Towards Effective Image Classification Using Class-Specific Codebooks and Distinctive Local Features

Altintakan U. L., YAZICI A.

IEEE TRANSACTIONS ON MULTIMEDIA, vol.17, no.3, pp.323-332, 2015 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 17 Issue: 3
  • Publication Date: 2015
  • Doi Number: 10.1109/tmm.2014.2388312
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.323-332
  • Keywords: Bag-of-words, class-specific codebooks, distinctive local features, image classification, self-organizing maps, UNIVERSAL
  • Middle East Technical University Affiliated: Yes


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.