Extracting an ontology of portrayable objects from Wordnet

S. Zinger, Chr. Millet, B. Mathieu, G. Grefenstette, P. Hede, P.-A. Mokllic

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review


We describe building a large-scale image ontology using the WordNet lexical resources. This ontology is based on English words identifying portrayable objects. We reviewed the upper structure and interconnections of WordNet and selected only the branches leading to portrayable objects. This article explains our pruning approach to WordNet. The words, which represent portrayable objects, are then used as queries in our VIKA (VIsual KAtaloguer) system which acquires images through a web image search engine, performs content-based image indexing and clustering. Coherent images form clusters and others are rejected. So images inside clusters mostly represent the object determined by the query, and in this way image collections representing objects are created. An ontology of portrayable objects with representative images in its nodes will be a useful tool for solving the object recognition task.
Originele taal-2Engels
TitelProceedings of the MUSCLE/ImageCLEF Workshop on Image and Video Retrieval Evaluation, 20 September 2005, Vienna, Austria
Plaats van productieVienna
UitgeverijVienna University of Technology
StatusGepubliceerd - 2005

Vingerafdruk Duik in de onderzoeksthema's van 'Extracting an ontology of portrayable objects from Wordnet'. Samen vormen ze een unieke vingerafdruk.

Citeer dit