A
Cognitive Vision Platform for Automatic Recognition of Natural Complex Objects
LES AUTEURS Celine Hudelot and
Monique Thonnat
RESUME:
This paper presents a generic cognitive vision platform for the automatic recognition
of natural complex objects. The recognition consists of three steps : image processing
for numerical object description, mapping of numerical data into symbolic data
and semantic interpretation for object recognition. The focus of this paper is
the distributed platform architecture composed of three highly specilaized Knowledge
Based Systems (KBS). The first KBS is dedicated to semantic interpretation. The
second one has to deal with the anchoring of symbolic data into image data. The
last KBS is dedicated to intelligent image processing. After a brief overview
of the natural object recognition problem, this paper describes the three subcomponents
of the platform
Mots clé: Cognitive Vision, Natural Object Recognition, Knowledge
Based System
Pour télécharger cet article,
cliquez ici
BibTeX reference:
@inproceedings{hudelot03ICTAI,
author="Hudelot, C. and Thonnat, M.",
editor= {IEEE},
title= {A cognitive Vision Platform for Automatic Recognition of Natural Complex Objects},
booktitle = {International Conference on Tools with Artificial Intelligence, ICTAI, Sacramento},
year = {2003}
}
Dernière mise à jour :
14/11/03
Catherine.Martin@sophia.inria.fr