Shapes Description by a Segments-Based Neural Network

Authors:
J. A. Gómez-Ruiz;J. Muñoz-Perez;M. A. García-Bernal
Affiliations:
Dept. of Languages, Computer Science, University of Málaga, Málaga, Spain 29071;Dept. of Languages, Computer Science, University of Málaga, Málaga, Spain 29071;Dept. of Languages, Computer Science, University of Málaga, Málaga, Spain 29071
Venue:
IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part I: Bio-Inspired Systems: Computational and Ambient Intelligence
Year:
2009

Citing 2
Cited 0

Self-organizing maps

Self-organizing maps
Residuals + directional gaps = skeletons

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Skeletonization is the process of transforming a shape in a digital image, composed of several pixels, to a line-based shape so that the topological properties of the original shape are preserved. The resulting shape is called skeleton. Such skeletons are useful in the recognition of elongated shaped objects, for example, character patterns, chromosome patterns, etc. The skeleton provides an abstraction of geometrical and topological features of the object, so that the skeletonization can be viewed as data compression. In this paper, a model of competitive neural network based in segments is proposed. This model is suitable for obtaining the skeleton of elongated shapes with an unsupervised method.