• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.3
• /
• pp.284-291
• /
• 2005

I propose a framework for detecting, recognizing and classifying facial features based on learned expression patterns. The framework recognizes facial expressions by using PCA and expression HMM(EHMM) which is Hidden Markov Model (HMM) approach to represent the spatial information and the temporal dynamics of the time varying visual expression patterns. Because the low level spatial feature extraction is fused with the temporal analysis, a unified spatio-temporal approach of HMM to common detection, tracking and classification problems is effective. The proposed recognition framework is accomplished by applying posterior probability between current visual observations and previous visual evidences. Consequently, the framework shows accurate and robust results of recognition on as well simple expressions as basic 6 facial feature patterns. The method allows us to perform a set of important tasks such as facial-expression recognition, HCI and key-frame extraction.

• Structural Engineering and Mechanics
• /
• v.52 no.2
• /
• pp.323-349
• /
• 2014

In this paper, linear buckling analysis of a curved sandwich beam with a flexible core is investigated. Derivation of equations for face sheets is accomplished via the classical theory of curved beam, whereas for the flexible core, the elasticity equations in polar coordinates are implemented. Employing the von-Karman type geometrical non-linearity in strain-displacement relations, nonlinear governing equations are resulted. Linear pre-buckling analysis is performed neglecting the rotation effects in pre-buckling state. Stability equations are concluded based on the adjacent equilibrium criterion. Considering the movable simply supported type of boundary conditions, suitable trigonometric solutions are adopted which satisfy the assumed edge conditions. The critical uniform load of the beam is obtained as a closed-form expression. Numerical results cover the effects of various parameters on the critical buckling load of the curved beam. It is shown that, face thickness, core thickness, core module, fiber angle of faces, stacking sequence of faces and openin angle of the beam all affect greatly on the buckling pressure of the beam and its buckled shape.

• KCI Concrete Journal
• /
• v.13 no.2
• /
• pp.19-25
• /
• 2001

A simple expression to predict bond strength of reinforcing bars with rib deformation to the surrounding is derived for the case of splitting bond failure. Finite element analysis is used to model the confining behavior of concrete cover. The roles of the interfacial properties, specifically, the friction coefficient, cohesion, the relative rib area and the rib face angle are examined. Values of bond strength obtained using the analytical model are in good agreement with the bond test results from the previous studies. The analytical model provides insight into interfacial bond mechanisms and the effects of the key variables on the bond strength of deformed bars to concrete. Based on the comparison between the analytical results and the test results, the values of cohesion, coefficient of friction, and the effective rib face angle are proposed.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.328-330
• /
• 2007

Emotion is getting one of the important elements of the intelligent service robots. Emotional communication can make more comfortable relation between humans and robots. We developed emotional head robot system using 3D character. We designed emotional engine for making emotion of the robot. The results of face recognition and hand recognition is used for the input data of emotional engine. 3D character expresses nine emotions and speaks about own emotional status. The head robot has memory of a degree of attraction. It can be chaIU!ed by input data. We tested the head robot and conform its functions.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.451-454
• /
• 2000

본 논문은 한글 단어에 따른 한글 발음에 적합한 입술의 움직임을 자동 생성하며 또한 단어에 적절한 얼굴 보정을 생성할 수 있는 입순 움직임과 얼굴 표정을 동기화하는 3차인 일관애니메이션 편집기를 구축하였다. 얼굴 애니메이션 편집기에서 얼굴 표정은 근육 기반 모델 방법으로 정의된 각 얼굴 부위별 근육에 따라 가중치를 조절하여 생성하여 입술 움직임은 텍스트 구동 방법으로 음소에 따른 정의된 입모양 연속적으로 표현하여 동작한다. 또한 이렇게 생성된 얼굴 표정을 저장관리한다. 따라서 3차원 얼굴 애니메이션 편집기는 6가지의 기본 얼굴 표정을 자동적으로 생성할 수 있으며 또한 입력 단어에 적합하도록 각 얼굴 부위별 근육 움직임을 편집한 수 있다. 이렇게 생성된 얼굴 표정들은 데이터베이스에 저장관리할 수 있으며 컴퓨터 대화시 자동적으로 입력 단어에 적합한 입술의 움직임과 얼굴 표정을 동기화하여 자연스러운 3차원 얼굴 애니메이션을 표현할 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.9
• /
• pp.3685-3700
• /
• 2015

To avoid influences caused by pose, illumination and facial expression variations, we propose a robust three-step algorithm based on ASM and POEM for facial landmark localization. Firstly, Model Selection Factor is utilized to achieve a pose-free initialized shape. Then, we use the global shape model of ASM to describe the whole face and the texture model POEM to adjust the position of each landmark. Thirdly, a second localization is presented to discriminatively refine the subtle shape variation for some organs and contours. Experiments are conducted in four main face datasets, and the results demonstrate that the proposed method accurately localizes facial landmarks and outperforms other state-of-the-art methods.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.9
• /
• pp.39-45
• /
• 2015

Along with the advance of digital technology, various methods are adopted for capturing the 3D animating data. Especially, in 3D animation production market, the motion capture system is widely used to make films, games, and animation contents. The technique quickly tracks the movements of the actor and translate the data to use as animating character's motion. Thus the animation characters are able to mimic the natural motion and gesture, even face expression. However, the conventional motion capture system needs tricky conditions, such as space, light, number of camera etc. Furthermore the data acquired from the motion capture system is frequently corrupted by noise, drift and surrounding environment. In this paper, we introduce the post production techniques to stabilizing the jitters of motion capture data from the low cost handy system based on Kinect.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.872-878
• /
• 2000

In this paper a computer programming for the expression of nearest neighbor atoms in face-centered cubic (FCC) and body-centered cubic (BCC) crystals was suggested as one of the approaches to understand each of the crystal structure. By using this computer programming the distance values between a reference atom and the nearest neighbor atoms, and the numbers of the nearest neighbor atoms were calculated ane compared for the FCC and BCC crystals. In this algorithm, the positions of the atoms in a crystal were defined as two categories: the corner atoms and face- or body-centered atoms, and considered respectively. For the same order of nearest neighbor atoms except the second order ones the distance values form the reference atom were smaller in the FCC crystals than those in the BCC. Also, the numbers of he first and third nearest neighbor atoms n the FCC crystals were larger than those in the BCC. This difference was explained by the comparison of each atomic packing ratio of the FCC and BCC crystals. The algorithm used in this programming can also be expanded to the analysis of other crystal structures.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.293-296
• /
• 2000

본 논문에서는 얼굴의 구조적 특성과 누적 히스토그램을 이용하여 다양한 정보를 포함하고 있는 얼굴의 6가지 표정을 인식하는 알고리즘을 기술하였다. 표정 인식을 위해 특징점 추출 전처리 과정으로 입력 영상으로부터 에지 추출, 이진화, 잡음 제거, 모폴로지 기법을 이용한 팽창, 레이블링 순으로 적용한다. 본 논문은 레이블 영역의 크기를 이용해 1차 특징점 영역을 추출하고 가로방향의 누적 히스토그램 값과 대칭성의 구조적인 관계를 이용하여 2차 특징점 추출 과정을 거쳐 정확하게 눈과 입을 찾아낸다. 또한 표정 변화를 정량적으로 측정하기 위해 추출된 특징점들의 눈과 입의 크기, 미간 사이의 거리 그리고 눈에서 입까지의 거리 정보를 이용하여 표정을 인식한다. 1, 2차 특징점 추출 과정을 거치므로 추출률이 매우 높고 특징점들의 표정에 따른 변화 거리를 이용하므로 표정 인식률이 높다. 본 논문은 안경 착용 영상과 같이 복잡한 얼굴 영상에서도 표정 인식이 가능하다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.4
• /
• pp.26-34
• /
• 2024

Most human emotions are conveyed through facial expressions, which represent the predominant source of emotional data. This research investigates the impact of crowds on human emotions by analysing facial expressions. It examines how crowd behaviour, face recognition technology, and deep learning algorithms contribute to understanding the emotional change according to different level of crowd. The study identifies common emotions expressed during congestion, differences between crowded and less crowded areas, changes in facial expressions over time. The findings can inform urban planning and crowd event management by providing insights for developing coping mechanisms for affected individuals. However, limitations and challenges in using reliable facial expression analysis are also discussed, including age and context-related differences.