Ontology-Based Approach for Online Arabic Character Recognition

The pattern recognition domain, particularly the online Arabic character recognition is a rich area of research. This paper puts forward a new approach for character recognition using domain ontology. Our main idea is based on the modeling of Arabic character by construction of ontology created by a domain expert. This ontology consists of a set of concepts and spatial relations between them. The concepts represent the strokes extracted by segmenting the character introduced. The aim of this work is to study the role of domain ontologies and their contributions in the recognition phase.

[1]  M. Thonnat,et al.  Symbol Grounding for Semantic Image Interpretation: From Image Data to Semantics , 2005, Tenth IEEE International Conference on Computer Vision Workshops (ICCVW'05).

[2]  Henrik Eriksson,et al.  The evolution of Protégé: an environment for knowledge-based systems development , 2003, Int. J. Hum. Comput. Stud..

[3]  Latifur Khan,et al.  Image classification using neural networks and ontologies , 2002, Proceedings. 13th International Workshop on Database and Expert Systems Applications.

[4]  Sahar Hassan,et al.  Segmentation de maillage guidée par une ontologie , 2009 .

[5]  Liyang Yu.  Jena: A Framework for Development on the Semantic Web , 2011 .

[6]  Michael G. Strintzis,et al.  An ontology approach to object-based image retrieval , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[7]  Thomas R. Gruber,et al.  A translation approach to portable ontology specifications , 1993, Knowl. Acquis..