Enriching Historical Manuscripts: The Bovary Project

Nicolas, Stéphane; Paquet, Thierry

doi:10.1007/978-3-540-28640-0_13

Cited by 7 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objectives of this project are the digitization of a manuscript folder compound of almost 5,000 original manuscripts issued from "Madame Bovary" and to provide an hypertextual edition allowing an interactive and free Web access to materials. Unlike BAMBI and EUMME, Bovary contains the digitized manuscripts, which is the manuscript of Gustav Flaubert"s on Madam Bovary [10]. Bovary includes a text editor that essentially provides an editing environment that integrates document analysis with interactive tools as well as making the original manuscripts collection available amongst researchers.…”

Section: Project Initiatives Worldwidementioning

confidence: 99%

A Collaborative e-Workspace for Digital Library of Malay Manuscripts

Zulkifli¹

2014

IJIET

View full text Add to dashboard Cite

Abstract-Philology studies are often associated with traditional methods of teaching and learning. This study shows the best tools that can be implemented in order to make a collaborative work among Malay manuscripts community. The Soft System Methodology (SSM) is used to guide the investigation. The manuscript community comprises lecturers, students and researchers in the field of philology. Data were gathered from interviews, focus group discussions and observations. Academy of Malay Studies, University of Malaya is the case study setting, focusing on lecturers who teach and students who enrol in a philology course as well as doctoral students researching on manuscript studies. The findings highlight the features and modules that are available in the Malay manuscripts collaborative e-workspace in order to improve teaching, learning and researching as well as utilizing digitized manuscript surrogates held in a digital library of Malay manuscripts.Index terms-Digital library, teaching and learning Malay manuscripts, collaborative workspace, soft system methodology.

show abstract

Section: Project Initiatives Worldwidementioning

confidence: 99%

A Collaborative e-Workspace for Digital Library of Malay Manuscripts

Zulkifli¹

2014

IJIET

View full text Add to dashboard Cite

show abstract

“…Characters, especially Kana (phonetic characters made from Kanji of Chinese origin), were deformed anomalously and cursively written as shown in the following sections, so even experts have difficulty reading them. Due to the demand for preserving historical documents and availing them for research without damaging physical documents, digitization and preservation of digital reproductions have been studied and practiced in many regions and languages [1]- [6].…”

Section: Introductionmentioning

confidence: 99%

Recognition of Anomalously Deformed Kana Sequences in Japanese Historical Documents

Nguyen

et al. 2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

This paper presents recognition of anomalously deformed Kana sequences in Japanese historical documents, for which a contest was held by IEICE PRMU 2017. The contest was divided into three levels in accordance with the number of characters to be recognized: level 1: single characters, level 2: sequences of three vertically written Kana characters, and level 3: unrestricted sets of characters composed of three or more characters possibly in multiple lines. This paper focuses on the methods for levels 2 and 3 that won the contest. We basically follow the segmentationfree approach and employ the hierarchy of a Convolutional Neural Network (CNN) for feature extraction, Bidirectional Long Short-Term Memory (BLSTM) for frame prediction, and Connectionist Temporal Classification (CTC) for text recognition, which is named a Deep Convolutional Recurrent Network (DCRN). We compare the pretrained CNN approach and the end-to-end approach with more detailed variations for level 2. Then, we propose a method of vertical text line segmentation and multiple line concatenation before applying DCRN for level 3. We also examine a twodimensional BLSTM (2DBLSTM) based method for level 3. We present the evaluation of the best methods by cross validation. We achieved an accuracy of 89.10% for the three-Kana-character sequence recognition and an accuracy of 87.70% for the unrestricted Kana recognition without employing linguistic context. These results prove the performances of the proposed models on the level 2 and 3 tasks.

show abstract

“…Indeed, several research projects have been recently promoted for the purposes of preservation, storage, indexing, and on-line fruition. Interesting examples are: the MASTER project, that has developed a standard for computer-readable descriptions of medieval manuscripts in European libraries with retrieval objectives [10]; the MEMORIAL project, whose goal is the establishment of a digital document workbench enabling the creation of distributed virtual archives of typewritten documents related to prisoners in World-War II concentration camps [3]; the Bovary project, that concerns the digitalization of 5,000 original manuscripts handwritten by Gustave Flaubert [12]; the D-SCRIBE project, that aims to develop an integrated system for digitization and processing of Old Greek manuscripts [6].…”

Section: Introductionmentioning

confidence: 99%

A color-based layout analysis to process censorship cards of film archives

Berardi

Altamura

Ceci

et al. 2005

Eighth International Conference on Document Analysis and Recognition (ICDAR'05)

View full text Add to dashboard Cite

Processing censorship cards of the 20th century in order to support annotation and retrieval processes, leads to a number of challenges for many DIA systems. Problems due to the low layout quality and standard of such a material can be reduced by exploiting information conveyed by color. In this paper, taking into account lessons learned in the context of the IST project Collate, we propose a new method for image segmentation and layout analysis that takes full advantage of color information. The method has been implemented in the DIA system WISDOM++ and tested on a corpus of multiformat documents concerning historic film censorships

show abstract

Enriching Historical Manuscripts: The Bovary Project

Cited by 7 publications

References 10 publications

A Collaborative e-Workspace for Digital Library of Malay Manuscripts

A Collaborative e-Workspace for Digital Library of Malay Manuscripts

Recognition of Anomalously Deformed Kana Sequences in Japanese Historical Documents

A color-based layout analysis to process censorship cards of film archives

Contact Info

Product

Resources

About