Intégration de connaissances linguistiques pour la reconnaissance de textes manuscrits en-ligne

Abstract : The aim of this thesis is to build a sentence regognition system based on an existing word regognition system. Two research axes are considered: the sentence segmentation int words as well as the integration of linguistic knowledge to take into account the context of the sentences. We studied several types of statistic language models by comparing their respective impact on the recognition system performances. We also tried to find the best strategy to introduce them efficiently into the whole recognition system. One of the originality of this study is the integration of a representation of the different sentence hypotheses in the form of a confusion network; which is then used to detect and correct the remaining regognition errors. Using the aforementioned techniques allowed us to considerably reduce the number of recognition errors among the words of the sentences.
Document type :
Theses
Human-Computer Interaction [cs.HC]. INSA de Rennes, 2007. French


https://tel.archives-ouvertes.fr/tel-00580623
Contributor : Solen Quiniou <>
Submitted on : Monday, March 28, 2011 - 5:21:00 PM
Last modification on : Monday, May 18, 2015 - 1:10:42 AM

Identifiers

  • HAL Id : tel-00580623, version 1

Collections

Citation

Solen Quiniou. Intégration de connaissances linguistiques pour la reconnaissance de textes manuscrits en-ligne. Human-Computer Interaction [cs.HC]. INSA de Rennes, 2007. French. <tel-00580623>

Export

Share

Metrics

Consultation de
la notice

124

Téléchargement du document

140