Share Email Print

Proceedings Paper

Recognition of Equations Using a Two-Dimensional Stochastic Context-Free Grammar
Author(s): P. A. Chou
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We propose using two-dimensional stochastic context-free grammars for image recognition, in a manner analogous to using hidden Markov models for speech recognition. The value of the approach is demonstrated in a system that recognizes printed, noisy equations. The system uses a two-dimensional probabilistic version of the Cocke-Younger-Kasami parsing algorithm to find the most likely parse of the observed image, and then traverses the corresponding parse tree in accordance with translation formats associated with each production rule, to produce eqn I troff commands for the imaged equation. In addition, it uses two-dimensional versions of the Inside/Outside and Baum re-estimation algorithms for learning the parameters of the grammar from a training set of examples. Parsing the image of a simple noisy equation currently takes about one second of cpu time on an Alliant FX/80.

Paper Details

Date Published: 1 November 1989
PDF: 14 pages
Proc. SPIE 1199, Visual Communications and Image Processing IV, (1 November 1989); doi: 10.1117/12.970095
Show Author Affiliations
P. A. Chou, AT&T Bell Laboratories (United States)

Published in SPIE Proceedings Vol. 1199:
Visual Communications and Image Processing IV
William A. Pearlman, Editor(s)

© SPIE. Terms of Use
Back to Top