Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Artificial Neural Networks for FrequencyDomain Pattern Recognition \Lambda Fernando C'esar C. De Castro
 

Summary: Artificial Neural Networks for Frequency­Domain Pattern Recognition \Lambda
Fernando C'esar C. De Castro
decastro@ee.pucrs.br
Jos'e Nelson Amaral
amaral@ee.pucrs.br
http://pegasus.ece.utexas.edu/~nelson/
Paulo Roberto G. Franco
pfranco@ee.pucrs.br
Electrical Engineering Department
Pontif'icia Universidade Cat'olica do Rio Grande do Sul
90619­900 ­ Porto Alegre ­ RS ­ Brazil
Abstract
Artificial Neural Networks (ANN) are used to detect
a pattern in a two dimensional gray­level image us­
ing a new method that not only recognizes a pattern
but also determines its translation, scaling and rota­
tion. Recognition is performed through spectral cor­
relation between a given reference pattern and the
input image. Images in the spatial domain are con­
verted to the spectral domain by means of a two di­

  

Source: Amaral, José Nelson - Department of Computing Science, University of Alberta

 

Collections: Computer Technologies and Information Sciences