3CAIR - Centre for Applied Internet Research (School of Computing & Communications Technology Glyndwr University Plas Coch Campus, Mold Road Wrexham, North Wales, LL11 2AW, UK Fax: +44 (0)1978 293203 - United Kingdom)
Abstract : Diagrams are widely used in our day to day communication. A knowledge of the spatial patterns used in diagrams is essential to read and understand them. In the context of diagrams, spatial patterns mean accepted spatial arrangements of graphical and textual elements used to represent diagram-specific concepts. In order to assist with the automated understanding of diagrams by computer applications, this paper presents an ontology-based approach to recognise diagram-specific concepts from the spatial patterns in diagrams. Specifically, relevant spatial patterns of diagrams are encoded in an ontology, and the automated instance classification feature of the ontology reasoners is utilised to map spatial patterns to diagram-specific concepts depicted in a diagram. A prototype of this approach to support automated recognition of UML and domain concepts from class diagrams and its performance are also discussed in this paper. This paper concludes with a reflection of the strengths and limitations of the proposed approach.
https://hal.inria.fr/hal-01821059 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Friday, June 22, 2018 - 11:45:27 AM Last modification on : Sunday, November 22, 2020 - 1:54:01 PM Long-term archiving on: : Tuesday, September 25, 2018 - 9:46:55 PM
Anitta Thomas, Aurona J. Gerber, Alta van Der Merwe. Ontology-Based Spatial Pattern Recognition in Diagrams. 14th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2018, Rhodes, Greece. pp.61-72, ⟨10.1007/978-3-319-92007-8_6⟩. ⟨hal-01821059⟩