Feature selection for object detection: the best group vs. the group of best

Luka Furst, Aleš Leonardis

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

Abstract

The problem of visual object detection, the goal of which is to predict the locations and sizes of all objects of a given visual category (e.g., cars) in a given set of images, is often based on a possibly large set of local features, only a few of which might actually be useful for the given detection setup. Feature selection is concerned with finding a 'useful' subset of features. In this paper, we compare two approaches to feature selection in a visual object detection setup. One of them selects features based on their individual utility scores alone, regardless of possible interdependence with other features. The other approach employs the AdaBoost framework and hence implicitly deals with interdependence. Using two feature extraction methods and several image datasets, we experimentally confirm the significance of feature interdependence: features that perform well individually do not necessarily perform well as a group.

Original languageEnglish
Title of host publication2014 37th International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2014 - Proceedings
PublisherIEEE Computer Society Press
Pages1192-1197
Number of pages6
ISBN (Electronic)978-953-233-077-9, 978-953-233-081-6 (CD)
DOIs
Publication statusPublished - 26 May 2014
Event2014 37th International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2014 - Opatija, Croatia
Duration: 26 May 201430 May 2014

Publication series

NameInternational Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)
Volume2014

Conference

Conference2014 37th International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2014
Country/TerritoryCroatia
CityOpatija
Period26/05/1430/05/14

Keywords

  • Feature extraction
  • Training
  • Object detection
  • Visualization
  • Image segmentation
  • Detection algorithms
  • Educational institutions

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Feature selection for object detection: the best group vs. the group of best'. Together they form a unique fingerprint.

Cite this