Learning similarity space


Carkacioglu A., Vural F.

IEEE International Conference on Image Processing, New-York, United States Of America, 22 - 25 September 2002, pp.405-408 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • City: New-York
  • Country: United States Of America
  • Page Numbers: pp.405-408
  • Middle East Technical University Affiliated: No

Abstract

In this study, we suggest a method to adapt an image retrieval system into a configurable one. Basically, original feature space of a content-based retrieval system is nonlinearly transformed into a new space, where the distance between the feature vectors is adjusted by learning. The transformation is realized by Artificial Neural Network architecture. A cost function is defined for learning and optimized by simulated annealing method. Experiments are done on the texture image retrieval system, which use Gabor Filter features. The results indicate that configured image retrieval system is significantly better than the original system.