Automatic understanding of symbol-connected diagrams

Author

Yu, Bin

Author_Institution

Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China

Volume

2

fYear

1995

fDate

14-16 Aug 1995

Firstpage

803

Abstract

A symbol-connected diagram is mainly composed of symbols and their connections. All symbols can be categorized into two groups: shape symbols and structure symbols. This paper proposes a system for automatic understanding of symbol-connected diagrams based on a graph, called the consistent attributed graph (CAG), which represents the diagram in a bottom-up fashion. The shape symbol processing is carried out by means of shape processing, followed by shape symbol identification with the use of two symbol windows in the CAG. Some experimental results for understanding logic circuit diagrams are given

Keywords

circuit diagrams; diagrams; document image processing; engineering graphics; graph theory; image recognition; knowledge based systems; logic CAD; bottom-up method; consistent attributed graph; intelligent diagram reader; logic circuit diagram understanding; shape processing; shape symbol identification; shape symbols; structure symbols; symbol windows; symbol-connected diagram understanding; Character recognition; Data mining; Design automation; Design engineering; Image analysis; Information science; Joining processes; Logic circuits; Logic design; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on

Conference_Location

Montreal, Que.

Print_ISBN

0-8186-7128-9

Type

conf

DOI

10.1109/ICDAR.1995.602023

Filename

602023