Image annotation using clickthrough data

  • Authors:

  • Theodora Tsikrika;Christos Diou;Arjen P. de Vries;Anastasios Delopoulos

  • Affiliations:

  • CWI, Amsterdam, The Netherlands;Aristotle University of Thessaloniki, Greece and Informatics and Telematics Institute, Hellas;CWI, Amsterdam, The Netherlands and Delft University of Technology, Delft, The Netherlands;Aristotle University of Thessaloniki, Greece and Informatics and Telematics Institute, Hellas

  • Venue:
  • Proceedings of the ACM International Conference on Image and Video Retrieval
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Automatic image annotation using supervised learning is performed by concept classifiers trained on labelled example images. This work proposes the use of clickthrough data collected from search logs as a source for the automatic generation of concept training data, thus avoiding the expensive manual annotation effort. We investigate and evaluate this approach using a collection of 97,628 photographic images. The results indicate that the contribution of search log based training data is positive; in particular, the combination of manual and automatically generated training data outperforms the use of manual data alone. It is therefore possible to use clickthrough data to perform large-scale image annotation with little manual annotation effort or, depending on performance, using only the automatically generated training data. The datasets used as well as an extensive presentation of the experimental results can be accessed at http://olympus.ee.auth.gr/~diou/civr2009/.