• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1418-1420
• /
• 2013

GPU는 범용 CPU와는 달리 수백 개의 코어로 이루어져 병렬처리에 특화된 형태로 발전되어 왔으며, 이미지 및 동영상 처리, 유체 역학 시뮬레이션, 의료, 지진 분석 등 점차 많은 영역에서 사용 되고 있다. 최근에는 GPU를 이용하여 볼륨 렌더링을 가속화하는 많은 기법들이 연구되고 있다. 본 논문에서는 볼륨 렌더링을 가속화하기 위한 GPU 기반의 쉐아-스큐 워프 기법을 제안한다. 여기서는 GPU를 이용하여 효율적인 메모리 사용, 코어의 활성화, 뱅크 충돌 감소 기법을 이용하여 기존의 CPU 기반 볼륨 렌더링 기법과 비교하여 빠른 시간에 동일한 결과물을 생성한다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.11-20
• /
• 2024

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.1
• /
• pp.111-120
• /
• 2022

It is essential to make a purchase decision to make sure that the furniture matches well with other structures in the room. Moreover, in the Untact Marketing situation caused by the COVID-19 crisis, this is becoming an even more impact factor. Accordingly, methods of measuring length using AR(Augmented Reality) are emerging with the advent of AR open sources such as ARCore and ARKit for furniture arrangement interior simulation. Since this existing method using AR generates a Depth Map based on a flat camera image and it also involves complex three-dimensional calculations, limitations are revealed in work that requires the information of accurate room size using a smartphone. In this paper, we propose a method to accurately measure the size of a room using only the accelerometer and gyroscope sensors built in smartphones without using ARCore or ARKit. In addition, as an example of application using the presented technique, a method for applying a pre-designed room interior to each room is presented.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.3
• /
• pp.191-196
• /
• 2018

The purpose of this study is to propose improvements for 3D garment simulation system by comparison with the difference between real garment and 3D garment simulation A, B of women's jacket. The process of the study was to take pictures on the standard sized subject wearing the jacket of basic size, to get a avatar from body sizes of the subject, and to obtain images of 3D garment simulation on the avatar. The appearance evaluation was resulted by the method of a questionnaire survey after presenting the images to 20 members of women's jacket customer. On that appearance evaluation, performed comparative analysis of same degree between the real garment and the Virtual garment A in women's jacket. And performed comparative analysis of same degree between the real garment and the Virtual garment B in women's jacket. It was done t-test for difference in appearance evaluation between real garment/virtual garment A and Real garment/virtual garment B. There were the differences on 4 areas: 1 question on the fabric, 9 questions on the front, 3 questions on the side, and 6 questions on the back.

• The korean journal of orthodontics
• /
• v.38 no.4
• /
• pp.252-264
• /
• 2008

Objective: To aid the development of a frontal image simulating program, we evaluated the soft tissue frontal changes in relationship to movement of hard tissue with orthognathic surgery of facial asymmetry patients. Methods: Preoperative and postoperative frontal cephalograms and frontal view photographs of 45 mandibular surgery patients with facial asymmetry were obtained in a standardized manner. Vertical and horizontal changes of hard tissue and soft tissue were measured from cephalograms and photographs, respectively. Soft tissue change in result to hard tissue change was then analyzed. Results: Both vertical and horizontal correlation analysis showed a weak relationship between the changes. Hard tissue points that were picked for 1 : 1 mean ratio with soft tissue points did not show any significant relevance. For each soft tissue change, regressive equation was formulated by stepwise multiple regression analysis, and the equation for soft tissue Menton was most reliable in predicting changes. Both vertical and horizontal hard tissue changes were used together in prediction of vertical or horizontal soft tissue change. Conclusions: The results suggest that computerized image simulation using regression analysis may be of help for prediction of soft tissue change, while 1:1 mean ratio method is not useful.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.157-162
• /
• 2009

As the improvement of computer performance and the development of IT technology have influence upon publishing industry, the e-Book system, a type of electronic resources, has come out. This is a method to use both texts and 2D image illustrations. Nowadays, there are more and more users who want high quality contents and a variety of contents such as the illustrated fish book using the 3D system. This article adds 3D animation objects to the current e-Book system and designs and realizes the 3D fish simulation system to which e-Book technology is applied so as to improve the comprehension of texts and readability of detailed information and increase readers' immersion as well.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.71-76
• /
• 2023

In this paper, we propose a fuzzy U-Net, a fuzzy deep learning model that applies fuzzy logic to improve performance in image segmentation using deep learning. Fuzzy modules using fuzzy logic were combined with U-Net, a deep learning model that showed excellent performance in image segmentation, and various types of fuzzy modules were simulated. The fuzzy module of the proposed deep learning model learns intrinsic and complex rules between feature maps of images and corresponding segmentation results. To this end, the superiority of the proposed method was demonstrated by applying it to dental CBCT data. As a result of the simulation, it can be seen that the performance of the ADD-RELU fuzzy module structure of the model using the addition skip connection in the proposed fuzzy U-Net is 0.7928 for the test dataset and the best.

• Journal of Korea Multimedia Society
• /
• v.12 no.8
• /
• pp.1128-1141
• /
• 2009

Graphical expressions are continuously improving, spurred by the astonishing growth of the game technology industry. Despite such improvements, users are still demanding a more natural gaming environment and true reflections of human emotions. In real life, people can read a person's moods from facial color and expression. Hence, interactive facial colors in game characters provide a deeper level of reality. In this paper we propose a facial color adaptive technique, which is a combination of an emotional model based on human emotion theory, emotional expression pattern using colors of animation contents, and emotional reaction speed function based on human personality theory, as opposed to past methods that expressed emotion through blood flow, pulse, or skin temperature. Experiments show this of expression of the Facial Color Model based on facial color adoptive technique and expression of the animation contents is effective in conveying character emotions. Moreover, the proposed Facial Color Adaptive Technique can be applied not only to 2D games, but to 3D games as well.

• Journal of Digital Contents Society
• /
• v.5 no.1
• /
• pp.12-21
• /
• 2004

Modem society is information oriented with countless people needing quick reliable information. They also wart to be freed from the limitations of reality such astime and space and experience the world of imagination as if it was reality. Design is creating something out of nothing which has an innate sense of virtual within it. Since it is a process of bringing an imagingnation or an image to life, it can be described as the realization of virtuality. there are many ways in which computer adapted methods were utilized for design up to now. With the advance of computers, the process of desinging became efficient, visually complex and much easier. Undoubtedly, computer is a powerful hardware an design and furthermore, find a way to maximize the presence and to actively incorporate this in designing. The virtual reality system can be widely applied to environmental design to provude a high quality design and enhance the feeling of reality through imitation experiments. Computer simulation such as virtual reality systems is expected to be used widely in environmental design.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.2
• /
• pp.235-242
• /
• 2008

An Autonomous mobile robot is a very useful system to achieve various tasks in dangerous environment, because it has the higher performance than a fixed base manipulator in terms of its operational workspace size as well as efficiency. A method for estimating the position of an object in the Cartesian coordinate system based upon the geometrical relationship between the image captured by 2-DOF active camera mounted on mobile robot and the real object, is proposed. With this position estimation, a method of determining an optimal path for the autonomous mobile robot from the current position to the position of object estimated by the image information using homogeneous matrices. Finally, the corresponding joint parameters to make the desired displacement are calculated to capture the object through the control of a mobile robot. The effectiveness of proposed method is demonstrated by the simulation and real experiments using the autonomous mobile robot.