A hybrid supervised-unsupervised vocabulary generation algorithm for visual concept recognition

  • Authors:

  • Alexander Binder;Wojciech Wojcikiewicz;Christina Müller;Motoaki Kawanabe

  • Affiliations:

  • Berlin Institute of Technology, Berlin, Germany;Berlin Institute of Technology, Berlin, Germany and Fraunhofer Institute FIRST, Berlin, Germany;Berlin Institute of Technology, Berlin, Germany and Fraunhofer Institute FIRST, Berlin, Germany;Berlin Institute of Technology, Berlin, Germany and Fraunhofer Institute FIRST, Berlin, Germany

  • Venue:
  • ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Vocabulary generation is the essential step in the bag-ofwords image representation for visual concept recognition, because its quality affects classification performance substantially. In this paper, we propose a hybrid method for visual word generation which combines unsupervised density-based clustering with the discriminative power of fast support vector machines. We aim at three goals: breaking the vocabulary generation algorithm up into two sections, with one highly parallelizable part, reducing computation times for bag of words features and keeping concept recognition performance at levels comparable to vanilla k-means clustering. On the two recent data sets Pascal VOC2009 and Image- CLEF2010 PhotoAnnotation, our proposed method either outperforms various baseline algorithms for visual word generation with almost same computation time or reduces training/test time with on par classification performance.