Using Bags of Symbols for Automatic Indexing of Graphical Document Image Databases [chapter]

Eugen Barbu, Pierre Héroux, Sébastien Adam, Éric Trupin
2006 Lecture Notes in Computer Science  
A database is only usefull if it is associated a set of proce-dures allowing to retrieve relevant elements for the users' needs. A lot of IR techniques have been developed for automatic indexing and retrieval in document databases. Most of these use indexes depending on the tex-tual content of documents, and very few are able to handle graphical or image content without human annotation. This paper describes an approach similar to the bag of words technique for automatic indexing of graphical
more » ... cument image databases and diferent ways to consequently query these databases. In an unsupervised manner, this approach proposes a set of automatically discovered sym-bols that can be combined with logical operators to build queries.
doi:10.1007/11767978_18 fatcat:y4ssebyeyvexxaqyozwan5ovji