Empirical Study of Multi-scale Filter Banks for Object Categorization

Author

Marín-Jiménez, Manuel J. ; de la Blanca, Nicolás Pérez

Author_Institution

Dpt. of Comput. Sci. & Artificial Intelligence, Granada Univ.

Volume

1

fYear

0

fDate

0-0 0

Firstpage

578

Lastpage

581

Abstract

The aim of this work is the evaluation of different multi-scale filter banks, mainly based on oriented Gaussian derivatives and Gabor functions, to be used in the generation of robust features for visual object categorization. In order to combine the responses obtained from several spatial scales, we use the biologically inspired HMAX model (Riesenhuber and Poggio, 1999). We have tested the different sets of features on the challenging Caltech-101 database, and we have performed the categorizarion procedure with AdaBoost, support vector machines and JointBoosting classifiers, achieving remarkable results

Keywords

Gabor filters; computer vision; image classification; support vector machines; AdaBoost; Caltech-101 database; Gabor functions; HMAX model; JointBoosting; multiscale filter banks; oriented Gaussian derivatives; support vector machines; visual object categorization; Artificial intelligence; Biological system modeling; Channel bank filters; Computer science; Filter bank; Gabor filters; Nonlinear filters; Object oriented databases; Robustness; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.491

Filename

1698959