Single-output color pattern recognition using a fractional correlator

Zeev Zalevsky*, Ido Raveh, Gal Shabtay, David Mendlovic, Javier Garcia

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

A novel method for performing color image pattern recognition using a fractional correlator (FC) is proposed. The input plane is illuminated with three different coherent sources of wavelengths corresponding to RGB (red, green, and blue) colors. The output plane provides a single output peak, which is a result of an incoherent addition between the three correlations obtained per each color. By using the fractional correlator, which is a partially space variant correlator, we achieve space-variance-controlled color pattern recognition. The use of the three-color illumination can drastically increase the discrimination ability of the suggested correlator.

Original languageEnglish
Pages (from-to)2127-2136
Number of pages10
JournalOptical Engineering
Volume36
Issue number8
DOIs
StatePublished - Aug 1997

Keywords

  • Color pattern recognition
  • Correlation
  • Fractional Fourier transform
  • Fractional correlator
  • Space-variant systems

Fingerprint

Dive into the research topics of 'Single-output color pattern recognition using a fractional correlator'. Together they form a unique fingerprint.

Cite this