Abstract
This paper describes a shape representation technique for learning shape classes. This representation technique is based on the notion of representing categorical shape knowledge; shape itself is represented by so-called conjunctions of local properties (CLP). Shape concepts are learned by a technique called property-based learning, an incremental learning method that inductively selects properties crucial for classification. Unlike other classification methods based on distances or similarities, classification performance does not degrade as the number of classes increases and classification can be done correctly with only partial information of instances.
Using this shape representation, shape prototypes can be learned and shapes can be classified in the presence of viewpoint changes, local movements (such as moving handles of pliers or fingers) and occlusion.
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
Brady M., Asada, H. (1984). Smoothed local symmetries and their implementation. In: Brady, M., Paul, R. (eds.), Robotics Research: The First International Symposium, pp. 331–354.
Cho, K. (1992). Learning Shape Classes, PhD thesis, Rutgers University.
Connell, J.H., Brady, M. (1987). Generating and generalizing models of visual objects, Artificial Intelligence, 34 (2), pp. 159–183.
Cromwell, R.L., Kak, A.C. (1991). Automatic generation of object class descriptions using symbolic learning techniques, Proc. 9th National Conf. on Artificial Intelligence, AAAI, pp. 710–717.
Marr, D. (1982). Vision. W.H. Freeman and Company.
Michalski, R.S. (1980). Pattern recognition as rule-guided inductive inference, IEEE Trans. on Pattern Analysis and Machine Intelligence, 2 (4), pp. 349–361.
Milner, P.M. (1974). A model for visual shape recognition, Psychological Review, 81 (6), pp. 521–535.
Quinlan, J.R. (1986). Induction of decision trees, Machine Learning, 1 (1), pp. 81–106.
Segen, J. (1988). Learning graph models of shape, Proc. 5th Int. Conf. on Machine Learning, pp. 29–35.
Segen, J. (1990). Graph clustering and model learning by data compression, Proc. 7th Int. Conf. on Machine Learning, pp. 93–101.
Shepherd, B.A. (1983). An appraisal of a decision tree approach to image classification, Proc. Int. Joint Conf. on Artificial Intelligence, pp. 473–475.
Stein, F., Medioni, G. (1992). Structural indexing: Efficient 3-D object recognition, IEEE Trans. on Pattern Analysis and Machine Intelligence, 14 (2), pp. 125–145.
Tversky, A. (1977). Features of similarity, Psychological Review, 84(4), pp. 327352.
Winston, P.H. (1975). Learning structural descriptions from examples. In: The Psychology of Computer Vision, McGraw-Hill.
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
Dunn, S.M., Cho, K. (1994). Learning Shape Classes. 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_35
Download citation
DOI: https://doi.org/10.1007/978-3-662-03039-4_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08188-0
Online ISBN: 978-3-662-03039-4
eBook Packages: Springer Book Archive