Class-associative pattern recognition using joint transform correlation

Mohammad S. Alam

doi:10.1117/12.456550

20 November 2002 Class-associative pattern recognition using joint transform correlation

Mohammad S. Alam

Proceedings Volume 4803, Photorefractive Fiber and Crystal Devices: Materials, Optical Properties, and Applications VIII; (2002) https://doi.org/10.1117/12.456550
Event: International Symposium on Optical Science and Technology, 2002, Seattle, WA, United States

Abstract

In this paper, we investigate the latest advancements in real time pattern recognition using the joint transform correlator (JTC) architectures and algorithms. We propose two class associative correlation filters to detect a class of objects consisting of dissimilar patterns. For enhanced performance, both phase and amplitude information is incorporated in the class detection filters. To suppress undesired crosscorrelation between selected objects a new algorithm is introduced. In addition fringe-adjusted joint transform correlation is utilized to enhance the correlation performance, thus ensuring strong and equal correlation peak for each element of the selected class. The feasibility of the proposed technique has been tested by computer simulation.

Citation Download Citation

Mohammad S. Alam "Class-associative pattern recognition using joint transform correlation", Proc. SPIE 4803, Photorefractive Fiber and Crystal Devices: Materials, Optical Properties, and Applications VIII, (20 November 2002); https://doi.org/10.1117/12.456550

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