2014
DOI: 10.1016/j.patcog.2013.10.020
|View full text |Cite
|
Sign up to set email alerts
|

Neural network language models for off-line handwriting recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
29
1
2

Year Published

2015
2015
2023
2023

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 62 publications
(32 citation statements)
references
References 31 publications
0
29
1
2
Order By: Relevance
“…For handwriting recognition, a high word recognition rate of 94.85 % [69] is reported on the RIMES database. The recognition rates on the IAM database vary [215,216]. These recognition rates, in general, are lower than those reported on the RIMES database.…”
Section: Experimental Protocols Evaluation Metrics and State-of-the-contrasting
confidence: 54%
“…For handwriting recognition, a high word recognition rate of 94.85 % [69] is reported on the RIMES database. The recognition rates on the IAM database vary [215,216]. These recognition rates, in general, are lower than those reported on the RIMES database.…”
Section: Experimental Protocols Evaluation Metrics and State-of-the-contrasting
confidence: 54%
“…Nevertheless, part of its success relied on a brilliant text line pre-processing. Indeed, the pre-processed lines have been recognized by other recognition engines, generally, improving their results [F. Zamora-Martínez, Frinken, et al 2014]. The TLN methods followed by this system were based on detecting the text reference lines and then scale the parts of the text to a fixed size.…”
Section: Text Line Normalizationmentioning
confidence: 99%
“…The reference lines from a subset of 773 text line images from the training data of the IAM database have been manually labeled using a bootstrapping approach and interactive tools, as described and used in [Espana-Boquera et al 2011;Pastor-Pellicer, España-Boquera, P. Zamora-Martínez, et al 2014;F. Zamora-Martínez, Frinken, et al 2014].…”
Section: C31 Interest Points Text Reference Lines and Mba Ground Tmentioning
confidence: 99%
See 1 more Smart Citation
“…Este capítulo estudia el impacto del uso de NN LMs dentro de este campo. De hecho, hemos sido los primeros en usar NN LMs en tareas de HTR España-Boquera et al, 2011;Frinken et al, 2012;Zamora-Martínez et al, 2012c].…”
Section: Introductionunclassified