Publications

2024

1. P445 Wireless capsule endoscopy reading support for Crohn’s disease patients using deep neural networks with an active learning method

   Raphaëlle Rouveyre, T Subileau-Langlois, Tristan Gomez, Harold Mouchère, and 2 more authors

   Journal of Crohn’s and Colitis, Jan 2024

   DOI HAL
2. A Survey on Handwritten Mathematical Expression Recognition: The Rise of Encoder-Decoder and GNN Models

   Thanh-Nghia Truong, Cuong Tuan Nguyen, Richard Zanibbi, Harold Mouchère, and 1 more author

   Pattern Recognition, Apr 2024

   DOI HAL
3. Influence of training and expertise on deep neural network attention and human attention during a medical image classification task

   Rémi Vallée, Tristan Gomez, Arnaud Bourreille, Nicolas Normand, and 2 more authors

   Journal of Vision, Apr 2024

   DOI PDF HAL

2023

1. Model-based inexact graph matching on top of DNNs for semantic scene understanding

   Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Rozenn Dahyot, and 1 more author

   Computer Vision and Image Understanding, Jun 2023

   27 pages, 9 figures, 11 tables

   DOI PDF HAL
2. Computing and evaluating saliency maps for image classification: a tutorial

   Tristan Gomez, and Harold Mouchère

   Journal of Electronic Imaging, Mar 2023

   DOI PDF HAL
3. A methodology to compare XAI explanations on natural language processing

   Gaëlle Jouis, Harold Mouchère, Fabien Picarougne, and Alexandre Hardouin

   In Explainable Deep Learning AI, Mar 2023

   DOI HAL
4. Point to segment distance DTW for online handwriting signals matching

   Elmokhtar Mohamed Moussa, Thibault Lelore, and Harold Mouchère

   In ICPRAM 2023, Feb 2023

   PDF HAL
5. SET, SORT! A Novel Sub-Stroke Level Transformers for Offline Handwriting to Online Conversion

   Elmokhtar Mohamed Moussa, Thibault Lelore, and Harold Mouchère

   In The 17th International Conference on Document Analysis and Recognition (ICDAR 2023), Aug 2023

   DOI PDF HAL
6. Handwritten Text Recognition from Crowdsourced Annotations

   Solène Tarride, Tristan Faine, Mélodie Boillet, Harold Mouchère, and 1 more author

   In Proceedings of the 7th International Workshop on Historical Document Imaging and Processing, Aug 2023

   Abs DOI PDF HAL

   In this paper, we explore different ways of training a model for handwritten text recognition when multiple imperfect or noisy transcriptions are available. We consider various training configurations, such as selecting a single transcription, retaining all transcriptions, or computing an aggregated transcription from all available annotations. In addition, we evaluate the impact of quality-based data selection, where samples with low agreement are removed from the training set. Our experiments are carried out on municipal registers of the city of Belfort (France) written between 1790 and 1946. The results show that computing a consensus transcription or training on multiple transcriptions are good alternatives. However, selecting training samples based on the degree of agreement between annotators introduces a bias in the training data and does not improve the results. Our dataset is publicly available on Zenodo.

7. ICDAR 2023 CROHME: Competition on Recognition of Handwritten Mathematical Expressions

   Yejing Xie, Harold Mouchère, Foteini Simistira Liwicki, Sumit Rakesh, and 4 more authors

   In Book cover Book cover International Conference on Document Analysis and Recognition, Aug 2023

   DOI PDF HAL

2022

1. Improving semantic segmentation with graph-based structural knowledge

   Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Rozenn Dahyot, and 1 more author

   In International Conference on Pattern Recognition and Artificial Intelligence, Jun 2022

   DOI HAL
2. QAP Optimisation with Reinforcement Learning for Faster Graph Matching in Sequential Semantic Image Analysis

   Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Rozenn Dahyot, and 1 more author

   In International Conference on Pattern Recognition and Artificial Intelligence, Jun 2022

   DOI HAL
3. A time-lapse embryo dataset for morphokinetic parameter prediction

   Tristan Gomez, Magalie Feyeux, Justine Boulant, Nicolas Normand, and 4 more authors

   Data in Brief, May 2022

   DOI HAL
4. Beyond deep learning: automatic morpho-kinetic parameter extraction using spatial attention

   T Gomez, T Fréour, and Harold Mouchère

   Human Reproduction, Jul 2022

   DOI PDF HAL
5. Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study

   Tristan Gomez, Thomas Fréour, and Harold Mouchère

   In XAI Workshop (ICPR 2022), Aug 2022

   PDF HAL
6. Metrics for saliency map evaluation of deep learning explanation methods

   Tristan Gomez, Thomas Fréour, and Harold Mouchère

   In International Conference on Pattern Recognition and Artificial Intelligence, Jun 2022

   DOI URL
7. BR-NPA: A non-parametric high-resolution attention model to improve the interpretability of attention

   Tristan Gomez, Suiyi Ling, Thomas Fréour, and Harold Mouchère

   Pattern Recognition, Dec 2022

   DOI PDF HAL
8. Applications of artificial intelligence and machine learning for the hip and knee surgeon: current state and implications for the future

   Christophe Nich, Julien Behr, Vincent Crenn, Nicolas Normand, and 2 more authors

   International Orthopaedics (SICOT), Dec 2022

   DOI
9. Using Knowledge Graphs and Human-Centric Artificial Intelligence for Reconfigurable Supply Chains: A Research Framework

   Benjamin Rolf, Nasser Mebarki, Sebastian Lang, Tobias Reggelin, and 3 more authors

   In MIM 2022: 10th IFAC Conference on Manufacturing Modelling, Management and Control, Jun 2022

   DOI PDF HAL
10. Improving Oracle Bone Characters Recognition via A CycleGAN-based Data Augmentation Method

    Wei Wang, Ting Zhang, Xinxin Jin, Harold Mouchère, and 1 more author

    In International Conference on Neural Information Processing (ICONIP), Nov 2022

    PDF HAL
11. Contrastive Self-Supervised Learning on Crohn’s Disease Detection

    Jing Xing, and Harold Mouchère

    In The 6th International Workshop on Deep Learning in Bioinformatics, Biomedicine, and Healthcare Informatics (DLB2H 2022), Dec 2022

    PDF HAL

2021

1. Anchors vs Attention: Comparing XAI on a Real-Life Use Case

   Gaëlle Jouis, Harold Mouchère, Fabien Picarougne, and Alexandre Hardouin

   In Pattern Recognition. ICPR International Workshops and Challenges - Virtual Event, January 10-15, 2021, Proceedings, Part III, Dec 2021

   DOI URL
2. Ancres vs Attention : comparaison de méthodes d’explicabilité des réseaux profonds sur un cas d’usage réel

   Gaëlle Jouis, Harold Mouchère, Fabien Picarougne, and Alexandre Hardouin

   In 21èmes Journées Francophones Extraction et Gestion des Connaissances, Jan 2021

   PDF HAL
3. Multi-expert annotation of Crohn’s disease images of the small bowel for automatic detection using a convolutional recurrent attention neural network

   Astrid Maissin, Remi Vallée, Mathurin Flamant, Marie Fondain-Bossiere, and 7 more authors

   Endoscopy International Open, Jan 2021

   DOI PDF HAL
4. Applying End-to-End Trainable Approach on Stroke Extraction in Handwritten Math Expressions Images

   Elmokhtar Mohamed Moussa, Thibault Lelore, and Harold Mouchère

   In 16th International Conference on Document Analysis and Recognition, ICDAR 2021, Lausanne, Switzerland, September 5-10, 2021, Proceedings, Part III, Jan 2021

   DOI URL
5. Influence of expertise on human and machine visual attention in a medical image classification task

   Rémi Vallée, Antoine Coutrot, Nicolas Normand, and Harold Mouchère

   In European Conference on Visual Perception, Aug 2021

   HAL

2020

1. Méthode d’analyse sémantique d’images combinant apprentissage profond et relations structurelles par appariement de graphes

   Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Isabelle Bloch, and 1 more author

   In Rencontres des Jeunes Chercheur\timesses en Intelligence Artificielle (RJCIA 2020), Jun 2020

   PDF HAL
2. Semantic image segmentation based on spatial relationships and inexact graph matching

   Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Rozenn Dahyot, and 1 more author

   In Tenth International Conference on Image Processing Theory, Tools and Applications, IPTA 2020, Paris, France, November 9-12, 2020, Jun 2020

   DOI
3. Apprentissage profond appliqué à la classification d’images microscopiques embryonnaires

   Tristan Gomez, Harold Mouchère, Thomas Fréour, and Magalie Feyeux

   In Rencontres des Jeunes Chercheur\timesses en Intelligence Artificielle (RJCIA 2020), Jun 2020

   PDF HAL
4. Tour d’horizon autour de l’explicabilité des modèles profonds

   Gaëlle Jouis, Harold Mouchère, Fabien Picarougne, and Alexandre Hardouin

   In Rencontres des Jeunes Chercheur\timesses en Intelligence Artificielle (RJCIA 2020), Jun 2020

   PDF HAL
5. A general framework for the recognition of online handwritten graphics

   Frank D. Julca-Aguilar, Harold Mouchère, Christian Viard-Gaudin, and Nina S. T. Hirata

   Int. J. Document Anal. Recognit., Jun 2020

   DOI
6. CrohnIPI: An endoscopic image database for the evaluation of automatic Crohn’s disease lesions recognition algorithms

   Rémi Vallée, Astrid De Maissin, Antoine Coutrot, Harold Mouchère, and 2 more authors

   In Medical Imaging 2020: Biomedical Applications in Molecular, Structural, and Functional Imaging, Feb 2020

   DOI

2019

1. On The Fly Generated Data for Industrial Part Orientation Estimation with Deep Neural Networks

   Julien Langlois, Harold Mouchère, Nicolas Normand, and Christian Viard-Gaudin

   In Fifteenth International Conference on Quality Control by Artificial Vision, May 2019

   DOI PDF HAL
2. ICDAR 2019 CROHME + TFD: Competition on Recognition of Handwritten Mathematical Expressions and Typeset Formula Detection

   Mahshad Mahdavi, Richard Zanibbi, Harold Mouchère, Christian Viard-Gaudin, and 1 more author

   In 15th IAPR International Conference on Document Analysis and Recognition (ICDAR 2019), Sep 2019

   PDF HAL
3. Accurate small bowel lesions detection in wireless capsule endoscopy images using deep recurrent attention neural network

   Rémi Vallée, Antoine Coutrot, Nicolas Normand, and Harold Mouchère

   In IEEE 21st International Workshop on Multimedia Signal Processing (MMSP 2019), Sep 2019

   PDF HAL
4. Réseau de neurones récurrent à attention pour la détection de lésions intestinales

   Rémi Vallée, A De Maissin, Harold Mouchère, A Boureille, and 2 more authors

   In ORASIS, May 2019

   PDF HAL

2018

1. Crowdsourcing-based Annotation of the Accounting Registers of the Italian Comedy

   Adeline Granet, Benjamin Hervy, Geoffrey Roman Jimenez, Marouane Hachicha, and 6 more authors

   In 11th edition of the Language Resources and Evaluation Conference (LREC 2018), May 2018

   HAL
2. Décodeur neuronal pour la transcription de documents manuscrits anciens

   Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou, and 1 more author

   In TALN, May 2018

   PDF HAL
3. Transfer Learning for a Letter-Ngrams to Word Decoder in the Context of Historical Handwriting Recognition with Scarce Resources

   Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou, and 1 more author

   In Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018), Aug 2018

   PDF HAL
4. Transfer Learning for Handwriting Recognition on Historical Documents

   Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou, and 1 more author

   In International Conference on Pattern Recognition Applications and Methods, Jan 2018

   HAL
5. Separating Optical and Language Models through Encoder-Decoder Strategy for Transferable Handwriting Recognition

   Adeline Granet, Emmanuel Morin, Solen Quiniou, Christian Viard-Gaudin, and 1 more author

   In 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Aug 2018

   PDF HAL
6. 3D Orientation Estimation of Industrial Parts from 2D Images using Neural Networks

   Julien Langlois, Harold Mouchère, Nicolas Normand, and Christian Viard-Gaudin

   In International Conference on Pattern Recognition Applications and Methods, Jan 2018

   HAL
7. Computer aided detection of Crohn’s disease small bowel lesions in wireless capsule endoscopy

   Astrid Maissin, Tristan Gomez, Catherine Le Berre, Nicolas Normand, and 3 more authors

   In European Crohn’s and Colitis Organisation (ECCO), Jan 2018

   DOI HAL
8. Document Analysis and Text Recognition, Benchmarking State-of-the-Art Systems

   Harold Mouchère, Christian Viard-Gaudin, Richard Zanibbi, and Utpal Garain

   Apr 2018

   DOI HAL
9. Transfer Learning for Structures Spotting in Unlabeled Handwritten Documents using Randomly Generated Documents

   Geoffrey Roman-Jimenez, Christian Viard-Gaudin, Adeline Granet, and Harold Mouchère

   In International Conference on Pattern Recognition Applications and Methods, Jan 2018

   HAL
10. A tree-BLSTM-based recognition system for online handwritten mathematical expressions

    Ting Zhang, Harold Mouchère, and Christian Viard-Gaudin

    Neural Computing and Applications (NCAA, indexée JCR), Oct 2018

    DOI PDF HAL

2017

1. Early Recognition of Handwritten Gestures based on Multi-classifier Reject Option

   Zhaoxin Chen, Harold Mouchère, Eric Anquetil, and Christian Viard-Gaudin

   In 14th IAPR International Conference on Document Analysis and Recognition (ICDAR2017), Nov 2017

   DOI PDF HAL
2. Étude préliminaire de reconnaissance d’écriture sur des documents historiques

   Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou, and 1 more author

   In Rencontre des Jeunes Chercheurs en Recherche d’Information (RJCRI), Mar 2017

   PDF HAL
3. Combining Speech and Handwriting Modalities for Mathematical Expression Recognition

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   IEEE Transactions on Human-Machine Systems (THMS, indexée JCR), Apr 2017

   DOI URL
4. Online flowchart understanding by combining max-margin Markov random field with grammatical analysis

   Chengcheng Wang, Harold Mouchère, Aurélie Lemaitre, and Christian Viard-Gaudin

   International Journal on Document Analysis and Recognition (IJDAR, indexée JCR), Jun 2017

   DOI PDF HAL
5. Tree-based BLSTM for mathematical expression recognition

   Ting Zhang, Harold Mouchère, and Christian Viard-Gaudin

   In International Conference on Document Analysis and Recognition (ICDAR), Nov 2017

   DOI PDF HAL

2016

1. The MUMTDB dataset for evaluating simultaneous composition of structured documents in a multi-user and multi-touch environment

   Zhaoxin Chen, Eric Anquetil, Harold Mouchère, and Viard-Gaudin Christian

   In Int. Conf. on Frontier in Handwriting Recognition (ICFHR), Nov 2016

   URL
2. Subexpression and Dominant Symbol Histograms for Spatial Relation Classification in Mathematical Expressions

   Frank Julca-Aguilar, Nina S. T. Hirata, Harold Mouchère, and Christian Viard-Gaudin

   In 23rd International Conference on Pattern Recognition (ICPR2016), Nov 2016

   HAL
3. ICFHR2016 Competition on Recognition of Handwritten Mathematical Expressions (CROHME2016)

   Harold Mouchère, Viard-Gaudin Christian, Richard Zanibbi, and Utpal Garain

   In Int. Conf. on Frontier in Handwriting Recognition (ICFHR), Nov 2016

   HAL
4. Advancing the state of the art for handwritten math recognition: the CROHME competitions, 2011–2014

   Harold Mouchère, Richard Zanibbi, Utpal Garain, and Christian Viard-Gaudin

   International Journal on Document Analysis and Recognition (IJDAR, indexée JCR), Nov 2016

   Abs DOI URL

   The CROHME competitions have helped organize the field of handwritten mathematical expression recognition. This paper presents the evolution of the competition over its first 4 years, and its contributions to handwritten math recognition, and more generally structural pattern recognition research. The competition protocol, evaluation metrics and datasets are presented in detail. Participating systems are analyzed and compared in terms of the central mathematical expression recognition tasks: (1) symbol segmentation, (2) classification of individual symbols, (3) symbol relationships and (4) structural analysis (parsing). The competition led to the development of label graphs, which allow recognition results with conflicting segmentations to be directly compared and quantified using Hamming distances. We introduce structure confusion histograms that provide frequencies for incorrect subgraphs corresponding to ground-truth label subgraphs of a given size and present structure confusion histograms for symbol bigrams (two symbols with a relationship) for CROHME 2014 systems. We provide a novel analysis combining results from competing systems at the level of individual strokes and stroke pairs; this virtual merging of system outputs allows us to more closely examine limitations for current state-of-the-art systems. Datasets along with evaluation and visualization tools produced for the competition are publicly available.

5. Combined Segmentation and Recognition of Online Handwritten Diagrams with High Order Markov Random Field

   Chengcheng Wang, Harold Mouchère, Viard-Gaudin Christian, and Lianwen Jin

   In Int. Conf. on Frontier in Handwriting Recognition (ICFHR), Nov 2016

   HAL
6. Online Handwritten Mathematical Expressions Recognition by Merging Multiple 1D Interpretations

   Ting Zhang, Harold Mouchère, and Viard-Gaudin Christian

   In Int. Conf. on Frontier in Handwriting Recognition (ICFHR), Nov 2016

   HAL
7. Using BLSTM for Interpretation of 2D Languages - Case of Handwritten Mathematical Expressions.

   Ting Zhang, Harold Mouchère, and Viard-Gaudin Christian

   In CORIA-CIFED, Nov 2016
8. Using BLSTM for Interpretation of 2D Languages - Case of Handwritten Mathematical Expressions.

   Ting Zhang, Harold Mouchère, and Viard-Gaudin Christian

   Document Numérique, Nov 2016

   DOI URL
9. SpottingNet: Learning the Similarity of Word Images with Convolutional Neural Network for Word Spotting in Handwritten Historical Documents

   Zhong Zhuoyao, Weishen Pan, Harold Mouchère, and Viard-Gaudin Christian

   In Int. Conf. on Frontier in Handwriting Recognition (ICFHR), Nov 2016

   HAL

2015

1. Recognize multi-touch gestures by graph modeling and matching

   Zhaoxin Chen, Eric Anquetil, Harold Mouchère, and Christian Viard-Gaudin

   In 17th Biennial Conference of the International Graphonomics Society. Drawing, Handwriting Processing Analysis: New Advances and Challenges, Nov 2015
2. Top-Down Online Handwritten Mathematical Expression Parsing with Graph Grammar

   Frank Julca-Aguilar, Harold Mouchère, Christian Viard-Gaudin, and Nina Hirata

   Nov 2015

   DOI
3. On-line Handwritten Isolated Symbol Recognition using Bidirectional Long Short-term Memory (BLSTM) Networks

   Ting Zhang, Harold Mouchère, and Viard-Gaudin Christian

   In Third Sino-French Workshop on Education and Research collaborations in Information and Communication Technologies SIFWICT 2015, Nov 2015

2014

1. A global learning approach for an online handwritten mathematical expression recognition system

   Ahmad-Montaser Awal, Harold Mouchère, and Christian Viard-Gaudin

   Pattern Recognition Letters, (PRL, indexée JCR), Jan 2014

   DOI URL
2. A graph modeling strategy for multi-touch gesture recognition

   Zhaoxin Chen, Eric Anquetil, Harold Mouchère, and Christian Viard-Gaudin

   In 14th International Conference on Frontiers in Handwriting Recognition (ICFHR-2014), Sep 2014

   PDF HAL
3. Mathematical symbol hypothesis recognition with rejection option

   Frank Julca-Aguilar, Nina S. T. Hirata, Christian Viard-Gaudin, Harold Mouchère, and 1 more author

   In 14th International Conference on Frontiers in Handwriting Recognition, Sep 2014

   DOI PDF HAL
4. Integration of Shape Context and Neural Networks for Symbol Recognition

   Frank Julca-Aguilar, Christian Viard-Gaudin, Harold Mouchère, Sofiane Medjkoune, and 1 more author

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2014), Mar 2014

   PDF HAL
5. An annotation assistance system using an unsupervised codebook composed of handwritten graphical multi-stroke symbols

   Jinpeng Li, Harold Mouchère, and Christian Viard-Gaudin

   Pattern Recognition Letters (PRL, indexée JCR), Jan 2014

   DOI HAL
6. Approches multimodales pour la reconnaissance d’expressions mathématiques

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   Document Numérique, Jan 2014

   URL
7. Vers l’Alignement des Signaux Écrit et Sonore

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2014), Mar 2014

   PDF HAL
8. Text Alignment from Bimodal Mathematical Expression Sources

   Sofiane Medjkoune, Harold Mouchère, Christian Viard-Gaudin, and Simon Petitrenaud

   In 14th International Conference on Frontiers in Handwriting Recognition, Sep 2014

   DOI PDF HAL
9. ICFHR 2014 - Competition on Recognition of On-line Mathematical Expressions (CROHME 2014)

   Harold Mouchère, Christian Viard-Gaudin, Richard Zanibbi, and Garain Utpal

   In Int. Conf. on Frontier in Handwriting Recognition (ICFHR), Sep 2014

2013

1. Interest of syntactic knowledge for on-line flowchart recognition

   Aurélie Lemaitre, Harold Mouchère, Jean Camillerapp, and Bertrand Couasnon

   Dec 2013

   DOI PDF HAL
2. Multimodal Mathematical Expressions Recognition: Case of Speech and Handwriting

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   Jul 2013

   DOI PDF HAL
3. Using Online Handwriting and Audio Streams for Mathematical Expressions Recognition: a Bimodal Approach

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   In Document Recognition and Retrieval XX, Feb 2013

   DOI PDF HAL
4. A dynamic Time Warping Algorithm for Recognition of Multi-Stroke On-Line Handwriten Characters

   Harold Mouchère, Jinpeng Li, Christian Viard-Gaudin, and Zhaoxin Chen

   Natural Science Edition, Journal of South China University of Technology, Jun 2013

   DOI PDF HAL
5. ICDAR 2013 CROHME: Third International Competition on Recognition of Online Handwritten Mathematical Expressions

   Harold Mouchère, Christian Viard-Gaudin, Richard Zanibbi, Utpal Garain, and 2 more authors

   In International Conference on Document Analysis and Recognition (ICDAR), Aug 2013
6. Evaluating Structural Pattern Recognition for Handwritten Math via Primitive Label Graphs

   Richard Zanibbi, Harold Mouchère, and Christian Viard-Gaudin

   In Proc. SPIE, Document Recognition and Retrieval XX, Aug 2013

   DOI PDF HAL

2012

1. Quantifying spatial relations to discover handwritten graphical symbols

   Jinpeng Li, Harold Mouchère, and Christian Viard-Gaudin

   In Document Recognition and Retrieval XIX, Part of the IS&T/SPIE 24th Annual Symposium on Electronic Imaging, Jan 2012

   HAL
2. Reducing AnnotationWorkload Using a Codebook Mapping and its Evaluation in On-Line Handwriting

   Jinpeng Li, Harold Mouchère, and Christian Viard-Gaudin

   In 2012 International Conference on Frontiers in Handwriting Recognition, Sep 2012

   PDF HAL
3. Une distance entre deux ensembles de séquences avec la contrainte de continuité

   Jinpeng Li, Harold Mouchère, and Christian Viard-Gaudin

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2012), Mar 2012

   PDF HAL
4. Fusion d’Informations Bi-modales pour la Reconnaissance d’Expressions Mathématiques Cas des modalités audio et écriture manuscrite en ligne

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2012), Mar 2012

   HAL
5. Using Speech for Handwritten Mathematical Expression Recognition Disambiguation

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   In 2012 International Conference on Frontiers in Handwriting Recognition, Sep 2012

   PDF HAL
6. ICFHR 2012 - Competition on Recognition of On-line Mathematical Expressions (CROHME 2012)

   Harold Mouchère, Christian Viard-Gaudin, Daehwan H. Kim, J. H. Kim, and 1 more author

   In Int. Conf. on Frontier in Handwriting Recognition (ICFHR), Sep 2012

2011

1. First Experiments on a new Online Handwritten Flowchart Database

   Ahmad-Montaser Awal, Guihuan Feng, Harold Mouchère, and Christian Viard-Gaudin

   In Document Recognition and Retrieval XVIII, Jan 2011

   DOI HAL
2. Encyclopedia of Cryptography and Security

   Patrizio Campisi, Emanuele Maiorana, Harold Mouchère, Christian Viard-Gaudin, and 1 more author

   Jan 2011

   DOI URL
3. Interest of Syntactic Knowledge for On-line Flowchart Recognition

   Aurélie Lemaitre, Harold Mouchère, Jean Camillerapp, and Bertrand B. Coüasnon

   In Graphics Recognition, GREC 2011, Sep 2011

   PDF HAL
4. Symbol Knowledge Extraction from a Simple Graphical Language

   Jinpeng Li, Harold Mouchère, and Christian Viard-Gaudin

   In 11th International Conference on Document Analysis and Recognition, ICDAR 2011, Sep 2011

   HAL
5. Unsupervised Handwriten Graphical Symbol Learning Using Minimum Description Length Principle on Relational Graph

   Jinpeng Li, Harold Mouchère, and Christian Viard-Gaudin

   In International Conference on Knowledge Discovery and Information Retrieval, KDIR 2011, Oct 2011

   HAL
6. Handwritten and Audio Information Fusion for Mathematical Symbol Recognition

   Sofiane Medjkoune, Harold Mouchère, Simon Petitrenaud, and Christian Viard-Gaudin

   In 11th International Conference on Document Analysis and Recognition, ICDAR 2011, Sep 2011

   HAL
7. CROHME2011: Competition on Recognition of Online Handwritten Mathematical Expressions

   Harold Mouchère, Christian Viard-Gaudin, Daehwan H. Kim, J. H. Kim, and 1 more author

   In Proc. Int. Conference on Document Analysis and Recognition, Sep 2011
8. HAMEX - A Handwritten and Audio Dataset of Mathematical Expressions

   Solen Quiniou, Harold Mouchère, Sébastian Saldarriaga, Christian Viard-Gaudin, and 3 more authors

   In International Conference on Document Analysis and Recognition (ICDAR), Sep 2011
9. Stroke-Based Performance Metrics for Handwritten Mathematical Expressions

   Richard Zanibbi, Amit Pillay, Harold Mouchère, Christian Viard-Gaudin, and 1 more author

   In Proc. Int. Conference on Document Analysis and Recognition, Sep 2011

   Abs

   Abstract—Evaluating mathematical expression recognition involves a complex interaction of input primitives (e.g. pen/finger strokes), recognized symbols, and recognized spatial structure. Existing performance metrics simplify this problem by separating the assessment of spatial structure from the assessment of symbol segmentation and classification. These metrics do not characterize the overall accuracy of a penbased mathematics recognition, making it difficult to compare math recognition algorithms, and preventing the use of machine learning algorithms requiring a criterion function characterizing overall system performance. To address this problem, we introduce performance metrics that bridge the gap from handwritten strokes to spatial structure. Our metrics are computed using bipartite graphs that represent classification, segmentation and spatial structure at the stroke level. Overall correctness of an expression is measured by counting the number of relabelings of nodes and edges needed to make the bipartite graph for a recognition result match the bipartite graph for ground truth. This metric may also be used with other primitive types (e.g. image pixels).

2010

1. A Hybrid Classifier for Handwritten Mathematical Expression Recognition

   Ahmad-Montaser Awal, Harold Mouchère, and Christian Viard-Gaudin

   In Electronic Imaging: Document Recognition and Retrieval XVI, Jan 2010

   DOI HAL
2. Apprentissage de relations spatiales pour la reconnaissance d’expressions mathématiques manuscrites en-ligne

   Ahmad-Montaser Awal, Harold Mouchère, and Christian Viard-Gaudin

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2010), Mar 2010

   PDF HAL
3. Improving online handwritten mathematical expressions recognition with contextual modeling

   Ahmad-Montaser Awal, Harold Mouchère, and Christian Viard-Gaudin

   In International Conference on Frontiers in Handwriting Recognition, Nov 2010

   DOI HAL
4. The Problem of Handwritten Mathematical Expression Recognition Evaluation

   Ahmad-Montaser Awal, Harold Mouchère, and Christian Viard-Gaudin

   In International Conference on Frontiers in Handwriting Recognition (ICFHR), Nov 2010
5. Un classifieur hybride pour la reconnaissance d’expressions mathématiques manuscrites en-ligne

   Ahmad-Montaser Awal, Harold Mouchère, and Christian Viard-Gaudin

   In 17ème Congrès Reconnaissance des Formes et Intelligence Artificielle (RFIA), Jan 2010

   HAL
6. Vers une approche générique pour la reconnaissance de formes manuscrites structurées : Application aux équations mathématiques et aux caractères chinois

   Adrien Delaye, and Harold Mouchère

   In Colloque International Francophone sur l’Ecrit et le Document (CIFED2010), Mar 2010

   PDF HAL
7. Identification du scripteur utilisant les fréquences de graphèmes - Application à des données en-ligne

   Jinpeng Li

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2010), Mar 2010
8. SCUT-COUCH2009-TL: An Unconstrained Online Handwritten Chinese Text Lines Dataset

   Hanyu Yan, Jin Lianwen, Christian Viard-Gaudin, and Harold Mouchère

   In Proceedings of the International Conference on Frontiers in Handwriting Recognition (ICFHR 2010), Mar 2010

2009

1. Apprentissage incrémental avec peu de données pour la reconnaissance de caractères manuscrits en-ligne

   Abdullah Almaksour, Harold Mouchère, and Eric Anquetil

   Traitement du Signal, Mar 2009

   DOI PDF HAL
2. Towards Handwritten Mathematical Expression Recognition

   Ahmad-Montaser Awal, Harold Mouchère, and Christian Viard-Gaudin

   In ICDAR, Mar 2009

   DOI

2008

1. Apprentissage incrémental et synthèse de données pour la reconnaissance de caractères manuscrits en-ligne

   Abdullah Almaksour, Harold Mouchère, and Eric Anquetil

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2008), Oct 2008

   PDF HAL
2. Fast Online Incremental Learning with Few Examples For Online Handwritten Character Recognition

   Eric Anquetil, Abdullah Almaksour, and Harold Mouchère

   In Proceedings of the Eleventh International Conference on Frontiers in Handwriting Recognition (ICFHR’08), Aug 2008

   HAL
3. Pattern Rejection Strategies for the Design of Self-Paced EEG-based Brain-Computer Interfaces

   Fabien Lotte, Harold Mouchère, and Anatole Lécuyer

   In Proceedings of the 19th International Conference on Pattern Recognition, Aug 2008

2007

1. Learning a classifier with very few examples: knowledg based and analogy generation of new exemples for character recognition.

   Sabri Bayoudh, Laurent Miclet, Harold Mouchère, and Eric Anquetil

   In ECML, Aug 2007
2. Writer Style Adaptation in On-line Handwriting Recognizers by a Fuzzy Mechanism Approach : The ADAPT Method

   Harold Mouchère, Eric Anquetil, and Nicolas Ragot

   International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI, indexée JCR), Aug 2007

   DOI URL
3. Synthetic On-line Handwriting Generation by Distortions and Analogy

   Harold Mouchère, Sabri Bayoudh, Eric Anquetil, and Laurent Miclet

   In 13th Conference of the International Graphonomics Society (IGS), Aug 2007

2006

1. Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network

   Harold Mouchère, and Eric Anquetil

   In Proceedings of the 10th International Workshop on Frontier in Handwriting Recognition (IWFHR’06), to be published, Oct 2006

   HAL
2. Synthèse de caractères manuscrits en-ligne pour la reconnaissance de l’écriture

   Harold Mouchère, and Eric Anquetil

   In Colloque International Francophone sur l’Écrit et le Document (CIFED2006), Oct 2006

   HAL
3. A Unified Strategy to Deal with Different Natures of Reject

   Harold Mouchère, and Éric Anquetil

   In 18th International Conference on Pattern Recognition (ICPR’06), Oct 2006
4. Etude et gestion des types de rejet pour l’optimisation de classifieurs

   Harold Mouchère, Éric Anquetil, and Nicolas Ragot

   In RFIA, Oct 2006