Ontology of Visual Objects

Svetla Koeva


Abstract
The focus of the paper is the Ontology of Visual Objects based on WordNet noun hierarchies. In particular, we present a methodology for bidirectional ontology engineering, which integrates the pre-existing knowledge resources and the selection of visual objects within the images representing particular thematic domains. The Ontology of Visual Objects organizes concepts labeled by corresponding classes (dominant classes, classes that are attributes to dominant classes, and classes that serve only as parents to dominant classes), relations between concepts and axioms defining the properties of the relations. The Ontology contains 851 classes (706 dominant and attribute classes), 15 relations and a number of axioms built upon them. The definition of relations between dominant and attribute classes and formulations of axioms based on the properties of the relations offers a reliable means for automatic object or image classification and description.
Anthology ID:
2022.clib-1.14
Volume:
Proceedings of the Fifth International Conference on Computational Linguistics in Bulgaria (CLIB 2022)
Month:
September
Year:
2022
Address:
Sofia, Bulgaria
Venue:
CLIB
SIG:
Publisher:
Department of Computational Linguistics, IBL -- BAS
Note:
Pages:
120–129
Language:
URL:
https://aclanthology.org/2022.clib-1.14
DOI:
Bibkey:
Cite (ACL):
Svetla Koeva. 2022. Ontology of Visual Objects. In Proceedings of the Fifth International Conference on Computational Linguistics in Bulgaria (CLIB 2022), pages 120–129, Sofia, Bulgaria. Department of Computational Linguistics, IBL -- BAS.
Cite (Informal):
Ontology of Visual Objects (Koeva, CLIB 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.clib-1.14.pdf
Data
ImageNetMS COCOYAGO