loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Third International Conference on Document Analysis and Recognition (ICDAR'95) - Volume 1
Design of a linguistic postprocessor using variable memory length Markov models
Montr?al, Canada
August 14-August 15
ISBN: 0-8186-7128-9
ASCII Text
x 
 
I. Guyon, F. Pereira, "Design of a linguistic postprocessor using variable memory length Markov models," Document Analysis and Recognition, International Conference on, vol. 1, pp. 454, Third International Conference on Document Analysis and Recognition (ICDAR'95) - Volume 1, 1995.
 
 
BibTex
x
 
@article{ 10.1109/ICDAR.1995.599034,
author = {I. Guyon and F. Pereira},
title = {Design of a linguistic postprocessor using variable memory length Markov models},
journal ={Document Analysis and Recognition, International Conference on},
volume = {1},
year = {1995},
isbn = {0-8186-7128-9},
pages = {454},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.1995.599034},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Document Analysis and Recognition, International Conference on
TI - Design of a linguistic postprocessor using variable memory length Markov models
SN - 0-8186-7128-9
SP
EP
A1 - I. Guyon,
A1 - F. Pereira,
PY - 1995
KW - finite automata; handwriting recognition; Markov processes; computational linguistics; linguistic postprocessor; variable memory length; Markov models; character recognizers; variable memory length Markov model; VLMM; finite state automata; handwriting recognition; OCR
VL - 1
JA - Document Analysis and Recognition, International Conference on
ER -
 
I. Guyon, AT&T Bell Labs., USA
F. Pereira, AT&T Bell Labs., USA
We describe a linguistic postprocessor for character recognizers. The central module of our system is a trainable variable memory length Markov model (VLMM) that predicts the next character given a variable length window of past characters. The overall system is composed of several finite state automata, including the main VLMM and a proper noun VLMM. The best model reported in the literature (Brown et al., 1992) achieves 1.75 bits per character on the Brown corpus. On that same corpus, our model, trained on 10 times less data, reaches 2.19 bits per character and is 200 times smaller (/spl sime/160,000 parameters). The model was designed for handwriting recognition applications but could also be used for other OCR problems and speech recognition.
Index Terms:
finite automata; handwriting recognition; Markov processes; computational linguistics; linguistic postprocessor; variable memory length; Markov models; character recognizers; variable memory length Markov model; VLMM; finite state automata; handwriting recognition; OCR
Citation:
I. Guyon, F. Pereira, "Design of a linguistic postprocessor using variable memory length Markov models," icdar, vol. 1, pp.454, Third International Conference on Document Analysis and Recognition (ICDAR'95) - Volume 1, 1995
Usage of this product signifies your acceptance of the Terms of Use.