Accès par le contenu aux documents manuscrits d'archives numérisés

This paper presents handwritten archives document retrieval by content. This retrieval is build on information (annotations) associated to document images. We propose two complementary ways of producing those annotations : automatically by using optical document recognition and collectively by using internet and a manual input by users. A platform for managing those annotations is presented as well as examples of automatic annotations on civil status registers, military forms and naturalization decrees, using a generic document recognition method. This method has been tested on more than 60,000 pages of documents. Examples of collective annotations built on automatic annotations are also given. MOTS-CLÉS : annotations, accès par le contenu, documents manuscrits, reconnaissance de documents, généricité, tableaux, formulaires, gestion des connaissances a priori, grammaire, reconnaissance de l’écriture manuscrite.