Foreground/background segmentation of optical character recognition (OCR) labels by a single-layer recurrent neural network

Lee F. Holeva

doi:10.1117/12.205182

6 April 1995 Foreground/background segmentation of optical character recognition (OCR) labels by a single-layer recurrent neural network

Lee F. Holeva

Author Affiliations +

Proceedings Volume 2492, Applications and Science of Artificial Neural Networks; (1995) https://doi.org/10.1117/12.205182
Event: SPIE's 1995 Symposium on OE/Aerospace Sensing and Dual Use Photonics, 1995, Orlando, FL, United States

Abstract

This paper describes the development of a recurrent neural network to segment gray scale label images into binary label images. To determine a pixel label, the neural network takes into account three sources of information: pixel intensities, correlations between neighboring labels, and edge gradients. These three sources of information are succinctly combined via the network's energy function. By changing its label state to minimize the energy function, the network satisfies constraints imposed by the input image and the current label values. To be mappable to analog hardware, it is desirable that the neural equations be deterministic. Two deterministic networks are developed and compared. The first operates at the zero temperature limit, the original Hopfield network. The second employs the mean field annealing algorithm. It is shown that with only a moderate increase in computational requirements, the mean field approach produces far superior results.

Citation Download Citation

Lee F. Holeva "Foreground/background segmentation of optical character recognition (OCR) labels by a single-layer recurrent neural network", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); https://doi.org/10.1117/12.205182

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
13 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Neural networks

Annealing

Neurons

Image segmentation

Image processing

Optical character recognition

Binary data

Show All Keywords

Keywords/Phrases

Search In:

Publication Years