Matches in SemOpenAlex for { <https://semopenalex.org/work/W2801596382> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2801596382 abstract "This thesis is about the design of a complete processing chain dedicated to unconstrained handwriting recognition. Three main difficulties are adressed: pre-processing, optical modeling and language modeling. The pre-processing stage is related to extracting properly the text lines to be recognized from the document image. An iterative text line segmentation method using oriented steerable filters was developed for this purpose. The difficulty in the optical modeling stage lies in style diversity of the handwriting scripts. Statistical optical models are traditionally used to tackle this problem such as Hidden Markov models (HMM-GMM) and more recently recurrent neural networks (BLSTM-CTC). Using BLSTM we achieve state of the art performance on the RIMES (for French) and IAM (for English) datasets. The language modeling stage implies the integration of a lexicon and a statistical language model to the recognition processing chain in order to constrain the recognition hypotheses to the most probable sequence of words (sentence) from the language point of view. The difficulty at this stage is related to the finding the optimal vocabulary with minimum Out-Of-Vocabulary words rate (OOV). Enhanced language modeling approaches has been introduced by using sub-lexical units made of syllables or multigrams. The sub-lexical units cover an important portion of the OOV words. Then the language coverage depends on the domain of the language model training corpus, thus the need to train the language model with in domain data. The recognition system performance with the sub-lexical units outperformes the traditional recognition systems that use words or characters language models, in case of high OOV rates. Otherwise equivalent performances are obtained with a compact sub-lexical language model. Thanks to the compact lexicon size of the sub-lexical units, a unified multilingual recognition system has been designed. The unified system performance have been evaluated on the RIMES and IAM datasets. The unified multilingual system shows enhanced recognition performance over the specialized systems, especially when a unified optical model is used." @default.
- W2801596382 created "2018-05-17" @default.
- W2801596382 creator A5079087211 @default.
- W2801596382 date "2017-10-04" @default.
- W2801596382 modified "2023-09-23" @default.
- W2801596382 title "Language Modelling for Handwriting Recognition" @default.
- W2801596382 hasPublicationYear "2017" @default.
- W2801596382 type Work @default.
- W2801596382 sameAs 2801596382 @default.
- W2801596382 citedByCount "0" @default.
- W2801596382 crossrefType "dissertation" @default.
- W2801596382 hasAuthorship W2801596382A5079087211 @default.
- W2801596382 hasConcept C111919701 @default.
- W2801596382 hasConcept C112640561 @default.
- W2801596382 hasConcept C137293760 @default.
- W2801596382 hasConcept C138885662 @default.
- W2801596382 hasConcept C154945302 @default.
- W2801596382 hasConcept C204321447 @default.
- W2801596382 hasConcept C23224414 @default.
- W2801596382 hasConcept C2777601683 @default.
- W2801596382 hasConcept C2778121359 @default.
- W2801596382 hasConcept C28490314 @default.
- W2801596382 hasConcept C41008148 @default.
- W2801596382 hasConcept C41895202 @default.
- W2801596382 hasConcept C52622490 @default.
- W2801596382 hasConcept C61423126 @default.
- W2801596382 hasConceptScore W2801596382C111919701 @default.
- W2801596382 hasConceptScore W2801596382C112640561 @default.
- W2801596382 hasConceptScore W2801596382C137293760 @default.
- W2801596382 hasConceptScore W2801596382C138885662 @default.
- W2801596382 hasConceptScore W2801596382C154945302 @default.
- W2801596382 hasConceptScore W2801596382C204321447 @default.
- W2801596382 hasConceptScore W2801596382C23224414 @default.
- W2801596382 hasConceptScore W2801596382C2777601683 @default.
- W2801596382 hasConceptScore W2801596382C2778121359 @default.
- W2801596382 hasConceptScore W2801596382C28490314 @default.
- W2801596382 hasConceptScore W2801596382C41008148 @default.
- W2801596382 hasConceptScore W2801596382C41895202 @default.
- W2801596382 hasConceptScore W2801596382C52622490 @default.
- W2801596382 hasConceptScore W2801596382C61423126 @default.
- W2801596382 hasOpenAccess W2801596382 @default.
- W2801596382 hasRelatedWork W1022496157 @default.
- W2801596382 hasRelatedWork W1707124376 @default.
- W2801596382 hasRelatedWork W1771922646 @default.
- W2801596382 hasRelatedWork W1844448538 @default.
- W2801596382 hasRelatedWork W1983912746 @default.
- W2801596382 hasRelatedWork W2004708879 @default.
- W2801596382 hasRelatedWork W2056157306 @default.
- W2801596382 hasRelatedWork W2110145858 @default.
- W2801596382 hasRelatedWork W2152626552 @default.
- W2801596382 hasRelatedWork W2153986034 @default.
- W2801596382 hasRelatedWork W2162160325 @default.
- W2801596382 hasRelatedWork W2170310063 @default.
- W2801596382 hasRelatedWork W23024349 @default.
- W2801596382 hasRelatedWork W2578205343 @default.
- W2801596382 hasRelatedWork W2735949438 @default.
- W2801596382 hasRelatedWork W2892115357 @default.
- W2801596382 hasRelatedWork W2944691285 @default.
- W2801596382 hasRelatedWork W2964309797 @default.
- W2801596382 hasRelatedWork W92696887 @default.
- W2801596382 hasRelatedWork W2149200625 @default.
- W2801596382 isParatext "false" @default.
- W2801596382 isRetracted "false" @default.
- W2801596382 magId "2801596382" @default.
- W2801596382 workType "dissertation" @default.