• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04a
• /
• pp.742-744
• /
• 2002

얼굴 애니메이션은 개인을 쉽게 구분하고 의사소통을 효율적으로 할 수 있는 보조도구로써 최근 연구가 활발하다. 본 논문에서는 얼굴 표정생성을 위해서 실제얼굴의 피부조직 얼굴 근육 등 해부학적 구조에 기반한 근육 기반 모델 방법을 사용하여 현실감 있고 자연스러운 얼굴 애니메이션이 이루어지도록 한다. 또한 부드러운 얼굴모델을 구현하기 위하여 폴리곤 메쉬를 분할하고 얼굴 표정에 중요한 영향을 미치는 얼굴근육을 추가하여 다양하고 자연스러운 표정을 연출하는 방법을 제시하고자 한다. 제안된 방법을 water〔3〕의 모델에 적용해 봄으로서 더 실감 있는 얼굴 애니메이션에 접근할 수 있는 결과를 얻을 수 있었다. 이 결과는 화상회의나 가상현실, 원격교육, 영화 등 많은 분야에서 활용될 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.175-177
• /
• 2003

This paper addresses a problem of classifying human breast cancer into its subtypes. A main ingredient in our approach is kernel machines such as support vector machine (SVM). kernel principal component analysis (KPCA). and kernel partial least squares (KPLS). In the task of breast cancer classification, we employ both SVM and KPLS and compare their results. In addition to this classification. we also analyze the patterns of clinical outcomes in the feature space. In order to visualize the clinical outcomes in low-dimensional space, both KPCA and KPLS are used. It turns out that these methods are useful to identify correlations between clinical outcomes and the nonlinearly protected expression profiles in low-dimensional feature space.

• The Journal of Information Technology
• /
• v.4 no.1
• /
• pp.97-108
• /
• 2001

This thesis is about the design and implementation of the system for controlling Avatar, user's alter ego in a simulated world using the EAI(External Authoring Interface) technology to be able to control VRML(Virtual Reality Modeling Language). In this thesis, user's Avatar described in VRML language embodied interactions to move and show an expression by JAVA according to a user's demand. In the future, this would be able to develop into a research to try to embody and construct a simulated society based on web for the purpose of various integration of society such as cyber government, lecture, trial performance, and auction.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.10
• /
• pp.1731-1737
• /
• 2016

In this paper, a method is proposed to recognize human actions as nonverbal expression; the proposed method is composed of two steps which are action representation and action recognition. First, MHI(Motion History Image) is used in the action representation step. This method includes segmentation based on depth information and generates spatio-temporal templates to describe actions. Second, CNN(Convolution Neural Network) which includes feature extraction and classification is employed in the action recognition step. It extracts convolution feature vectors and then uses a classifier to recognize actions. The recognition performance of the proposed method is demonstrated by comparing other action recognition methods in experimental results.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.10
• /
• pp.587-598
• /
• 2003

This paper construct two-level word similarity relation matrices about title and to scientific treatise. As guide keyword similarity relation matrices which is constructed to co-occurrence frequency base same time keeps recall rater by query expansion by tolerance relation, it is index structure to improve the precision rate by two-level contents base retrieval. Therefore, draw area knowledge through subject analysis and reasoned user's information request and area knowledge to fuzzy logic base. This research is research to improve vocabulary mismatch problem and information expression having essentially on query.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.696-699
• /
• 2003

In this study, we suggested the model to precisely evaluate the ferroelectric hysteresis loop, using the modified Sawyer-Tower circuit and the ferroelectric capacitor with a MDFM(Metal-Dielectric-ferroelectric-Metal) structure. The mathematical expression of dipole polarization is applied to the numerical integration algorithm, and the fatigue property can be considered including the dielectric layer between ferroelectrics and bottom electrode. The validity of our model is proved comparing the estimated value of our model and the measured results of PLT(10) thin film.

• Journal of information and communication convergence engineering
• /
• v.9 no.5
• /
• pp.505-509
• /
• 2011

This paper attempts to classify known facial expressions and to establish the correlations between two regions (eye + eyebrows and mouth) in identifying the six prototypic expressions. Covariance is used to describe region texture that captures facial features for classification. The texture captured exhibit the pattern observed during the execution of particular expressions. Feature matching is done by simple distance measure between the probe and the modeled representations of eye and mouth components. We target JAFFE database in this experiment to validate our claim. A high classification rate is observed from the mouth component and the correlation between the two (eye and mouth) components. Eye component exhibits a lower classification rate if used independently.

• Journal of Applied Reliability
• /
• v.9 no.1
• /
• pp.13-28
• /
• 2009

In this paper we propose a method for designing optimum degradation test based on nonlinear random-coefficients models. We use the approximated expression of the Fisher information matrix for nonlinear random-coefficients models. We apply the simplex algorithm to the inverse of the determinant of Fisher information matrix to satisfy the D-optimal criterion. By comparison of the results from PDP degradation data, we suggest a general guideline to obtain optimum experimental design for determining inspection intervals and number of samples in degradation testing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.477-480
• /
• 2018

Viola and Jones object detection algorithm is a representative face detection algorithm. The algorithm uses Haar-like features for face expression and uses a cascade-Adaboost algorithm consisting of strong classifiers, a linear combination of weak classifiers for classification. This algorithm requires several parameter settings for its implementation and the set values affect its performance. This paper analyzes face detection performance according to the parameters set in the algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.11A
• /
• pp.1237-1243
• /
• 2004

This paper presents and analyses the closed-form expression of the average bit error rate (BER) for an asynchronous direct-sequence code division multiple access (DS-CDMA) system with coherent binary phase shift keying (BPSK) modulation scheme using a maximal ratio combining (MRC) diversity over a Rician fading channel. In addition to the average BER, outage probability, and user capacity of system are estimated as performance measures. The results are general enough so that it includes Rayleigh fading and nonfading channel with zero and infinite Rician factor, respectively, as special cases. The effects of various channel models, processing gains, and diversity orders on the system performances are also considered for the typical multipath delay profiles characterized by Rician fading channel.