This Article 
 Bibliographic References 
 Add to: 
Hierarchical Decomposition and Axial Shape Description
October 1993 (vol. 15 no. 10)
pp. 973-981

A method for producing a segmented axial description of a given shape together with a hierarchical decomposition of the shape into its parts is presented. The novelty of this approach lies in the combination of several competing approaches and tools into a unified scheme and an efficient implementation producing natural descriptions. Smooth local symmetries are used for the axial description of parts, which are suggested by curvature sign changes. Parallel symmetries are used to provide information on global relationships within the shape. This information is used for parsing shape into a hierarchy of parts. This approach uses both region and contour information, can handle shapes with corners, and addresses the issue of local versus global information, the issue of scale, and the notion of part. The method is computationally efficient, robust, and stable. Results that show that it provides an intuitive shape description are included.

[1] F. Attneave, "Some informational aspects of visual perception,"Psycholog. Rev., vol. 61, pp. 183-193, 1954.
[2] R.H. Bartels, J.C. Beatty, and B.A. Barsky,An Introduction to Splines for Use in Computer Graphics and Geometric Modeling, Morgan Kaufmann Publishers, Los Altos, Calif., 1987.
[3] I. Biederman, "Matching image edges to object memory," inProc. IEEE Int. Conf. Comput. Vision(London), June 1987, pp. 384-392.
[4] I. Biederman, "Recognition by components,"Psycholog. Rev., vol. 94, pp. 115-147, 1987.
[5] T. O. Binford, "Visual perception by computer," inProc. IEEE Conf. Syst. Contr.(Miami, FL), 1971.
[6] H. Blum,A Transformation for Extracting New Descriptors of Shape. Cambridge, MA: MIT Press, 1967.
[7] H. Blum and R. N. Nagel, "Shape description using weighted symmetric axis features,"Patt. Recogn., vol. 10, pp. 167-180, 1978.
[8] M. Brady and H. Asada, "Smoothed local symmetries and their implementation,"Int. J. Robotics Res., vol. 3, no. 3, pp. 36-61, 1984.
[9] R. A. Brooks, "Symbolic reasoning among 3-D models and 2-D images,"Artificial Intell., vol. 17, pp. 285-348, 1981.
[10] J. H. Connell and M. Brady, "Generating and generalizing models of visual objects," Tech. Rep. AIM-823, Mass. Inst. Technol., July 1985.
[11] J. H. Connell and M. Brady, "Generating and generalizing models of visual objects,"Artificial Intell., vol. 31, pp. 159-183, 1987.
[12] P. J. Giblin and S. A. Brassett, "Local symmetry of plane curves,"Amer. Math. Monthly, vol. 92, pp. 689-707, 1985.
[13] V. Guillemin and A. Pollack,Differential Topology. Englewood Cliffs, NJ: Prentice Hall, 1974.
[14] D. D. Hoffman, "Representing shapes for visual recognition," Ph.D. thesis, Mass. Inst. Technol., May 1983.
[15] D. D. Hoffman and W. A. Richards, "Parts of recognition,"Cognition, vol. 18, pp. 65-96, 1985.
[16] B. B. Kilmia, A. Tannenbaum, and S.W. Zucker, "Towards a computational theory of shape," inProc. 1st ECCV, Antibes, 1990, pp. 402-407.
[17] M. Leyton, "Symmetry-curvature duality,"Comput. Vision Graphics Image Processing, vol. 38, pp. 327-341, 1987.
[18] M. Leyton, "A process grammar for shape,"Artificial Intell. J., vol. 34, pp. 213-247, Mar. 1988.
[19] M. Leyton, "Inferring causal history from shape,"Cognitive Sci., vol. 13, pp. 357-387, 1989.
[20] D. Marr,Vision. San-Fransisco, CA: W. H. Freeman, 1982.
[21] D. Marr and K. Nishihara, "Representation and recognition of the spatial organization of three-dimensional shapes," inProc. Royal Soc. London, vol. B(200), pp. 269-294, 1977.
[22] R. Nevatia,Machine Perception. Englewood Cliffs, NJ: Prentice Hall, 1982.
[23] J. Ponce, "On characterizing ribbons and finding skewed symmetries,"Comput. Vision Graphics Image Processing, vol. 52, pp. 328-340, 1990.
[24] K. Rao, "Shape description from sparse and imperfect data," Ph.D. thesis, Univ. of Southern Calif., Dec. 1988; IRIS Tech. Rep. 250.
[25] W. A. Richards and D. D. Hoffman, "Codon constraints on closed 2D shapes,"Comput. Vision Graphics Image Processing, vol. 31, pp. 265-281, 1985.
[26] A. Rosenfeld, "Axial representation of shape,"Comput. Vision Graphics Image Processing, vol. 33, pp. 156-173, 1986.
[27] P. Saint-Marc and G. Medioni, "B-spline contour representation and symmetry detection," inProc. Euro. Conf. Comput. Vision(Antibes, France), 1990, pp. 604-606.
[28] P. Saint-Marc, H. Rom, and G. Medioni, "B-spline contour representation and symmetry detection,"IEEE Trans. Patt. Anal. Machine Intell., to be published.
[29] J. B. Subirana-Vilanova, "The skeleton sketch: Finding salient frames of reference," inProc. DARPA Image Understanding Workshop(Pittsburgh, PA), Sept. 1990, pp. 614-622.
[30] F. Ulupinar and R. Nevatia, "Perception of 3-D surfaces from 2-D contours," inProc. 10th Int Conf. Patt. Recogn.(Atlantic City, NJ), 1990, pp. 147-154.

Index Terms:
smooth local symmetries; parallel symmetries; shape parsing; region information; robustness; computational efficiency; stability; axial shape description; segmented axial description; hierarchical decomposition; curvature sign changes; contour information; scale; image segmentation
H. Rom, G. Medioni, "Hierarchical Decomposition and Axial Shape Description," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 973-981, Oct. 1993, doi:10.1109/34.254054
Usage of this product signifies your acceptance of the Terms of Use.