loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2008 The Eighth IAPR International Workshop on Document Analysis Systems
End-to-End Trainable Thai OCR System Using Hidden Markov Models
September 16-September 19
ISBN: 978-0-7695-3337-7
ASCII Text
x 
 
Kriste Krstovski, Ehry MacRostie, Rohit Prasad, Premkumar Natarajan, "End-to-End Trainable Thai OCR System Using Hidden Markov Models," Document Analysis Systems, IAPR International Workshop on, pp. 607-614, 2008 The Eighth IAPR International Workshop on Document Analysis Systems, 2008.
 
 
BibTex
x
 
@article{ 10.1109/DAS.2008.76,
author = {Kriste Krstovski and Ehry MacRostie and Rohit Prasad and Premkumar Natarajan},
title = {End-to-End Trainable Thai OCR System Using Hidden Markov Models},
journal ={Document Analysis Systems, IAPR International Workshop on},
volume = {0},
year = {2008},
isbn = {978-0-7695-3337-7},
pages = {607-614},
doi = {http://doi.ieeecomputersociety.org/10.1109/DAS.2008.76},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Document Analysis Systems, IAPR International Workshop on
TI - End-to-End Trainable Thai OCR System Using Hidden Markov Models
SN - 978-0-7695-3337-7
SP607
EP614
A1 - Kriste Krstovski,
A1 - Ehry MacRostie,
A1 - Rohit Prasad,
A1 - Premkumar Natarajan,
PY - 2008
KW - OCR
KW - Thai
KW - HHM
KW - script-independent
KW - integrated workflow
KW - end-to-end
KW - annotation
KW - transcription
KW - training
KW - document images
KW - Thai script
VL - 0
JA - Document Analysis Systems, IAPR International Workshop on
ER -
 
In this paper we present an end-to-end trainable Optical Character Recognition (OCR) system for recognizing machine-printed text in Thai documents. The end-to-end OCR system is based on a script-independent methodology using hidden Markov models. Our system provides an integrated workflow beginning with annotation and transcription of training images to performing OCR on new images with models trained on transcribed training images. The efficacy of our end-to-end OCR system is demonstrated by rapidly configuring our OCR engine for the Thai script. We present experimental results on Thai documents to highlight the specific challenges posed by the Thai script and analyze the recognition performance as a function of amount of training data.
Index Terms:
OCR, Thai, HHM, script-independent, integrated workflow, end-to-end, annotation, transcription, training, document images, Thai script
Citation:
Kriste Krstovski, Ehry MacRostie, Rohit Prasad, Premkumar Natarajan, "End-to-End Trainable Thai OCR System Using Hidden Markov Models," das, pp.607-614, 2008 The Eighth IAPR International Workshop on Document Analysis Systems, 2008
Usage of this product signifies your acceptance of the Terms of Use.