• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 가을 학술발표논문집 Vol.28 No.2 (2)
• /
• pp.412-414
• /
• 2001

In this paper, we describe an real-time facial feature tracker. We only used a general USB PC Camera without a frame grabber. The system has achieved a rate of 8+ frames/second without any low-level library support. It tracks pupils, nostrils and corners of the lip. The signal from USB Camera is YUV 4:2:0 vertical Format. we converted the signal into RGB color model to display the image and We interpolated V channel of the signal to be used for extracting a facial region. and we analysis 2D blob features in the Y channel, the luminance of the image with geometric restriction to locate each facial feature within the detected facial region. Our method is so simple and intuitive that we can make the system work in real-time.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2000년도 추계학술대회 논문집
• /
• pp.571-574
• /
• 2000

Seals in universal joint bearing are a important component reinforcing lubrication performance by holding a lubricant and preventing infiltration of dust, moisture, etc. There is a great difference in seal performance according to seal shape and bonding position. Therefore, in this study, as for the lib type seal and O-ring type seal, FEM analysis are conducted using Mooney-Rivlin Model. The results are indicate that O-ring having higher contact stress and larger contact area than lib type is more profitable.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2005년도 춘계학술발표대회
• /
• pp.225-228
• /
• 2005

얼굴표정은 상대방에게 자신의 감정과 생각을 간접적으로 나타내는 중요한 의사소통의 표현이 되며 상대방에게 직접적인 표현방법의 수단이 되기도 한다. 이러한 표현 방법은 컴퓨터를 매개체로 하는 메신저간의 의사 전달에 있어서 얼굴표정을 사용함으로써 상대방의 감정을 문자로만 인식하는 것이 아니라 현재 상대방이 느끼는 내적인 감정까지 인식하여 대화할 수 있다. 본 논문은 3D 메시로 구성된 얼굴 모델을 이용하여 사용자가 입력한 한글 메시지의 한글 음절을 분석 추출 하고, 3D 얼굴 메시에 서 8개의 입술 제어점을 사용하여 입 모양의 변화를 보여주는 3D Avatar 아바타 메신저 시스템을 설계 및 구현 하였다.

• Journal of Communications and Networks
• /
• 제5권3호
• /
• pp.240-248
• /
• 2003

This paper analyzes mobile agent performance in network management compared to the client-server model used in the Simple Network Management Protocol (SNMP). Prototypes of an application that gathers MIB-II (Management Information Base-II) variables have been created and tested on a LAN. After acquiring implementation parameters related to network management and to the mobile agent infrastructure, simulation results have been obtained on large topologies similar in shape to the Internet. Response time results show that mobile agents perform better than SNMP when the number of managed elements ranges between two specific limits, an inferior bound and a superior one, determined by the number of messages that pass through a backbone and by the mobile agent size which grows along with MIB-II variables collected on network elements. The results also show that a significant improvement is achieved when the mobile agent returns or sends data to the management station after visiting a fixed number of nodes.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 하계학술대회 논문집 B
• /
• pp.892-894
• /
• 1995

This paper deals with developmeant and application of coating thickness control system in hot dip galvanizing process. According to the line conditions, such as line speed, strip size and target coating weight, a predictive preset model sets the initial oprating conditions. Referring the zine coating informations from the gauge, mean coating value controller adjusts the chamber pressure and horizontal distance between strip and air knife, while coating deviation controller adjusts the lip gap profile of the air knife. All adaptive gains are interactively calculated by numeric models based on the theoretical analysis. The operating result with this system effectively reduces the coating deviation in transverse direction as well as in longitudinal direction.

• 음성과학
• /
• 제8권3호
• /
• pp.123-132
• /
• 2001

In recent years research on HCI technology has been very active and speech recognition is being used as its typical method. Its recognition, however, is deteriorated with the increase of surrounding noise. To solve this problem, studies concerning the multimodal HCI are being briskly made. This paper describes automated lipreading for bimodal speech recognition on the basis of image- and speech information. It employs audio-visual DB containing 1,074 words from 70 voice and tri-viseme as a recognition unit, and state tied HMM as a recognition model. Performance of automated recognition of 22 to 1,000 words are evaluated to achieve word recognition of 60.5% in terms of 22word recognizer.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2009년도 추계학술발표대회 논문집
• /
• pp.222-226
• /
• 2009

The parts of building which has the most influence on thermal load are skins, outer walls and windows. Among them, window is the worst weak point of building even if it has many advantage of solar radiation gain than other parts. The present time, many researches on various performance of window and many types of system-window are being made. This study evaluates thermal performance of tilt & sliding system window by simulation program Therm 5.2 and Window 5.2. After making a sample model improving it's thermal weak point, this study evaluates real thermal performance of system window. As a result, this study understands manufacture ability condition of domestic company and proposes a research plan of system window.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.51-54
• /
• 2005

This paper analyzes the vocal tract area estimation algorithm used as a part of a speech analysis program to help deaf children correct their pronunciations by comparing their vocal tract shape with normal children's. Assuming that a vocal tract is a concatenation of cylinder tubes with a different cross section, we compute the relative vocal tract area of each tube using the reflection coefficients obtained from linear predictive coding. Then, obtain the absolute vocal tract area by computing the height of lip opening with a formula modified for children's speech. Using the speech data for five Korean vowels (/a/, /e/, /i/, /o/, and /u/), we investigate the effects of the sampling frequency, frame size, and model order. We compare vocal tract shapes obtained from deaf and normal children's speech.

• 한국멀티미디어학회논문지
• /
• 제22권8호
• /
• pp.852-859
• /
• 2019

With the development of IT technology and smart devices, various applications utilizing image information are being developed. In order to provide an intuitive interface for pronunciation recognition, there is a growing need for research on pronunciation recognition using mouth feature values. In this paper, we propose a system to distinguish Korean vowel pronunciations by detecting feature points of lips region in images and applying Bayesian based learning model. The proposed system implements the recognition system based on Bayes' theorem, so that it is possible to improve the accuracy of speech recognition by accumulating input data regardless of whether it is speaker independent or dependent on small amount of learning data. Experimental results show that it is possible to effectively distinguish Korean vowels as a result of applying probability based Bayesian classification using only visual information such as mouth shape features.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.444-446
• /
• 2011

본 논문은 실시간으로 카메라 영상으로부터 얼굴의 각 특징점을 검출하고, 검출된 특징점을 이용하여 웃음 표정을 인식하는 시스템을 제안한다. 제안된 시스템은 ASM(Active Shape Model)을 이용하여 실시간 검출부에서 얼굴 영상을 획득한 다음 ASM 학습부에서 학습된 결과를 가지고 얼굴의 특징을 찾는다. 얼굴 특징의 영상으로부터 입술 영역을 검출한다. 이렇게 검출된 입술 영역과 얼굴 특징점을 이용하여 사용자의 웃음 표정을 검출하고 인식하는 방법을 사용함으로써 웃음 표정 인식의 정확도를 높힐 수 있음을 알 수 있었다.