DE eng

Search in the Catalogues and Directories

Hits 1 – 17 of 17

1
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition — RRC-MLT-2019
In: 2019 International Conference on Document Analysis and Recognition (ICDAR) ; https://hal.archives-ouvertes.fr/hal-02889909 ; 2019 International Conference on Document Analysis and Recognition (ICDAR), Sep 2019, Sydney, Australia. pp.1582-1587, ⟨10.1109/ICDAR.2019.00254⟩ (2019)
BASE
Show details
2
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019 ...
BASE
Show details
3
Automatic Matching and Expansion of Abbreviated Phrases without Context
In: 19th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing2018) ; https://hal.archives-ouvertes.fr/hal-02316286 ; 19th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing2018), Mar 2018, Hanoi, Vietnam (2018)
BASE
Show details
4
Knowledge Representation and Phonological Rules for the Automatic Transliteration of Balinese Script on Palm Leaf Manuscript
In: ISSN: 1405-5546 ; EISSN: 2007-9737 ; Computación y sistemas ; https://hal.archives-ouvertes.fr/hal-02889822 ; Computación y sistemas, Instituto Politécnico Nacional IPN Centro de Investigación en Computación, 2018, 21 (4), ⟨10.13053/cys-21-4-2851⟩ (2018)
BASE
Show details
5
Text-independent speech balloon segmentation for comics and manga ; Segmentation des bulles de bandes dessinées et manga indépendante du texte
In: Graphic Recognition. Current Trends and Challenges 11th International Workshop, GREC 2015, Nancy, France, August 22–23, 2015, Revised Selected Papers ; https://hal.archives-ouvertes.fr/hal-01719513 ; Graphic Recognition. Current Trends and Challenges 11th International Workshop, GREC 2015, Nancy, France, August 22–23, 2015, Revised Selected Papers, 2017 (2017)
BASE
Show details
6
Segmentation-free speech text recognition for comic books ; Reconnaissance du texte de bandes dessinées sans segmentation
In: 2nd International Workshop on coMics Analysis, Processing, and Understanding (MANPU) ; https://hal.archives-ouvertes.fr/hal-01719619 ; 2nd International Workshop on coMics Analysis, Processing, and Understanding (MANPU), Nov 2017, Kyoto, Japan. ⟨10.1109/ICDAR.2017.288⟩ (2017)
BASE
Show details
7
ICDAR2017 Robust Reading Challenge on Multi-Lingual Scene Text Detection and Script Identification - RRC-MLT
In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) ; https://hal.archives-ouvertes.fr/hal-02889922 ; 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Nov 2017, Kyoto, Japan. pp.1454-1459, ⟨10.1109/ICDAR.2017.237⟩ (2017)
BASE
Show details
8
Knowledge Representation and Phonological Rules for the Automatic Transliteration of Balinese Script on Palm Leaf Manuscript
In: International Conference on Computational Linguistics and Intelligent Text Processing ; https://hal.archives-ouvertes.fr/hal-02890040 ; International Conference on Computational Linguistics and Intelligent Text Processing, Apr 2017, Budapest, Hungary (2017)
BASE
Show details
9
Camera-based document image spotting system for complex linguistic maps
In: IEEE SMC 2016 International Conference on Systems, Man, and Cybernetics ; https://hal.archives-ouvertes.fr/hal-02889927 ; IEEE SMC 2016 International Conference on Systems, Man, and Cybernetics, Oct 2016, Budapest, Hungary. pp.003246-003251, ⟨10.1109/SMC.2016.7844734⟩ (2016)
BASE
Show details
10
MAD : une plateforme mobile pour l'annotation de document vers la classification
In: CORIA-CIFED 2014 ; https://hal.archives-ouvertes.fr/hal-01247976 ; CORIA-CIFED 2014, Mar 2014, Nancy, France. pp.223-238 (2014)
Abstract: National audience ; Aujourd’hui, l’incroyable explosion de l’acquisition mobile d’images ou de documentsparait sans limite. Bien qu’il soit facile de les partager sur les réseaux sociaux ou sur le cloud,il est encore très difficile de les classer automatiquement, de les trier ou de rechercher à l’intérieurde cette base de connaissance. Pour répondre à ce défi, nous devons d’abord proposer uneannotation automatique pertinente pour pouvoir utiliser par la suite une recherche lexicale robuste.C’est l’objectif de cet article que de proposer une plate-forme mobile pour l’annotationde document automatique, claire, efficace et rapide qui permet d’envisager une recherche entexte clair. Notre approche repose sur une nouvelle méthode d’annotation automatique de documentsbasée sur la reconnaissance de zones saillantes comme le logo. Les résultats montrentla pertinence de l’approche, nous obtenons une moyenne rappel de 80,6 % et une précision de100%. La précision (100%) met en évidence la robustesse de l’approche que nous proposons.ABSTRACT. Nowadays, the incredible explosion of mobile acquisition of image or documents isunstoppable. While it is easy to share them, it is still very difficult to automatic classify, sort andsearch inside this knowledge. To answer this challenge, we first have to provide an appropriateautomatic annotation to use lexical search robust methods. It is the objective of this paper topropose a mobile platform for clear, efficient and quick automatic document annotation thatenable to consider a plain text search. Our approach relies on a new automatic documentannotation method based on logo recognition. We evaluate the method on a corpus composedof 1766 administrative documents The results show the relevance of the approach, we obtainan average recall of 80.6% and a precision of 100%. The precision (100%) highlights therobustness of the approach.
Keyword: [INFO]Computer Science [cs]
URL: https://hal.archives-ouvertes.fr/hal-01247976
BASE
Hide details
11
MAD : une plateforme mobile pour l'annotation de document vers la classification. ...
BASE
Show details
12
PEDIVHANDI: Multimodal Indexation and Retrieval System for Lecture Videos
In: ISSN: 1868-5137 ; EISSN: 1868-5145 ; Journal of Ambient Intelligence and Humanized Computing ; https://hal.archives-ouvertes.fr/hal-02519310 ; Journal of Ambient Intelligence and Humanized Computing, Springer, 2013, 3 (4), pp.382-393. ⟨10.1007/978-3-642-37444-9_30⟩ (2013)
BASE
Show details
13
A local evaluation of vectorized documents by means of polygon assignments and matching
In: International journal on document analysis and recognition. - Berlin ; Heidelberg : Springer 15 (2012) 1, 21-43
BLLDB
OLC Linguistik
Show details
14
Towards historical document indexing: extraction of drop cap letters
In: International journal on document analysis and recognition. - Berlin ; Heidelberg : Springer 14 (2011) 3, 243-254
BLLDB
OLC Linguistik
Show details
15
Cursive on-line Handwriting word recognition using a bi-character model for large lexicon applications
In: Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition (ICFHR 2010) ; 15th International Conference on Frontiers in Handwriting Recognition (ICFHR 2010) ; https://hal.archives-ouvertes.fr/hal-00860700 ; 15th International Conference on Frontiers in Handwriting Recognition (ICFHR 2010), Nov 2010, Kolkata, India. pp.194-199 (2010)
BASE
Show details
16
A general framework for the evaluation of symbol recognition methods
In: International journal on document analysis and recognition. - Berlin ; Heidelberg : Springer 9 (2007) 1, 59-74
BLLDB
OLC Linguistik
Show details
17
A general framework for the evaluation of symbol recognition methods
In: International journal on document analysis and recognition. - Berlin ; Heidelberg : Springer 9 (2007) 1, 59-74
OLC Linguistik
Show details

Catalogues
0
0
4
0
0
0
0
Bibliographies
3
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
13
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern