Title :
Qualitatively describing objects using spatial prepositions
Author :
Abella, A. ; Kender, John R.
Author_Institution :
Dept. of Comput. Sci., Columbia Univ., New York, NY, USA
Abstract :
The paper presents a framework for a system that describes objects in a qualitative fashion. A subset of spatial prepositions is chosen and an appropriate quantification is applied to each of them that capture their inherent qualitative properties. The quantifications use such object attributes as area, centers, and elongation properties. The familiar zeroth, first, and second order moments are used to characterize these attributes. The paper details how and why the particular quantifications were chosen. Since spatial prepositions are by their nature rather vague and dependent on context a technique for fuzzifying the definition of the spatial preposition is explained. Finally an example task is chosen to illustrate the appropriateness of the quantification techniques
Keywords :
computational geometry; image recognition; natural languages; spatial reasoning; area; centers; elongation properties; object attributes; qualitative properties; spatial prepositions; Bicycles; Computational modeling; Computer science; Encoding; Natural languages; Shape; Tail;
Conference_Titel :
Qualitative Vision, 1993., Proceedings of IEEE Workshop on
Conference_Location :
New York City, NY
Print_ISBN :
0-8186-3692-0
DOI :
10.1109/WQV.1993.262952