Abstract
For matching a template to a target object in an image under influences from obstructing objects, a two dimensional array of figure-and-ground classifiers is introduced. Each classifier in the array observes a corresponding point in an image and determines if the point belongs to the target object (figure) or its background (ground). Neighboring classifiers communicate via local connections. The local communication is used to transmit the shape transformation parameter values so that the neighboring classifiers interpret their observing points under continuous and topology preserving shape transformation. Some basic experiments were conducted to evaluate the performance of the method and the method’s effectiveness was confirmed.
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.
Reference
Ballard, D.H.: Generalizing the Hough Transform to Detect Arbitrary Shapes. Pattern Recognition 13(2),(1981) 111–122.
Bardinet, E., Cohen, L.D.: A Parametric Deformable Model to Fit Unstructured 3D Data. Computer Vision and Image Understanding, 71(1),(1998) 39–54.
Ben-Arie, J., Rao, J.K., Wang, Z.: A Neural Network Approach for Shape Description and Invariant Recognition. Proc. 1994 Image Understanding Workshop. Monterey, CA, II, (1994) 863–870.
Geman, D., Geman, S.: Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-6(6), (1984) 721–741.
Jain, A.K., Zhong, Y., Lakshmanan, S.: Object Matching Using Deformable Templates. IEEE Trans. Pattern Analysis and Machine Intelligence 18,(3), (1996) 267–278
Kumazawa, I.: Shape extraction by cellular Hough transform, Technical report of IEICE, PRMU96-105, (1996) 9–16
Kumazawa, I.: Learning and Tracking Target Shapes by Compact Neural Network, Proceedings of ICONIP/ANZIIS/ANNES’99 International Workshop, (1999) 41–44
Kumazawa, I.: A cellular neural network framework for shape representation and matching, Proceedings of Third International Conference on Kowledge-based Intelligent Information Engineering Systems, (1999) 178–181
Roska, T., Vandewalle, J. (eds.): Cellular Neural Networks, John Wiley & Sons, Inc.(1993)
Suzuki, M., Kumazawa, I.: Functional representation of template and cellular parallel computing model for shape extraction, Technical report of IEICE, PRMU97-144, (1997) 117–124.
Staib, L.H., Duncan, J.S.: Parametrically deformable contour models. Computer Vision and Pattern Recognition. IEEE Computer Society Press, (1989) 98–103.
Shum, H.Y., Hebert, M., Ikeuchi, K., Reddy, R.: An Integral Approach to Free-Form Object Modeling, IEEE Trans. Pattern Analysis and Machine Intelligence 19,(12), (1997) 1,366–1,375.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kumazawa, I. (2000). Shape Matching and Extraction by an Array of Figure-and-Ground Classifiers. In: Multiple Classifier Systems. MCS 2000. Lecture Notes in Computer Science, vol 1857. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45014-9_38
Download citation
DOI: https://doi.org/10.1007/3-540-45014-9_38
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67704-8
Online ISBN: 978-3-540-45014-6
eBook Packages: Springer Book Archive