Share Email Print

Proceedings Paper

Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition
Author(s): L. Mioulet; G. Bideault; C. Chatelain; T. Paquet; S. Brunessaux
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 8 February 2015
PDF: 11 pages
Proc. SPIE 9402, Document Recognition and Retrieval XXII, 94020F (8 February 2015); doi: 10.1117/12.2075665
Show Author Affiliations
L. Mioulet, Univ. de Rouen (France)
Airbus Defense and Space (France)
G. Bideault, Univ. de Rouen (France)
C. Chatelain, Institut National des Sciences Appliquées de Rouen (France)
T. Paquet, Univ. de Rouen (France)
S. Brunessaux, Airbus Defense and Safety (France)

Published in SPIE Proceedings Vol. 9402:
Document Recognition and Retrieval XXII
Eric K. Ringger; Bart Lamiroy, Editor(s)

© SPIE. Terms of Use
Back to Top