Towards Generic Image Classification using Tree-based Learning: an Extensive Empirical Study

This is the author post-print (ie. final draft post-refereeing) accepted version of the paper. Publisher (Elsevier) version will be available in Pattern Recognition Letters. http://www.journals.elsevier.com/pattern-recognition-letters/

All documents in ORBi are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Abstract :

[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).

Disciplines :

Computer science

Author, co-author :

Marée, Raphaël ; Université de Liège > GIGA-Research

Geurts, Pierre ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique

Wehenkel, Louis ; Université de Liège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation

Language :

English

Title :

Towards Generic Image Classification using Tree-based Learning: an Extensive Empirical Study

Publication date :

2016

Journal title :

Pattern Recognition Letters

ISSN :

0167-8655

Publisher :

Elsevier, Netherlands

Volume :

Issue :

Pages :

17-23

Peer reviewed :

Peer Reviewed verified by ORBi

Tags :

CÉCI : Consortium des Équipements de Calcul Intensif

Funders :

Service public de Wallonie : Direction générale opérationnelle de l'économie, de l'emploi et de la recherche - DG06

Available on ORBi :

since 14 January 2016

Statistics

Number of views

573 (78 by ULiège)

Number of downloads

819 (49 by ULiège)

More statistics

Scopus citations^®

Scopus citations^®
without self-citations

OpenCitations

OpenAlex citations

Bibliography

D.C. Ciresan, U. Meier, and J. Schmidhuber Multi-column deep neural networks for image classification Computer Vision and Pattern Recognition 2012 3642 3649
A. Criminisi, and J. Shotton Decision forests for computer vision and medical image analysis Advances in Computer Vision and Pattern Recognition 2013 Springer
A. Delga, F. Goffin, R. Marée, C. Lambert, and P. Delvenne Evaluation of cellsolutions bestprep(r) automated thin-layer liquid-based cytology papanicolaou slide preparation and bestcyte(r) cell sorter imaging system Acta Cytol. 58 5 2014 469 477
M. Dumont, R. Marée, L. Wehenkel, and P. Geurts Fast multi-class image annotation with random subwindows and multiple output randomized trees Proceedings of the 2009 International Conference on Computer Vision Theory and Applications (VISAPP) 2009 196 203
M. Everingham, L. Van Gool, C.K.I. Williams, J. Winn, and A. Zisserman The PASCAL Visual Object Classes (VOC) challenge Int. J. Comput. Vis. 88 2 2010 303 338
P.V. Gehler, and S. Nowozin On feature combination for multiclass object classification Proceedings of the IEEE International Conference on Computer Vision (ICCV) 2009 221 228
P. Geurts, D. Ernst, and L. Wehenkel Extremely randomized trees Mach. Learn. 36 1 2006 3 42
G.B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments 2007 University of Massachusetts, Amherst
N. Jeanray, R. Marée, B. Pruvot, O. Stern, P. Geurts, L. Wehenkel, and M. Muller Phenotype classification of zebrafish embryos by supervised learning PLos ONE 10 1 2015 e0116989
T. Kotseruba, C. Cumbaa, and I. Jurisica High-throughput protein crystallization on the world community grid and the GPU J. Phys. Conf. Ser. 341 2012
Q.V. Le, J. Ngiam, Z. Chen, D. Chia, P.W. Koh, and A.Y. Ng Tiled convolutional neural networks J. Lafferty, C. Williams, J. Shawe-Taylor, R. Zemel, A. Culotta, Advances in Neural Information Processing Systems 23 2010 Neural Information Processing Systems (NIPS) Foundation 1279 1287
Y. LeCun, Y. Bengio, and G. Hinton Deep learning Nature 521 2015 436 444
C.J. Lintott, K. Schawinski, A. Slosar, K. Land, S. Bamford, D. Thomas, M.J. Raddick, R.C. Nichol, A. Szalay, D. Andreescu, P. Murray, and J. Vandenberg Galaxy Zoo: Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey Mon. Not. R. Astron. Soc. 389 2008 1179 1189
R. Marée, P. Geurts, J. Piater, and L. Wehenkel A generic approach for image classification based on decision tree ensembles and local sub-windows K.-S. Hong, Z. Zhang, Proceedings of the Sixth Asian Conference on Computer Vision 2 2004 860 865
R. Marée, P. Geurts, J. Piater, and L. Wehenkel Random subwindows for robust image classification Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 1 2005 IEEE 34 40
R. Marée, P. Geurts, G. Visimberga, J. Piater, and L. Wehenkel An empirical comparison of machine learning algorithms for generic image classification F. Coenen, A. Preece, A. Macintosh, Proceedings of the Twenty-third SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence 2003 Springer 169 182
R. Marée, P. Geurts, L. Wehenkel, Random subwindows and extremely randomized trees for image classification in cell biology, Proceedings of the International Workshop on Multiscale Biological Imaging, Data Mining and Informatics, vol. 8, (S1) (2007). BMC Cell Biology
R. Marée, P. Geurts, and L. Wehenkel Content-based image retrieval by indexing random subwindows with randomized trees IPSJ Trans. Comput. Vis. Appl. 1 1 2009 46 57
R. Marée, L. Rollus, B. Stévens, R. Hoyoux, G. Louppe, R. Vandaele, J.-M. Begon, P. Kainz, P. Geurts, and L. Wehenkel Collaborative analysis of multi-gigapixel imaging data using cytomine Bioinformatics 2016 10.1093/bioinformatics/btw013
F. Moosmann, E. Nowak, and F. Jurie Randomized clustering forests for image classification IEEE Trans. PAMI 30 9 2008 1632 1646
A. Oliva, and A. Torralba Modeling the shape of the scene: a holistic representation of the spatial envelope Int. J. Comput. Vis. 42 3 2001 145 175
N. Orlov, L. Shamir, T. Macura, J. Johnston, D.M. Eckley, and I. Goldberg Wnd-charm: Multi-purpose image classification using compound transforms Pattern Recognit. Lett. 29 11 2008 1684 1693
N. Pinto, J. Dicarlo, and D. Cox Establishing good benchmarks and baselines for face recognition Proceedings of the European Conference on Computer Vision, Workshop on Faces in 'Real-Life' Images (ECCV 2008) 2008
N. Pinto, D. Doukhan, J. DiCarlo, and D. Cox A high-throughput screening approach to discovering good forms of biologically-inspired visual representation PLoS Comput. Biol. 5 11 2009
A. Quattoni, and A.Torralba Recognizing indoor scenes Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009 413 420
M. Ranzato, A. Krizhevsky, and G.E. Hinton Factored 3-way restricted Boltzmann machines for modeling natural images J. Mach. Learn. Res. Proc. Track 9 2010 621 628
L. Shamir Evaluation of face datasets as tools for assessing the performance of face recognition method Int. J. Comput. Vis. 79 3 2008 225 230
O. Stern, R. Marée, J. Aceto, N. Jeanray, M. Muller, L. Wehenkel, and P. Geurts Automatic localization of interest points in zebrafish images with tree-based methods Proceedings of the Sixth IAPR International Conference on Pattern Recognition in Bioinformatics Lecture Notes in Bioinformatics 2011 Springer-Verlag 179 190
J. Xiao, J. Hays, K. Ehinger, A. Oliva, and A. Torralba Sun database: Large-scale scene recognition from abbey to zoo Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR2010) 2010 3485 3492