This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Learning Visual Models from Shape Contours Using Multiscale Convex/Concave Structure Matching
April 1993 (vol. 15 no. 4)
pp. 337-352

A novel approach is proposed for learning a visual model from real shape samples of the same class. The approach can directly acquire a visual model by generalizing the multiscale convex/concave structure of a class of shapes, that is, the approach is based on the concept that shape generalization is shape simplification wherein perceptually relevant features are retained. The simplification does not mean the approximation of shapes but rather the extraction of the optimum scale convex/concave structure common to shape samples of the class. The common structure is obtained by applying the multiscale convex/concave structure-matching method to all shape pairs among given shape samples of the class and by integrating the matching results. The matching method, is applicable to heavily deformed shapes and is effectively implemented with dynamic programming techniques. The approach can acquire a visual model from a few samples without any a priori knowledge of the class. The obtained model is very useful for shape recognition. Results of applying the proposed method are presented.

[1] P. H. Winston, "Learning structural descriptions from examples,"The Psychology of Computer Vision(P. H. Winston, Ed.). New York, McGraw-Hill, 1975, ch. 5.
[2] P. H. Winston, "Learning and reasoning by analogy,"Commun. ACM, vol. 23, pp. 869-703, 1979.
[3] R. S. Michalski, "Pattern recognition as rule-guided inductive inference,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-2, no. 4, pp. 349-361, 1980.
[4] P. Langley and J. G. Carbonell, "Machine learning: Technique and foundations," Carnegie-Mellon Univ., Pittsburgh, PA, Tech. Rep. 87-09, 1987.
[5] J. H. Connell and M. Brady, "Learning shape descriptions," inProc. 9th IJCAI(Los Angeles), 1985, pp. 922-925.
[6] J. H. Connell and M. Brady, "Generating and generalizing models of visual objects,"Artificial Intell., vol. 31, pp. 159-183, 1987.
[7] J. Segen, "Model learning and recognition of nonrigid objects," inProc. CVPR '89, San Diego, CA, pp. 597-602.
[8] L. G. Shapiro and R. M. Haralick, "Structural descriptions and inexact matching,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-3, no. 5, pp. 504-519, 1981.
[9] M. A. Eshera and K. S. Fu, "A graph distance measure for image analysis,"IEEE Trans. Syst. Man Cybern., vol. SMC-14, no. 3, pp. 398-408, 1984.
[10] T. G. Dietterich and R. S. Michalski, "A comparative review of selected methods for learning from examples," inMachine Learning(R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, Eds.). Los Altos, CA: Morgan Kaufmann, 1983.
[11] M. Leyton, "A process grammar for shape,"Artificial Intell. J., vol. 34, pp. 213-247, Mar. 1988.
[12] F. Moktarian and A. Mackworth, "Scale-based description and recognition of planar curves and two-dimensional shapes,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, no. 1, pp. 34-43, Jan. 1986.
[13] H. Sakou, H. Yoda, and M. Ejiri, "An algorithm for matching distorted waveforms using a scale-based description," inProc. IAPR Workshop CV(Tokyo), 1988, pp. 329-334.
[14] A. K. Mackworth and F. Mokhtarian, "The renormalized curvature scale space and the evolution properties of planar curves,"Proc. IEEE CVPR(Ann Arbor, MI), 1988, pp. 318-326.
[15] N. Ueda and S. Suzuki, "Automatic shape model acquisition using multiscale segment matching," inProc. ICPR, 1990, pp. 897-902.
[16] A. P. Witkin, "Scale space filtering," inProc. 8th IJCAI(Karlsruhe, West Germany), 1983, pp. 1019-1022.
[17] H. H. Baker and T. O. Binford, "Depth from edge and intensity based stereo," inProc. 7th IJCAI, 1981, pp. 631-636.
[18] M. Drumheller and T. Poggio, "On parallel stereo," in Proc. IEEE Int Conf. Robotics and Automation, Cambridge, MA, Apr. 1986, pp. 1439-1448.
[19] H. Sakoe and S. Chiba, "Dynamic programming algorithm optimization for spoken word recognition,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-26, Feb. 1978.
[20] Y. Ohta and T. Kanade, "Stereo by intra- and inter-scanline search using dynamic programming,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-7, no. 2, pp. 139-154, 1985.
[21] H. Maitre and Y. Wu, "Improving dynamic programming to solve image registration,"Patt. Recogn., vol. 20, no. 4, pp. 443-462, 1987.
[22] E. E. Milios, "Shape matching using curvature processes,"Comp. Vision Graphics Image Processing, vol. 47, pp. 203-226, 1989.
[23] D. G. Lowe, "Organization of smooth image curves at multiple scales," inProc. 2nd Int. Conf. Computer Vision, 1988, pp. 558-567, 1988.
[24] J. J. Koenderink, "The structure of images,"Biol. Cybern., vol. 50, pp. 363-370, 1984.
[25] K. Fukunaga,Introduction to Statistical Pattern Recognition. New York: Academic, 1972.
[26] N. Ueda and S. Suzuki, "Automatic shape model acquisition based on a generalization of convex/concave structure,"Trans. Inst. Elec. Inf. Com. Eng. Japan, vol. J74-DII, no. 2, pp. 220-229, 1991.

Index Terms:
computer vision; pattern recognition; visual models; shape contours; multiscale convex/concave structure matching; shape generalization; shape simplification; perceptually relevant features; dynamic programming; shape recognition; computer vision; dynamic programming; pattern recognition
Citation:
N. Ueda, S. Suzuki, "Learning Visual Models from Shape Contours Using Multiscale Convex/Concave Structure Matching," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 4, pp. 337-352, April 1993, doi:10.1109/34.206954
Usage of this product signifies your acceptance of the Terms of Use.