Offline Cursive Word Recognition using Continuous Density Hidden Markov Models trained with PCA or ICA Features (2001)
Cached
Download Links
- [ftp.idiap.ch]
- [ftp.idiap.ch]
- [infoscience.epfl.ch]
- DBLP
Other Repositories/Bibliography
by
A. Vinciarelli
,
S. Bengio
| Venue: | ICA Features,” Sixth International Conference on Pattern Recognition (ICPR 2002 |
| Citations: | 8 - 3 self |
BibTeX
@INPROCEEDINGS{Vinciarelli01offlinecursive,
author = {A. Vinciarelli and S. Bengio},
title = {Offline Cursive Word Recognition using Continuous Density Hidden Markov Models trained with PCA or ICA Features},
booktitle = {ICA Features,” Sixth International Conference on Pattern Recognition (ICPR 2002},
year = {2001},
pages = {81--84}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This work presents an Offline Cursive Word Recognition System dealing with single writer samples. The system is based on a continuous density Hiddden Markov Model trained using either the raw data, or data transformed using Principal Component Analysis or Independent Component Analysis. Both techniques significantly improved the recognition rate of the system.
