Comparison of feature sets using multimedia translation

Duygulu P., Ozcanli O., Papernick N.

COMPUTER AND INFORMATION SCIENCES - ISCIS 2003, vol.2869, pp.513-520, 2003 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 2869
  • Publication Date: 2003
  • Journal Name: COMPUTER AND INFORMATION SCIENCES - ISCIS 2003
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, EMBASE, MathSciNet, Philosopher's Index, zbMATH
  • Page Numbers: pp.513-520
  • Middle East Technical University Affiliated: No

Abstract

Feature selection is very important for many computer vision applications. However, it is hard to find a good measure for the comparison. In this study, feature sets are compared using the translation model of object recognition which is motivated by the availablity of large annotated data sets. Image regions are linked to words using a model which is inspired by machine translation. Word prediction performance is used to evaluate large numbers of images.