• The Transactions of the Korea Information Processing Society
• /
• v.5 no.3
• /
• pp.842-850
• /
• 1998

In this paper, we propose a method that recognize hatched area based on segmentation and vectorization of a machine drawing. This recogntion of hatched area is composed of three parts. First, the proposed method segments an object, arrowheads and interpretation lines from the machine drawing and vectorizes the object and interpretation lines. Second, closed-loops are labeled with the vectorized objects, and then candidates of hatched areas arc determined. Finally, by recognizing hatched lines included in hatched areas, recognition of the hatched areas is completed. The proposed method is more useful in extracting and recognizing the hatched areas.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• pp.459-465
• /
• 2003

본 연구는 사전준비 조사 부족 등의 사유로 인하여 당초 목표했던 효율성이 발휘되지 못하고 있는 지적도면 정보화의 문제점을 조사하고 개선방향을 제시하고자 하였다. 서울시 기술분야 공무원을 대상으로 실무에서 가장 빈번하게 사용되고 있는 지도를 조사한 후, 종로구와 서대문구를 사례지역으로 정보화된 지적도면의 오류유형 분석 및 인터넷 토지정보 서비스 등 현재 활용되고 있는 업무를 조사하였다. 또한, 건설교통부ㆍ행정자치부를 비롯한 중앙정부 및 지방자치단체에서 개별적으로 추진하고 있는 지적도면 정보화 사업의 문제점을 조사하고 개선방향을 제시하였다. 따라서, 실무적인 차원에서 정보화가 완료된 지적행정시스템과 지적도면 정보화 자료를 연계하여 다양한 토지정보원으로의 기능 등을 담당할 수 있는 기반을 마련할 수 있는 방향을 제시할 수 있었다.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2009.04a
• /
• pp.573-577
• /
• 2009

최근 건설업계에서는 3D객체기반인 Building Information Modelling(이하 BIM)에 대해 관심이 증가하기 시작했다. 하지만 BIM도입에 어려움을 격고 있는 것이 현실이며 특히 전통적인 정보교환 방식에서의 BIM을 적용하는데 가장 큰 어려움을 격고 있다. 현재 국내에 활용되는 전자도면 표준지침에는 BIM도입에 필요한 2D표준에 대한 내용은 없으며, BIM소프트웨어들도 이 부분에 대해서 충분히 커스터마이징 되지 않았다. 이는 BIM과도기에 2D도면의 필요성을 인식한다면 원할한 BIM도입을 위해서 반드시 그 대안이 필요하다. 따라서 본 논문에서는 국내 BIM 도입 시 국내 2D 전자도면표준을 고려한 BIM 모델에서의 원할한 2D도면추출에 대해 Template을 활용하는 방안을 제안하였다. 도면표준의 기준은 "건설CALS/EC 전자도면 작성 표준"에 근거 하여 표현기준 및 데이터 작성기준을 Template파일에 적용 시켰으며, 이 후 실험을 통해 BIM 도입 시 효율적인 도면 생산의 가능성을 확인 하였다.

• Korea Information Processing Society Review
• /
• v.6 no.4
• /
• pp.60-66
• /
• 1999

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.249-251
• /
• 2012

Augmented Reality (AR) enables the enhanced realism and interaction by providing the overlaid digital information on the user's view of the physical world. In this paper, we propose an AR-based ship design visualization system for presenting ship 3D model in smart phones or table PCs. The proposed system compute corner points and feature points by contour finding method and harris corner detector, and build a ship-design drawing database. By using SURF algorithm, key feature points are extracted from ship-design drawing image which is obtained by mobile camera. Then ship-design drawing image is recognized by matching the feature points stored in DB and extracted key feature points. 3D ship structures are visualized by overlaying the ship-design drawing image on the smart phone or table PC's screen. Compared to conventional 2D ship-design, proposed system helps to easily understand the structures of the ship and reduce the business design period. Thus, Enhanced competitiveness of business is expected.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.17-25
• /
• 2023

In this paper, we propose a lightweight deep learning architecture tailored for efficient text detection in fashion design sketch images. Given the increasing prominence of Digital Transformation in the fashion industry, there is a growing emphasis on harnessing digital tools for creating fashion design sketches. As digitization becomes more pervasive in the fashion design process, the initial stages of text detection and recognition take on pivotal roles. In this study, a lightweight network was designed by building upon existing text detection deep learning models, taking into consideration the unique characteristics of apparel design drawings. Additionally, a separately collected dataset of apparel design drawings was added to train the deep learning model. Experimental results underscore the superior performance of our proposed deep learning model, outperforming existing text detection models by approximately 20% when applied to fashion design sketch images. As a result, this paper is expected to contribute to the Digital Transformation in the field of clothing design by means of research on optimizing deep learning models and detecting specialized text information.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.10
• /
• pp.5243-5250
• /
• 2013

BIM(Building Information Modeling) enables 3D model-base management for all information produced by construction project during its life cycle. Also as a national policy, BIM has been institutionalized as design criteria. But, on the matter of 2D drawing using BIM software (Revit Architecture), it has been recognized as difficult to realize the same quality drawing drawn by CAD. The purpose of this study is verifying the possibility of printable design drawing implemented by BIM software at the same quality of 2D shop drawing drawn by 2D CAD. Through the analysis of basic design elements of 3D BIM software and 2D CAD software, with the case of partial cross sectional drawing which is most faithful representation of the basic design elements, this study find out that the 3D BIM software can produce the same quality 2D printable drawing utilizing its implicit function.

• Journal of Convergence for Information Technology
• /
• v.9 no.2
• /
• pp.172-179
• /
• 2019

Recently, design automation of installation drawings and design elements has been required in the elevator industry. This is recognized as an important role in securing adaptability on site, reducing design errors, and enhancing export competitiveness. However, in case of a small company doesn't have enough resources to develop the program, and it is difficult to develop a design automation program. Therefore, it is necessary to have an automatic drawing generation program that enables small companies to easily invest and use, while allowing users to concentrate on productive tasks. In this paper, we propose an automatic drawing generation program using parametric coding technique. This program is linked with the web service and automatically creates the drawing when the user enters the site information on the web. This is useful for elevator installation and maintenance due to reduced drawing time for elevator drawings.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.1
• /
• pp.223-235
• /
• 1998

도면 중에 내재한 지리정보를 이해해서 공간 자료에 대한 사용자의 질의에 응답할 수 있는 지능형 시스템의 설계는 화상처리 연구의 중요한 응용분야이다. 특히, 지도도면에는 도로, 강, 지역경계, 문자, 심벌 등의 지리정보가 존재하며, 이 개체와 개체 사이의 관계를 포함하는 데이터베이스의 구축은 매우 어려운 일이다. 본 논문에서는 지도도면으로부터 문자정보의 추출과 인식을 위해서 시신경계의 특징추출 이론을 적용한 공간 필터링 신경회로망을 제안한다. 본 시스템을 국립지리원 발행의 1/5,000지도에 적용하여 그 유효성을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1665-1668
• /
• 2000

본 논문에서는 한국전력공사의 배전지리정보시스템를 보다 효과적으로 구축하기 위하여 배전설비 도면으로부터 설비정보를 자동취득하여 배전지리정보시스템의 데이타베이스에 입력하는 방법에 관하여 기술한다. 제안된 방법은 충남지사와 인천지사 관내 배전설비도면 약 30매를 대상으로 실험하고 그 결과를 제시한다.