Invariant pattern-recognition filter based on the wavelet transform

Zeev Zalevsky*, David Mendlovic, Carlos Ferreira

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

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 languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
EditorsDaniel Malacara-Hernandez, Sofia E. Acosta, Ramon Rodriguez-Vera, Zacarias Malacara, Arquimedes A. Morales
Pages275-283
Number of pages9
StatePublished - 1996
EventSecond Iberoamerican Meeting on Optics - Guanajuato, Mex
Duration: 18 Sep 199522 Sep 1995

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume2730
ISSN (Print)0277-786X

Conference

ConferenceSecond Iberoamerican Meeting on Optics
CityGuanajuato, Mex
Period18/09/9522/09/95

Fingerprint

Dive into the research topics of 'Invariant pattern-recognition filter based on the wavelet transform'. Together they form a unique fingerprint.

Cite this