A fast technique for recursive scene matching using pyramids

  • Authors:
  • V.V Alexandrov;N.D Gorsky;S.N Mysko

  • Affiliations:
  • Leningrad Research Computer Centre of the USSR Academy of Sciences, 199164, USSR;Leningrad Research Computer Centre of the USSR Academy of Sciences, 199164, USSR;Leningrad Research Computer Centre of the USSR Academy of Sciences, 199164, USSR

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 1985

Quantified Score

Hi-index 0.10

Visualization

Abstract

An algorithm of a fast correlation technique for scene matching using pyramidal image representation is introduced. A mathematical model of the image registration process based on the pyramidal representation of a separable Markov random field is considered in order to evaluate threshold sequence for the algorithm. Experimental results are presented for matching images, both free of noise and corrupted by noise. Theoretical and experimental results given in the paper show that computational efficiency in scene matching could be improved in three orders of magnitude comparatively to the traditional correlation technique.