct al. An identity verification system using fingerprints. IEEE Proceedings,1999,85(9):1365-1388.
[5]D Marr. Vision:a computational investigation into human representation and processing of visual information. Inc. New York, USA,:Henry Holt and Co.,1982.
[6]Wang C, Li Z, Zhang L. MindFinder:image search by interactive sketching and tagging. in: Proceedings of International World Wide Web Conference (WWW),2010.
[7]Cao Y, Wang C, Zhang L, et al. Edgel inverted index for large-scale sketch-based image search. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[8]Wang C, Li Z, Zhang L. Sketch-Based Image Search Patent 20120054177, march,2012.
[9]Blum H. Biological shape and visual science. J. Theor. Biol.,1973,38:205-287.
[10]Blum H. A Transformation for extracting new descriptors of shape, in:models for the perception of speech and visual form. MIT Press,1967, pages 363-380.
[11]Canny J. A computational approach to edge detection. IEEE Trans. Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[12]Martin D, Fowlkes C, Malik J. Learning to detect natural image boundaries using local brightness, color and texture cues. IEEE Trans. Pattern Analysis and Machine Intelligence,2004,26(5):530-549.
[13]Dollar P, Tu Z, Belongie S. Supervised learning of edges and object boundaries. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2006.
[14]Yao C, Shen W, Bai X, et al. Class-specific object contour detection by iteratively combining context information. in:Proceedings of IEEE International Conference on Information, Commu-nications, and Signal Processing (ICICS),2011.
[15]Bai X, Wang X, Latecki L J, et al. Active skeleton for non-rigid object detection. in:Proceedings of IEEE International Conference on Computer Vision (ICCV), Kyoto, Japan,2009.
[16]Trinh N H, Kimia B B. Category-specific object recognition and segmentation using a skeletal shape model. in:Proceedings of British Machine Vision Conference (BMVC),2009.
[17]Sorantin E, Halmai C, Erdoelyi B, et al. Spiral-CT-based assessment of tracheal stenoses using 3D-skeletonization. IEEE Trans. Medical Imaging,2002,21(3):263-273.
[18]Grau V, Mewes A U J, Alcanz M, et al. Improved watershed transform for medical image segmen-tation using prior information. IEEE Trans. Medical Imaging,2004,23(4):447^458.
[19]Jiang H, Liu W, Wang D, et al. CASE:connectivity-based skeleton extraction in wireless sensor networks. in:Proceedings of IEEE Conference on Computer Communications (INFOCOM), 2009,2916-2920.
[20]Jiang H, Liu W, Wang D, et al. Connectivity-based skeleton extraction in wireless sensor networks. IEEE Trans. on Parallel and Distributed Systems,2010,21 (5):710-721.
[21]August J, Siddiqi K, Zucker S. Ligature instabilities and the perceptual organization of shape. Computer Vision and Image Understanding,1999,76(3):231-243.
[22]Aslan C, Erdem A, Erdem E, et al. Disconnected skeleton:shape at its absolute scale. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(12):2188-2203.
[23]Ruberto C D. Recognition of shapes by attributed skeletal graphs. Pattern Recognition,2004, 37(1):21-31.
[24]Zhu S, Yuille A L. FORMS:a flexible object recognition and modeling system. International Journal of Computer Vision,1996,20(3):187-212.
[25]Siddiqi K, Shkoufandeh A, Dickinson S, et al. Shock graphs and shape matching. in:Proceedings of IEEE International Conference on Computer Vision (ICCV),1998,222-229.
[26]A. Shokoufandeh K S, Dickinson S, Zucker S. Shock graphs and shape matching. International Journal of Computer Vision,1999,35(1):13-32.
[27]Macrini D, Siddiqi K, Dickinson S. From skeletons to bone graphs:medial abstraction for object recognition. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2008.
[28]Microsoft Corp. Kinect for XBOX 360. Redmond WA.
[29]Lai K, Bo L, Ren X, et al. A large-scale hierarchical multi-view RGB-D object dataset. in: Proceedings of IEEE International Conference on Robotics and Automation (ICRA),2011,1817-1824.
[30]Shotton J, Fitzgibbon A, Cook M, et al. Real-time human pose recognition in parts from a single depth image. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[31]Liu H, Latccki L J, Liu W. A Unified Curvature Definition for Regular, Polygonal, and Digital Planar Curves. International Journal of Computer Vision,2008,80:104-124.
[32]Lam L, Lee S W, Suen C Y. Thinning methodologies-a comprehensive survey. IEEE Trans. Pattern Analysis and Machine Intelligence,1996,14(9):869-885.
[33]Leymarie F, Levine M. Simulating the grassfire transaction form using an active contour model. IEEE Trans. Pattern Analysis and Machine Intelligence,1992,14(1):56-75.
[34]Arcelli C, Baja G S. A width-independent fast thinning algorithm. IEEE Trans. Pattern Analysis and Machine Intelligence,1985,7(4):463-474.
[35]Ogniewicz R, Ilg M. Voronoi skeletons:theory and applications. in:Proceedings of IEEE Inter-national Conference on Computer Vision and Pattern Recognition (CVPR),1992,63-69.
[36]Brandt J W, Algazi V R. Continuous skeleton computation by Voronoi diagram. CVGIP:Image Understanding,1999,55(3):329-338.
[37]Mayya N, Rajan V T. Voronoi diagrams of polygons:a framework for shape representation. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),1994,638-643.
[38]Niblack C W, Gibbons P B, Capson D W. Generating skeletons and centerlines from the distance transform. CVGIP:Image Understanding,1992,54(5):420-437.
[39]Ge Y, Fitzpatrick J M. On the generation of skeletons from discrete Euclidean distance maps. IEEE Trans. Pattern Analysis and Machine Intelligence,1996,18(11):1055-1066.
[40]Choi W P, Lam K M, Siu W C. Extraction of the Euclidean skeleton based on a connectivity criterion. Pattern Recognition,2003,36:721-729.
[41]Arcelli C, Baja G S. A one-pass two-operations process to detect the skeletal pixels on the 4-distance transform. IEEE Trans. Pattern Analysis and Machine Intelligence,1989,11(4):411-414.
[42]Baja G S. Well-shaped, stable and reversible skeletons from the (3,4)-distance transform. Journal of Visual Communication and Image Representation,1994,5:107-115.
[43]Baja G S, Thiel E. Skeletonization algorithm running on path-based distance maps. Image and Vision Computing,1996,14(1):47-57.
[44]Arcelli C, Baja G S. Euclidean skeleton via center-of-maximal-disc extraction. Image and Vision Computing,1993,11 (3):163-173.
[45]Yu Z Y, Bajaj C. A segmentation-free approach for skeletonization of gray-scale images via anisotropic vector diffusion. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2000,415-420.
[46]Krinidis S, Chatzis V. A skeleton family generator via physics-based deformable models. IEEE Trans. Image Processing,2009,18(1):1-11.
[47]Gorelick L, Galun M, Sharon E, et al. Simulating the grassfire transaction form using an active contour model. IEEE Trans. Pattern Analysis and Machine Intelligence,2006,28(12):1991-2005.
[48]Dimitrov P, Damon J N, Siddiqi K. Flux invariants for shape, in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2003,835-841.
[49]Golland P, Grimson E. Fixed topology skeletons. in:Proceedings of IEEE International Confer-ence on Computer Vision and Pattern Recognition (CVPR),2000.
[50]Dimitrov P, Phillips C, Siddiqi K. Robust and efficient skeletal graphs, in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2000.
[51]Siddiqi K, Bouix S, Tannenbaum A, et al. Hamilton-jacobi skeletons. International Journal of Computer Vision,2002,48(3):215-231.
[52]Siddiqi K, Kimia B B, Shu C. Geometric shock-capturing ENO schemes for subpixel interpolation, computation, and curve evolution. in:Proceedings of ISCV,1995.
[53]Bai X, Latecki L, Liu W. Skeleton pruning by contour partitioning with discrete curve evolution. IEEE Trans. Pattern Analysis and Machine Intelligence,2007,29(3):449-462.
[54]Ogniewicz R, Kubler O. Hierarchic voronoi skeletons. Pattern Recognition,1995,28(3):343-359.
[55]Shaked D, Bruckstein A. Pruning medial axes. Computer Vision and Image Understanding,1998, 69(2):156-169.
[56]Couprie M, Zrour R. Discrete bisector function and Euclidean skeleton in 2D and 3D. Image and Vision Computing,2007,25(10):1543-1556.
[57]Latecki L J, Lakamper R. Polygon evolution by vertex deletion. in:Proceedings of Int'l Conf. Scale-Space,1999.
[58]Latecki L J, Lakamper R. Convexity rule for shape decompostion based on discrete curve evolu-tion. Computer Vision and Image Understanding,1999,73:441-454.
[59]Latecki L J, Lakamper R. Shape similarity measure based on correspondence of visual parts. EEEE Trans. Pattern Analysis and Machine Intelligence,2000,22(10):1185-1190.
[60]Choi H, Choi S, Moon H. Mathematical theory of medial axis transform. Pacific Journal of Math., 1997,181(1):57-88.
[61]Xu C J, Liu J Z, Tang X O.2D shape matching by contour flexibility. IEEE Trans. Pattern Analysis and Machine Intelligence,2009,31 (10):180-186.
[62]Leyton M. A process-grammar for shape. Artificial Intelligence,1988,34(2):213-247.
[63]Bai X, Latecki L. Path similarity skeleton graph matching. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(7):1282-1292.
[64]Bai X, Yang X W, Yu D, et al. Skeleton-based shape classification using path similarity. Int. Journal of Pattern Recognition and Art. Intell.,2008,22(4):733-746.
[65]Bai X, Liu W Y, Tu Z. Integrating contour and skeleton for shape classification. in:Proceedings of IEEE Workshop on NORDIA,2009.
[66]Latecki L J, Lakamper R, Eckhardt U. Shape descriptors for non-rigid shapes with a single closed contour. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2000,1424-1429.
[67]Bai X, Latecki L J. Discrete skeleton evolution. in:Proceedings of EMMCVPR,2007.
[68]Telea A, Wijk J. An augmented fast marching method for computing skeletons and centerlines. IEEE TCVG Symposium on Visualization,2002, pages 251-259.
[69]Pelillo M, Siddiqi K, Zucker S. Matching hierarchical structure using association graphs. IEEE Trans. Pattern Analysis and Machine Intelligence,1999,21(11):1105-1120.
[70]Siddiqi K, Kimia B B. A shock grammar for recognition. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),1996,507-513.
[71]Aslan C, Tari S. An axis-based representation for recognition. in:Proceedings of IEEE Interna-tional Conference on Computer Vision (ICCV),2005.
[72]Lin H, Jacobs D W. Shape classification using the inner-distance. IEEE Trans. Pattern Analysis and Machine Intelligence,2007,29(2):286-299.
[73]Siddiqi K, Pizer S. Medial representations:Mathematics, algorithms and applications. Springer, 2011.
[74]Torsello A, Hancock E. Correcting curvature-density effects in the Hamilton-Jacobi skeleton. IEEE Trans. Image Processing,2006,15(4):887-891.
[75]Borgefors G, Ramella G, Baja G S. Hierarchical decomposition of multiscale skeleton. IEEE Trans. Pattern Analysis and Machine Intelligence,2001,13(11):1296-1312.
[76]Katz R, Pizer S. Untangling the blum medial axis transform. International Journal of Computer Vision,2003,55:139-153.
[77]Eede M, Macrini D, Telea A, et al. Canonical skeletons for shape matching. in:Proceedings of International Conference on Pattern Recognition (ICPR),2006.
[78]Ward A, Hamarneh G. Gmat:the groupwise medial axis transform for fuzzy skeletonization and intelligent pruning. Technical report, School of Computing Science, Simon Fraser University, 2008.
[79]Ward A, Hamarneh G. The groupwise medial axis transform for fuzzy skeletonization and pruning. IEEE Trans. Pattern Analysis and Machine Intelligence,2010,32(6):1084-1096.
[80]Levinshtein A, Sminchisescu C, Dickinson S. Multiscale symmetric part detection and grouping, in:Proceedings of IEEE International Conference on Computer Vision (ICCV),2009.
[81]Adluru N, Latecki L J, Lakamper R, et al. Contour grouping based on local symmetry. in:Pro-ceedings of IEEE International Conference on Computer Vision (ICCV),2007.
[82]Feldman J, Singh M. Bayesian estimation of the shape skeleton. Proceeding of National Academy of Sciences of the United States of America,2006,103(47):18014-18019.
[83]Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,24(4):509-522.
[84]Cootes T, Taylor C, Cooper D, et al. Active shape models — their training and application. Com-puter Vision and Image Understanding,1995,61(1):38-59.
[85]Davies R, Twining C, Cootes T, et al. A minimum description length approach to statistical shape modeling. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,21(5):525-537.
[86]Ghebreab S, Smeulders A. Strings:variational deformable models of multivariate continuous boundary features. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(11):1399-1410.
[87]Grigorescu C, Petkov N. Distance sets for shape filters and shape recognition. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,12(10):1274-1286.
[88]Sebastian T, Klein P, Kimia B. Shock-based indexing into large shape databases. in:Proceedings of Europeon Conference on Computer Vision (ECCV),2002,731-746.
[89]Rissanen J. Modelling by shortest data description. Automatica,1978,14:465-471.
[90]Sun K B, Super B J. Classification of contour shapes using class segment sets. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2005, 727-733.
[91]Latecki L, Megalooikonomou V, Wang Q, et al. Partial elastic matching of time series. in:Pro-ceedings of IEEE International Conference on Data Mining (ICDM),2005.
[92]Felzenszwalb P F, Schwartz J. Hierarchical matching of deformable shapes. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2007.
[93]Daliri M R, Torre V. Robust symbolic representation for shape recognition and retrieval. Pattern Recognition,2008,41(5):1799-1815.
[94]Geiger D, Liu T L, Kohn R V. Representation and self-similarity of shapes. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(1):86-99.
[95]Torsello A, ER E R H. A skeletal measure of 2D shape similarity. Computer Vision and Image Understanding,2004,95(1):1-29.
[96]Xie J, Heng P, Shah M. Shape matching and modeling using skeletal context. Pattern Recognition, 2008,41 (5):1756-1767.
[97]Goh W. Strategies for shape matching using skeletons. Computer Vision and Image Understand-ing,2008,110(3):326-345.
[98]Sebastian T B, Kimia B B. Curves vs skeletons in object recognition. in:Proceedings of IEEE International Conference on Image Processing (ICIP),2001.
[99]Basri R, Costa L, Geiger D, et al. Determining the similarity of deformable shapes. Vision Research,1998,38:2365-2385.
[100]Siddiqi K, Kimia B, Tannenbaum A, et al. Shocks, shapes, and wiggles. Image and Vision Computing,1999,17:365-373.
[101]Sebastian T, Klein P, Kimia B. Recognition of shapes by editing shock graphs. in:Proceedings of IEEE International Conference on Computer Vision (ICCV),2001.
[102]Liu T, Geiger D. Approximate Tree Matching and Shape Similarity. in:Proceedings of IEEE International Conference on Computer Vision (ICCV),1999,456-462.
[103]Demirci M, Shokoufandeh A, Keselman Y, et al. Object recognition as many-to-many feature matching. International Journal of Computer Vision,2006,69(2):203-222.
[104]Baseski E, Erdem A, Tari S. Dissimilarity between two skeletal trees in a context. Pattern Recog-nition,2009,42(3):370-385.
[105]Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. New York:Springer, 2009.
[106]Spath H. Cluster analysis algorithms. Chichester:Ellis Horwood,1980.
[107]Sokal R, Michener C. A statistical method for evaluating systematic relationships. University of Kansas Science Bulletin,38:1409-1438.
[108]Lakaemper R, Zeng J. A context dependent distance measure for shape clustering. in:Proceedings of IS VC,2008.
[109]Srivastava A, Joshi S, Mio W, et al. Statistical shape analysis:clustering, learning, and testing. IEEE Trans. Pattern Analysis and Machine Intelligence,2005,27(4):590-602.
[110]Yankov D, Keogh E. Manifold clustering of shapes. in:Proceedings of IEEE International Con-ference on Data Mining (ICDM),2006.
[111]Mio W, Srivastava A, Joshi S. On shape of plane elastic curves. International Journal of Computer Vision,2007,73(3):307-324.
[112]Demirci M, Shokoufandeh A, Dickinson S. Skeletal shape abstraction from examples. IEEE Trans. Pattern Analysis and Machine Intelligence,2009,31(5):944-952.
[113]Torsello A, Hancock E. Learning shape-classes using a mixture of tree-unions. IEEE Trans. Pattern Analysis and Machine Intelligence,2006,28(6):954-967.
[114]Kuhn H W. The Hungarian method for the assignment problem. Naval Research Logistics Quar-terly,1955,2:83-97.
[115]Shi J, Malik J. Normalized cuts and image segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[116]Tan P N, Steinbach M, Kumar V. Introduction to Data Mining. Addison Wesley,2005.
[117]Girshick R, Shotton J, Kohli P, et al. Real-time human pose recognition in parts from a single depth image, in:Proceedings of IEEE International Conference on Computer Vision (ICCV),2011.
[118]Isard M, Blake A. CONDENSATION-Conditional density propagation for visual tracking. In-ternational Journal of Computer Vision,1998,29(1):5-28.
[119]Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Trans. Pattern Analysis and Machine Intelligence,2003,25(5):564-575.
[120]Dollar P, Rabaud V, Cottrell G, et al. Behavior recognition via sparse spatio-temporal features. in: Proceedings of ICCV VS-PETS,2005.
[121]Bourdev L D, Malik J. Poselets:body part detectors trained using 3D human pose annotations. in: Proceedings of IEEE International Conference on Computer Vision (ICCV),2009.
[122]Niebles J C, Chen C W, Fei-Fei L. Modeling temporal structure of decomposable motion segments for activity classification. in:Proceedings of Europeon Conference on Computer Vision (ECCV), 2010.
[123]Moeslund T, Hilton A, Kruger V. A survey of advances invision-based human motion capture and analysis. Computer Vision and Image Understanding,2006.
[124]Poppe R. Vision-based human motion analysis:An overview. Computer Vision and Image Un-derstanding,2007,108.
[125]Grest D, Woetzel J,, et al. Nonlinear body pose estimation from depth images. in:Proceedings of DAGM,2005.
[126]Knoop S, Vacek S, Dillmann R. Sensor fusion for 3D human body tracking with an articulated 3D body model. in:Proceedings of IEEE International Conference on Robotics and Automation (ICRA),2006.
[127]Siddiqui M, Medioni G. Human pose estimation from a single view point, real-time range sensor, in:Proceedings of CVPR-CVCG,2010.
[128]Christian P R, Casella G. Monte Carlo statistical methods. New York:Springer,2004.
[129]Fanelli G, Gall J, Gool L V. Real Time Head Pose Estimation with Random Regression Forests. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2011.
[130]Breiman L. Random forests. Machine learning,2001,45(1):5-32.
[131]Lepetit V, Lagger P, Fua P. Randomized trees for real-time keypoint recognition. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2005, 775-781.
[132]Quinlan J R. Induction of decision trees. Machine Learning,1986.
[133]Comaniciu D, Meer P. Mean shift:a robust approach toward feature space analysis. IEEE Trans. Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[134]Birnbaum A. A unified theory of estimation. The Annals of Mathematical Statistics,1961,32(1).
[135]Tak S, Ko H S. Physically-based motion retargeting filter. ACM Transactions on Graphics,2005, 24(1).
[136]Lee J, Shin S Y. Motion fairing. in:Proceedings of Computer Animation,1996,136-143.
[137]Lou H, Chai J. Example-based human motion denoising. IEEE Trans. Visualization and Computer Graphics,2010,16(5).
[138]Duda R, Hart P, Stork D. Pattern classification and scene analysis. John Wiley and Sons,2000.
[139]Rasmussen C E, Williams C. Gaussian processes for machine learning. MIT Press,2006.
[140]Scholkopf B, Smola A, Williamson R, et al. New support vector algorithms. Neural Computation, 2000,12:1207-1245.
[141]Peduzzi P, Concato J, Kemper E, et al. A simulation study of the number of events per variable in logistic regression analysis. J Clin Epidemiol,1996,49(12):1373-1379.
[142]Wang J M, Fleet D J, Hertzmann A. Gaussian process dynamical models for human motion. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(2):283-298.
[143]Wang J M, Fleet D J, Hertzmann A. Gaussian process dynamical models. in:Proceedings of Neural Information Processing Systems,2005,1441-1448.
[144]Breiman L. Random forests. Machine learning,2001,45(1):5-32.
[145]Liaw A, Wiener M. Classification and regression by random forest,2002.
[146]Dollar P, Welinder P, Perona P. Cascaded pose regression. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2010.
[147]Tu Z. Auto-context and its application to high-level vision tasks. in:Proceedings of IEEE Inter-national Conference on Computer Vision and Pattern Recognition (CVPR),2008.
[148]Tu Z, Bai X. Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence,2010,32(10):1744-1757.
[149]Gelfand A E, Smith A F M. Sampling-based approaches to calculating marginal densities. Jounal of the American Statistical Association,1990,85(410):398-409.
[150]Rasmussen C E, Nickisch H. Gaussian processes for machine learning (GPML) toolbox. Jour-nal of Machine Learning Research,2010,11:3011-3015. Software available at http://www. gaussianprocess.org/gpml.
[151]Chang C C, Lin C J. LIBSVM:A library for support vector machines. ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27. Software available at http://www.csie.ntu. edu.tw/-cjlin/libsvm.
[152]Stahl J S, Wang S. Globally optimal grouping for symmetric boundaries. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2006.
[153]Ferrari V, Fevrier L, Jurie F, et al. Groups of Adjacent Contour Segments for Object Detection. IEEE Trans. Pattern Analysis and Machine Intelligence,2008,30(1):36-51.
[154]Stahl J S, Wang S. Edge Grouping Combining Boundary and Region Information. IEEE Trans. Image Processing,2007,16(10):2590-2606.
[155]Sundar H, Silver D, Gagvani N, et al. Skeleton based shape matching and retrieval. in:Proceedings of International Conference on Shape Modeling and Applications (SMI),2003.
[156]Cornea N D, Demirci M, Silver D, et al.3D object retrieval using many-to-many matching of curve skeletons. in:Proceedings of International Conference on Shape Modeling and Applications (SMI),2005.
[157]Wagg D K, Nixon M S. On automated model-based extraction and analysis of gait. in:Proceedings of International Conference Automatic Face and Gesture Recognition (FG),2004.
[158]Tanawongsuwan R, Bobick A. Gait recognition from time-normalized joint-angle trajectories in the walking plane. in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR),2001.