ORBi: Marée Raphaël - A generic approach for image classification based on decision tree ensembles and local sub-windows

Reference : A generic approach for image classification based on decision tree ensembles and local s...


	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/12601

Title :	A generic approach for image classification based on decision tree ensembles and local sub-windows
Language :	English
Author, co-author :	Marée, Raphaël [Université de Liège - ULg > Department of Electrical Engineering and Computer Science > Systèmes et Modélisation > >]
	Geurts, Pierre [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Piater, Justus [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > INTELSIG Group >]
	Wehenkel, Louis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Editor :	Hong, K.-S. [> > > >]
	Zhang, Z. [> > > >]
Publication date :	2004
Main document title :	Proceedings of the 6th Asian Conference on Computer Vision
Publisher :	Asian Federation of Computer Vision Societies (AFCV)
Volume :	2
Pages :	860-865
On invitation :	No
Audience :	International
Event name :	6th Asian Conference on Computer Vision
Event place (city) :	Jeju
Event country :	South Korea
Keywords :	[en] machine learning
Abstract :	[en] A novel and generic approach for image classification is presented. The method operates directly on pixel values and does not require feature extraction. It combines a simple local sub-window extraction technique with induction of ensembles of extremely randomized decision trees. We report results on four well known and publicly available datasets corresponding to representative applications of image classification problems: handwritten digits (MNIST), faces (ORL), 3D objects (COIL-100), and textures (OUTEX). A comparison with studies from the computer vision literature shows that our method is competitive with the state of the art, an interesting result considering its generality and conceptual simplicity. Further experiments are carried out on the COIL-100 dataset to evaluate the robustness of the learned models to rotation, scaling, or occlusion of test images. These preliminary results are very encouraging
Funders :	Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS ; Région wallonne : Direction générale des Technologies, de la Recherche et de l'Energie - DGTRE
Permalink :	http://hdl.handle.net/2268/12601
Other URL :	http://www.montefiore.ulg.ac.be/services/stochastic/pubs/2004/MGPW04

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	maree-accv2004.pdf		Author postprint	96.25 kB	View/Open

Additional material(s):

	File	Commentary	Version	Size	Access
Open access	maree-accv2004-poster.ppt	Poster	-	414.5 kB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5