Automatic knowledge acquisition for spatial document interpretation

Author

Walischewski, Hanno

Author_Institution

Text Understanding Syst., Daimler Benz Res., Ulm, Germany

Volume

1

fYear

1997

fDate

18-20 Aug 1997

Firstpage

243

Abstract

In this paper, a qualitative representation for the layout of structured documents as well as classes of documents is presented, which is established by means of supervised learning from a labeled training set of documents. For this formal representation, an inference algorithm has been developed, adopted from error-tolerant subgraph isomorphism, which assigns logic labels to the layout objects of a test document

Keywords

document image processing; fault tolerant computing; graph theory; inference mechanisms; knowledge acquisition; knowledge representation; learning (artificial intelligence); automatic knowledge acquisition; document classes; error-tolerant subgraph isomorphism; formal representation; inference algorithm; labeled training set; layout objects; logic labels; qualitative representation; spatial document interpretation; structured document layout; supervised learning; Computer science education; Data mining; Humans; Inference algorithms; Inference mechanisms; Information analysis; Knowledge acquisition; Logic testing; Training data; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on

Conference_Location

Ulm

Print_ISBN

0-8186-7898-4

Type

conf

DOI

10.1109/ICDAR.1997.619849

Filename

619849