Abstract
In this paper a novel non-rigid matching technique is presented to reliably detect near-regular object configurations in images in the presence of substantial clutter. The objects in near-regular configurations span a grid with not necessarily congruent grid cells. In addition, the output of object detectors is typically associated with ambiguities, causing occasional spurious false alarms. We propose a detection approach of spatially extended near-regular structures which reliably deals with missing objects and clutter. The search for the optimal local spatial object arrangement is formulated as a non-rigid matching problem and it is guided by the criterion of structural energy minimization while maximizing image likelihood. The applicability of the approach is demonstrated by presenting experimental results for the detection of near-regular object configurations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. IEEE TC 22(1), 67–92 (1973)
Widrow, B.: The rubber mask technique. Pattern Recognition 5(3), 174–211 (1973)
Amit, Y., Kong, A.: Graphical templates for model registration. IEEE PAMI 18(3), 225–236 (1996)
Felzenszwalb, P.F.: Representation and detection of deformable shapes. IEEE PAMI 27(2), 208–220 (2005)
DiMaio, F., Shavlik, J.: Belief Propagation in Large, Highly Connected Graphs for 3D Part-Based Object Recognition. In: Perner, P. (ed.) ICDM 2006. LNCS (LNAI), vol. 4065, pp. 845–850. Springer, Heidelberg (2006)
Cootes, T.: An Introduction to Active Shape Models. In: Baldock, R., Graham, J. (eds.) Image Processing and Analysis, pp. 223–248. Oxford University Press, Oxford (2000)
Wiskott, L., Fellous, J.M., Kruger, N., von der Malsburg, C.: Face Recognition by Elastic Bunch Graph Matching. In: Jain, L.C., et al. (eds.) Intelligent Biometric Techniques in Fingerprint and Face Recognition, ch. 11, pp. 355–396. CRC Press, Boca Raton (1999) ISBN 0-8493-2055-0
Kushal, A., Schmid, C., Ponce, J.: Flexible Object Models for Category-Level 3D Object Recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8 (2007)
Loy, G., Zelinsky, E.: A Fast Radial Symmetry Transform for Detecting Points of Interest. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 358–368. Springer, Heidelberg (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Croonen, G., Beleznai, C. (2010). Detection of Near-Regular Object Configurations by Elastic Graph Search. In: Bolc, L., Tadeusiewicz, R., Chmielewski, L.J., Wojciechowski, K. (eds) Computer Vision and Graphics. ICCVG 2010. Lecture Notes in Computer Science, vol 6374. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15910-7_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-15910-7_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15909-1
Online ISBN: 978-3-642-15910-7
eBook Packages: Computer ScienceComputer Science (R0)