2018
|
Renton, Guillaume; Soullard, Yann; Chatelain, Clément; Adam, Sébastien; Kermorvant, Christopher; Paquet, Thierry Fully Convolutional Network with dilated convolutions for Handwritten text line segmentation Journal Article International Journal on Document Analysis and Recognition, 2018. BibTeX @article{ijdar2018_fcn,
title = {Fully Convolutional Network with dilated convolutions for Handwritten text line segmentation},
author = {Guillaume Renton and Yann Soullard and Clément Chatelain and Sébastien Adam and Christopher Kermorvant and Thierry Paquet},
year = {2018},
date = {2018-01-01},
journal = { International Journal on Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Moysset, Bastien; Kermorvant, Christopher; Wolf, Christian Learning to detect, localize and recognize many text objects in document images from few examples Journal Article International Journal on Document Analysis and Recognition, 2018. Links | BibTeX @article{ijdar2018_sdl,
title = {Learning to detect, localize and recognize many text objects in document images from few examples},
author = {Bastien Moysset and Christopher Kermorvant and Christian Wolf},
url = {http://www.teklia.com/wp-content/uploads/2018/07/IJDAR2018_publishedVersion.pdf},
year = {2018},
date = {2018-01-01},
journal = {International Journal on Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
2017
|
Bluche, Théodore; Hamel, Sebastien; Kermorvant, Christopher; Puigcerver, Joan; Stutzmann, Dominique; Toselli, Alejandro; Vidal, Enrique Preparatory KWS Experiments for Large-Scale Indexing of a Vast Medieval Manuscript Collection in the HIMANIS Project Inproceedings International Conference on Document Analysis and Recognition, 2017. Links | BibTeX @inproceedings{icdar_himanis2017,
title = {Preparatory KWS Experiments for Large-Scale Indexing of a Vast Medieval Manuscript Collection in the HIMANIS Project},
author = {Théodore Bluche and Sebastien Hamel and Christopher Kermorvant and Joan Puigcerver and Dominique Stutzmann and Alejandro Toselli and Enrique Vidal},
url = {http://www.teklia.com/wp-content/uploads/2018/01/3586a312.pdf},
year = {2017},
date = {2017-11-09},
booktitle = { International Conference on Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Moysset, Bastien; Kermorvant, Christopher; Wolf, Christian Full-Page Text Recognition: Learning Where to Start and When to Stop Inproceedings International Conference on Document Analysis and Recognition, 2017. Links | BibTeX @inproceedings{icdar_sdl2017,
title = {Full-Page Text Recognition: Learning Where to Start and When to Stop},
author = {Bastien Moysset and Christopher Kermorvant and Christian Wolf},
url = {http://www.teklia.com/wp-content/uploads/2018/01/3586a871.pdf},
year = {2017},
date = {2017-11-09},
booktitle = {International Conference on Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Kermorvant, Christopher; Touzet, Claude; Glotin, Hervé Cortical-Inspired Open-Bigram Representation for Handwritten Word Recognition Inproceedings International Conference on Document Analysis and Recognition, 2017. Links | BibTeX @inproceedings{icdar_bigram2017,
title = {Cortical-Inspired Open-Bigram Representation for Handwritten Word Recognition},
author = {Théodore Bluche and Christopher Kermorvant and Claude Touzet and Hervé Glotin},
url = {http://www.teklia.com/wp-content/uploads/2018/01/3586a073.pdf},
year = {2017},
date = {2017-11-09},
booktitle = { International Conference on Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Guillaume Renton Clément Chatelain, Sébastien Adam Christopher Kermorvant Thierry Paquet Handwritten text line segmentation using Fully Convolutional Network Conference International Workshop on Historical Document Imaging and Processing, 2017. Links | BibTeX @conference{hip2017_renton,
title = {Handwritten text line segmentation using Fully Convolutional Network},
author = {Guillaume Renton, Clément Chatelain, Sébastien Adam, Christopher Kermorvant, Thierry Paquet},
url = {http://www.teklia.com/wp-content/uploads/2018/01/3586f005.pdf},
year = {2017},
date = {2017-10-11},
booktitle = {International Workshop on Historical Document Imaging and Processing},
journal = {International Workshop on Historical Document Imaging and Processing},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
Ney, Théodore Bluche
Christopher Kermorvant
Hermann How to Design Deep Neural Networks for Handwriting Recognition Book Chapter Pirlo, Byron Leite Dantas Bezerra Cleber Zanchettin Alejandro Toselli Giuseppe H (Ed.): Nova Science Pub Inc, 2017, ISBN: 978-1536119374. BibTeX @inbook{book_2017,
title = {How to Design Deep Neural Networks for Handwriting Recognition},
author = {Théodore Bluche
Christopher Kermorvant
Hermann Ney},
editor = { Byron Leite Dantas Bezerra
Cleber Zanchettin
Alejandro H. Toselli
Giuseppe Pirlo},
isbn = {978-1536119374},
year = {2017},
date = {2017-07-21},
publisher = {Nova Science Pub Inc},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
|
2016
|
Moysset, Bastien; Louradour, Jérôme; Kermorvant, Christopher; Wolf, Christian Learning text-line localization with shared and local regression neural networks Inproceedings International Conference on Frontiers in Handwriting Recognition , 2016. Links | BibTeX @inproceedings{moysset2016,
title = {Learning text-line localization with shared and local regression neural networks},
author = {Bastien Moysset and Jérôme Louradour and Christopher Kermorvant and Christian Wolf},
url = {http://www.teklia.com/wp-content/uploads/2017/01/icfhr2016_bm_jl_ck_cw.pdf},
year = {2016},
date = {2016-10-23},
booktitle = {International Conference on Frontiers in Handwriting Recognition },
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Stutzmann, Dominique; Kermorvant, Christopher Automatic Handwritten Character Segmentation for Paleographical Character Shape Analysis Inproceedings Document Analysis Systems, 2016. Abstract | Links | BibTeX @inproceedings{bluche2016,
title = {Automatic Handwritten Character Segmentation for Paleographical Character Shape Analysis},
author = { Théodore Bluche and Dominique Stutzmann and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2016/06/DAS2016.pdf},
year = {2016},
date = {2016-01-01},
booktitle = {Document Analysis Systems},
abstract = {Written texts are both physical (signs, shapes and graphical systems) and abstract objects (ideas), whose meanings and social connotations evolve through time. To study this dual nature of texts, palaeographers need to analyse large scale corpora at the finest granularity, such as character shape. This goal can only be reached through an automatic segmentation process. In this paper, we present a method, based on Handwritten Text Recognition, to automatically align images of digitized manuscripts with texts from scholarly editions, at the levels of page, column, line, word, and character. It has been successfully applied to two datasets of medieval manuscripts, which are now almost fully segmented at character level. The quality of the word and character segmentations are evaluated and further palaeographical analysis are presented.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Written texts are both physical (signs, shapes and graphical systems) and abstract objects (ideas), whose meanings and social connotations evolve through time. To study this dual nature of texts, palaeographers need to analyse large scale corpora at the finest granularity, such as character shape. This goal can only be reached through an automatic segmentation process. In this paper, we present a method, based on Handwritten Text Recognition, to automatically align images of digitized manuscripts with texts from scholarly editions, at the levels of page, column, line, word, and character. It has been successfully applied to two datasets of medieval manuscripts, which are now almost fully segmented at character level. The quality of the word and character segmentations are evaluated and further palaeographical analysis are presented. |
Bluche, Théodore; Kermorvant, Christopher; Ney, Hermann; Louradour, Jerome La CTC et son intrigant label Inproceedings Colloque International Francophone sur l’Écrit et le Document 2016 (CIFED), 2016. Abstract | Links | BibTeX @inproceedings{bluche2016b,
title = {La CTC et son intrigant label },
author = { Théodore Bluche and Christopher Kermorvant and Hermann Ney and Jerome Louradour},
url = {http://www.teklia.com/wp-content/uploads/2016/06/cifed2016.pdf},
year = {2016},
date = {2016-01-01},
booktitle = {Colloque International Francophone sur l’Écrit et le Document 2016 (CIFED)},
abstract = {Les systèmes de reconnaissance d’écriture vainqueurs d’évaluations internationales ces dernières années sont basés sur des réseaux de type LSTM, entraînés avec un critère de classification temporelle connexionniste (CTC). L’algorithme de la CTC est basé sur une procédure "forward-backward", sans segmentation de la séquence d’entrée avant l’entraînement. Les sorties du réseau sont les caractères à modéliser, auxquels on ajoute un label spécial, noncaractère, (blank). D’autre part, dans les systèmes hybrides réseaux de neurones / modèles de Markov cachés (MMCs), les réseaux sont entraînés au niveau trame à prédire des états de MMC. Dans cet article, nous montrons que la CTC est une forme dérivée de l’entraînement forward-backward de MMCs, et qu’elle peut donc être étendue à des topologies arbitraires de MMC. Nous appliquons cette méthode à des perceptrons multicouches et la comparons à l’entraînement au niveau trame dans diverses situations. Enfin, nous analysons le rôle intrigant de ce label spécial "blank".},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Les systèmes de reconnaissance d’écriture vainqueurs d’évaluations internationales ces dernières années sont basés sur des réseaux de type LSTM, entraînés avec un critère de classification temporelle connexionniste (CTC). L’algorithme de la CTC est basé sur une procédure "forward-backward", sans segmentation de la séquence d’entrée avant l’entraînement. Les sorties du réseau sont les caractères à modéliser, auxquels on ajoute un label spécial, noncaractère, (blank). D’autre part, dans les systèmes hybrides réseaux de neurones / modèles de Markov cachés (MMCs), les réseaux sont entraînés au niveau trame à prédire des états de MMC. Dans cet article, nous montrons que la CTC est une forme dérivée de l’entraînement forward-backward de MMCs, et qu’elle peut donc être étendue à des topologies arbitraires de MMC. Nous appliquons cette méthode à des perceptrons multicouches et la comparons à l’entraînement au niveau trame dans diverses situations. Enfin, nous analysons le rôle intrigant de ce label spécial "blank". |
Stutzmann, Dominique; Bluche, Théodore; Kermorvant, Christopher; Englin, Véronique; Vincent, Nicole; Leydier, Yann; Cloppet, Florence Text-Image Alignment and Automated Letter-form Classification: Reading vs. Looking at Inproceedings Second International Conference on Natural Sciences and Technology in Manuscript Analysis, 2016. BibTeX @inproceedings{Bluche2016bb,
title = {Text-Image Alignment and Automated Letter-form Classification: Reading vs. Looking at},
author = { Dominique Stutzmann and Théodore Bluche and Christopher Kermorvant and Véronique Englin and Nicole Vincent and Yann Leydier and Florence Cloppet},
year = {2016},
date = {2016-01-01},
booktitle = {Second International Conference on Natural Sciences and Technology in Manuscript Analysis},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2015
|
Benzeghiba, Mohamed Faouzi; Louradour, Jérôme; Kermorvant, Christopher Hybrid Word / Part-of-Arabic-Word Language Models for Arabic Text Document Recognition Inproceedings International Conference of Document Analysis and Recognition, 2015. Links | BibTeX @inproceedings{Benzeghiba2015,
title = {Hybrid Word / Part-of-Arabic-Word Language Models for Arabic Text Document Recognition},
author = { Mohamed Faouzi Benzeghiba and Jérôme Louradour and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2016/06/icdar2015_paw_poster.pdf},
year = {2015},
date = {2015-01-01},
booktitle = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Kermorvant, Christopher; Louradour, Jérôme Where to Apply Dropout in Recurrent Neural Networks for Handwriting Recognition ? Inproceedings International Conference of Document Analysis and Recognition, 2015. Links | BibTeX @inproceedings{Bluche2015,
title = {Where to Apply Dropout in Recurrent Neural Networks for Handwriting Recognition ?},
author = { Théodore Bluche and Christopher Kermorvant and Jérôme Louradour},
url = {http://www.teklia.com/wp-content/uploads/2016/08/icdar2015_dropout.pdf
http://www.teklia.com/wp-content/uploads/2016/08/icdar2015_dropout_poster.pdf},
year = {2015},
date = {2015-01-01},
booktitle = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Ney, Hermann; Kermorvant, Christopher The LIMSI Handwriting Recognition System for the HTRtS 2014 Contest Inproceedings International Conference of Document Analysis and Recognition, 2015. Links | BibTeX @inproceedings{Bluche2015a,
title = {The LIMSI Handwriting Recognition System for the HTRtS 2014 Contest},
author = { Théodore Bluche and Hermann Ney and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2016/08/icdar2015_bentham.pdf},
year = {2015},
date = {2015-01-01},
booktitle = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Ney, Hermann; Kermorvant, Christopher Framewise and CTC Training of Neural Networks for Handwriting Recognition Inproceedings International Conference of Document Analysis and Recognition, 2015. Links | BibTeX @inproceedings{Bluche2015b,
title = {Framewise and CTC Training of Neural Networks for Handwriting Recognition},
author = { Théodore Bluche and Hermann Ney and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2016/06/icdar2015_trainingcosts.pdf},
year = {2015},
date = {2015-01-01},
booktitle = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Stutzmann, Dominique; Bluche, Théodore; Lavrentev, Alexei; Leydier, Yann; Kermorvant, Christopher From Text and Image to Historical Resource : Text-Image Alignment for Digital Humanists Inproceedings Digital Humanities, 2015. BibTeX @inproceedings{Stutzmann2015,
title = {From Text and Image to Historical Resource : Text-Image Alignment for Digital Humanists},
author = { Dominique Stutzmann and Théodore Bluche and Alexei Lavrentev and Yann Leydier and Christopher Kermorvant},
year = {2015},
date = {2015-01-01},
booktitle = {Digital Humanities},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Moysset, Bastien; Kermorvant, Christopher; Wolf, Christian; Louradour, Jérôme Paragraph text segmentation into lines with Recurrent Neural Networks Inproceedings 2015. Links | BibTeX @inproceedings{Moysset2015,
title = {Paragraph text segmentation into lines with Recurrent Neural Networks},
author = { Bastien Moysset and Christopher Kermorvant and Christian Wolf and Jérôme Louradour},
url = {http://www.teklia.com/wp-content/uploads/2016/07/icdar2015_linedetection.pdf},
year = {2015},
date = {2015-01-01},
journal = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2014
|
Bluche, Théodore; Louradour, Jérôme; Knibbe, Maxime; Moysset, Bastien; Benzeghiba, Mohamed Faouzi; Kermorvant, Christopher The A2iA Handwritten Arabic Text Recognition System at the OpenHaRT2013 Evaluation Campaign Inproceedings Document Analysis Systems, 2014. Links | BibTeX @inproceedings{Bluche2014b,
title = {The A2iA Handwritten Arabic Text Recognition System at the OpenHaRT2013 Evaluation Campaign},
author = { Théodore Bluche and Jérôme Louradour and Maxime Knibbe and Bastien Moysset and Mohamed Faouzi Benzeghiba and Christopher Kermorvant},
url = {http://www.a2ialab.com/lib/exe/fetch.php?media=publications:das2014_openhart.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Document Analysis Systems},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Moysset, Bastien; Kermorvant, Christopher Automatic Line Segmentation and Ground-Truth Alignment of Handwritten Documents Inproceedings International Conference on Frontiers in Handwriting Recognition., 2014. Links | BibTeX @inproceedings{Bluche2014a,
title = {Automatic Line Segmentation and Ground-Truth Alignment of Handwritten Documents},
author = { Théodore Bluche and Bastien Moysset and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2014/11/icfhr2014_munch.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {International Conference on Frontiers in Handwriting Recognition.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Ney, Hermann; Kermorvant, Christopher A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling for Handwriting Recognition Inproceedings International Conference on Statistical Language and Speech Processing, 2014. Links | BibTeX @inproceedings{Bluche2014,
title = {A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling for Handwriting Recognition},
author = { Théodore Bluche and Hermann Ney and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/slsp2014.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {International Conference on Statistical Language and Speech Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Louradour, Jérome; Kermorvant, Christopher Curriculum Learning for Handwritten Text Line Recognition Inproceedings Document Analysis Systems, 2014. Links | BibTeX @inproceedings{Louradour2014,
title = {Curriculum Learning for Handwritten Text Line Recognition},
author = { Jérome Louradour and Christopher Kermorvant},
url = {http://www.a2ialab.com/lib/exe/fetch.php?media=publications:das2014_curriculum.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Document Analysis Systems},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Messina, Ronaldo; Kermorvant, Christopher Surgenerative Finite State Transducer n-gram for Out-Of-Vocabulary Word Recognition Inproceedings Document Analysis Systems, 2014. Links | BibTeX @inproceedings{Messina2014,
title = {Surgenerative Finite State Transducer n-gram for Out-Of-Vocabulary Word Recognition},
author = { Ronaldo Messina and Christopher Kermorvant},
url = {http://www.a2ialab.com/lib/exe/fetch.php?media=publications:das2014_oov.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Document Analysis Systems},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Moysset, Bastien; Bluche, Théodore; Knibbe, Maxime; Benzeghiba, Mohamed Faouzi; Messina, Ronaldo; Louradour, Jérôme; Kermorvant, Christopher The A2iA Multi-lingual Text Recognition System at the Maurdor Evaluation Inproceedings International Conference on Frontiers in Handwriting Recognition, 2014. Links | BibTeX @inproceedings{Moysset2014,
title = {The A2iA Multi-lingual Text Recognition System at the Maurdor Evaluation},
author = { Bastien Moysset and Théodore Bluche and Maxime Knibbe and Mohamed Faouzi Benzeghiba and Ronaldo Messina and Jérôme Louradour and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2016/12/ICFHR2014_maurdor.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {International Conference on Frontiers in Handwriting Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Moysset, Bastien; Messina, Ronaldo; Kermorvant, Christopher A Comparison of Recognition Strategies for Printed / Handwritten Composite Documents Inproceedings International Conference on Frontiers in Handwriting Recognition, 2014. Links | BibTeX @inproceedings{icfhr2014_composite,
title = {A Comparison of Recognition Strategies for Printed / Handwritten Composite Documents},
author = { Bastien Moysset and Ronaldo Messina and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/icfhr2014_composite.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {International Conference on Frontiers in Handwriting Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Pham, Vu; Bluche, Théodore; Kermorvant, Christopher; Louradour, Jérôme Dropout improves recurrent neural networks for handwriting recognition Inproceedings International Conference on Frontiers in Handwriting Recognition, 2014. Links | BibTeX @inproceedings{Pham2014,
title = {Dropout improves recurrent neural networks for handwriting recognition},
author = { Vu Pham and Théodore Bluche and Christopher Kermorvant and Jérôme Louradour},
url = {http://www.teklia.com/wp-content/uploads/2017/01/icfhr2014_dropout.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {International Conference on Frontiers in Handwriting Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Touzet, Claude; Kermorvant, Christopher; Glotin, Hervé A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words Inproceedings Workshop on Self-Organizing Maps., 2014. BibTeX @inproceedings{Touzet2014,
title = {A Biologically Plausible SOM Representation of the Orthographic Form of 50,000 French Words},
author = { Claude Touzet and Christopher Kermorvant and Hervé Glotin},
year = {2014},
date = {2014-01-01},
booktitle = {Workshop on Self-Organizing Maps.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2013
|
Bluche, Théodore; Ney, Hermann; Kermorvant, Christopher Feature extraction with convolutional neural networks for handwritten word recognition Inproceedings International Conference of Document Analysis and Recognition, 2013. Links | BibTeX @inproceedings{Bluche2013,
title = {Feature extraction with convolutional neural networks for handwritten word recognition},
author = { Théodore Bluche and Hermann Ney and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2016/08/icdar2013_conv_poster.pdf
http://www.teklia.com/wp-content/uploads/2014/11/icdar2013_conv.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bluche, Théodore; Ney, Hermann; Kermorvant, Christopher Tandem HMM with convolutional neural network for handwritten word recognition Inproceedings International Conference on Acoustics Speech and Signal Processing, 2013. Abstract | Links | BibTeX @inproceedings{Bluche,
title = {Tandem HMM with convolutional neural network for handwritten word recognition},
author = { Théodore Bluche and Hermann Ney and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/icassp2013.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {International Conference on Acoustics Speech and Signal Processing},
abstract = {In this paper, we investigate the association of hidden Markov models and convolutional neural networks for handwritten word recognition. The convolutional neural networks have been successfully applied to various computer vision tasks, including handwritten character recognition. In this work, we show that they can replace Gaussian mixtures to compute emission probabilities in hidden Markov models (hybrid association), or serve as feature extractor for a standard Gaussian HMM system. The proposed systems outperform a basic HMM based on either decorrelated pixels or handcrafted features. We validated the approach on two publicly available databases, and we report up to 60% (Rimes) and 35% (IAM) relative improvement compared to a Gaussian HMM based on pixel values. The final systems give comparable to recurrent neural networks, which are the best systems since 2009.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we investigate the association of hidden Markov models and convolutional neural networks for handwritten word recognition. The convolutional neural networks have been successfully applied to various computer vision tasks, including handwritten character recognition. In this work, we show that they can replace Gaussian mixtures to compute emission probabilities in hidden Markov models (hybrid association), or serve as feature extractor for a standard Gaussian HMM system. The proposed systems outperform a basic HMM based on either decorrelated pixels or handcrafted features. We validated the approach on two publicly available databases, and we report up to 60% (Rimes) and 35% (IAM) relative improvement compared to a Gaussian HMM based on pixel values. The final systems give comparable to recurrent neural networks, which are the best systems since 2009. |
Moysset, Bastien; Kermorvant, Christopher On the evaluation of handwritten text line detection algorithms Inproceedings International Conference of Document Analysis and Recognition, 2013. Links | BibTeX @inproceedings{Moysset2013,
title = {On the evaluation of handwritten text line detection algorithms},
author = { Bastien Moysset and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2014/11/icdar2013_line.pdf
http://www.teklia.com/wp-content/uploads/2016/08/ICDAR13_line_poster.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Nion, Thibauld; Menasri, Farès; Louradour, Jérôme; Sibade, Cédric; Retornaz, Thomas; Métaireau, Pierre-Yves; Kermorvant, Christopher Handwritten information extraction from historical census documents Inproceedings International Conference of Document Analysis and Recognition, 2013. Links | BibTeX @inproceedings{Nion2013,
title = {Handwritten information extraction from historical census documents},
author = { Thibauld Nion and Farès Menasri and Jérôme Louradour and Cédric Sibade and Thomas Retornaz and Pierre-Yves Métaireau and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/icdar2013_archives.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {International Conference of Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Kermorvant, Hervé Glotin
Xanadu Halkias
Christopher Evolution of Sparse Constraints in Deep AI: From a general sparse penalty to Structured Sparsity Technical Report 2013. BibTeX @techreport{glotin2013,
title = {Evolution of Sparse Constraints in Deep AI: From a general sparse penalty to Structured Sparsity},
author = {Hervé Glotin
Xanadu Halkias
Christopher Kermorvant},
year = {2013},
date = {2013-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
|
Kermorvant, Hervé Glotin
Xanadu Halkias
Christopher General Sparse Penalty in Deep Belief Networks: Towards Domain Adaptation Technical Report 2013. BibTeX @techreport{glotin2013b,
title = {General Sparse Penalty in Deep Belief Networks: Towards Domain Adaptation},
author = {Hervé Glotin
Xanadu Halkias
Christopher Kermorvant},
year = {2013},
date = {2013-01-01},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
|
2012
|
Bianne-bernard, Anne-laure; Menasri, Fares; Likforman-sulem, Laurence; Mokbel, Chafic; Kermorvant, Christopher Variable length and context-dependent HMM letter form models for Arabic handwritten word recognition Inproceedings Document Recognition and Retrieval Conference, 2012. Links | BibTeX @inproceedings{Bianne-bernard2012,
title = {Variable length and context-dependent HMM letter form models for Arabic handwritten word recognition},
author = { Anne-laure Bianne-bernard and Fares Menasri and Laurence Likforman-sulem and Chafic Mokbel and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/drr2012.pdf},
year = {2012},
date = {2012-01-01},
booktitle = {Document Recognition and Retrieval Conference},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Likforman-Sulem, Laurence; Hajj, Ramy Mohammad Al; Mokbel, Chafic; Menasri, Fares; Bianne-Bernard, Anne-Laure; Kermorvant, Christopher Features for HMM-Based Arabic Handwritten Word Recognition Systems Incollection Märgner, Volker ; El Abed, Haikal (Ed.): Guide to OCR for Arabic Scripts, Springer, 2012, ISBN: 978-1-4471-4071-9. BibTeX @incollection{Likforman-Sulem2012,
title = {Features for HMM-Based Arabic Handwritten Word Recognition Systems},
author = { Laurence Likforman-Sulem and Ramy Mohammad Al Hajj and Chafic Mokbel and Fares Menasri and Anne-Laure Bianne-Bernard and Christopher Kermorvant},
editor = {Märgner, Volker and El Abed, Haikal},
isbn = {978-1-4471-4071-9},
year = {2012},
date = {2012-01-01},
booktitle = {Guide to OCR for Arabic Scripts},
publisher = {Springer},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
|
Louradour, Jérôme; Bluche, Théodore; Bianne-Bernard, Anne-Laure; Menasri, Farès; Kermorvant, Christopher De l'usage des scores et des alternatives de reconnaissance pour la classification d'images de documents manuscrits Inproceedings Colloque International Francophone sur l'Ecrit et le Document, 2012. Links | BibTeX @inproceedings{Louradour,
title = {De l'usage des scores et des alternatives de reconnaissance pour la classification d'images de documents manuscrits},
author = { Jérôme Louradour and Théodore Bluche and Anne-Laure Bianne-Bernard and Farès Menasri and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/cifed2012.pdf},
year = {2012},
date = {2012-01-01},
booktitle = {Colloque International Francophone sur l'Ecrit et le Document},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Menasri, Farès; Louradour, Jérôme; Bianne-Bernard, Anne-laure; Kermorvant, Christopher The A2iA French handwriting recognition system at the Rimes-ICDAR2011 competition Inproceedings Document Recognition and Retrieval Conference, 2012. Links | BibTeX @inproceedings{Menasi2012,
title = {The A2iA French handwriting recognition system at the Rimes-ICDAR2011 competition},
author = { Farès Menasri and Jérôme Louradour and Anne-laure Bianne-Bernard and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/drr2012b.pdf},
year = {2012},
date = {2012-01-01},
booktitle = {Document Recognition and Retrieval Conference},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Louradour, Christopher Kermorvant
Anne-Laure Bianne-Bernard
Théodore Bluche
Jérôme On using alternative recognition candidates and scores for handwritten documents classification Technical Report A2iA Lab 2012. Links | BibTeX @techreport{kermorvant2012,
title = {On using alternative recognition candidates and scores for handwritten documents classification},
author = {Christopher Kermorvant
Anne-Laure Bianne-Bernard
Théodore Bluche
Jérôme Louradour},
url = {http://www.teklia.com/wp-content/uploads/2017/01/a2ia-rr-2012-1.pdf},
year = {2012},
date = {2012-01-01},
institution = {A2iA Lab},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
|
2011
|
Bianne-Bernard, A -L; Kermorvant, C; Likforman-Sulem, L; Mokbel, C Modélisation de HMMs en contexte avec des arbres de décision pour la reconnaissance de mots manuscrits Journal Article Document Numérique, 2011. BibTeX @article{Mokbel2011a,
title = {Modélisation de HMMs en contexte avec des arbres de décision pour la reconnaissance de mots manuscrits},
author = { A.-L. Bianne-Bernard and C. Kermorvant and L. Likforman-Sulem and C. Mokbel},
year = {2011},
date = {2011-01-01},
journal = {Document Numérique},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Bianne, A -L; Menasri, F; Al-Hajj, R; Mokbel, C; Kermorvant, C; Likforman-Sulem, L Dynamic and Contextual Information in HMM modeling for Handwriting Recognition Journal Article IEEE Trans. on Pattern Analysis and Machine Intelligence, 33 (10), 2011. BibTeX @article{Bianne_etal,
title = {Dynamic and Contextual Information in HMM modeling for Handwriting Recognition},
author = { A.-L. Bianne and F. Menasri and R. Al-Hajj and C. Mokbel and C. Kermorvant and L. Likforman-Sulem},
year = {2011},
date = {2011-01-01},
journal = {IEEE Trans. on Pattern Analysis and Machine Intelligence},
volume = {33},
number = {10},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Kermorvant-Duchemin, Elsa; Iacobelli, Silvia; Dit-Trolli, Sergio Eleni; Bonsante, Francesco; Kermorvant, Christopher; Sarfati, Gilles; Gouyon, Jean-Bernard; Lapillonne, Alexandre Early chloride intake does not parallel that of sodium in extremely low birth weight infants and may impair neonatal outcomes. Journal Article Journal of pediatric gastroenterology and nutrition, 2011, ISSN: 1536-4801. Abstract | Links | BibTeX @article{Kermorvant-Duchemin2011,
title = {Early chloride intake does not parallel that of sodium in extremely low birth weight infants and may impair neonatal outcomes.},
author = { Elsa Kermorvant-Duchemin and Silvia Iacobelli and Sergio Eleni Dit-Trolli and Francesco Bonsante and Christopher Kermorvant and Gilles Sarfati and Jean-Bernard Gouyon and Alexandre Lapillonne},
url = {http://www.ncbi.nlm.nih.gov/pubmed/22173302},
doi = {10.1097/MPG.0b013e318245b428},
issn = {1536-4801},
year = {2011},
date = {2011-01-01},
journal = {Journal of pediatric gastroenterology and nutrition},
abstract = {BACKGROUND:: Accurate data on the optimal chloride intake in premature infants are scarce. OBJECTIVE:: To describe chloride (Cl) intakes in the first 10 days (D) of life and to assess the relationships between high Cl intakes and corrected serum chloride level or markers of severe acidosis in infants less than 28 weeks gestation. METHODS:: Retrospective cohort study including all infants < 28 weeks admitted to the neonatal intensive care unit over a 3-year period and cared for from birth until D10 or more. RESULTS:: Fifty-six infants were included. Cumulative total Cl intakes reached (mean +/- SD) 9.6 +/- 3.7 mmol/kg at day 3 and 49.2 +/- 13.5 mmol/kg at D10. Inadvertent intakes (from intravenous fluids other than parenteral nutrition) represented on average 70% of total Cl intakes in the first 3 days. Difference between Cl and sodium intakes reached (mean +/- SD) 7.8 +/- 4.8 mmol/kg at D10 and mainly originated from parenteral nutrition. By multivariate analysis, cumulative Cl intake > 10 mmol/kg during the first 3 days was an independent risk factor of base excess <-10 mmol/l. Cumulative Cl intake > 45 mmol/kg during the first 10 days was an independent risk factor of corrected chloremia > 115 mmol/l and of base excess <-10 mmol/l. CONCLUSIONS:: Cumulative Cl intake over 10 mmol/kg during the first 3 days (i.e. 3.3 mmol/kg/d on average) and over 45 mmol/kg during the first 10 days (i.e. 4.5 mmol/kg/d on average) may have unwanted metabolic consequences and should be avoided. Imbalance between electrolytes provided by the parenteral nutrition solution need to be detected and corrected.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
BACKGROUND:: Accurate data on the optimal chloride intake in premature infants are scarce. OBJECTIVE:: To describe chloride (Cl) intakes in the first 10 days (D) of life and to assess the relationships between high Cl intakes and corrected serum chloride level or markers of severe acidosis in infants less than 28 weeks gestation. METHODS:: Retrospective cohort study including all infants < 28 weeks admitted to the neonatal intensive care unit over a 3-year period and cared for from birth until D10 or more. RESULTS:: Fifty-six infants were included. Cumulative total Cl intakes reached (mean +/- SD) 9.6 +/- 3.7 mmol/kg at day 3 and 49.2 +/- 13.5 mmol/kg at D10. Inadvertent intakes (from intravenous fluids other than parenteral nutrition) represented on average 70% of total Cl intakes in the first 3 days. Difference between Cl and sodium intakes reached (mean +/- SD) 7.8 +/- 4.8 mmol/kg at D10 and mainly originated from parenteral nutrition. By multivariate analysis, cumulative Cl intake > 10 mmol/kg during the first 3 days was an independent risk factor of base excess <-10 mmol/l. Cumulative Cl intake > 45 mmol/kg during the first 10 days was an independent risk factor of corrected chloremia > 115 mmol/l and of base excess <-10 mmol/l. CONCLUSIONS:: Cumulative Cl intake over 10 mmol/kg during the first 3 days (i.e. 3.3 mmol/kg/d on average) and over 45 mmol/kg during the first 10 days (i.e. 4.5 mmol/kg/d on average) may have unwanted metabolic consequences and should be avoided. Imbalance between electrolytes provided by the parenteral nutrition solution need to be detected and corrected. |
Louradour, Jérôme; Kermorvant, Christopher Sample-dependent feature selection for faster document image categorization Inproceedings International Conference on Document Analysis and Recognition, 2011. Links | BibTeX @inproceedings{Louradour2011,
title = {Sample-dependent feature selection for faster document image categorization},
author = { Jérôme Louradour and Christopher Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2018/07/louradour_kermorvant.pdf},
year = {2011},
date = {2011-01-01},
booktitle = {International Conference on Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sibade, Cédric; Retornaz, Thomas; Nion, Thibauld; Lerallut, Romain; Kermorvant, Christopher Automatic indexing of French handwritten census registers for probate genealogy Inproceedings First International Workshop on Historical Document Imaging and Processing, 2011, ISBN: 9781450309165. BibTeX @inproceedings{Sibade2011a,
title = {Automatic indexing of French handwritten census registers for probate genealogy},
author = { Cédric Sibade and Thomas Retornaz and Thibauld Nion and Romain Lerallut and Christopher Kermorvant},
isbn = {9781450309165},
year = {2011},
date = {2011-01-01},
booktitle = {First International Workshop on Historical Document Imaging and Processing},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2010
|
Bianne, Anne-Laure; Kermorvant, Christopher; Likforman-Sulem, Laurence Context-dependent HMM modeling using tree-based clustering for the recognition of handwritten words Inproceedings Document Recognition and Retrieval Conference, 2010. Links | BibTeX @inproceedings{Bianne2010a,
title = {Context-dependent HMM modeling using tree-based clustering for the recognition of handwritten words},
author = { Anne-Laure Bianne and Christopher Kermorvant and Laurence Likforman-Sulem},
url = {http://link.aip.org/link/PSISDG/v7534/i1/p75340I/s1&Agg=doi},
doi = {10.1117/12.838806},
year = {2010},
date = {2010-01-01},
booktitle = {Document Recognition and Retrieval Conference},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Bianne, Anne-Laure; Kermorvant, Christopher; Likforman-sulem, Laurence; Mokbel, Chafic Modélisation de HMMs en contexte avec des arbres de décision pour la reconnaissance de mots manuscrits Inproceedings Colloque International Francophone sur l'Ecrit et le Document, 2010. BibTeX @inproceedings{Bianne2010b,
title = {Modélisation de HMMs en contexte avec des arbres de décision pour la reconnaissance de mots manuscrits},
author = { Anne-Laure Bianne and Christopher Kermorvant and Laurence Likforman-sulem and Chafic Mokbel},
year = {2010},
date = {2010-01-01},
booktitle = {Colloque International Francophone sur l'Ecrit et le Document},
volume = {0},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Kermorvant, C; Louradour, J How to save feature extraction time for fast and robust classification? Inproceedings Proceedings of the Int. Conf. on Artificial Intelligence and Statistics, 2010. BibTeX @inproceedings{Kermorvant2010d,
title = {How to save feature extraction time for fast and robust classification?},
author = { C. Kermorvant and J. Louradour},
year = {2010},
date = {2010-01-01},
booktitle = {Proceedings of the Int. Conf. on Artificial Intelligence and Statistics},
number = {"Breaking News" poster session},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Kermorvant, C; Louradour, J Handwritten mail classification experiments with the Rimes database Inproceedings Proc. of the Int. Conf. on Frontiers in Handwriting Recognition, 2010. BibTeX @inproceedings{Kermorvant2010c,
title = {Handwritten mail classification experiments with the Rimes database},
author = { C. Kermorvant and J. Louradour},
year = {2010},
date = {2010-01-01},
booktitle = {Proc. of the Int. Conf. on Frontiers in Handwriting Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Kermorvant, C; Menasri, F; Bianne, A -L; Al-Hajj, R; Mokbel, C; Likforman-Sulem, L The A2iA-Telecom ParisTech-UOB System for the ICDAR 2009 Handwriting Recognition Competition. Inproceedings Proc. of the Int. Conf. on Frontiers in Handwriting Recognition, 2010. BibTeX @inproceedings{Kermorvant_etal2010,
title = {The A2iA-Telecom ParisTech-UOB System for the ICDAR 2009 Handwriting Recognition Competition.},
author = { C. Kermorvant and F. Menasri and A.-L. Bianne and R. Al-Hajj and C. Mokbel and L. Likforman-Sulem},
year = {2010},
date = {2010-01-01},
booktitle = {Proc. of the Int. Conf. on Frontiers in Handwriting Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2009
|
Bianne, Anne-Laure; Kermorvant, Christopher; Marty, Patrick; Menasri, Farès Les caractères ne sont pas la clef des champs Inproceedings Conférence Francophone sur l'Apprentissage Automatique, 2009. BibTeX @inproceedings{Bianne2009a,
title = {Les caractères ne sont pas la clef des champs},
author = { Anne-Laure Bianne and Christopher Kermorvant and Patrick Marty and Farès Menasri},
year = {2009},
date = {2009-01-01},
booktitle = {Conférence Francophone sur l'Apprentissage Automatique},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Kermorvant, C; Bianne, A -L; Marty, Patrick; Menasri, Farès From Isolated Handwritten Characters to Fields Recognition: There's Many a Slip twixt Cup and Lip Inproceedings International Conference on Document Analysis and Recognition, 2009. Links | BibTeX @inproceedings{Kermorvant2009a,
title = {From Isolated Handwritten Characters to Fields Recognition: There's Many a Slip twixt Cup and Lip},
author = { C. Kermorvant and A.-L. Bianne and Patrick Marty and Farès Menasri},
url = {http://www.teklia.com/wp-content/uploads/2016/12/icdar2009.pdf},
year = {2009},
date = {2009-01-01},
booktitle = {International Conference on Document Analysis and Recognition},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2008
|
Kermorvant, C Some Hints on the Teaching of Machine Learning to Industrial Practitioners Inproceedings 2008. Links | BibTeX @inproceedings{Kermorvant2008,
title = {Some Hints on the Teaching of Machine Learning to Industrial Practitioners},
author = { C. Kermorvant},
url = {http://www.teklia.com/wp-content/uploads/2017/01/kermorvant_TML.pdf},
year = {2008},
date = {2008-01-01},
journal = {Teaching Machine Learning: workshop on open problems and new directions},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
