Skip to Main content Skip to Navigation
Conference papers

BLSTM-CTC Combination Strategies for Off-line Handwriting Recognition

Luc Mioulet 1 G. Bideault 2 C. Chatelain 1 T. Paquet 2 S. Brunessaux 2
1 UNIROUEN - Université de Rouen Normandie
2 Airbus [France]
Abstract : In this paper we present several combination strategies using multiple BLSTM-CTC systems. Given several feature sets our aim is to determine which strategies are the most relevant to improve on an isolated word recognition task (the WR2 task of the ICDAR 2009 competition), using a BLSTM-CTC architecture. We explore different combination levels: early integration (feature combination), mid level combination and late fusion (output combinations). Our results show that several combinations outperform single feature BLSTM-CTCs.
Keywords : Neural Network Recurrent Neural Network Feature Combination Handwriting Recognition
Document type :
Conference papers
Complete list of metadatas
https://hal-normandie-univ.archives-ouvertes.fr/hal-02087427
Contributor : Thierry Paquet <>
Submitted on : Tuesday, April 2, 2019 - 9:45:20 AM
Last modification on : Tuesday, November 24, 2020 - 9:38:03 AM

Links full text

openaccess

Identifiers

Collections

COMUE-NORMANDIE | UNIROUEN

Citation

Luc Mioulet, G. Bideault, C. Chatelain, T. Paquet, S. Brunessaux. BLSTM-CTC Combination Strategies for Off-line Handwriting Recognition. International Conference on Pattern Recognition Applications and Methods, Jan 2015, Lisbon, France. pp.173-180, ⟨10.5220/0005178601730180⟩. ⟨hal-02087427⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

79