A Bayesian network for combining descriptors: application to symbol recognition

Authors:
Sabine Barrat;Salvatore Tabbone
Affiliations:
University of Nancy 2, LORIA-UMR 7503, BP 239, 54506, Vandoeuvre-lès-Nancy, France;University of Nancy 2, LORIA-UMR 7503, BP 239, 54506, Vandoeuvre-lès-Nancy, France
Venue:
International Journal on Document Analysis and Recognition
Year:
2010

Citing 0
Cited 4

From engineering diagrams to engineering models: Visual recognition and applications

Computer-Aided Design
A non-rigid appearance model for shape description and recognition

Pattern Recognition
Spatio-structural symbol description with statistical feature add-on

GREC'11 Proceedings of the 9th international conference on Graphics Recognition: new trends and challenges
Spectra of shape contexts: An application to symbol recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a descriptor combination method, which enables to improve significantly the recognition rate compared to the recognition rates obtained by each descriptor. This approach is based on a probabilistic graphical model. This model also enables to handle both discrete and continuous-valued variables. In fact, in order to improve the recognition rate, we have combined two kinds of features: discrete features (corresponding to shape measures) and continuous features (corresponding to shape descriptors). In order to solve the dimensionality problem due to the large dimension of visual features, we have adapted a variable selection method. Experimental results, obtained in a supervised learning context, on noisy and occluded symbols, show the feasibility of the approach.