A Comparative Study on Extraction and Recognition Method of CAD Data from CAD
Drawings
Mohamad Faizal Ab. Jabal
1
Department of Computer Graphics and Multimedia
FSKSM, Universiti Teknologi Malaysia
81310 Skudai, Johor, Malaysia
mfaizal75@utm.my
Mohd. Shafry Mohd. Rahim
2
Department of Computer Graphics and Multimedia
FSKSM, Universiti Teknologi Malaysia
81310 Skudai, Johor, Malaysia
shafry@fsksm.utm.my
Nur Zuraifah Syazrah Othman
3
Department of Computer Graphics and Multimedia
FSKSM, Universiti Teknologi Malaysia
81310 Skudai, Johor, Malaysia
zuraifah@utm.my
Zahabidin Jupri
4
Department of Computer Graphics and Multimedia
FSKSM, Universiti Teknologi Malaysia
81310 Skudai, Johor, Malaysia
zaha@utm.my
Abstract—In recent years, various researchers have put in great
effort to produce an efficient method of drawing extraction. This
paper will focus on CAD data extraction from CAD drawing and
study the method that has been proposed by previous
researchers. CAD data extraction became a popular research
since the early 80’s. Nowadays, most applications in engineering
field are already computerized. This includes the CAD
application system, the systems used by engineers to design their
products. As the use of computerized application became
important tool in engineering field, the production field is also
affected. This raises the issue of integrating CAD with
manufacture systems. For that reason, most researchers try to
create a system that can extract meaningful information from the
CAD drawing and create a connection between CAD and
manufacture system. For example in manufacturing field,
manufacture system is a machine system where it is also known
as CAM systems. However, there is no direct connection from
CAD system to CAM system. Therefore, many approaches have
been proposed by the previous researchers to solve the issues.
Focus on this paper is to study the approaches and make
comparison among it. Finding from this paper is suitable
approach can be used for next stage in this research.
Keywords- Extraction; Recognition; CAD data; CAM system
I. INTRODUCTION
Extraction CAD data from the CAD drawing was attracted
many researchers to do research in CAD/CAM field.
CAD/CAM application is directly depend on CAD drawing.
However, there has a gap between CAD and CAM application.
To create a connection between CAD and CAM is the main
issue in CAD/CAM field. Extraction is a key to make the
connection between CAD and CAM [2, 21, 22].
Extraction is a process to extract CAD data from the CAD
drawing. Basically, the technique used to program the
extraction process was simulated from the engineer technique
to read and extract the data from the drawing. From the basic
technique there was made many researchers to propose the new
approach in extraction process with purpose to improve the
weakness in the previous extraction process. Recent many
approaches have been proposed.
B.S Prabhu et al [1] have proposed the AUTOFEAT
algorithm to extract the geometry and non-geometry
information from CAD drawing. The proposed algorithm
solves the problem on how to extract non-geometry
information and how to organize the extracted geometry and
non-geometry information inside the database. According to
[2], among the non-geometry information in CAD drawing are
dimensions, text and labels. The research tested the proposed
algorithm on CAD drawings, where the algorithm shows that it
is capable in extracting geometry and non-geometry
information, and all of the information is stored inside a
structured database.
No communication between low level data with a high
level data is a problem to integrate the CAD application and
CAM application. Low level data is a CAD data such as lines,
points, curves and circles. While high level data is machine
data which is involved processes and planning [2, 4, 21, 22].
H.C. Huang et al [3], a CAD drawing contains original
geometrical information of graphical primitives. The goal of
[3] is to make the pre-process task more accurate. However, to
increase the accuracy, meaningful CAD information need to be
extracted. For this reason, the research has proposed Graph
Theory-Based Approach.
Based on the highlighted approaches, there are still a lot of
extraction techniques and methods that have been proposed by
previous researchers. Difficulty to extract CAD data was
motivated researchers to do the research and proposed the new
approaches in CAD data extracting. The extracted data from
Sponsor by Ministry of Science Technology and Innovation of Malaysia
(MOSTI), grant VOT 79233
2009 International Conference on Information Management and Engineering
978-0-7695-3595-1/09 $25.00 © 2009 IEEE
DOI 10.1109/ICIME.2009.56
709
2009 International Conference on Information Management and Engineering
978-0-7695-3595-1/09 $25.00 © 2009 IEEE
DOI 10.1109/ICIME.2009.56
709