Reference : Towards generic image classification: an extensive empirical study
E-prints/Working papers : First made available on ORBi
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/175525
Towards generic image classification: an extensive empirical study
English
Marée, Raphaël mailto [Université de Liège - ULg > Electrical Engineering and Computer Science > GIGA-Research > >]
Geurts, Pierre mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique >]
Wehenkel, Louis mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
23-Dec-2014
1
Université de Liège
48
No
Liège
Belgique
[en] This paper considers the general problem of image classification
without using any prior knowledge about image classes. We study
variants of a method based on supervised learning whose common steps
are the extraction of random subwindows described by raw pixel intensity values
and the use of ensemble of extremely randomized trees to directly
classify images or to learn image features. The influence of method
parameters and variants is thoroughly evaluated so as to provide baselines and
guidelines for future studies. Detailed results are provided on 80
publicly available datasets that depict very diverse types of images
(more than 3800 image classes and over 1.5 million images).
Giga-Systems Biology and Chemical Biology
Région wallonne : Direction générale des Relations extérieures - DGRE
Cytomine
Researchers ; Professionals
http://hdl.handle.net/2268/175525

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
maree-Towards-TR2014-full.pdfAuthor preprint3.18 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.