Design and evaluation of three-level composite filters obtained by optimizing a compromise average performance measure

Charles D. Hendrix; Bhagavatula Vijaya Kumar

doi:10.1117/12.170734

1 June 1994 Design and evaluation of three-level composite filters obtained by optimizing a compromise average performance measure

Charles D. Hendrix, Bhagavatula Vijaya Kumar

Author Affiliations +

Optical Engineering, Vol. 33, Issue 6, (June 1994). https://doi.org/10.1117/12.170734

Abstract

Correlation filters with three transmittance levels ( +1 , 0, and -1) are of interest in optical pattern recognition because they can be implemented on available spatial light modulators and because the zero level allows us to include a region of support (ROS). The ROS can provide additional control over the filter's noise tolerance and peak sharpness. A new algorithm based on optimizing a compromise average performance measure (CAPM) is proposed for designing three-level composite filters. The performance of this algorithm is compared to other three-level composite filter designs using a common image database and using figures of merit such as the Fisher ratio, error rate, and light efficiency. It is shown that the CAPM algorithm yields better results.

Citation Download Citation

Charles D. Hendrix and Bhagavatula Vijaya Kumar "Design and evaluation of three-level composite filters obtained by optimizing a compromise average performance measure," Optical Engineering 33(6), (1 June 1994). https://doi.org/10.1117/12.170734

Published: 1 June 1994

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