Towards effective image classification using class-specific codebooks and distinctive local features

Umit Lutfu Altintakan, Adnan Yazici

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)

Abstract

Local image features, which are robust to scale, view, and orientation changes in images, play a key factor in developing effective visual classification systems. However, there are two main limitations to exploit these features in image classification problems: 1) a large number of key-points are located during the feature detection process, and 2) most of the key-points arise in background regions, which do not contribute to the classification process. In order to decrease the inverse effects of these limitations, we propose a new codebook generation approach through employing a new clustering method that generates class-specific codebooks along with a novel feature selection method in the bag-of-words model. We evaluate the performance of different classification techniques including Naive Bayesian, k-NN, and SVM on distinctive features. Experiments conducted on PASCAL Visual Object Classification collections have shown that the class-specific codebooks along with distinctive image features can significantly improve the classification performances.

Original languageEnglish
Article number7001714
Pages (from-to)323-332
Number of pages10
JournalIEEE Transactions on Multimedia
Volume17
Issue number3
DOIs
Publication statusPublished - Mar 1 2015

Keywords

  • Bag-of-words
  • class-specific codebooks
  • distinctive local features
  • image classification
  • self-organizing maps

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Towards effective image classification using class-specific codebooks and distinctive local features'. Together they form a unique fingerprint.

Cite this