Abstract
We explore the use of holistic shape matching for recognition using bottom-up image structures such as image contours, for object shape detection and segmentation. Holistic shape matching utilizes global information about object shape for matching, rather than local image features which often contain too little information to match reliably to the object model. By examining several different tasks related to object recognition, we demonstrate the value of holistic shape matching in a broad range of problems, including perceptual grouping, human pose estimation, and generic object recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Keselman Y, Dickinson S (2005) Generic model abstraction from examples. IEEE Trans Pattern Anal Mach Intell 22(7):1141–1156
Demirci MF, Shokoufandeh A, Keselman Y, Bretzner L, Dickinson S (2006) Object recognition as many-to-many feature matching. Int J Comput Vis 69(2):203–222
Rubner Y, Tomasi C, Guibas LJ (2000) The earth mover’s distance as a metric for image retrieval. Int J Comput Vis 40(2):99–121
Pelillo M, Siddiqi K, Zucker SW (1998) Matching hierarchical structures using association graphs. IEEE Trans Pattern Anal Mach Intell 21:1105–1120
Zhu Q, Wang L, Wu Y, Shi J (2008) Contour context selection for object detection: a set-to-set contour matching approach. In: ECCV (2), pp 774–787
Ferrari V, Jurie F, Schmid C (2007) Accurate object detection with deformable shape models learnt from images. In: CVPR
Binford TO (1971) Visual perception by computer. In: IEEE conf on systems and controls
Biederman I (1987) Recognition-by-components: a theory of human image understanding. Psychol Rev 94:115–147
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: CVPR
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522
Ling H, Jacobs DW (2005) Using the inner-distance for classification of articulated shapes. In: CVPR
Siddiqi K, Kimia BB, Tannenbaum A, Zucker SW (2001) On the psychophysics of the shape triangle. Vis Res 41(9):1153–1178
Felzenszwalb PF, Huttenlocher DP (2004) Distance transforms of sampled functions. Technical report, Cornell Computing and Information Science
Gaston PC, Lozano-Prez T (1983) Tactile recognition and localization using object models: the case of polyhedra on a plane. IEEE Trans Pattern Anal Mach Intell 6:257–265
Felzenszwalb P, McAllester D, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: CVPR
Coughlan JM, Ferreira SJ (2002) Finding deformable shapes using loopy belief propagation. In: ECCV, vol 3, pp 453–468
Srinivasan P, Zhu Q, Shi J (2010) Many-to-one contour matching for describing and discriminating object shape. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, New York, pp 1673–1680
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24:509–521
Latecki LJ, Lakamper R (1999) Polygon evolution by vertex deletion. In: Scale-space
Ferrari V, Jurie F, Schmid C (2009) From images to shape models for object detection. In: PAMI
Maji S, Malik J (2009) A max-margin hough transform for object detection. In: CVPR
Ravishankar S, Jain A, Mittal A (2008) Multi-stage contour based detection of deformable objects. In: ECCV
Lu C, Latecki LJ, Adluru N, Ling H, Yang X (2009) Shape guided contour grouping with particle filters. In: ICCV
Zhang W, Srinivasan P, Shi J (2011) Discriminative image warping with attribute flow. In: 2011 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, New York, pp 2393–2400
Zhu CS, Mumford D (2006) A stochastic grammar of images. In: Foundations and trends in computer graphics and vision. Now Publishers, Hanover, pp 259–362
Acknowledgement
The Contour Packing algorithm described here are based on Ph.D. thesis works of Qihui Zhu and Praveen Srinivasan.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Shi, J. (2013). Holistic Shape Recognition: Where-to-Look and How-to-Look. In: Dickinson, S., Pizlo, Z. (eds) Shape Perception in Human and Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-5195-1_23
Download citation
DOI: https://doi.org/10.1007/978-1-4471-5195-1_23
Publisher Name: Springer, London
Print ISBN: 978-1-4471-5194-4
Online ISBN: 978-1-4471-5195-1
eBook Packages: Computer ScienceComputer Science (R0)