Item


Object and Scene Classification: what does a Supervised Approach Provide us?

Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurrences to perform a scene classification (e.g. beach scene, mountain scene). We achieve this by using a supervised learning algorithm able to learn with few images to facilitate the user task. We use a probabilistic model to recognise the objects and further we classify the scene based on their object occurrences. Experimental results are shown and evaluated to prove the validity of our proposal. Object recognition performance is compared to the approaches of He et al. (2004) and Marti et al. (2001) using their own datasets. Furthermore an unsupervised method is implemented in order to evaluate the advantages and disadvantages of our supervised classification approach versus an unsupervised one

© 18th International Conference on Pattern Recognition : 2006 : ICPR 2006, 2006, vol. 1, p. 773-777

IEEE

Author: Bosch Rué, Anna
Muñoz Pujol, Xavier
Oliver i Malagelada, Arnau
Martí Marly, Robert
Date: 2006
Abstract: Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurrences to perform a scene classification (e.g. beach scene, mountain scene). We achieve this by using a supervised learning algorithm able to learn with few images to facilitate the user task. We use a probabilistic model to recognise the objects and further we classify the scene based on their object occurrences. Experimental results are shown and evaluated to prove the validity of our proposal. Object recognition performance is compared to the approaches of He et al. (2004) and Marti et al. (2001) using their own datasets. Furthermore an unsupervised method is implemented in order to evaluate the advantages and disadvantages of our supervised classification approach versus an unsupervised one
Format: application/pdf
Citation: Bosch Rué, A., Muñoz, X., Oliver, A., i Martí, R. (2006). Object and Scene Classification: what does a Supervised Approach Provide us?. 18th International Conference on Pattern Recognition : 2006 : ICPR 2006, 1, 773 - 777. Recuperat 10 maig 2010, a http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1699006
ISBN: 0-7695-2521-0
ISSN: 1051-4651
Document access: http://hdl.handle.net/10256/2316
Language: eng
Publisher: IEEE
Collection: Reproducció digital del document publicat a: http://dx.doi.org/10.1109/ICPR.2006.874
Articles publicats (D-ATC)
Is part of: © 18th International Conference on Pattern Recognition : 2006 : ICPR 2006, 2006, vol. 1, p. 773-777
Rights: Tots els drets reservats
Subject: Imatges -- Processament -- Tècniques digitals
Reconeixement de formes (Informàtica)
Visió per ordinador
Computer vision
Image processing -- Digital techniques
Pattern recognition systems
Title: Object and Scene Classification: what does a Supervised Approach Provide us?
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors