• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2006년도 춘계학술대회 학술발표 논문집 제16권 제1호
• /
• pp.416-419
• /
• 2006

본 논문에서는 음성 속도를 고려한 새로운 립싱크 방법에 대해서 제안한다. 실험을 통해 구축한 데이터베이스로부터 음성속도와 입모양 및 크기와의 관계를 퍼지 알고리즘을 이용하여 정립하였다. 기존 립싱크 방법은 음성 속도를 고려하지 않기 때문에 말의 속도와 상관없이 일정한 입술의 모양과 크기를 보여준다. 본 논문에서 제안한 방법은 음성 속도와 입술 모양의 관계를 적용하여 보다 인간에 근접한 립싱크의 구현이 가능하다. 또한 퍼지 이론을 사용함으로써 수치적으로 정확하게 표현할 수 없는 애매한 입 크기와 모양의 변화를 모델링 할 수 있다. 이를 증명하기 위해 제안된 립싱크 알고리즘과 기존의 방법을 비교하고 3차원 그래픽 플랫폼을 제작하여 실제 응용 프로그램에 적용한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.323-327
• /
• 1995

A new air knife system for coating thickness control in hot dip galvanizing process had been developed and installed on the CGL in Pohang Steel Works, POSCO. This new system consists of air knives with remotely adjustable nozzle slot and an automatic control system which can control both longitudinal and traverse coating deviations. Based on the optimal control algorithm, a traverse coating deviation control was designed. The controller controls the lip profile of the air knives with flexible structure according to the deviation of coating weight. From the measured values which are dependent on the strip width, the lip gaps are calculated with optimal algorithm and the model of the coating deviation. Time delay between knives and a coating thickness gauge is solved by the Smith Predictor.

• KSTLE International Journal
• /
• 제1권1호
• /
• pp.43-47
• /
• 2000

Oil seals will experience a small amplitude dynamic excitation due to the shaft eccentricity as well as out-of-roundness of the shaft. The direct integration method is selected to analyze the time domain response of the seal lip-shaft contact. The physical properties of rubber seal materials are experimentally analyzed. Effects of both frequency and temperature on the material stiffness behavior are investigated for the linear viscoelastic materials of the seal. Using the nonlinear transient model, a finite element analysis of the lip-shaft contact behaviors under dynamic conditions is presented as a function of the shaft eccentricity, the shaft interference and the garter spring stiffness. The FEM results based on the experimental data indicate that the increased rotating speed may produce the separation conditions. These results will be very useful in predicting the leakage of oil seals under dynamic conditions.

• 대한구순구개열학회지
• /
• 제15권2호
• /
• pp.51-60
• /
• 2012

Craniofacial sutures absorb the stress transferred to skull. It was reported the cells of craniofacial sutures respond to exogenetic factors to be involved in growth control mechanism. In this study, we constructed a finite element model composed of cortical bone, cancellous bone, suture, PDL, and teeth by using CT images of a growing patient, simulating maxillary expansion to evaluate the effects of the thickness of sutures and type of maxillary expansion appliance on stress distribution in circummaxillary sutures.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.15-18
• /
• 2000

In this study, we improve the performance of a speech recognition system of visual information depending on lip movements. This paper focuses on the robustness of the word recognition system with the rotation, transition and scaling of the lip images. The different methods of lipreading have been used to estimate the stability of recognition performance. Especially, we work out the special system of the log-polar mapping, which is called Mellin transform with quasi RTS-invariant and related approaches to machine vision. The results of word recognition are reported with HMM (Hidden Markov Model) recognition system.

• 전기학회논문지
• /
• 제63권6호
• /
• pp.813-819
• /
• 2014

The purpose of this study was to extract accurate parameters of facial movement features using 3-D motion capture system in speech recognition technology through lip-reading. Instead of using the features obtained through traditional camera image, the 3-D motion system was used to obtain quantitative data for actual facial movements, and to analyze 11 variables that exhibit particular patterns such as nose, lip, jaw and cheek movements in monosyllable vocalizations. Fourteen subjects, all in 20s of age, were asked to vocalize 11 types of Korean vowel monosyllables for three times with 36 reflective markers on their faces. The obtained facial movement data were then calculated into 11 parameters and presented as patterns for each monosyllable vocalization. The parameter patterns were performed through learning and recognizing process for each monosyllable with speech recognition algorithms with Hidden Markov Model (HMM) and Viterbi algorithm. The accuracy rate of 11 monosyllables recognition was 97.2%, which suggests the possibility of voice recognition of Korean language through quantitative facial movement analysis.

• 한국정보통신학회논문지
• /
• 제3권1호
• /
• pp.59-68
• /
• 1999

최근 통신 시스템의 연구와 발전 방향은 목소리의 음성 정보와 말하는 얼굴 영상의 화상 정보를 함께 적용하므로서 음성 정보만을 제공하는 경우보다 높은 인식율을 제공한다. 따라서 본 연구는 청각장애자들의 언어 대체수단 중 하나인 구화(speechreading)에서 가장 시각적 변별력이 높은 입모양 인식을 일반 퍼스널 컴퓨터상에서 구현하고자 한다. 본 논문은 기존의 방법과 달리 말하는 영상 시퀀스에서 입모양 인식을 행하기 위해 3차원 모델을 사용하여 입의 벌어진 정도, 턱의 움직임, 입술의 돌출과 같은 3차원 특징 정보를 제공하였다. 이와 같은 특징 정보를 얻기 위해 3차원 형상 모델을 입력 동영상에 정합시키고 정합된 3차원 형상 모델에서 각 특징점의 변화량을 인식파라미터로 사용하였다. 그리고, 인식단위로 동영상을 분리하는 방법은 3차원 특징점 변화량에서 얻어지는 강도의 기울기에 의하여 이루어지고, 인식은 각각의 3차원 특징벡터를 이산 HMM 인식기의 인식 파라메타로 사용하였다. 본 논문에서는 한국어 10개 모음에 대하여 인식실험하여 비교적 높은 인식율을 얻을 수 있는 것으로 보아 본 연구에서 사용한 특징 벡터를 시간적 변별 요소로서 사용할 수 있음을 제시하였다.

• 제어로봇시스템학회논문지
• /
• 제5권5호
• /
• pp.593-599
• /
• 1999

A mobile robot in FMS environment should be able to nevigate itself. Therefore, path planning is necessary for the mobile robot to perform its tasks without being lost. Path planning using a network model gives oprimal paths to every pair of nodes but building this model demands accurate information of environments. In this paper, a method to build a network model using sonar sensors is presented. The main idea is to build a quad tree model by using sonar sensors and convert the model to a network model for path planning. The new method has been implemented on a mobile robot. Experimental results show that the mobile robot constructs an accurate network model using inaccurate sonar data.

• 한국유변학회:학술대회논문집
• /
• 한국유변학회 2006년도 춘계 학술발표회 논문집
• /
• pp.81-84
• /
• 2006

Slot coating process, in continuous and patch modes, has been applied for the many precise coating products, e.g., flat panel displays and second batteries. However, manufacturing uniform coating products is not a trivial task at high-speed operations because various flow instabilities or defects such as leaking, bubbles, ribbing, and rivulets are frequently observed in this process. It is no wonder, therefore, that many efforts to understand the various aspects of dynamics and coating windows of this process have been made both in academia and industry. In this study, as the first topic, flow dynamics within the coating bead in slot coating process has been investigated using the one-dimensional viscocapillary model by lubrication approximation and two-dimensional model by Flow-3D software. Especially, operability windows in both 1D and 2D cases with various slot die lip designs have been successfully portrayed. Also, effects of process conditions like viscosity and coating gap size on slot coating window have been analyzed. Also, some experiments to find minimum coating thickness and coating windows have been conducted using slot die coater implemented with flow visualization device, corroborating the numerical results. As the second topic, flow dynamics of both Newtonian and Non-Newtonian fluids in patch or pattern slot coating process, which is employed in manufacturing IT products such as secondary batteries, has been investigated for the purpose of optimal process designs. As a matter of fact, the flow control in this system is more difficult than in continuous case because od its transient or time-dependent nature. The internal die and die lip designs for patterned uniform coating products have been obtained by controlling flow behaviors of coating liquids issuing from slot. Numerical simulations have been performed using Fluent and Flow-3D packages. Flow behavior and pressure distribution inside the slot die has been compared with various die internal shapes and geometries. In the coating bead region, efforts to reduce irregular coating defects in head and tail parts of one patterned coating unit have been tried by changing die lip shapes. It has been concluded that optimal die internal design gas been developed, guaranteeing uniform velocity distribution of both Newtonian and shear thinning fluids at the die exit. And also optimal die lip design has been established, providing the longer uniform coating layer thickness within one coating unit.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.45-47
• /
• 2006

Cleft palate is a congenital deformity condition with separation of the two sides of the lip resulting in nose deformity. Evaluation of surgical corrections and outcome assessments for nose deformity due to the cleft lip depends mainly on doctor's subjective judgment. An objective method for evaluation of the condition and surgical outcome of nose deformity due to the cleft palate is needed. This study aimed at objective assessment of a cleft palate nose deformity condition by analyzing the following parameters obtained from photographic images of a cleft palate patients: (1) angle difference between two nostril axes. (2) center of the nostril and distance between two centers. (3) overlapped area of two nostrils, and (4) the overlapped area ratio of the two nostrils. A regression equation of doctor's grades was obtained using the eight parameters. Three plastic surgeons gave us the grades for the each photographic image by 10 increments with maximum grade of 100. The average reproducibility of the grades given by the three plastic surgeons and the three laymen using the developed program was $10.8{\pm}4.6%$ and $7.4{\pm}1.8%$, respectively. Kappa values representing the degree of consensus of the plastic surgeons and the three laymen were 0.43 and 0.83. respectively. Correlation coefficient of the grades evaluated by the surgeons and obtained by the neural network was 0.798. In conclusion. the developed neural network model provided us better reproducibility and much better consensus than doctor's subjective evaluation in addition to objectiveness and easy application.