A nonlinear training set superposition filter derived by neural network training methods for implementation in a shift-invariant optical correlator

Ioannis Kypraios; Rupert C. D. Young; Philip M. Birch; Christopher R. Chatwin

doi:10.1117/12.486334

6 August 2003 A nonlinear training set superposition filter derived by neural network training methods for implementation in a shift-invariant optical correlator

Ioannis Kypraios, Rupert C. D. Young, Philip M. Birch, Christopher R. Chatwin

Author Affiliations +

Proceedings Volume 5106, Optical Pattern Recognition XIV; (2003) https://doi.org/10.1117/12.486334
Event: AeroSense 2003, 2003, Orlando, Florida, United States

Abstract

The various types of synthetic discriminant function (sdf) filter result in a weighted linear superposition of the training set images. Neural network training procedures result in a non-linear superposition of the training set images or, effectively, a feature extraction process, which leads to better interpolation properties than achievable with the sdf filter. However, generally, shift invariance is lost since a data dependant non-linear weighting function is incorporated in the input data window. As a compromise, we train a non-linear superposition filter via neural network methods with the constraint of a linear input to allow for shift invariance. The filter can then be used in a frequency domain based optical correlator. Simulation results are presented that demonstrate the improved training set interpolation achieved by the non-linear filter as compared to a linear superposition filter.

Citation Download Citation

Ioannis Kypraios, Rupert C. D. Young, Philip M. Birch, and Christopher R. Chatwin "A nonlinear training set superposition filter derived by neural network training methods for implementation in a shift-invariant optical correlator", Proc. SPIE 5106, Optical Pattern Recognition XIV, (6 August 2003); https://doi.org/10.1117/12.486334

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available