Dual template optical correlator for pattern recognition

Freddie Yun Heng Chin; Michael G. Somekh; M. S. Valera; John A. Crowe

doi:10.1117/12.60191

1 August 1992 Dual template optical correlator for pattern recognition

Freddie Yun Heng Chin, Michael G. Somekh, M. S. Valera, John A. Crowe

Author Affiliations +

Proceedings Volume 1647, Holography, Interferometry, and Optical Pattern Recognition in Biomedicine II; (1992) https://doi.org/10.1117/12.60191
Event: OE/LASE '92, 1992, Los Angeles, CA, United States

Abstract

A new coherent optical correlator system has been developed for intended application to breast cancer screening. Such a system must have an inherent capability to deal with patterns that have high degrees of similarity between the desired and rejected classes, due to the overall similarity between benign and malignant cells. Consequently, effort has been directed toward achieving this goal. This paper presents an optical configuration that contains two coherent optical processors (COPs) working in parallel and utilizes phase-stepping detection at the output to multiply the two correlation signals. It is shown how this scheme offers an excellent compromise between good discrimination and immunity from noise added in the input plane

Citation Download Citation

Freddie Yun Heng Chin, Michael G. Somekh, M. S. Valera, and John A. Crowe "Dual template optical correlator for pattern recognition", Proc. SPIE 1647, Holography, Interferometry, and Optical Pattern Recognition in Biomedicine II, (1 August 1992); https://doi.org/10.1117/12.60191

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