Keybook: unbias object recognition using keywords

Wai Lam Hoo, Chern Hong Lim, Chee Seng Chan

Research output: Contribution to journalArticleResearchpeer-review

4 Citations (Scopus)

Abstract

The presence of bias in existing object recognition datasets is now a well-known problem in the computer vision community. In this paper, we proposed an improved codebook representation in the Bag-of-Words (BoW) approach by generating Keybook. In specific, our Keybook is composed from the keywords that significantly represent the object classes. It is extracted utilizing the concept of mutual information. The intuition is to perform feature selection by maximize the mutual information of the features between the object classes; while minimize the mutual information of the features between the domains. With this, the Keybook will not bias to any of the domain and consists of valuable keywords among the object classes. The proposed method is tested on four public datasets to evaluate the classification performance in seen and unseen datasets. Experiment results have showed the effectiveness of our proposed methods in undo the dataset bias problem.

Original languageEnglish
Pages (from-to)3991-3999
Number of pages9
JournalExpert Systems with Applications
Volume42
Issue number8
DOIs
Publication statusPublished - 15 May 2015
Externally publishedYes

Keywords

  • Bag-of-Words model
  • Codebook generation
  • Dataset bias
  • Object recognition

Cite this