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