Graph based descriptor evaluation towards automatic feature selection

Anita Keszler, Levente Kovács, T. Szirányi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents the first steps towards an automated image and video feature descriptor evaluation framework, based on several points of view. First, evaluation of distance distributions of images and videos for several descriptors are performed, then a graph-based representation of database contents and evaluation of the appearance of the giant component is performed. The goal is to lay the foundations for an evaluation framework where different descriptors and their combinations can be analyzed, with the goal of later application for automatic feature selection.

Original languageEnglish
Title of host publicationVISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications
Pages375-380
Number of pages6
Volume1
Publication statusPublished - 2012
EventInternational Conference on Computer Vision Theory and Applications, VISAPP 2012 - Rome, Italy
Duration: Feb 24 2012Feb 26 2012

Other

OtherInternational Conference on Computer Vision Theory and Applications, VISAPP 2012
CountryItaly
CityRome
Period2/24/122/26/12

Fingerprint

Feature extraction

Keywords

  • Components
  • Feature selection
  • Graph representation

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Keszler, A., Kovács, L., & Szirányi, T. (2012). Graph based descriptor evaluation towards automatic feature selection. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications (Vol. 1, pp. 375-380)

Graph based descriptor evaluation towards automatic feature selection. / Keszler, Anita; Kovács, Levente; Szirányi, T.

VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2012. p. 375-380.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Keszler, A, Kovács, L & Szirányi, T 2012, Graph based descriptor evaluation towards automatic feature selection. in VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. vol. 1, pp. 375-380, International Conference on Computer Vision Theory and Applications, VISAPP 2012, Rome, Italy, 2/24/12.
Keszler A, Kovács L, Szirányi T. Graph based descriptor evaluation towards automatic feature selection. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1. 2012. p. 375-380
Keszler, Anita ; Kovács, Levente ; Szirányi, T. / Graph based descriptor evaluation towards automatic feature selection. VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 1 2012. pp. 375-380
@inproceedings{897e967e59ee41938f9f58c8f1a19125,
title = "Graph based descriptor evaluation towards automatic feature selection",
abstract = "This paper presents the first steps towards an automated image and video feature descriptor evaluation framework, based on several points of view. First, evaluation of distance distributions of images and videos for several descriptors are performed, then a graph-based representation of database contents and evaluation of the appearance of the giant component is performed. The goal is to lay the foundations for an evaluation framework where different descriptors and their combinations can be analyzed, with the goal of later application for automatic feature selection.",
keywords = "Components, Feature selection, Graph representation",
author = "Anita Keszler and Levente Kov{\'a}cs and T. Szir{\'a}nyi",
year = "2012",
language = "English",
isbn = "9789898565037",
volume = "1",
pages = "375--380",
booktitle = "VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications",

}

TY - GEN

T1 - Graph based descriptor evaluation towards automatic feature selection

AU - Keszler, Anita

AU - Kovács, Levente

AU - Szirányi, T.

PY - 2012

Y1 - 2012

N2 - This paper presents the first steps towards an automated image and video feature descriptor evaluation framework, based on several points of view. First, evaluation of distance distributions of images and videos for several descriptors are performed, then a graph-based representation of database contents and evaluation of the appearance of the giant component is performed. The goal is to lay the foundations for an evaluation framework where different descriptors and their combinations can be analyzed, with the goal of later application for automatic feature selection.

AB - This paper presents the first steps towards an automated image and video feature descriptor evaluation framework, based on several points of view. First, evaluation of distance distributions of images and videos for several descriptors are performed, then a graph-based representation of database contents and evaluation of the appearance of the giant component is performed. The goal is to lay the foundations for an evaluation framework where different descriptors and their combinations can be analyzed, with the goal of later application for automatic feature selection.

KW - Components

KW - Feature selection

KW - Graph representation

UR - http://www.scopus.com/inward/record.url?scp=84862122862&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862122862&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84862122862

SN - 9789898565037

VL - 1

SP - 375

EP - 380

BT - VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications

ER -