Fuzzy Closed Concept for the Correction of Errors in the Dematerialization Process

In this paper, we propose a new method able to correct errors related to the recognition of invoice type documents. We rely on automated document readers that can read and recognize the various, relevant information in a scanned document. The process consists of digitizing a large volume of documents, and passes them through automatic documents readers, then carries out the correction of the different errors. The final objective is to find an electronic document reflecting all information included in the background document. The main goal is the generation of organized electronic documents, like a data basis or files XML. To achieve this issue we develop a new parser which is applicable to a various kind of documents, especially the corrections for the recognition errors by using the fuzzy closed concept, this formalism allow the detection of the set of rules to be applied in a set of documents.