Definition
When objects exhibit large within-class variation and/or when image features are under- or over-segmented, the image features extracted from two exemplars belonging to the same category may no longer be in one-to-one correspondence but, in general, many-to-many correspondence. If the features are structured, i.e., captured in a graph, then computing the correct correspondence can be formulated as a many-to-many graph matching problem.
Background
The matching of image features to object models is typically formulated as a one-to-one assignment problem, based on the assumption that for every salient image feature belonging to the object to be matched, e.g., SIFT feature, image patch, contour fragment, there exists a single corresponding feature on the model (and vice versa). While the one-to-one correspondence assumption has been prevalent in the object recognition...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bunke H (1982) Attributed graph grammars and their application to schematic diagram interpretation. IEEE Trans Pattern Anal Mach Intell 4:574–582
Bunke H (1997) On a relation between graph edit distance and maximum common subgraph. Pattern Recognit Lett 18(8):689–694
Bunke H, Shearer K (1998) A graph distance metric based on the maximal common subgraph. Pattern Recognit Lett 19:255–259
Caelli T, Kosinov S (2004) An eigenspace projection clustering method for inexact graph matching. IEEE Trans Pattern Anal Mach Intell 26:515–519
Demirci F, Shokoufandeh A, Dickinson S (2009) Skeletal shape abstraction from examples. IEEE Trans Pattern Anal Mach Intell 31:944–952
Demirci F, 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
Dickinson S (2009) The evolution of object categorization and the challenge of image abstraction. In: Dickinson S, Leonardis A, Schiele B, Tarr M (eds) Object categorization: computer and human vision perspectives. Cambridge University Press, New York, pp 1–37
Ferrari V, Jurie F, Schmid C (2010) From images to shape models for object detection. Int J Comput Vis 87(3): 284–303
Fischler MA, Eschlager RA (1973) The representation and matching of pictorial structures. IEEE Trans Comput 22(1):67–92
Keselman Y, Dickinson S (2005) Generic model abstraction from examples. IEEE Trans Pattern Anal Mach Intell 27(7):1141–1156
Lamdan Y, Schwartz J, Wolfson H (1990) Affine invariant model-based object recognition. IEEE Trans Rob Autom 6(5):578–589
Levinshtein A, Sminchisescu C, Dickinson S (2005) Learning hierarchical shape models from examples. In: Proceedings of the EMMCVPR, St. Augustine. Springer, Berlin, pp 251–267
Lowe D (1985) Perceptual organization and visual recognition. Academic, Norwell
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
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
Sebastian T, Klein P, Kimia B (2004) Recognition of shapes by editing their shock graphs. IEEE Trans Pattern Anal Mach Intell 26:550–571
Shokoufandeh A, Bretzner L, Macrini D, Demirci MF, Jönsson C, Dickinson S (2006) The representation and matching of categorical shape. Comput Vis Image Underst 103(2):139–154
Shokoufandeh A, Macrini D, Dickinson S, Siddiqi K, Zucker SW (2005) Indexing hierarchical structures using graph spectra. IEEE Trans Pattern Anal Mach Intell 27(7):1125–1140
Siddiqi K, Shokoufandeh A, Dickinson S, Zucker S (1999) Shock graphs and shape matching. Int J Comput Vis 30: 1–24
Zaslavskiy M, Bach F, Vert J (2010) Many-to-many graph matching: a continuous relaxation approach. Lecture Notes in Computer Science, http://arxiv.org/abs/1004.4965, DBLP, http://dblp.uni-trier.de 6323:515–530
Zhu S, Mumford D (2006) A stochastic grammar of images. Found Trends Comput Graph Vis 2:259–362
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Demirci, F., Shokoufandeh, A., Dickinson, S. (2014). Many-to-Many Graph Matching. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_775
Download citation
DOI: https://doi.org/10.1007/978-0-387-31439-6_775
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30771-8
Online ISBN: 978-0-387-31439-6
eBook Packages: Computer ScienceReference Module Computer Science and Engineering