Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Rotation invariant detection in a noisy environment using wavelet based joint transform correlator
 

Summary: Rotation invariant detection in a noisy environment using wavelet
based joint transform correlator
Farid Ahmed, M. S. Alamt and M. A. Karim
University of Dayton
Department of Electrical Engineering and Center for Electro-Optics
Dayton, OH 45469-0245
tDepartment of Engineering
Purdue University at Fort Wayne, Fort Wayne, IN 46805-1499
AB STRACT
Wavelet based Joint transform correlator (JTC) for rotation invariant automatic target detection is proposed
in this paper. Wavelet features of a set of rotationally distorted training images are first extracted at different
levels of resolution. A simple composite filter formulation is then employed to construct the reference image of
the JTC. Simulation results are presented showing the improved rotation-invariant detection performance of the
proposed technique.
Keywords: joint transform correlator, rotation invariant detection, wavelet feature, filter modulation, com-
posite reference image
1 INTRODUCTION
Rotation invariant detection is addressed in literature primarily in two different ways. The first approach uses
geometric invariance properties in the filter formulation.13 In these works, circular harmonic filter expansion for
rotation invariance has been used. The main difficulty with this method is the proper choice of the harmonic

  

Source: Ahmed, Farid - Department of Electrical Engineering and Computer Science, Catholic University of America

 

Collections: Engineering