Automatic visual classification of printed documents

Author

Dengel, Andreas

Author_Institution

Dept. of Comput. Sci., Stuttgart Univ., West Germany

fYear

1989

fDate

10-12 Apr 1989

Firstpage

276

Lastpage

281

Abstract

The author presents the knowledge-based document-analysis system ANASTASIL. The system uses a formalism for document layout description and modeling. The model is realized by a tree structure, which describes the layout of a document page in different layout abstraction levels. The tree is used to initiate a best-first search in combination with a hypothesize-and-test strategy to establish a high-level electronic representation of the contents of a document. Results obtained in the different analysis phases are shown and confirm the soundness of the approach

Keywords

computerised pattern recognition; knowledge based systems; ANASTASIL; automatic visual classification; best-first search; document layout description; document page; high-level electronic representation; hypothesize-and-test strategy; knowledge-based document-analysis system; layout abstraction levels; modeling; printed documents; tree structure; Artificial intelligence; Computer science; Computer vision; Data structures; Electronic equipment testing; Image segmentation; Intelligent systems; Knowledge representation; Text analysis; Tree data structures;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Applications of Machine Intelligence and Vision, 1989., International Workshop on

Conference_Location

Tokyo

Type

conf

DOI

10.1109/MIV.1989.40563

Filename

40563