• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.1-9
• /
• 2022

The goal of this paper is to create a deep learning model based on triplet loss for generating similar child drawing selection algorithms. To assess the similarity of children's drawings, the distance between feature vectors belonging to the same class should be close, and the distance between feature vectors belonging to different classes should be greater. Therefore, a similar child drawing selection algorithm was developed in this study by building a deep learning model combining Triplet Loss and residual network(ResNet), which has an advantage in measuring image similarity regardless of the number of classes. Finally, using this model's similar child drawing selection algorithm, the similarity between the target child drawing and the other drawings can be measured and drawings with a high similarity can be chosen.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.536-539
• /
• 2002

In this paper, we developed the automatic optical fiber aligner by image processing and automatic loading system. Optical fiber is indispensable for optical communication systems that transmit large volumes of data at high speed, but super-precision technology in sub-micron units is required for optical axis adjustment, we have developed 6-axis micro stage system for I/O optical fiber arrays, the initial automatic aligning system/software for a input optical array by the image processing technique, fast I/O-synchronous aligning strategy, the automatic loading/unloading system and the automatic UV bonding mechanism. In order to adjust the alignment it used on PC based motion controller, a $10\mu\textrm{mm}$ repeat-detailed drawing of automatic loading system is developed by a primary line up for high detailed drawing. Also, at this researches used the image processing system and algorithm instead of the existing a primary hand-line up. and fiber input array and waveguide chip formed in line by automatic. Therefore, the developed and manufactured optical aligning system in this research fulfills the great role of support industry for major electronics manufacturers, telecommunications companies, universities, government agencies and other research institutions.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2777-2781
• /
• 2001

This paper presents an algorithm of the watermark insertion and extraction on the vector image. Most parts of the vector image consist of the array of the coordinate values. The vector watermarking method by Sakamoto et al [1] uses the mask within which all the coordinate values of all the vertices are changed depending on the value of the watermark. The proposed algorithm is the change of the vector image file instead of the change of the coordinate values on the vector image. We use the Drawing Exchange Format (DXF) files since the DXF file is one of the general files in the field of the vector image.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.466-469
• /
• 2002

Burr is a projected part of finished workpiece. It is unavoidable and undesirable by-product of most metal cutting or shearing process. Also, it must be removed to improve the fit of machined parts, safety of workers, and the effectiveness of finishing operation. But deburring process is one of manufacturing processes that have net been successfully automated, so deburring automation is strongly needed. This paper focused on developing a basic algorithm to find edge of workpiece and match two different image data for deburring automation which includes automatic recognition of parts, generation of deburring tool paths and edge/corner finding ability by analyzing the DXF drawing file which contains information of part geometry. As an algorithm for corner finding, SUSAN method was chosen. It makes good performance in finding edge and corner in suitable time. And this paper suggested a simple algorithm to find matching point between CCD image and drawing file.

• 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 KIISE:Computer Systems and Theory
• /
• v.34 no.12
• /
• pp.665-682
• /
• 2007

Line drawing is a widely used style in non-photorealistic rendering because it generates expressive descriptions of object shapes with a set of strokes. Although various techniques for line drawing of 3D objects have been developed, line drawing of 2D images has attracted little attention despite interesting applications, such as image stylization. This paper presents a robust and effective technique for generating line drawings from 2D images. The algorithm consists of three parts; filtering, linking, and stylization. In the filtering process, it constructs a likelihood function that estimates possible positions of lines in an image. In the linking process, line strokes are extracted from the likelihood function using clustering and graph search algorithms. In the stylization process, it generates various kinds of line drawings by applying curve fitting and texture mapping to the extracted line strokes. Experimental results demonstrate that the proposed technique can be applied to the various kinds of line drawings from 2D images with detail control.

• Journal of Ocean Engineering and Technology
• /
• v.31 no.2
• /
• pp.141-154
• /
• 2017

A production management system is developed to enhance both the information and productivity of ship and offshore plant deckhouse floor outfitting. The functions of the production management system for the deckhouse floor outfitting were reviewed based on a literature survey of several production management systems with respect to the ship building and architecture fields. This study investigated numerous daily production reports and their application to actual work places to utilize the system development. The developed scanned drawing-based production management (SDPM) system minimizes any loss and/or distortion of work information between the workshop and management office when applying a scanned production drawing to the daily report. The SDPM system increases the data objectivity, as well as intuitiveness of the information generation by adopting an efficient user interface, which makes it possible to perform image annotations on the scanned drawing for the daily production report while simultaneously interacting with the production management database. Applying the system operation to actual deckhouse floor covering work verified that it was feasible to use the SDPM system for production management in the ship outfitting work process.

• Journal of Korea Multimedia Society
• /
• v.14 no.5
• /
• pp.691-702
• /
• 2011

Recently, several researchers have attempted to combine human visual perception and computer graphics. Cole et. al. suggest the study results in which line drawing algorithm in computer graphics characterize the properties of line drawing made by artists. The paper also evaluates CG line drawing algorithms depending on whether people recognize effectively specific 3D shape from the image made by those CG line drawing algorithms. However, human recognizes the shape of objects more effectively in image made by BRDF shading model than line drawing algorithm. It means that the shading factor is important to recognize shape with human perception. In this paper, we analyze the correlation between shading made by human artists and that made by CG shading algorithms. The study is to characterize the mathematical properties of artists' shading and CG shading. This type of analysis can guide the future development of new CG shading algorithm in computer graphics for the purpose of shape perception.

• Journal of The Korean Association For Science Education
• /
• v.38 no.5
• /
• pp.753-763
• /
• 2018

The image of scientists that learners have has an important impact on science learning and on science-related career choices. The image of the scientist was mainly analyzed using the drawing analysis method. Drawing analysis has limitations on drawing, mainly analyzing the external image of scientist. Science teachers' images of scientists and their perception of science-related careers are important factors in students' science learning and science-related career choices. However, research on science teachers is lacking. Therefore, the purpose of this study is to investigate the usefulness of measurement tools by developing and applying a scientist image measurement tool through the semantic analysis method, and to discuss the educational implications of the research by investigating the image of scientists and science-related professions of secondary pre-service science teachers. The subjects of the study were 79 male and 55 female for a total of 134 students in the 2nd and 3rd grades majoring in science education at a teachers college. The results of the research show that the image measurement tool consisted of four components: 'ability,' 'evaluation,' 'activity,' and 'emotion,' in 24 items. As a result of applying the developed measurement tool to the secondary pre-service science teachers, the image of the 'evaluation,' 'ability,' and 'activity' elements of the scientist were high, but 'emotion' was low. There was no statistically significant difference according to gender. It is found that science-related career perceive them as 'hard,' 'professional,' 'smart,' and 'complex.' In particular, male students perceive themselves as 'hard and difficult' while female students perceive it as 'challenging and complicated'. Finally, we discussed the usefulness of using the image measurement tool of the scientists, the image of the scientists of the secondary pre-service science teachers, and the educational implications on science-related career.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.6
• /
• pp.128-135
• /
• 2002

Burr is a projected part of finished workpiece. It is unavoidable and undesirable by-product of most metal cutting or shearing process. Also, it must be removed to improve the fit of machined parts, safety of workers, and the effectiveness of finishing operation. But deburring process Is one of manufacturing processes that have not been successfully automated, so deburring automation is strongly needed. This paper focused on developing a basic algorithm to find edge of workpiece and match two different image data for deburring automation which includes automatic recognition of parts, generation of deburring tool paths and edge/comer finding ability by analyzing the DXF drawing file which contains information of part geometry. As an algorithm fur corner finding, SUSAN method was chosen. It makes good performance in finding edge and corner in suitable time. And this paper suggested a simple algorithm to find matching point between CCD image and drawing file.