Skip to main content
European Commission logo
français français
CORDIS - Résultats de la recherche de l’UE
CORDIS
CORDIS Web 30th anniversary CORDIS Web 30th anniversary

Recognition and Enrichment of Archival Documents

Livrables

Finland - Layout Analysis and Crowd-Sourcing P1

Finland - Layout Analysis and Crowd-Sourcing

ScriptNet Large Scale Dataset P3

Collecting and making available of a large scale datasets to the research community. Final version

Document Understanding Tools P2

A toolkit for the automated annotation of document features. Updated version

Table and Form Analysis Tools P3

A toolkit for forms and table processing. Final version

Passau - Keyword Spotting in Registry Books P3

Passau - Keyword Spotting in Registry Books

Page Image Explorer P3

An search interface based on layout features of documents. Final version

Binarisation and Image Enhancement Tools P1

A toolkit for postprocessing and enhancing images in order to support all other processes in the workflow (LA, HTR, Writer Identification, etc.). Protoype version

Finland - Layout Analysis and Crowd-Sourcing P3

Finland - Layout Analysis and Crowd-Sourcing

Table and Form Analysis Tools P1

A toolkit for forms and table processing. Prototype version

Page Image Explorer P1

A search interface based on layout features of documents. Protoype version

Document Understanding Tools P3

A toolkit for the automated annotation of document features. Final version

Finland - Layout Analysis and Crowd-Sourcing P2

Finland - Layout Analysis and Crowd-Sourcing

HTR Engine Based on NNs P2

A toolkit for HTR processing based on NN models. Updated version

READ Platform P1

Implementation and maintenance of the READ platform including service and tool integration. Report for reporting period 1

Binarisation and Image Enhancement Tools P3

A toolkit for postprocessing and enhancing images in order to support all other processes in the workflow (LA, HTR, Writer Identification, etc.). Final version

Mobile Crowd-Sorcung Tools P1

Development and Implementation of mobile Crowd-Sourcing Tools. Protoype version

E-Learning Application P1

Development and Implementation of an E-Learning Application. Protoype version

Model for semi and Unsupervised HTR Training P2

A toolkit for enhanced training methods of the two HTR engines based on large amounts of images and text which are just loosly connected. Updated version

Language Toolkit and Resources P2

Implementation of the language toolkit and collecting and processing of language resources. Final version

Language Toolkit and Resources P1

Implementation of the language toolkit and collecting and processing of language resources. Protoype version

Basic Layout Analysis Tools P1

A toolkit for the layout analysis of historical documents including text and image detection. Protoype version

Line and Word Segmentation Tools P3

A toolkit for segmenting lines and words in order to support HTR and KWS. Final version

Writer Identification and Retrieval Tool P2

A toolkit for identifying different hands and clustering similar hands (writers) in historical documents. Updated version

Zurich - Evaluation and Bootstrapping P1

Zurich - Evaluation and Bootstrapping

HTR Engine Based on HMMs P2

A toolkit for HTR processing based on HMM models. Updated version

Model for semi and Unsupervised HTR Training P3

A toolkit for enhanced training methods of the two HTR engines based on large amounts of images and text which are just loosly connected. Final version

Venice Time Machine – Meta-learning Model P3

Venice Time Machine – Meta-learning Model

Service and Tool Integration P1

Integration of services and tools into READ platform. Report for reporting period 1

Binarisation and Image Enhancement Tools P2

A toolkit for postprocessing and enhancing images in order to support all other processes in the workflow (LA, HTR, Writer Identification, etc.). Updated version

Writer Identification and Retrieval Tool P1

A toolkit for identifying different hands and clustering similar hands (writers) in historical documents. Prototype version

Basic Layout Analysis Tools P2

A toolkit for the layout analysis of historical documents including text and image detection. Updated version

HTR Engine Based on NNs P1

A toolkit for HTR processing based on NN models. Prototype version

ScanREAD

An application which enables users to use their mobile phone as a document scanner and to upload images directly to the READ Platform. Final version

Service and Tool Integration P3

Integration of services and tools into READ platform. Report for reporting period 1

Document Understanding Tools P1

A toolkit for the automated annotation of document features. Prototype version

Transcribe Bentham P3

Implementation and maintenance of the transcribe Bentham collection. Report for reporting period 3

Page Image Explorer P2

A search interface based on layout features of documents. Updated version

HTR Engine Based on NNs P3

A toolkit for HTR processing based on NN models. Final version

Interactive Predictive Transcription Engine P2

A toolkit for the interactive transcription of handwritten documents. Updated version

Language models P3

A toolkit for enhancing language data for HTR processing. Final version

Line and Word Segmentation Tools P1

A toolkit for segmenting lines and words in order to support HTR and KWS. Prototype version

Transcribe Bentham P1

Implementation and maintenance of the transcribe Bentham collection. Report for reporting period 1

Basic Layout Analysis Tools P3

A toolkit for the layout analysis of historical documents including text and image detection. Final version

Writer Identification and Retrieval Tool P3

A toolkit for identifying different hands and clustering similar hands (writers) in historical documents. Final version

Line and Word Segmentation Tools P2

A toolkit for segmenting lines and words in order to support HTR and KWS. Updated version

Model for semi and Unsupervised HTR Training P1

A toolkit for enhanced training methods of the two HTR engines based on large amounts of images and text which are just loosly connected. Prototype version

Interactive Predictive Transcription Engine P1

A toolkit for the interactive transcription of handwritten documents. Prototype version

Table and Form Analysis Tools P2

A toolkit for forms and table processing. Updated version

Mobile Crowd-Sourcing Tools P2

Development and Implementation of mobile Crowd-Sourcing Tools. Updated version

HPC Integration

Integration of the High Performance Computing Cluster

ScriptNet Large Scale Dataset P2

Collecting and making available of a large scale datasets to the research community. Updated version

Zurich - Evaluation and Bootstrapping P2

Zurich - Evaluation and Bootstrapping

Interactive Predictive Transcription Engine P3

A toolkit for the interactive transcription of handwritten documents. Final version

Venice Time Machine – Meta-learning Model P2

Venice Time Machine – Meta-learning Model

Keyword Spotting Engines: QbE, QbS P3

Toolkits for indexing and searching handwritten documents without prior recognition of the actual text. Final version

HTR Engine Based on HMMs P1

A toolkit for HTR processing based on HMM models. Prototpye version

Language Models P2

A toolkit for enhancing language data for HTR processing. Updated version

Service and Tool Integration P2

Integration of services and tools into READ platform. Report for reporting period 2

E-Learning Application P2

Development and Implementation of an E-Learning Application. Final version

READ Platform P2

Implementation and maintenance of the READ platform including service and tool integration. Report for reporting period 2

Zurich - Evaluation and Bootstrapping P3

Zurich - Evaluation and Bootstrapping

Keyword Spotting Engines: QbE, QbS P2

Toolkits for indexing and searching handwritten documents without prior recognition of the actual text. Updated version

Venice Time Machine – Meta-learning Model P1

Venice Time Machine – Meta-learning Model

Transcribe Bentham P2

Implementation and maintenance of the transcribe Bentham collection. Report for reporting period 2

ScriptNet Large Scale Dataset P1

Collecting and making available of a large scale datasets to the research community. First version

Keyword Spotting Engines: QbE, QbS P1

Toolkits for indexing and searching handwritten documents without prior recognition of the actual text. Prototype version

READ Platform P3

Implementation and maintenance of the READ platform including service and tool integration. Report for reporting period 3

Language models P1

A toolkit for enhancing language data for HTR processing. Prototype version

HTR Engine Based on HMMs P3

A toolkit for HTR processing based on HMM models. Final version

Passau - Keyword Spotting in Registry Books P1

Passau - Keyword Spotting in Registry Books

Modern Crowd-Sourcing Tools P3

Development and Implementation of mobile Crowd-Sourcing Tools. Final version

Passau - Keyword Spotting in Registry Books P2

Passau - Keyword Spotting in Registry Books

Advisory Board P1

Implementation of the Advisory Board

ScriptNet: Competition P3

Implementation of research competitions. Report for period 3

ScriptNet: Competition P2

Implementation of research competitions. Report for period 2

Workshops P3

Organisation of workshops for various target groups. Report for reporting period 1

Workshops P1

Organisation of workshops for various target groups. Report for reporting period 1

ScriptNet: Competition P1

Implementation of research competitions. Report for period 1

Workshops P2

Organisation of workshops for various target groups. Report for reporting period 2

Advisory Board P2

Maintenance of the Advisory board

Advisory Board P3

Maintenance of the Advisory board

Open Innovation Forum P2

Open Innovation Forum

Dissemination and Awareness Plan P2

Dissemination and Awareness Plan

Dissemination and Awareness Plan P1

Dissemination and Awareness Plan

General Dissemination Report P2

Dissemination Report

User Satisfaction P1

Evaluation of the user satisfaction. Report for reporting period 1

Open Innovation Forum P1

Open Innovation Forum

General Dissemination Report P1

Dissemination Report

Open Innovation Forum P3

Open Innovation Forum

User Satisfaction P2

Evaluation of the user satisfaction. Report for reporting period 2

Integration of MOU Partners P1

Incorporation of MOU partners. Report for reporting period 1

Data Management Plan P1

Data Management Plan for period 1

User Satisfaction P3

Evaluation of the user satisfaction. Report for reporting period 3

Dissemination and Awareness Plan P3

Dissemination and Awareness Plan

Integration of MOU Partners P2

Incorporation of MOU partners. Report for reporting period 2

Integration of MOU Partners P3

Incorporation of MOU partners. Report for reporting period 3

General Dissemination Report P3

Dissemination Report

Data Management Plan P2

Data Management Plan for reporting period 2

European Hands P2

A marketing campaign addressed towards the general public. Report for reporting period 2

European Hands P3

A marketing campaign addressed towards the general public. Report for reporting period 3

Website

Implementation of the project website

European Hands P1

A marketing campaign addressed towards the general public. Report for reporting period 1

Data Management Plan P3

Data Management Plan for reporting period 3

Publications

Archiv 4.0 oder warum die automatisierte Texterkennung alles verändern wird

Auteurs: Mühlberger, Günter
Publié dans: Tagungsband Archivtag Wolfsburg (2017), Numéro 87, 2018
Éditeur: Verband Deutscher Archivare

Mass Digitization of Archival Documents using Mobile Phones

Auteurs: Florian Kleber, Markus Diem, Fabian Hollaus, Stefan Fiel
Publié dans: Proceedings of the 4th International Workshop on Historical Document Imaging and Processing - HIP2017, 2017, Page(s) 65-70, ISBN 9781-450353908
Éditeur: ACM Press
DOI: 10.1145/3151509.3151526

Transkribus Python Toolkit

Auteurs: Jean-Luc Meunier, Hervé Déjean
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, ISBN 978-1-5386-3586-5
Éditeur: IEEE

Joint Structured Learning and Predictions under Logical Constraints in Conditional Random Fields

Auteurs: Jean-Luc Meunier
Publié dans: Caps 2017 Conference sur l'apprentissage, 2017
Éditeur: ??

PyStruct Extension for Typed CRF Graphs

Auteurs: Jean-Luc Meunier
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 5-10, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.305

Machine Vision algorithms on cadaster plans

Auteurs: Sofia Ares Oliveira, Isabella di Lenardo, Frederic Kaplan
Publié dans: Premiere Annual Conference of the International Alliance of Digital Humanities Organizations, 2017
Éditeur: Alliance of Digital Humanities Organizations

ICDAR2017 Competition on Handwritten Text Recognition on the READ Dataset

Auteurs: Joan Andreu Sanchez, Veronica Romero, Alejandro H. Toselli, Mauricio Villegas, Enrique Vidal
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 1383-1388, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.226

ICDAR2017 Competition on Information Extraction in Historical Handwritten Records

Auteurs: Alicia Fornes, Veronica Romero, Arnau Baro, Juan Ignacio Toledo, Joan Andreu Sanchez, Enrique Vidal, Josep Llados
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 1389-1394, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.227

Handwritten Music Recognition for Mensural Notation: Formulation, Data and Baseline Results

Auteurs: Jorge Calvo-Zaragoza, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 1081-1086, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.179

Simple and Effective Multi-word Query Spotting in Handwritten Text Images

Auteurs: Ernesto Noya-García, Alejandro H. Toselli, Enrique Vidal
Publié dans: Pattern Recognition and Image Analysis. IbPRIA 2017, Numéro Lecture Notes in Computer Science, vol 10255, 2017, Page(s) 76-84, ISBN 978-3-319-58837-7
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-58838-4_9

Information Extraction in Handwritten Marriage Licenses Books Using the MGGI Methodology

Auteurs: Verónica Romero, Alicia Fornés, Enrique Vidal, Joan Andreu Sánchez
Publié dans: Pattern Recognition and Image Analysis. IbPRIA 2017, Numéro vol 10255, 2017, Page(s) 287-294, ISBN 978-3-319-58837-7
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-58838-4_32

Interactive Layout Detection

Auteurs: Lorenzo Quirós, Carlos-D. Martínez-Hinarejos, Alejandro H. Toselli, Enrique Vidal
Publié dans: Pattern Recognition and Image Analysis. IbPRIA 2017, Numéro Lecture Notes in Computer Science, vol 10255, 2017, Page(s) 161-168, ISBN 978-3-319-58837-7
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-58838-4_18

A Historical Document Handwriting Transcription End-to-end System

Auteurs: Verónica Romero, Vicente Bosch, Celio Hernández, Enrique Vidal, Joan Andreu Sánchez
Publié dans: Pattern Recognition and Image Analysis. IbPRIA 2017, Numéro Lecture Notes in Computer Science, vol 10255, 2017, Page(s) 149-157, ISBN 978-3-319-58837-7
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-58838-4_17

Baseline Detection on Arabic Handwritten Documents

Auteurs: Ahmed Fawzi, Moisés Pastor, Carlos D. Martínez-Hinarejos
Publié dans: Proceedings of the 2017 ACM Symposium on Document Engineering - DocEng '17, 2017, Page(s) 193-196, ISBN 9781-450346894
Éditeur: ACM Press
DOI: 10.1145/3103010.3121037

Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?

Auteurs: Joan Puigcerver
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 67-72, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.20

Preparatory KWS Experiments for Large-Scale Indexing of a Vast Medieval Manuscript Collection in the HIMANIS Project

Auteurs: Theodore Bluche, Sebastien Hamel, Christopher Kermorvant, Joan Puigcerver, Dominique Stutzmann, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 311-316, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.59

ICDAR2017 Competition on Document Image Binarization (DIBCO 2017)

Auteurs: Ioannis Pratikakis, Konstantinos Zagoris, George Barlas, Basilis Gatos
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 1395-1403, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.228

Bio-Inspired Modeling for the Enhancement of Historical Handwritten Documents

Auteurs: Konstantinos Zagoris, Ioannis Pratikakis
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 287-292, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.55

CITlab ARGUS for Keyword Search in Historical Handwritten Documents: Description of CITlab's System for the ImageCLEF 2016 Handwritten Scanned Document Retrieval Task

Auteurs: Tobias Strauß, Tobias Grüning, Gundram Leifert, Roger Labahn
Publié dans: CLEF2016 Working Notes, Numéro vol. 1609, 2016, Page(s) 399-412, ISSN 1613-0073
Éditeur: CEUR-WS.org

Zoning Aggregated Hypercolumns for Keyword Spotting

Auteurs: Giorgos Sfikas, George Retsinas, Basilis Gatos
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition, 2016
Éditeur: IEEE

ICDAR2017 Competition on Historical Document Writer Identification (Historical-WI)

Auteurs: Stefan Fiel, Florian Kleber, Markus Diem, Vincent Christlein, Georgios Louloudis, Stamatopoulos Nikos, Basilis Gatos
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 1377-1382, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.225

cBAD: ICDAR2017 Competition on Baseline Detection

Auteurs: Markus Diem, Florian Kleber, Stefan Fiel, Tobias Gruning, Basilis Gatos
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 1355-1360, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/ICDAR.2017.222

READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents

Auteurs: Tobias Gruning, Roger Labahn, Markus Diem, Florian Kleber, Stefan Fiel
Publié dans: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), 2018, Page(s) 351-356, ISBN 978-1-5386-3346-5
Éditeur: IEEE
DOI: 10.1109/DAS.2018.38

Nonlinear Manifold Embedding on Keyword Spotting Using t-SNE

Auteurs: G. Retsinas, N. Stamatopoulos, G. Louloudis, G. Sfikas and B. Gatos
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017
Éditeur: IEEE

A PHOC Decoder for Lexicon-Free Handwritten Word Recognition

Auteurs: G. Sfikas, G. Retsinas and B. Gatos
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017
Éditeur: IEEE

Transferable Deep Features for Keyword Spotting

Auteurs: G.Retsinas, G.Sfikas and B.Gatos
Publié dans: 2017 International Workshop on Computational Intelligence for Multimedia Understanding, 2017
Éditeur: MDPI

SemiCCA: A New Semi-Supervised Probabilistic CCA Model for Keyword Spotting

Auteurs: G.Sfikas, B.Gatos and C.Nikou
Publié dans: 2017 International Conference on Image processing (ICIP), 2017
Éditeur: IEEE

Historical Document Processing

Auteurs: B. Gatos, G. Louloudis, N. Stamatopoulos and G. Sfikas
Publié dans: 2017 17th ACM Symposium on Document Engineering (DocEng 2017), 2017
Éditeur: ACM

Two Methods to Improve Confidence Scores for Lexicon-Free Word Spotting in Handwritten Text

Auteurs: Alejandro Hector Toselli, Joan Puigcerver, Enrique Vidal
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 349-354, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/icfhr.2016.0072

Early Handwritten Music Recognition with Hidden Markov Models

Auteurs: Jorge Calvo-Zaragoza, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 319-324, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/icfhr.2016.0067

Using the MGGI Methodology for Category-Based Language Modeling in Handwritten Marriage Licenses Books

Auteurs: Veronica Romero, Alicia Fornes, Enrique Vidal, Joan Andreu Sanchez
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 331-336, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/icfhr.2016.0069

ICFHR2016 Handwritten Keyword Spotting Competition (H-KWS 2016)

Auteurs: Ioannis Pratikakis, Konstantinos Zagoris, Basilis Gatos, Joan Puigcerver, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 613-618, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/icfhr.2016.0117

Exploiting Existing Modern Transcripts for Historical Handwritten Text Recognition

Auteurs: Mauricio Villegas, Alejandro H. Toselli, Veronica Romero, Enrique Vidal
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 66-71, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/ICFHR.2016.0025

ICFHR2016 Competition on Handwritten Text Recognition on the READ Dataset

Auteurs: Joan Andreu Sanchez, Veronica Romero, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 630-635, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/icfhr.2016.0120

On the Design of Personal Digital Bodyguards: Impact of Hardware Resolution on Handwriting Analysis

Auteurs: Daniel Martin-Albo, Luis A. Leiva, Rejean Plamondon
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 174-179, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/icfhr.2016.0043

Handwritten Text Recognition for Bengali

Auteurs: Joan Andreu Sanchez, Umapada Pal
Publié dans: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 542-547, ISBN 978-1-5090-0981-7
Éditeur: IEEE
DOI: 10.1109/ICFHR.2016.0105

Comparing Different Feedback Modalities in Assisted Transcription of Manuscripts

Auteurs: Carlos-D. Martinez-Hinarejos, Emilio Granell-Romero, Veronica Romero-Gomez
Publié dans: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), 2018, Page(s) 115-120, ISBN 978-1-5386-3346-5
Éditeur: IEEE
DOI: 10.1109/DAS.2018.13

Automatic Alignment of Handwritten Images and Transcripts for Training Handwritten Text Recognition Systems

Auteurs: Veronica Romero-Gomez, Alejandro H. Toselli, Vicente Bosch, Joan Andreu Sanchez, Enrique Vidal
Publié dans: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), 2018, Page(s) 328-333, ISBN 978-1-5386-3346-5
Éditeur: IEEE
DOI: 10.1109/DAS.2018.41

Probabilistic Music-Symbol Spotting in Handwritten Scores

Auteurs: Jorge Calvo-Zaragoza, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2018 16th International Conference on Frontiers in Handwritting Recognition (ICFHR), 2018, Page(s) 558-563, ISBN 978-1-5386-5875-8
Éditeur: IEEE
DOI: 10.1109/ICFHR-2018.2018.00103

From HMMs to RNNs: Computer-Assisted Transcription of a Handwritten Notarial Records Collection

Auteurs: Lorenzo Quiros, Vicente Bosch, Lluis Serrano, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2018, Page(s) 116-121, ISBN 978-1-5386-5875-8
Éditeur: IEEE
DOI: 10.1109/ICFHR-2018.2018.00029

Text Line Extraction Based on Distance Map Features and Dynamic Programming

Auteurs: Vicente Bosch, Verónica Romero, Alejandro H. Toselli, Enrique Vidal
Publié dans: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2018, Page(s) 357-362, ISBN 978-1-5386-5875-8
Éditeur: IEEE
DOI: 10.1109/ICFHR-2018.2018.00069

Probabilistic Indexing and Search for Information Extraction on Handwritten German Parish Records

Auteurs: Eva Lang, Joan Puigcerver, Alejandro Hector Toselli, Enrique Vidal
Publié dans: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2018, Page(s) 44-49, ISBN 978-1-5386-5875-8
Éditeur: IEEE
DOI: 10.1109/ICFHR-2018.2018.00017

Advances on the Transcription of Historical Manuscripts based on Multimodality, Interactivity and Crowdsourcing

Auteurs: Emilio Granell, Carlos David Martinez Hinarejos, Verónica Romero
Publié dans: IberSPEECH 2018, 2018, Page(s) 174-178
Éditeur: ISCA
DOI: 10.21437/IberSPEECH.2018-35

Generierung von Trainingsdaten für die Handschrifterkennung aus TEI annotierten Dokumenten - Ein Erfahrungsbericht aus dem EU-Projekt READ

Auteurs: Maximilian Bryan, Tobias Hodel, Nathanael Philipp
Publié dans: GI-Workshop: Im Spannungsfeld zwischen Tool-Building und Forschung auf Augenhöhe – Informatik und die Digital Humanities, 2018
Éditeur: Gesellschaft für Informatik

Handwriting Transcription and Keyword Spotting in Historical Daily Records Documents

Auteurs: Veronica Romero, Alejandro H. Toselli, Joan Andreu Sanchez, Enrique Vidal
Publié dans: 2016 12th IAPR Workshop on Document Analysis Systems (DAS), 2016, Page(s) 275-280, ISBN 978-1-5090-1792-8
Éditeur: IEEE
DOI: 10.1109/DAS.2016.70

ICFHR2016 Handwritten Keyword Spotting Competition (H-KWS 2016)

Auteurs: Ioannis Pratikakis, Konstantinos Zagoris, Basilis Gatos, Joan Puigcerver, Alejandro H. Toselli and Enrique Vidal
Publié dans: International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016, Page(s) 613-618
Éditeur: International Conference on Frontiers in Handwriting Recognition (ICFHR)

Accuracy of Gradient based Skew Estimation

Auteurs: F. Kleber, M. Diem and R. Sablatnig
Publié dans: Document Analysis Systems (DAS), 2016
Éditeur: Document Analysis Systems (DAS)

Overview of the ImageCLEF 2016 Handwritten Scanned Document Retrieval Task

Auteurs: Mauricio Villegas, Joan Puigcerver, Alejandro H. Toselli, Joan-Andreu Sánchez and Enrique Vidal
Publié dans: Cross Language Evaluation Forum (CLEF), 2016, Page(s) 233-253
Éditeur: Cross Language Evaluation Forum (CLEF)

A Robust and Binarization-Free Approach for Text Line Detection in Historical Documents

Auteurs: Tobias Gruuening, Gundram Leifert, Tobias Strauss, Roger Labahn
Publié dans: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, Page(s) 236-241, ISBN 978-1-5386-3586-5
Éditeur: IEEE
DOI: 10.1109/icdar.2017.47

Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition

Auteurs: Michael, Johannes; Labahn, Roger; Grüning, Tobias; Zöllner, Jochen
Publié dans: ICDAR 2019, 2019
Éditeur: ICDAR 2019

End-To-End Measure for Text Recognition

Auteurs: Leifert, Gundram; Labahn, Roger; Grüning, Tobias; Leifert, Svenja
Publié dans: ICDAR 2019, 2019
Éditeur: ICDAR 2019

System Description of CITlab's Recognition & Retrieval Engine for ICDAR2017 Competition on Information Extraction in Historical Handwritten Records

Auteurs: Tobias Strauß, Max Weidemann, Johannes Michael, Gundram Leifert, Tobias Grüning, Roger Labahn
Publié dans: 2017
Éditeur: ICDAR 2017

Transcribing a 17th-century botanical manuscript: Longitudinal evaluation of document layout detection and interactive transcription

Auteurs: Alejandro H. Toselli, Luis A. Leiva, Isabel Bordes-Cabrera, Celio Hernández-Tornero, Vicent Bosch, Enrique Vidal
Publié dans: Digital Scholarship in the Humanities, 2017, ISSN 2055-7671
Éditeur: Oxford Academic
DOI: 10.1093/llc/fqw064

On the Derivational Entropy of Left-to-Right Probabilistic Finite-State Automata and Hidden Markov Models

Auteurs: Joan Andreu Sánchez, Martha Alicia Rocha, Verónica Romero, Mauricio Villegas
Publié dans: Computational Linguistics, 2017, Page(s) 1-21, ISSN 0891-2017
Éditeur: MIT Press
DOI: 10.1162/coli_a_00306

Unsupervised Word Spotting in Historical Handwritten Document Images Using Document-Oriented Local Features

Auteurs: Konstantinos Zagoris, Ioannis Pratikakis, Basilis Gatos
Publié dans: IEEE Transactions on Image Processing, Numéro 26/8, 2017, Page(s) 4032-4041, ISSN 1057-7149
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/TIP.2017.2700721

Archivnutzung ohne Limit. Digitalisierung, Onlinestellung und das Projekt READ für barrierefreies Forschen.

Auteurs: Fronhöfer Andrea / Mühlbauer Elena
Publié dans: Der Archivar, Zeitschrift für Archivwesen, Numéro 70, 2017, Page(s) 422-427, ISSN 2199-9252
Éditeur: Landesarchiv Nordrhein-Westfalen

Regular expressions for decoding of neural network outputs

Auteurs: Tobias Strauß, Gundram Leifert, Tobias Grüning, Roger Labahn
Publié dans: Neural Networks, Numéro 79, 2016, Page(s) 1-11, ISSN 0893-6080
Éditeur: Pergamon Press Ltd.
DOI: 10.1016/j.neunet.2016.03.003

Cells in Multidimensional Recurrent Neural Networks

Auteurs: Gundram Leifert, Tobias Strauß, Tobias Grüning, Welf Wustlich, Roger Labahn
Publié dans: Journal of Machine Learning Research, Numéro 17 (97), 2016, Page(s) 1-37, ISSN 1532-4435
Éditeur: MIT Press

A survey of document image word spotting techniques

Auteurs: Angelos P. Giotis, Giorgos Sfikas, Basilis Gatos, Christophoros Nikou
Publié dans: Pattern Recognition, Numéro 68, 2017, Page(s) 310-332, ISSN 0031-3203
Éditeur: Pergamon Press
DOI: 10.1016/j.patcog.2017.02.023

Multimodal Crowdsourcing for Transcribing Handwritten Documents

Auteurs: Emilio Granell, Carlos-D. Martinez-Hinarejos
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numéro 25/2, 2017, Page(s) 409-419, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/TASLP.2016.2634123

Probabilistic multi-word spotting in handwritten text images

Auteurs: Alejandro H. Toselli, Enrique Vidal, Joan Puigcerver, Ernesto Noya-García
Publié dans: Pattern Analysis and Applications, 2018, ISSN 1433-7541
Éditeur: Springer Verlag
DOI: 10.1007/s10044-018-0742-z

Multimodality, interactivity, and crowdsourcing for document transcription

Auteurs: Emilio Granell, Verónica Romero, Carlos D. Martínez-Hinarejos
Publié dans: Computational Intelligence, Numéro 34/2, 2018, Page(s) 398-419, ISSN 0824-7935
Éditeur: Blackwell Publishing Inc.
DOI: 10.1111/coin.12169

Indexación y reconocimiento automático de texto manuscrito

Auteurs: Celio Hernández Tornero, Verónica Romero Gómez, Joan Andreu Sánchez Peiró, Alejandro Héctor Toselli Rossi, Enrique Vidal Ruiz
Publié dans: Cuadernos AISPI. Estudios de lenguas y literaturas hispánicas., Numéro Vol. 11, 2018, Page(s) 131-146, ISSN 2283-981X
Éditeur: Associazione Ispanisti Italiani
DOI: 10.14672/0.2018.1432

Word graphs size impact on the performance of handwriting document applications

Auteurs: Alejandro H. Toselli, Verónica Romero, Enrique Vidal
Publié dans: Neural Computing and Applications, Numéro 28/9, 2017, Page(s) 2477-2487, ISSN 0941-0643
Éditeur: Springer Verlag
DOI: 10.1007/s00521-016-2336-2

Querying out-of-vocabulary words in lexicon-based keyword spotting

Auteurs: Joan Puigcerver, Alejandro H. Toselli, Enrique Vidal
Publié dans: Neural Computing and Applications, Numéro 28/9, 2017, Page(s) 2373-2382, ISSN 0941-0643
Éditeur: Springer Verlag
DOI: 10.1007/s00521-016-2197-8

HMM word graph based keyword spotting in handwritten document images

Auteurs: Alejandro Héctor Toselli, Enrique Vidal, Verónica Romero, Volkmar Frinken
Publié dans: Information Sciences, Numéro 370-371, 2016, Page(s) 497-518, ISSN 0020-0255
Éditeur: Elsevier BV
DOI: 10.1016/j.ins.2016.07.063

A two-stage method for text line detection in historical documents

Auteurs: Tobias Grüning, Gundram Leifert, Tobias Strauß, Johannes Michael, Roger Labahn
Publié dans: International Journal on Document Analysis and Recognition (IJDAR), 2019, ISSN 1433-2833
Éditeur: Springer Verlag
DOI: 10.1007/s10032-019-00332-1

Advances in Handwritten Keyword Indexing and Search Technologies

Auteurs: Vidal, Enrique
Publié dans: Codicology and Palaeography in the Digital Age 4, Numéro 11, 2017, Page(s) 103-119, ISBN 978-3-7448-3877-1
Éditeur: Books on Demand

Handwritten keyword spotting – The Query by Example (QbE) case

Auteurs: G. Barlas, K. Zagoris and I. Pratikakis
Publié dans: Handwriting: Recognition, Development and Analysis, 2017, ISBN 978-1-53611-957-2
Éditeur: Nova Science Publishers

Historical Document Processing

Auteurs: B. Gatos, G. Louloudis, N. Stamatopoulos and G. Sfikas
Publié dans: Handwriting: Recognition, Development and Analysis, 2017, ISBN 978-1-53611-957-2
Éditeur: Nova Science Publishers

Handwriting Segmentation

Auteurs: N. Stamatopoulos, G. Louloudis and B. Gatos
Publié dans: Document Analysis and Text Recognition: Benchmarking State-of-the-Art Systems, 2017
Éditeur: World Scientific Publishing Co.

Writer Identification

Auteurs: G. Louloudis, N. Stamatopoulos and B. Gatos
Publié dans: Document Analysis and Text Recognition: Benchmarking State-of-the-Art Systems, 2017, ISBN 978-981-3229-26-6
Éditeur: World Scientific Publishing Co.

Handwritten Text Recognition Competitions With the tranScriptorium Dataset

Auteurs: Joan Andreu Sánchez, Verónica Romero, Alejandro H. Toselli, Enrique Vidal
Publié dans: Document Analysis and Text Recognition - Benchmarking State-of-the-Art Systems, Numéro 82, 2017, Page(s) 213-239, ISBN 978-981-322-926-6
Éditeur: WORLD SCIENTIFIC
DOI: 10.1142/9789813229273_0008

Matching Table Structures of Historical Register Books using Association Graphs

Auteurs: Kleber; Diem; Dejean; Meunier; Lang
Publié dans: 16th International Conference on Frontiers in Handwriting Recognition (ICFHR 2018), 2018, Page(s) 217-222
Éditeur: IEEE

General Overview of ImageCLEF at the CLEF 2016 Labs

Auteurs: Mauricio Villegas, Henning Müller, Alba García Seco de Herrera, Roger Schaer, Stefano Bromuri, Andrew Gilbert, Luca Piras, Josiah Wang, Fei Yan, Arnau Ramisa, Emmanuel Dellandrea, Robert Gaizauskas, Krystian Mikolajczyk, Joan Puigcerver, Alejandro H. Toselli, Joan-Andreu Sánchez, Enrique Vidal
Publié dans: Experimental IR Meets Multilinguality, Multimodality, and Interaction, 2016, Page(s) 267-285, ISBN 978-3-319-44564-9
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-319-44564-9_25

Decoding the output of neural networks - A discriminative approach

Auteurs: Tobias Strauß
Publié dans: 2017
Éditeur: Universität Rostock
DOI: 10.18453/rosdok_id00001919

Neural text line extraction in historical documents:a two-stage clustering approach

Auteurs: Grüning, Tobias
Publié dans: 2018
Éditeur: University of Rostock
DOI: 10.18453/rosdok_id00002427

System Description of CITlab's Recognition & Retrieval Engine for ICDAR2017 Competition on Information Extraction in Historical Handwritten Records

Auteurs: Strauß, Tobias; Weidemann, Max; Michael, Johannes; Leifert, Gundram; Grüning, Tobias; Labahn, Roger
Publié dans: Numéro 2, 2017
Éditeur: arXiv

A Two-Stage Method for Text Line Detection in Historical Documents

Auteurs: Grüning, Tobias; Leifert, Gundram; Strauß, Tobias; Labahn, Roger
Publié dans: Numéro 2, 2018
Éditeur: arXiv

Bench-Marking Information Extraction in Semi-Structured Historical Handwritten Records

Auteurs: Animesh Prasad, Hervé Déjean, Jean-Luc Meunier, Max Weidemann, Johannes Michael, Gundram Leifert
Publié dans: 2018
Éditeur: arXiv

Recherche de données OpenAIRE...

Une erreur s’est produite lors de la recherche de données OpenAIRE

Aucun résultat disponible