Abstract
Shape interpretation methods that model a shape using stochastic graphs can recognize many classes of nonrigid objects, even if the objects are partially occluded, and interpret complete scenes composed of overlapping nonrigid shapes. These methods can also identify most parts of each shape. This paper describes the use of a stochastic graph as a model for a class of 2-D or 3-D shapes, and presents learning methods that infer stochastic graph models and their symbolic primitives from examples. These methods, as well as a graph-covering method used for scene interpretation, use a criterion of minimum description complexity which eliminates the need for subjective parameters. One practical application of this work is a trainable real-time system that recognizes hand gestures in 2-D images.
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
Barrow, H. G., Ambler, A. P., Burstall, R. M. (1972). Some techniques for recognizing structure in pictures. In: Watanabe, S. (ed.), Frontiers of Pattern Recognition, Academic Press, New York, pp. 1–29.
Biederman, I. (1987). Matching of image edges to object memory, Proc. First Int. Conf. on Computer Vision, London, England: IEEE Comp. Soc. Press, pp. 384–392.
Connel, J. H., Brady, M. (1985). Learning shape descriptions, Proc. 9th Int. Conf. on Artificial Intelligence, Los Angeles, CA, Morgan Kaufmann, pp. 922–925.
Levinson, R. (1985). A self-organizing retrieval system for graphs. Ph.D. Thesis, University of Texas, Austin, TX.
Marr, D. Nishihara, H. K. (1978). Representation and recognition of spatial organization of three-dimensional structures, Proc. R. Soc. B 200, pp. 269–294.
Nackman, L. R. (1984). Two-dimensional critical point configuration graphs, IEEE Trans. on Pattern Analysis and Machine Intelligence, 6, pp. 442–449.
Rissanen, J. (1978). Modeling by shortest data description, Automatica 14, pp. 465–471.
Rissanen, J. (1987). Stochastic complexity. J. R. Stat. Soc. 49, pp. 223–239.
Segen, J. (1980). Pattern-directed signal analysis, Ph.D. Thesis, Carnegie-Mellon University, Pittsburgh, PA.
Segen, J. (1989). Model Learning and Recognition of Nonrigid Shapes, Proc. Conf. on Computer Vision and Pattern Recognition, San Diego, pp. 597–602.
Segen, J. (1990). Graph clustering and model learning by data compression, Proc. 7th Int. Conf. on Machine Learning, Austin, Texas, pp. 93–101.
Segen, J. (1993). GEST: A learning computer vision system that recognizes hand gestures. In: Michalski, R.S., Tecuci, G. (eds.) Machine Learning IV, Morgan Kaufmann.
Segen, J., Dana, K. (1991). Parallel symbolic recognition of deformable shapes. In: Burkhardt, H., Nuevo, Y., Simon, J.C. (eds.), From Pixels to Features II, North-Holland.
Segen, J., Sanderson, A. C. (1979). A minimal representation criterion for clustering. Proc. 12th Annual Symposium on Comp. Science and Statistics, Univ. of Waterloo, Canada.
Shapiro, L. G. (1980). A structural model of shape. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2, pp. 111–126.
Solomonoff, R. J. (1964). A formal theory of inductive inference I & II, Information and Control, 7, pp. 1–22 & 224–254.
Truve, S., Richards, W. (1987). From Waltz to Winston (via the connection table), Proc. First Int. Conf. on Computer Vision, London, England, IEEE Comp. Soc. Press, pp. 393–404.
Wallace, C. S. Boulton, D. M. (1968). An information measure for classification, Comp. Journal 11 (2), pp. 185–194.
Winston, P. H. (1975). Learning structural descriptions from examples. In: Winston, P.H. (ed.), The Psychology of Computer Vision, Chapter 5, McGraw Hill, New York.
Wong, A. K. C., You, M. (1985). Entropy and distance of random graphs with application to structural pattern recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence, 7, pp. 599–609.
Wong, A. K. C., Lu, S. W. (1985). Recognition and knowledge synthesis of 3-D object images, Proc. Conf. on Computer Vision and Pattern Recognition, San Francisco, pp. 162–166.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Segen, J. (1994). Inference of Stochastic Graph Models for 2-D and 3-D Shapes. In: O, YL., Toet, A., Foster, D., Heijmans, H.J.A.M., Meer, P. (eds) Shape in Picture. NATO ASI Series, vol 126. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-03039-4_36
Download citation
DOI: https://doi.org/10.1007/978-3-662-03039-4_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08188-0
Online ISBN: 978-3-662-03039-4
eBook Packages: Springer Book Archive