Handwritten Text Recognition for Marriage Register Books

Romero, Verónica; ́nchez, Joan Andreu S; Serrano, Nicolás; Vidal, Enrique

doi:10.1109/icdar.2011.113

Cited by 6 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, given the simple and regular syntactic structure of the lines, a fixed, prior grammar that restricts the search space in a more effective way than bi-grams seems to be promising as well. Such kind of simple language model has been recently used with good results in [29]. The obtained results suggest that, using prior knowledge, a higher recognition accuracy can be obtained.…”

Section: Discussion Of Resultsmentioning

confidence: 65%

See 1 more Smart Citation

The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition

Romero

Fornés

Serrano

et al. 2013

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Historical records of daily activities provide intriguing insights into the life of our ancestors, useful for demography studies and genealogical research. Automatic processing of historical documents, however, has mostly been focused on single works of literature and less on social records, which tend to have a distinct layout, structure, and vocabulary. Such information is usually collected by expert demographers that devote a lot of time to manually transcribe them. To support research in automatic handwriting recognition for historical documents containing social records, this paper presents a new database compiled from a marriage license books collection. Marriage license books are documents that were used for centuries by ecclesiastical institutions to register marriage licenses. Books from this collection are handwritten and span nearly half a millennium until the beginning of the 20th century. In addition, a study is presented about the capability of state-of-the-art handwritten text recognition systems, when applied to the presented database. Baseline results are reported for reference in future studies.

show abstract

Section: Discussion Of Resultsmentioning

confidence: 65%

“…As far as recognition technologies are concerned, we plan to follow the ideas previously developed in [29] and study the integration of prior knowledge by taking advantage of the regular structure of the script.…”

Section: Discussionmentioning

confidence: 99%

The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition

Romero

Fornés

Serrano

et al. 2013

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, an HTR experiment was reported in [2] in which an n-gram model was used as language model, and the Word Error Rate (WER) for that experiment was 31.1% (see Table 6 in [2]). The same experiment with an improved language model for the same task provided a WER of 28.6% (see Section IV.C in [1]). …”

Section: Introductionmentioning

confidence: 85%

“…The recent advances in HTR have made possible to tackle the transcription of document collections that were not considered in the past like the marriage license books that are considered in this paper [1], [2]. This type of documents contain relevant semantic information that is very interesting for migratory studies, population research and genealogical investigation [3].…”

Section: Introductionmentioning

confidence: 98%

Category-Based Language Models for Handwriting Recognition of Marriage License Books

Romero¹,

Lafuente²

2013

2013 12th International Conference on Document Analysis and Recognition

Self Cite

View full text Add to dashboard Cite

Handwritten marriage licenses books have been used for centuries by ecclesiastical institutions to register marriages. These documents have interesting information, useful for demography studies, organized in a list of individual marriage license records, such as an accounting book. The information in these books is usually collected by expert demographers that devote a lot of time to transcribe them. Despite the structure of the text, the automatic transcription and semantic information extraction of these documents is quite difficult due to the distinct and evolutionary vocabulary, which is composed mainly of proper names that change along the time. In this paper, we have defined some categories taking into account the semantic information included in the licenses. Then a category-based language model has been generated and integrated into the handwritten text recognition system. We study how the use of these categories can benefit not only the handwriting recognition step, but also the posterior semantic information extraction and knowledge discovery.

show abstract

“…La experiencia acumulada por los autores de este trabajo nos quiere poner de manifiesto, que la enseñanza problematizada y modelizada (Romero, 2000) de las matemáticas nos permite hacer realidad, y estamos convencidos de ello, que existe un proceso de modelización detrás de todo modelo matemático (De Lange et al, 1993;Romero, 2011). Esto significa que debemos de manera implícita o explícita inculcar, a nuestros estudiantes, la idea de recorrer el proceso entre la situación real y la idea matematizada, y viceversa.…”

Section: Conclusionesunclassified

La resolución de problemas como instrumentos para la modelización matemática:Ejemplos para la vida real

Sánchez¹,

Rodríguez²,

Benítez³

et al. 2015

Model. sci. educ. learn.

View full text Add to dashboard Cite

No hace muchos años que los investigadores en Educación Matemática han centrado su atención en el diseño de actividades basado en la modelización matemática de situaciones reales con el convencimiento de obtener una mayor garantía en la ganancia, por parte de nuestros alumnos, del aprendizaje matemático, y por ende en la enseñanza por parte de los enseñantes. El trabajo que presentamos, en el contexto del CURSO DE VERANO-2014-Matemáticas a lo largo de la vida, en las IV Jornadas de Modelización Matemática, pretende utilizar la Resolución de Problemas (RdP's) como un instrumentoútil y necesario para llegar al concepto de Modelización Matemática.Not many years ago that researchers in mathematics education have focused on designing activities based on mathematical modelling of real situations with the conviction to get a better guarantee on profit, by our students, the mathematical learning, and thus teaching by the teachers. The work presented in the context of the SUMMER-2014-Mathematics throughout life, in the Fourth Conference on Mathematical Modelling, intends to use the Problem Solving (PS) as a useful and necessary tool to reach the concept of Mathematical Modelling.

show abstract

Handwritten Text Recognition for Marriage Register Books

Cited by 6 publications

References 12 publications

The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition

The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition

Category-Based Language Models for Handwriting Recognition of Marriage License Books

La resolución de problemas como instrumentos para la modelización matemática:Ejemplos para la vida real

Contact Info

Product

Resources

About