Abstract
People often recognize 3D objects by their boundary shape. Designing an algorithm for such a task is interesting and useful for retrieving objects from a shape database. In this paper, we present a fast 2-stage algorithm for recognizing 3D objects using a new feature space, built from curvature scale space images, as a shape representation that is scale, translation, rotation and reflection invariant. As well, the new shape representation removes the inherent ambiguity of the zero position of arc length for a scale space image. The 2-stage matching algorithm, conducted in the eigenspaces of the feature space, is analogous to the way people recognize an object: first identifying the type of object, and then determining the actual object. We test the new algorithm on a 3D database comprising 209 colour objects in 2926 different view poses, and achieve a 97% recognition rate for the object type and 95% for the object pose.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Mokhtarian, F., Mackworth, A.: Scale-based description and recognition of planar curves and two-dimensional shapes. PAMI 8, 34–43 (1986)
Mokhtarian, F.: Silhouette-based isolated object recognition through curvature scale space. PAMI 17, 539–544 (1995)
Mokhtarian, F., Bober, M.: Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization. Kluwer Academic Publishers, Dordrecht (2003)
Murase, H., Nayar, S.: Learning object models from appearance. In: AAAI93, pp. 836–843 (1993)
Murase, H., Nayar, S.: Illumination planning for object recognition in structured environments. In: CVPR94, pp. 31–38 (1994)
Turk, M., Pentland, A.: Face recognition using eigenfaces. In: Computer Vision and Patt. Recog.: CVPR91, pp. 586–591 (1991)
Drew, M.S., Lee, T.K., Rova, A.: Shape retrieval with eigen-css search. Submitted for publication (Feb. 24, 2005)
Kuglin, C., Hines, D.: The phase correlation image alignment method. In: Int’l Conf. on Cybernetics and Society, pp. 163–165 (1975)
Drew, M.S., Lee, T.K., Rova, A.: Shape retrieval with eigen-css search. Technical Report TR 2005-07, School of Computing Science, Simon Fraser University, Burnaby, BC, Canada (2005)
Arbter, K., et al.: Application of affine invariant Fourier descriptors to recognition of 3-D objects. IEEE Trans. Patt. Anal. and Mach. Intell. 12, 640–647 (1990)
Kunttu, I., et al.: Recognition of shapes by editing shock graphs. In: Int. Conf. on Computer Vision: ICCV2001, pp. 755–762 (2001)
Tarr, M.J.: The object databank. Available from http://alpha.cog.brown.edu:8200/stimuli/objects/objectdatabank.zip
Sonka, M., Hlavac, V., Boyle, R.: Image Processing, Analysis and Machine Vision, p. 129. Chapman & Hall, Boca Raton (1993)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Lee, T.K., Drew, M.S. (2007). 3D Object Recognition by Eigen-Scale-Space of Contours. In: Sgallari, F., Murli, A., Paragios, N. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2007. Lecture Notes in Computer Science, vol 4485. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72823-8_76
Download citation
DOI: https://doi.org/10.1007/978-3-540-72823-8_76
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72822-1
Online ISBN: 978-3-540-72823-8
eBook Packages: Computer ScienceComputer Science (R0)