PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Emergence of ontological relations from visual data with self-organizing maps
Jorma Laaksonen and Ville Viitaniemi
In: 9th Scandinavian Conference on Artificial Intelligence, Espoo, Finland(2006).


In this paper we examine how Self-Organizing Maps (SOMs) can be used in detecting and describing emergent ontological relations between semantic objects and object classes in a visual database. The ontological relations we have studied include co-existence, taxonomies of visual and semantic similarity and spatial relationships. The used database contains 2618 images each of which belongs to one or more of ten predefined semantic classes.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:2554
Deposited By:Ville Viitaniemi
Deposited On:22 November 2006