Shift-invariant optoelectronic associative memory by using a cascade of correlators

Rafal Kasztelanic; Juan Campos; Katarzyna Chalasinska-Macukow

doi:10.1117/1.602454

1 April 2000 Shift-invariant optoelectronic associative memory by using a cascade of correlators

Rafal Kasztelanic, Juan Campos, Katarzyna Chalasinska-Macukow

Optical Engineering, Vol. 39, Issue 4, (April 2000). https://doi.org/10.1117/1.602454

We present a shift-invariant optoelectronic associative memory (OAM) which is realized in a cascade of correlators. The starting point is the OAM architecture proposed in 1995. Its crucial modification, which we propose, consists in the codification of each class of objects on the recognition filter by different carrier frequencies. This ensures the proper work of the system regardless of the location of the pattern in the input scene. As a result of such a filter design an additional intermediate layer has to be introduced into the OAM between the thresholder and reconstruction layer. We present a description and analysis of all elements of the modified OAM, with special regards to these subsystems (layers) which are particularly valid for the shift-invariant recognition and reconstruction. The final results of digital analysis of the behavior of the shift-invariant OAM are included.

Citation Download Citation

Rafal Kasztelanic, Juan Campos, and Katarzyna Chalasinska-Macukow "Shift-invariant optoelectronic associative memory by using a cascade of correlators," Optical Engineering 39(4), (1 April 2000). https://doi.org/10.1117/1.602454

Published: 1 April 2000

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