ANASTASIL: A Hybrid Knowledge-Based System for Document Layout Analysis

Abstract

This paper describes a know ledge-based system for the identification of the different regions of a document image. It uses a hybrid, modular knowledge representation, a so called geometric tree being its essential part. This tree is used to perform a best-first search in combination with a "hypothesize & test"strategy. It produces an internal, editable description of the entire document and its constituents. The system has been implemented for the analysis of single-sided business letters in Common Lisp on a SUN 3/60 Workstation. It is running for a large population of different business letters. The results obtained have been very encouraging and have convincingly confirmed the soundness of the approach. 1

Cite

Text

Dengel and Barth. "ANASTASIL: A Hybrid Knowledge-Based System for Document Layout Analysis." International Joint Conference on Artificial Intelligence, 1989.

Markdown

[Dengel and Barth. "ANASTASIL: A Hybrid Knowledge-Based System for Document Layout Analysis." International Joint Conference on Artificial Intelligence, 1989.](https://mlanthology.org/ijcai/1989/dengel1989ijcai-anastasil/)

BibTeX

@inproceedings{dengel1989ijcai-anastasil,
  title     = {{ANASTASIL: A Hybrid Knowledge-Based System for Document Layout Analysis}},
  author    = {Dengel, Andreas and Barth, Gerhard},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {1989},
  pages     = {1249-1254},
  url       = {https://mlanthology.org/ijcai/1989/dengel1989ijcai-anastasil/}
}