loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Sean Ryan Fanello 1 ; Nicoletta Noceti 2 ; Giorgio Metta 3 and Francesca Odone 2

Affiliations: 1 Istituto Italiano di Tecnologia and Università degli Studi di Genova, Italy ; 2 Università degli Studi di Genova, Italy ; 3 Istituto Italiano di Tecnologia, Italy

Keyword(s): Sparse Representation, Discriminative Dictionary Learning, Object Recognition and Categorization.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Features Extraction ; Image and Video Analysis

Abstract: It is well assessed that sparse representations improve the overall accuracy and the systems performances of many image classification problems. This paper deals with the problem of finding sparse and discriminative representations of images in multi-class settings. We propose a new regularized functional, which is a modification of the standard dictionary learning problem, designed to learn one dictionary per class. With this new formulation, while positive examples are constrained to have sparse descriptions, we also consider a contribution from negative examples which are forced to be described in a denser and smoother way. The descriptions we obtain are meaningful for a given class and highly discriminative with respect to other classes, and at the same time they guarantee real-time performances. We also propose a new approach to the classification of single image features which is based on the dictionary response. Thanks to this formulation it is possible to directly classify lo cal features based on their sparsity factor without losing statistical information or spatial configuration and being more robust to clutter and occlusions. We validate the proposed approach in two image classification scenarios, namely single instance object recognition and object categorization. The experiments show the effectiveness in terms of performances and speak in favor of the generality of our method. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.145.76.159

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Fanello, S.; Noceti, N.; Metta, G. and Odone, F. (2013). Multi-class Image Classification - Sparsity does it Better. In Proceedings of the International Conference on Computer Vision Theory and Applications (VISIGRAPP 2013) - Volume 1: VISAPP; ISBN 978-989-8565-47-1; ISSN 2184-4321, SciTePress, pages 800-807. DOI: 10.5220/0004295908000807

@conference{visapp13,
author={Sean Ryan Fanello. and Nicoletta Noceti. and Giorgio Metta. and Francesca Odone.},
title={Multi-class Image Classification - Sparsity does it Better},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications (VISIGRAPP 2013) - Volume 1: VISAPP},
year={2013},
pages={800-807},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004295908000807},
isbn={978-989-8565-47-1},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the International Conference on Computer Vision Theory and Applications (VISIGRAPP 2013) - Volume 1: VISAPP
TI - Multi-class Image Classification - Sparsity does it Better
SN - 978-989-8565-47-1
IS - 2184-4321
AU - Fanello, S.
AU - Noceti, N.
AU - Metta, G.
AU - Odone, F.
PY - 2013
SP - 800
EP - 807
DO - 10.5220/0004295908000807
PB - SciTePress