@inproceedings{serrano-etal-2010-rodrigo,
title = "The {RODRIGO} Database",
author = "Serrano, Nicolas and
Castro, Francisco and
Juan, Alfons",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/477_Paper.pdf",
abstract = "Annotation of digitized pages from historical document collections is very important to research on automatic extraction of text blocks, lines, and handwriting recognition. We have recently introduced a new handwritten text database, GERMANA, which is based on a Spanish manuscript from 1891. To our knowledge, GERMANA is the first publicly available database mostly written in Spanish and comparable in size to standard databases. In this paper, we present another handwritten text database, RODRIGO, completely written in Spanish and comparable in size to GERMANA. However, RODRIGO comes from a much older manuscript, from 1545, where the typical difficult characteristics of historical documents are more evident. In particular, the writing style, which has clear Gothic influences, is significantly more complex than that of GERMANA. We also provide baseline results of handwriting recognition for reference in future studies, using standard techniques and tools for preprocessing, feature extraction, HMM-based image modelling, and language modelling.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="serrano-etal-2010-rodrigo">
<titleInfo>
<title>The RODRIGO Database</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Serrano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Castro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfons</namePart>
<namePart type="family">Juan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Annotation of digitized pages from historical document collections is very important to research on automatic extraction of text blocks, lines, and handwriting recognition. We have recently introduced a new handwritten text database, GERMANA, which is based on a Spanish manuscript from 1891. To our knowledge, GERMANA is the first publicly available database mostly written in Spanish and comparable in size to standard databases. In this paper, we present another handwritten text database, RODRIGO, completely written in Spanish and comparable in size to GERMANA. However, RODRIGO comes from a much older manuscript, from 1545, where the typical difficult characteristics of historical documents are more evident. In particular, the writing style, which has clear Gothic influences, is significantly more complex than that of GERMANA. We also provide baseline results of handwriting recognition for reference in future studies, using standard techniques and tools for preprocessing, feature extraction, HMM-based image modelling, and language modelling.</abstract>
<identifier type="citekey">serrano-etal-2010-rodrigo</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/477_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The RODRIGO Database
%A Serrano, Nicolas
%A Castro, Francisco
%A Juan, Alfons
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F serrano-etal-2010-rodrigo
%X Annotation of digitized pages from historical document collections is very important to research on automatic extraction of text blocks, lines, and handwriting recognition. We have recently introduced a new handwritten text database, GERMANA, which is based on a Spanish manuscript from 1891. To our knowledge, GERMANA is the first publicly available database mostly written in Spanish and comparable in size to standard databases. In this paper, we present another handwritten text database, RODRIGO, completely written in Spanish and comparable in size to GERMANA. However, RODRIGO comes from a much older manuscript, from 1545, where the typical difficult characteristics of historical documents are more evident. In particular, the writing style, which has clear Gothic influences, is significantly more complex than that of GERMANA. We also provide baseline results of handwriting recognition for reference in future studies, using standard techniques and tools for preprocessing, feature extraction, HMM-based image modelling, and language modelling.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/477_Paper.pdf
Markdown (Informal)
[The RODRIGO Database](http://www.lrec-conf.org/proceedings/lrec2010/pdf/477_Paper.pdf) (Serrano et al., LREC 2010)
ACL
- Nicolas Serrano, Francisco Castro, and Alfons Juan. 2010. The RODRIGO Database. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).