Searching technique in a spectral image database

  • Authors:

  • Markku Hauta-Kasari;Kanae Miyazawa;Jussi Parkkinen;Timo Jaaskelainen

  • Affiliations:

  • Department of Computer Science, University of Joensuu, Joensuu, Finland;Department of Computer Science, University of Joensuu, Joensuu, Finland;Department of Computer Science, University of Joensuu, Joensuu, Finland;Department of Physics, University of Joensuu, Joenssu, Finland

  • Venue:
  • SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a technique for searching images from a spectral image database. In the current stage, the technique uses spectral color information. The technique is based on the Self-Organizing Map (SOM), which is used to create the Best-Matching Unit (BMU) histogrmns for every spectral image in a database. Searching program calculates BMU-histogram for the wanted spectral image, and then the histogram similarities between the wanted BMU-histogram and the BMU-histogram database are caculated. The search result is shown as images that are ordered according to the histogram similarity. The searching technique and the current, experimental results are reported.