Abstract
domain of pattern recognition and especially the character recognition is an area rich in term of scientific production, despite the abundance of work in this area but there are always anomalies. In this paper, we present a new approach for character recognition based on ontology, this last is carefully created with a domain expert, it contains a set of concepts and relationships, where each concept represents a grapheme, it is a feature extracted by an extraction module of a recognition system. Relationships between concepts are type spatial; describing the different possible relationships can be used between the graphemes, thus the characters in a document written in Latin alphabet. Our ontology is generic and can support other languages by enriching it by new specific spatial relationships. Keywordsharacters recognition, grapheme, ontology, spatial relation, typographical features.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
