Abstract
In real world problems, where the objects are in general complex and deformed, the automatic generation of local characteristics is necessary in order to distinguish different object classes.
This paper presents an approach towards the automatic synthesis of significant local contour sections of closed, discrete, complex, and deformed 2D-object contours for the distinction of different classes. Neighboring contour points are determined and synthesized (feature fusion) into feature groups. Exclusively with the help of these feature groups the method distinguishes between different 2D-object contour classes of a certain domain. The basic idea is to get only the necessary information of a contour or a contour class for recognition.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Alt, H., Guibas, L. J.: Discrete Geometric Shapes: Matching, Interpolation, and Approximation-A Survey. Technical Reports of FU Berlin (1996), Institut für Informatik u. Mathematik. 521
Basri, R., Costa, L., Geiger, D., Jacobs, D.: Determining the similarity of deformable shapes. Vision Research 38 (1998), 2365–2385. 518
Bellman, R.: Dynamic Programming. Princeton University Press, Princeton, New Jersey (1957). 521
Hoffman, D. D., Singh, M.: Salience of visual parts. Cognition 63 (1997), 29–78. 518
Kimia, B. B., Tannenbaum, A. R., Zucker, S.: Shapes, shocks, and deformations 1: The components of shape and the reaction-diffusion space. Int. Journal of Computer vision 15(3) (1995), 189–224. 518
Kupeev, K., Wolfson, H.: A new method of estimating shape similarity. Pattern Recognition Letters 17 (1996), 873–887. 518
Latecki, L. J., Lakämper, R.: Discrete Approach to Curve Evolution. In Levi, P., Ahlers, R.-J., May, F. and Schanz, M. (Edts.): Mustererkennung 1998, 20. DAGM-Symposium, 85–92. 518
Latecki, L. J., Lakämper, R.: Shape decomposition and shape similarity measure. In Levi, P., Ahlers, R.-J., May, F. and Schanz, M. (Edts.): Mustererkennung 1998, 20. DAGM-Symposium, 367–376. 518
Loncaric, S.: A survey of shape analysis techniques. Pattern Recognition 31 (1997), 983–1001. 518
Pavlidis, T.:Structural Pattern Recognition. Springer-Verlag, Berlin (1977). 518
Pechtel, D., Kuhnert, K.-D.: Generating Automatically Local Feature Groups of Complex and Deformed Objects. Appears in Gaul, W., Decker, R. (eds.): Classification and Information Processing at the Turn of the Millenium. Proc. 23th Ann. Conf. of GfKl, Bielefeld, March 10–12, 1999. Springer, Heidelberg, 2000, 237–244. 519, 520, 521, 523
Pitts, W., McCulloch W.: How we know universals: the perception of auditory and visual forms. Bulleting of Mathematical Biophysics 9 (1947), 127–147. 518
Sederberg, T., Gao, P., Wang, G., Mu, H.: 2D shape blending: An Intrinsic Solution to the Vertex Path Problem. Computer Graphics 38 (1993) 15–18. 518
Siddiqi, K., Kimia, B.: Parts of Visual Form: Computational Aspects. IEEE Transactions On Pattern Anal. And Mach. Intell. 17 (1995) 239–251. 518
Siddiqi, K., Tresnes, K., and Kimia, B.: Parts of visual form: ecological and psychophysical aspects. In Proc. IAPR’s Int.Workshop on Visual Form (1994). 518
Sanko., D., Kruskal, B. K. (Eds.): Time warps, String Edits, and Macromolecules: The Theory and Practice of Sequence Comparison. Addison-Wesley, Reading (1983). 519, 521
Ullman, S.: High-level Vision. A Bradford Book, The MIT Press, Cambridge, Massachusetts (1996). 518
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pechtel, D., Klaus-Dieter, K. (2000). Towards Feature Fusion - The Synthesis of Contour Sections Distinguishing Contours from Different Classes. In: Borgefors, G., Nyström, I., di Baja, G.S. (eds) Discrete Geometry for Computer Imagery. DGCI 2000. Lecture Notes in Computer Science, vol 1953. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44438-6_42
Download citation
DOI: https://doi.org/10.1007/3-540-44438-6_42
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41396-7
Online ISBN: 978-3-540-44438-1
eBook Packages: Springer Book Archive