Skeletal shape extraction from dot patterns by self-organization

Author

Datta, A. ; Parui, S.K. ; Chaudhuri, B.B.

Author_Institution

Comput. & Stat. Service Centre, Indian Stat. Inst., Calcutta, India

Volume

4

fYear

1996

fDate

25-29 Aug 1996

Firstpage

80

Abstract

Extraction of skeletal shape from a 2D dot pattern is discussed. We use a self-organizing neural network model to get a piecewise linear approximation of a skeleton of the pattern. It is found that even without a proper definition of a skeleton, the proposed algorithm is able to produce skeletons that are quite close to what we intuitively feel it should be. In Kohonen´s self-organizing model, the set of processors and their neighbourhoods are fixed. We suggest here some modifications of it in which the set of processors and their neighbourhoods change adaptively

Keywords

approximation theory; character recognition; computer vision; feature extraction; self-organising feature maps; trees (mathematics); 2D dot patterns; Kohonen self-organizing model; character recognition; feature extraction; piecewise linear approximation; self-organizing neural network; skeletal shape extraction; skeleton; tree patterns; Computer networks; Network topology; Neural networks; Pattern analysis; Pattern recognition; Piecewise linear approximation; Shape; Skeleton; US Department of Transportation;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1996., Proceedings of the 13th International Conference on

Conference_Location

Vienna

ISSN

1051-4651

Print_ISBN

0-8186-7282-X

Type

conf

DOI

10.1109/ICPR.1996.547238

Filename

547238