Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition

L. Mioulet; G. Bideault; C. Chatelain; T. Paquet; S. Brunessaux

doi:10.1117/12.2075665

8 February 2015 Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition

L. Mioulet, G. Bideault, C. Chatelain, T. Paquet, S. Brunessaux

Author Affiliations +

Proceedings Volume 9402, Document Recognition and Retrieval XXII; 94020F (2015) https://doi.org/10.1117/12.2075665
Event: SPIE/IS&T Electronic Imaging, 2015, San Francisco, California, United States

Abstract

The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term dependencies in temporal signals in order to label unsegmented data. This paper describes different ways of combining features using a BLSTM-CTC architecture. Not only do we explore the low level combination (feature space combination) but we also explore high level combination (decoding combination) and mid-level (internal system representation combination). The results are compared on the RIMES word database. Our results show that the low level combination works best, thanks to the powerful data modeling of the LSTM neurons.

Citation Download Citation

L. Mioulet, G. Bideault, C. Chatelain, T. Paquet, and S. Brunessaux "Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition", Proc. SPIE 9402, Document Recognition and Retrieval XXII, 94020F (8 February 2015); https://doi.org/10.1117/12.2075665

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