• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.10
• /
• pp.521-528
• /
• 2007

This paper proposes a new method for the high- speed penetration detection between the 3D human body model and the 3D cloth model using a virtual cylinder, and for the correction of the 3D cloth model. Penetration sometimes occurs locally, when the cloth model is adopted geometrically to the body. This method establishes the virtual cylinder surrounding the body model and the cloth model, and selects at a time the candidates of the penetrated points using the virtual cylinder. Finally, the penetrated points are detected among the candidates. Shift of the vertices or division of the edges in the penetrated points can correct the cloth model geometrically. This method works faster than the physical-based method. The latter requires the repeated detection of the penetrated points using bounding volume and the repeated corrections of the cloth model using dynamics.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.221-222
• /
• 2022

본 논문에서는 모발 정밀검사(Phototrichogram)를 통해 일정 간격을 두고 촬영된 환자의 모발 두피 사진을 이용하여 머리카락 검출 및 머리카락의 개수 변화 추이에 따른 환자의 탈모 진단에 도움을 줄 방법을 제안하였다. 모발 정밀검사를 진행하여 촬영된 환자의 모발 사진으로부터 딥러닝 기반의 영상 분할 기법(Image Segmentation)의 하나인 DetectoRS 모델을 활용하여 머리카락을 자동 검출한다. 실험 결과 DetectoRS 모델의 분할 성능은 74.74%로 효과적으로 머리카락을 검출하였음을 확인할 수 있었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.3
• /
• pp.1401-1407
• /
• 2011

Abstract In this paper, we describe client/server puretone audiometer supporting video chat. Our system makes it possible for one audiometrist to concurrently assess multiple subjects. An audiometrist in remote place can monitor assessment procedure through video and/or result of each assessment step. This system also provides a video chat facility to lead audiometrist without a hitch whenever there occurs any problem during assessment. The one-to-many model of this system makes subjects to reduce not only expense but also waiting time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.18-20
• /
• 2022

3D 프린팅 임플란트 부품은 표면에 결함이 생기기 쉬우므로, 출력 후 표면을 검사하는 과정이 필요하다. 표면 검사를 자동화하기 위해서는 임플란트를 3D 스캔하여 점군 (point cloud)와 같은 스캔 모델로 구성하는 방법이 효과적이다. 스캔 모델을 구성할 때, 임플란트가 일반적인 3D 프린팅 출력물과는 다른 특성들을 가지므로 이에 대한 고려가 필요하다. 본 논문에서는 3D 프린터로 출력된 의료용 임플란트 부품의 특성에 맞게 3D 스캔을 수행하여 스캔 모델을 구성하는 방법을 제안하고, 실험을 통해 생성된 스캔 모델을 보인다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.5
• /
• pp.913-918
• /
• 2006

Patients of dyslexia have an reading disorder marked by the occurrence of semantic errors. Because there is little understanding of dyslexia in korea, we use a translation version of foreign tester for testing the patients of dyslexia. However, the foreign testers is not suitable for testing the korean patients, because language is sensitive to national culture and trait. In this paper, we propose a model of tester for dyslexia Which is used for classification and analysis of korean patients. In addition, we show some characteristics of the implemented tester by a performance study.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.21 no.3
• /
• pp.269-276
• /
• 2001

Ultrasonic testing of composite materials is much more difficult than that of isotropic materials, because of the beam skew phenomenon caused by their elastic anisotropy. An established analytical method exists for elastic wave propagation in anisotropic media as a result of previous research efforts. Yet, due to the complexity of the analytical method, solution of real problems must resort to the numerical method. In this work, analytical solutions have first been obtained for the wavefield due to a point source in a unidirectional fiber-reinforced composite, which may be modeled as transversely isotropic. Then, the corresponding numerical solutions have been obtained using the mass-spring lattice model(MSLM). The two solutions have agreed well with each other. Other problems such as reflection from free boundaries and scattering from cracks have also been solved numerically, and the results have been investigated from the viewpoint of wave mechanics. The numerical model whose validity has been confirmed by this work will be of great use in simulating ultrasonic testing of composite materials.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.8
• /
• pp.729-736
• /
• 2017

In this study, the physics-based model and machine learning technique were used to conduct model-assisted probability of detection (MAPOD) experiments. The possibility of using in-service cracked parts was also investigated. Bolt hole shaped specimens with fatigue crack on the hole surface were inspected using eddy current inspection. Owing to MAPOD, the number of experimental factors decreased significantly. The uncertainty in the crack length measurement for in-service cracked parts was considered by the application of Monte Carlo simulation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

Currently, the inspection method printed on food packages and boxes is to sample only a few products and inspect them with human eyes. Such a sampling inspection has the limitation that only a small number of products can be inspected. Therefore, accurate inspection using a camera is required. This paper proposes a deep learning object recognition technology model, which is an artificial intelligence technology, as a method for detecting the defects of expiration date printed on the product packaging. Using the Faster R-CNN (region convolution neural network) model, the color images, converted gray images, and converted binary images of the printed expiration date are trained and then tested, and each detection rates are compared. The detection performance of expiration date printed on the package by the proposed method showed the same detection performance as that of conventional vision-based inspection system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.21-26
• /
• 2000

인간의 잠재적 능력을 측정하기 위하여 많은 검사가 이루어진다. 이러한 검사를 위하여 양질의 문항 제작이 필수적이다. 그러나 문항 제작의 중요성을 인식하지 못하고 단시간에 쉽게 제작된 문항들을 쓰고 폐기하는 경우가 많다. 본 논문에서는 양지르이 문항 제작을 위하여 문항 내용 분석, 문항 응답 자료 분석, 문항 난이도, 문항 변별도, 문항 추측도, 오답의 능률도를 이용하여 자료분석에 유용한 효과를 보이는 신경망을 이용한 학업 성취도 시스템 모델을 제안하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.31-33
• /
• 2003

기능 검사(function simulation)란 하드웨어 시스템의 설계시 모델의 기능, 성능, 표준 준수 여부, 그리고 다른 상위 수준 조건의 관점에서 그 설계를 분석하는 중요한 설계 흐름이다. 하지만 복잡한 기존의 기능 검사의 절차는 사용자의 요구에 의해 하드웨어 시스템이 점점 복잡해지고 정보산업의 발전에 따라 개발 주기가 점점 빨라지는 시장의 특성으로 인해 설계자에게 많은 시간적 경제적인 부담감을 준다. 본 논문에서는 설계자에게 가중되는 부담을 극복하고 보다 효율적인 하드웨어 시스템의 모델링 및 기능 검사를 위해 오토마타 동치성 검사를 통한 하드웨어 시스템의 논리적 정확성 확인 방법론을 제안한다.