Enhancement of optical correlation system performance utilizing a neural-network-based preprocessor filter

Steve T. Kacenjar; H. Chen; D. Tong; T. Rimlinger; J. Blike

doi:10.1117/12.19591

1 July 1990 Enhancement of optical correlation system performance utilizing a neural-network-based preprocessor filter

Steve T. Kacenjar, H. Chen, D. Tong, T. Rimlinger, J. Blike

Proceedings Volume 1246, Parallel Architectures for Image Processing; (1990) https://doi.org/10.1117/12.19591
Event: Electronic Imaging: Advanced Devices and Systems, 1990, Santa Clara, CA, United States

Abstract

Map annotations (such as lettering) normally degrade automatic map-to-image optical correlation system performance which when removed, improves both the SNR and accuracy of such systems when generating conjugate data point pairs between the two optical formats. This paper describes improvements to the map-to-image correlation that results when an annotation removal preprocessor filter is applied first to map data. Specifically, the paper describes the impact of implementing a neural network annotation filter on the performance of map-to-image optical correlation systems. This new filter is capable of automatically identifying and then removing annotations before performing the optical correlation. As shown, this removal process impacts the correlation SNR and phase-only filtering systems. Greatest improvement in system performance is achieved when the annotation filter is applied first to map data before implementing a binary, phase-only filtering process.

Citation Download Citation

Steve T. Kacenjar, H. Chen, D. Tong, T. Rimlinger, and J. Blike "Enhancement of optical correlation system performance utilizing a neural-network-based preprocessor filter", Proc. SPIE 1246, Parallel Architectures for Image Processing, (1 July 1990); https://doi.org/10.1117/12.19591

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