This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Learning Shape Classes
September 1994 (vol. 16 no. 9)
pp. 882-888

This paper is a summary of a new approach to learning shape concepts. In this system, a shape is represented by conjunctions of local shape properties. Conjunctions of local properties are consistent and unique for distinct shapes and are robust enough to represent shape in the presence of occlusion. A new learning method, called property based learning, is developed and used to learn conjunctions of local properties. Unlike other classification methods based on distances or similarities, classification performance does not degrade linearly as the number of classes increases and classification can be done correctly with only partial information of instances. Property based learning is an incremental learning method that selects properties crucial for classification. Two experiments are reported. In the first experiment with tool shapes, this shape learning system is used to classify shapes in the presence of view point changes, local movements such as moving handles of pliers, and occlusion. In the second experiment with hand gestures, the system can classify different gestures regardless of the movement in joints, fingers, and palms.

[1] D. H. Aha, D. Kibler, and M. K. Albert, "Instance-based learning algorithms,"Machine Learning, vol. 6, no. 1, pp. 37-66, 1991.
[2] J. B. Burns, A. R. Hanson, and E. M. Riseman, "Extracting straight lines," inImage Understanding Workshop, DARPA, 1984, pp. 165-168.
[3] K. Cho, "Learning shape classes," Ph.D. thesis, Rutgers Univ., 1992.
[4] J. H. Connell and M. Brady, "Generating and generalizing models of visual objects,"Artificial Intell., vol. 31, pp. 159-183, 1987.
[5] R. L. Cromwell and A. C. Kak, "Automatic generation of object class descriptions using symbolic learning techniques," inProc. 9th Nat. Conf. Artificial Intell., AAAI, 1991, pp. 710-717.
[6] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[7] J.G. Dunham, "Optimum uniform piecewise linear approximation of planar curves,"IEEE Trans., vol. PAMI-8, no. 1, pp. 66-75, Jan. 1986.
[8] B. Everitt,Cluster Analysis, 2nd ed. London: Heinemann Educational Books, 1980.
[9] K. Fukunaga,Introduction to Statistical Pattern Recognition. New York: Academic, 1972.
[10] A. Khotanzad and Y. H. Hong, "Invariant image recognition by Zernike moments,"IEEE Trans. Pattern Anal. Machine Intell., vol. 12, no. 5, pp. 489-497, 1990.
[11] D. Marr,Vision. New York: Freeman, 1982.
[12] R. S. Michalski, "Pattern recognition as rule-guided inductive inference,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, no. 4, pp. 349-361, 1980.
[13] R. S. Michalski, "A theory and methodology of inductive learning,"Artificial Intelligence, vol. 20, no. 2, pp. 111-116, 1983.
[14] P. M. Milner, "A model for visual shape recognition,"Psychological Rev., vol. 81, no. 6, pp. 521-535, 1974.
[15] T. M. Mitchell, "Generalization as search,"Artificial Intell., vol. 18, no. 2, pp. 203-226, 1982.
[16] T. Pavlidis,Algorithms for Graphics and Image Processing. Rockville, MD: Computer Science Press, 1982.
[17] J. R. Quinlan, "Learning efficient classification procedures and their application to chess and games," inMachine Learning: An Artificial Intelligence Approach, R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds. Palo Alto, CA: Tioga, 1983.
[18] J. R. Quinlan, "Induction of decision trees,"Machine Learning, vol. 1, no. 1, pp. 81-106, 1986.
[19] A. Rattarangsi and R. T. Chin, "Scale-based detection of corners of planar curves,"IEEE Trans. Pattern Anal. Machine Intell., vol. 14, no. 4, pp. 430-449, 1992.
[20] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representation by error propagation,"Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vols. 1 and 2. Cambridge, MA: MIT Press, 1986.
[21] S. L. Salzberg,Learning with Nested Generalized Exemplars. New York: Kluwer Academic, 1990.
[22] J. Segen, "Learning graph models of shape," inProc. 5th Int. Conf. Machine Learning, 1988, pp. 29-35.
[23] B. A. Shepherd, "An appraisal of a decision tree approach to image classification," inProc. Int. Joint Conf. on Artificial Intell., 1983, pp. 473-475.
[24] F. Stein and G. Medioni, "Structural indexing: Efficient 3-D object recognition,"IEEE Trans. Pattern Anal. Machine Intell., vol. 14, no. 2, pp. 125-145, 1992.
[25] A. Tversky, "Features of similarity,"Psychological Rev., vol. 84, no. 4, pp. 327-352, 1977.
[26] P. H. Winston, "Learning structural descriptions from examples," inThe Psychology of Computer Vision. New York: McGraw Hill, 1975.

Index Terms:
pattern recognition; learning (artificial intelligence); learning systems; shape classes learning; local shape properties; occlusion; property based learning; classification; incremental learning; shape learning system; hand gestures
Citation:
K. Cho, S.M. Dunn, "Learning Shape Classes," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 882-888, Sept. 1994, doi:10.1109/34.310683
Usage of this product signifies your acceptance of the Terms of Use.