Wavelet-transform-based composite filters for invariant pattern recognition

Zeev Zalevsky, Ido Ouzieli, David Mendlovic

Research output: Contribution to journalArticlepeer-review

Abstract

A wavelet-transformation-based optical processor for performing invariant pattern recognition is suggested. It contains a composite filter that consists of several wavelet daughter functions derived from the reference object. The intensity of the correlation peak is determined to be invariant to various deformations of the reference object. Computer simulations show explicitly the promising capability of the new technique. Laboratory experimental results are given.

Original languageEnglish
Pages (from-to)3141-3147
Number of pages7
JournalApplied Optics
Volume35
Issue number17
DOIs
StatePublished - 10 Jun 1996

Fingerprint

Dive into the research topics of 'Wavelet-transform-based composite filters for invariant pattern recognition'. Together they form a unique fingerprint.

Cite this