Invariant Pattern Recognition Filter based on the Wavelet Transform

Z. Zalevsky, David Mendlovic, Carlos Ferreira

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-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 ability of the new technique.
Original languageAmerican English
Title of host publicationSecond Iberoamerican Meeting on Optics. International Society for Optics and Photonics
PublisherSPIE
StatePublished - 1996

Bibliographical note

Place of conference:Mexico

Fingerprint

Dive into the research topics of 'Invariant Pattern Recognition Filter based on the Wavelet Transform'. Together they form a unique fingerprint.

Cite this