http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
오늘 본 자료
Cascade Method Pedestrian Recognition using Haar-like features based on Adaboost Algorithm
Yeunghak Lee,Taesun Kim,Misoon Choi,Jooyoung Ko,Jaechang Shim,Sanghunn Yoon,Taemoon Rho 한국멀티미디어학회 2010 한국멀티미디어학회 국제학술대회 Vol.2010 No.-
We integrate the cascade method approach with Haar-like features to achieve accurate pedestrian recognition system, which is applied Adaboost algorithm to make a strong classification. The features used in our system are basic Haar-like features which includes horizontal and vertical characteristic. In the proposed method, we use one feature vector and one strong classification for the first stage of recognition. For the recognition-failed image, the other feature and strong classification will be used for the second stage of recognition. Experiment results on two common datasets and the proposed algorithm shows higher recognition rate compared to the previous methods.
다객체 모델에 대한 사용자 중요도 기반 시점/조명 조절 기법
김태문(Taemoon Kim),이성길(Sungkil Lee) Korean Institute of Information Scientists and Eng 2018 정보과학회논문지 Vol.45 No.9
In computer graphics, viewpoint selection for objects in a scene has been performed by evaluating the goodness of sampled viewpoints. Since the definition of a good viewpoint varies according to the user’s purpose, various measurements such as entropy and mesh saliency have been used. In this paper, we propose a method of selecting the best viewpoint and lighting for a multi-object scene, based on the user-assigned importance of each object. After sampling a viewpoint and lighting from the surrounding sphere of the scene, we render the images by combining the sampled viewpoint and lighting. We then select the best result that coincides with user-assigned importance by quantifying the saliency of each object in the rendered image. While this technique has the disadvantage of high computation cost due to the need to render combinations of viewpoints and lighting, it obtains the viewpoint and lighting most suitable for the user`s needs. In order to minimize the computation cost, an object-by-object pixel classification technique on GPU is also proposed in this paper.
Yong-Ku Kong,Hyunjoon Park,Dujeong Kim,Taemoon Lee,Eunyoung Roh,Seulki Lee,Wenbin Zhao,Dae-Min Kim,Hyun-Sung Kang 대한인간공학회 2013 大韓人間工學會誌 Vol.32 No.6
Objective: The purpose of this study is to analyze the individual finger force between dominant hand and non-dominant hand and to investigate an effect of the individual finger on the total grip strength depending on dominant hand and non-dominant hand. Background: Many studies on the ratio of the grip force between dominant hand and non-dominant hand has been researched. While a 10% rule which is a ratio of the grip force between dominant hand and non-dominant hand has been applied in most studies, studies on the rate of the individual finger force between dominant hand and non-dominant hand have been insufficiently researched. Method: The experiment was preceded with 17 subjects (male, mean 25.8 ages). The individual finger force and total grip strength were measured using pliers being able to change the grip span from 45 to 80mm. Results: The difference of total grip strength between dominant hand and non-dominant hand is following 10% rule. However, the difference of individual finger force between dominant hand and non-dominant hand are not same as the difference of total grip strength. Especially in the case of grip span with 50mm, the differences between total grip strength, index finger, middle finger, ring finger, and little finger were 9.87±14.80%, 8.95±37.17%, 13.71±28.27%, 6.77±24.35%, 39.29±42.46%, respectively, with p=0.018 of statistical significance. Additionally, the results of regression analysis in 50 and 60mm of grip span showed that the difference in ring finger affected the most to the total grip strength; and the effects followed in order of index finger, middle finger, and little finger. Conclusion: Our study suggests that an effect of individual finger and grip span of pliers have to be considered when explaining the difference of the total grip strength between dominant hand and non-dominant hand. Application: This result is expected to be used for designing ergonomic hand tool.
얼굴 인식을 통한 신뢰성 있는 디지털 도어록 제어 시스템
임지민,김찬,차원석,한태문,허규원,송상근,이상준,Lim, Jimin,Kim, Chan,Cha, Wonsuk,Han, Taemoon,Huh, Guewon,Song, Sanggeun,Lee, Sangjun 한국전기전자학회 2013 전기전자학회논문지 Vol.17 No.4
Automation is being progressed rapidly in various fields with the advancement of IT technology. Home automation is a typical application and is being used in a variety of ways now. Most of digital door lock systems simply support to open and close a door using the methods of password and a particular magnetic key. In this paper, we propose a intelligent digital door lock system using face recognition technology. Our proposed system can control the locking device opening and closing from a remote location after confirming the identification of the visitor via a smart device, and support the reliable and secure control of door systems. IT 기술 발전과 함께 다양한 분야에서 자동화가 진행되고 있다. 홈오토메이션 또한 현재 다양한 형태로 적용되고 있다. 현재 이용 중인 디지털 도어록 시스템은 단순히 비밀번호 입력 및 마그네틱 전자키 방식을 통한 잠금장치의 개폐만을 지원하고 있다. 본 논문에서는 홈오토메이션과 디지털 도어록 시스템 안전성 확보를 위한 지능화된 얼굴인식기술을 활용한 도어록 시스템을 제안한다. 제안 시스템은 원격지에서 방문자의 신원을 확인한 후 이를 바탕으로 잠금장치의 개폐를 조정할 수 있으며, 이를 통해 안전한 출입 통제 관리가 가능하도록 지원해준다.