Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Chatelain, Clément"'
Publikováno v:
DRR
Document Recognition and retrieval
Document Recognition and retrieval, 2015, San Francisco, United States
Document Recognition and Retrieval
Document Recognition and Retrieval, 2015, San Fransisco, United States
Document Recognition and retrieval
Document Recognition and retrieval, 2015, San Francisco, United States
Document Recognition and Retrieval
Document Recognition and Retrieval, 2015, San Fransisco, United States
International audience; In this article, we propose a hybrid model for spotting words and regular expressions (REGEX) in handwritten documents. The model is made of the state-of-the-art BLSTM (Bidirectional Long Short Time Memory) neural network for
Publikováno v:
Document Recognition and Retrieval
Document Recognition and Retrieval, 2015, San Francisco, United States
DRR
Document Recognition and Retrieval, 2015, San Francisco, United States
DRR
International audience; The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6231cc6ec999314a6d08b31685b7a460
https://hal.archives-ouvertes.fr/hal-01089164/document
https://hal.archives-ouvertes.fr/hal-01089164/document
Publikováno v:
Pattern Analysis and Applications
Pattern Analysis and Applications, Springer Verlag, 2015, 18 (4), pp.1003-1015
Pattern Analysis and Applications, Springer Verlag, 2015, 18 (4), pp.1003-1015
International audience; In this paper, we propose a query by string word spotting system able to extract arbitrary key-words in handwritten documents, taking both segmen-tation and recognition decisions at the line level. The system relies on the com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3bb3ee8c17e8435fb6f6d7d8af486700
https://hal.archives-ouvertes.fr/hal-01089151
https://hal.archives-ouvertes.fr/hal-01089151
Publikováno v:
Document Analysis Systems
Document Analysis Systems, Apr 2014, Tours, France. 6p
Document Analysis Systems, Apr 2014, Tours, France. 6p
International audience; This paper presents a Document Image Analysis (DIA) system able to extract homogeneous typed and handwritten text regions from complex layout documents of various types. The method is based on two connected component classific
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::726f649228b631bb093a90d51fb30443
https://hal.archives-ouvertes.fr/hal-00981245/document
https://hal.archives-ouvertes.fr/hal-00981245/document
Publikováno v:
Proceedings of ICDAR'13
Internation conférence on document analysis and recognition
Internation conférence on document analysis and recognition, Aug 2013, Washington, United States. pp.1185-1189, ⟨10.1109/ICDAR.2013.240⟩
ICDAR
ICDAR, 2013, France. pp.1185-1189
Internation conférence on document analysis and recognition
Internation conférence on document analysis and recognition, Aug 2013, Washington, United States. pp.1185-1189, ⟨10.1109/ICDAR.2013.240⟩
ICDAR
ICDAR, 2013, France. pp.1185-1189
International audience; This paper presents a method to detect table regions in document images by identifying the column and row line-separators and their properties. The method employs a run-length approach to identify the horizontal and vertical l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb2ed57d747d2d0c210d63593d371d2e
https://hal.archives-ouvertes.fr/hal-00934902
https://hal.archives-ouvertes.fr/hal-00934902
Publikováno v:
ICDAR
ICDAR, 2013, United States. pp.516-520
ICDAR, 2013, United States. pp.516-520
International audience; In this paper, we propose a novel system for word spotting and regular expression detection in Handwritten documents. The proposed approach is lexicon-free, i.e., able to spot arbitrary keywords that are not required to be kno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae0a810529781298a2f0cfbf3cb16198
https://hal.archives-ouvertes.fr/hal-00905535
https://hal.archives-ouvertes.fr/hal-00905535
Publikováno v:
International Journal on Document Analysis and Recognition
International Journal on Document Analysis and Recognition, Springer Verlag, 2012, 15 (4), pp.315-330
International Journal on Document Analysis and Recognition, Springer Verlag, 2012, 15 (4), pp.315-330
International audience; This paper presents a complete system able to categorize handwritten documents, i.e. to classify documents according to their topic. The categorization approach is based on the detection of some discrim- inative keywords prior
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f7bd711311373a3756dba8a70b26349b
https://hal.archives-ouvertes.fr/hal-00778177
https://hal.archives-ouvertes.fr/hal-00778177
Publikováno v:
ICFHR
ICFHR, Nov 2010, India. pp.6
ICFHR, Nov 2010, India. pp.6
International audience; In this paper, we introduce an alpha-numerical sequences extraction system (keywords, numerical fields or alpha-numerical sequences) in unconstrained handwritten documents. Contrary to most of the approaches presented in the l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6cdb36d1cd63e8e27efb3897c9451298
https://hal.archives-ouvertes.fr/hal-00488290/document
https://hal.archives-ouvertes.fr/hal-00488290/document
Publikováno v:
ICPR
ICPR, Istanbul, Turkey
ICPR, Istanbul, Turkey, Aug 2010, France. pp.4
ICPR, Istanbul, Turkey
ICPR, Istanbul, Turkey, Aug 2010, France. pp.4
International audience; In this paper, a new information extraction system by statistical shallow parsing in unconstrained handwritten documents is introduced. Unlike classical approaches found in the literature as keyword spotting or full document r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb7842de07db7ad604ca13e4876be432
https://hal.archives-ouvertes.fr/hal-00486107
https://hal.archives-ouvertes.fr/hal-00486107
Publikováno v:
Pattern Recognition
Pattern Recognition, Elsevier, 2010, 43 (3), pp.815-823
Pattern Recognition, Elsevier, 2010, 43 (3), pp.815-823
International audience; In this paper, we tackle the problem of model selection when misclassification costs are unknown and/or may evolve. Unlike traditional approaches based on a scalar optimization, we propose a generic multi-model selection frame
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e8c5a1e5f50bc0e757ad22ecf534fb7
https://hal.archives-ouvertes.fr/hal-00435954/file/pr_chatelain.pdf
https://hal.archives-ouvertes.fr/hal-00435954/file/pr_chatelain.pdf