Isolating symbols from connection lines in a class of engineering drawings

Yuhong Yu, Ashok K Samal, Sharad Seth

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

The class of drawings considered here is characterized by alternative instances of symbols and connections, includes flow charts and diagrams describing chemical plants, electrical circuits, and digital logic. After preprocessing of the scanned binary image, symbols and connection lines are separated using a few simple yet effective generic drawing properties, such as: (a) symbols contain mostly closed simple shapes, slant lines and open lines, and (b) connection lines contain mostly horizontal and vertical lines with each line end connected to a symbol. Accurate results are achieved in experiments on a set of 24 drawings drawn from four applications and scanned with resolutions varying from 75 to 300 dpi. Such high accuracy of segmentation can form the basis for symbol and connection recognition in any automated drawing understanding system.

Original languageEnglish (US)
Pages (from-to)391-404
Number of pages14
JournalPattern Recognition
Volume27
Issue number3
DOIs
StatePublished - Mar 1994

Fingerprint

Drawing (graphics)
Binary images
Chemical plants
Networks (circuits)
Experiments

Keywords

  • Benchmark results
  • Domain independence
  • Engineering drawing analysis
  • Flow drawings
  • Loop analysis
  • Segmentation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Isolating symbols from connection lines in a class of engineering drawings. / Yu, Yuhong; Samal, Ashok K; Seth, Sharad.

In: Pattern Recognition, Vol. 27, No. 3, 03.1994, p. 391-404.

Research output: Contribution to journalArticle

@article{052a7aa91dad49f3bff4773240979bab,
title = "Isolating symbols from connection lines in a class of engineering drawings",
abstract = "The class of drawings considered here is characterized by alternative instances of symbols and connections, includes flow charts and diagrams describing chemical plants, electrical circuits, and digital logic. After preprocessing of the scanned binary image, symbols and connection lines are separated using a few simple yet effective generic drawing properties, such as: (a) symbols contain mostly closed simple shapes, slant lines and open lines, and (b) connection lines contain mostly horizontal and vertical lines with each line end connected to a symbol. Accurate results are achieved in experiments on a set of 24 drawings drawn from four applications and scanned with resolutions varying from 75 to 300 dpi. Such high accuracy of segmentation can form the basis for symbol and connection recognition in any automated drawing understanding system.",
keywords = "Benchmark results, Domain independence, Engineering drawing analysis, Flow drawings, Loop analysis, Segmentation",
author = "Yuhong Yu and Samal, {Ashok K} and Sharad Seth",
year = "1994",
month = "3",
doi = "10.1016/0031-3203(94)90116-3",
language = "English (US)",
volume = "27",
pages = "391--404",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Isolating symbols from connection lines in a class of engineering drawings

AU - Yu, Yuhong

AU - Samal, Ashok K

AU - Seth, Sharad

PY - 1994/3

Y1 - 1994/3

N2 - The class of drawings considered here is characterized by alternative instances of symbols and connections, includes flow charts and diagrams describing chemical plants, electrical circuits, and digital logic. After preprocessing of the scanned binary image, symbols and connection lines are separated using a few simple yet effective generic drawing properties, such as: (a) symbols contain mostly closed simple shapes, slant lines and open lines, and (b) connection lines contain mostly horizontal and vertical lines with each line end connected to a symbol. Accurate results are achieved in experiments on a set of 24 drawings drawn from four applications and scanned with resolutions varying from 75 to 300 dpi. Such high accuracy of segmentation can form the basis for symbol and connection recognition in any automated drawing understanding system.

AB - The class of drawings considered here is characterized by alternative instances of symbols and connections, includes flow charts and diagrams describing chemical plants, electrical circuits, and digital logic. After preprocessing of the scanned binary image, symbols and connection lines are separated using a few simple yet effective generic drawing properties, such as: (a) symbols contain mostly closed simple shapes, slant lines and open lines, and (b) connection lines contain mostly horizontal and vertical lines with each line end connected to a symbol. Accurate results are achieved in experiments on a set of 24 drawings drawn from four applications and scanned with resolutions varying from 75 to 300 dpi. Such high accuracy of segmentation can form the basis for symbol and connection recognition in any automated drawing understanding system.

KW - Benchmark results

KW - Domain independence

KW - Engineering drawing analysis

KW - Flow drawings

KW - Loop analysis

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=0028400883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028400883&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(94)90116-3

DO - 10.1016/0031-3203(94)90116-3

M3 - Article

AN - SCOPUS:0028400883

VL - 27

SP - 391

EP - 404

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 3

ER -