• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.491-500
• /
• 2002

In this paper, we propose a real-time face detection and recognition system by using skin color informations, geometrical feature vectors of face, and facial angle informations from color face image. The proposed algorithm improved face region extraction efficiency by using skin color informations on the HSI color coordinate and face edge information. And also, it improved face recognition efficiency by using geometrical feature vectors of face and facial angles from the extracted face region image. In the experiment, the proposed algorithm shows more improved recognition efficiency as well as face region extraction efficiency than conventional methods.

• ETRI Journal
• /
• v.35 no.6
• /
• pp.1038-1047
• /
• 2013

Augmented reality (AR) is currently being applied actively to commercial products, and various types of intelligent AR systems combining both the Global Positioning System and computer-vision technologies are being developed and commercialized. This paper suggests an in-vehicle head-up display (HUD) system that is combined with AR technology. The proposed system recognizes driving-safety information and offers it to the driver. Unlike existing HUD systems, the system displays information registered to the driver's view and is developed for the robust recognition of obstacles under bad weather conditions. The system is composed of four modules: a ground obstacle detection module, an object decision module, an object recognition module, and a display module. The recognition ratio of the driving-safety information obtained by the proposed AR-HUD system is about 73%, and the system has a recognition speed of about 15 fps for both vehicles and pedestrians.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.11
• /
• pp.1022-1032
• /
• 2000

We propose a sliding mode controller tracking the states of a time-varying reference model. The reference model generates the desired trajectories of the states, and the sliding mode controller regulates robustly the errors between the desired states and the measured states. We apply this controller to the overhead crane. Its reference model generates the trajectories of the damped-out swing angle and the swing angular velocity to suppress the swinging motion caused by the acceleration and the deceleration of crane transportation. Also, this model generates the desired trajectories of the position and velocity of the crane. The crane model is identified from the experimental data using an orthogonal function. Kalman filtering is applied to estimate the crane states. The designed controller is simulated on a computer and is tested through a 2-ton industrial overhead crane using the vector-controlled servo motor system. It is verified that, from the simulated and experimental results, the sliding mode controller tracking a time-varying reference model works well.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.4
• /
• pp.364-371
• /
• 2013

Emotion Recognition is one of the important part to develop in human-human and human computer interaction. In this paper, we have focused on the performance of multi-class SVM (Support Vector Machine) with Gaussian RFB (Radial Basis function) kernel, which has been used to solve the problem of emotion recognition from physiological signals and to improve the accuracy of emotion recognition. The experimental paradigm for data acquisition, visual-stimuli of IAPS (International Affective Picture System) are used to induce emotional states, such as fear, disgust, joy, and neutral for each subject. The raw signals of acquisited data are splitted in the trial from each session to pre-process the data. The mean value and standard deviation are employed to extract the data for feature extraction and preparing in the next step of classification. The experimental results are proving that the proposed approach of multi-class SVM with Gaussian RBF kernel with OVO (One-Versus-One) method provided the successful performance, accuracies of classification, which has been performed over these four emotions.

• Journal of the Korean Chemical Society
• /
• v.41 no.3
• /
• pp.123-129
• /
• 1997

In order to consider the reduced mass effects on the out-of-plane ring inversion vibration of 1,3-CHD, the vector-based computer program has been written and the kinetic energy expansion function for the large amplitude ring inversion vibration has been calculated using this program. The structural parameters for the calculations have been determined from the ab initio HF/6-31G** calculation. The potential energy function for the out-of-plane ring inversion vibration of 1,3-CHD has been determined from the kinetic energy expansion function and previously reported low-frequency Raman data. The vibrational Hamiltonian calculation including kinetic energy expansion function made it possible to determine the more reliable out-of-plane potential energy function for the ring inversion of 1,3-CHD.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.1
• /
• pp.83-89
• /
• 2000

Antenna arrays at base-stations can be used to transmit and receive information selectively in space by reducing the interference effects. In this paper, a new model of locally scattered signals in the vicinity of mobiles is proposed, and under this model the weights of the beamformer are obtained. Computer simulation results demonstrate that the proposed scheme shows an excellent performance and works well even in the urban environment where there exist many multipath propagations with wide angular spread.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.1057-1062
• /
• 2007

얼굴표정 인식은 심리학 연구, 얼굴 애니메이션 합성, 로봇공학, HCI(Human Computer Interaction) 등 다양한 분야에서 중요성이 증가하고 있다. 얼굴표정은 사람의 감정 표현, 관심의 정도와 같은 사회적 상호작용에 있어서 중요한 정보를 제공한다. 얼굴표정 인식은 크게 정지영상을 이용한 방법과 동영상을 이용한 방법으로 나눌 수 있다. 정지영상을 이용할 경우에는 처리량이 적어 속도가 빠르다는 장점이 있지만 얼굴의 변화가 클 경우 매칭, 정합에 의한 인식이 어렵다는 단점이 있다. 동영상을 이용한 얼굴표정 인식 방법은 신경망, Optical Flow, HMM(Hidden Markov Models) 등의 방법을 이용하여 사용자의 표정 변화를 연속적으로 처리할 수 있어 실시간으로 컴퓨터와의 상호작용에 유용하다. 그러나 정지영상에 비해 처리량이 많고 학습이나 데이터베이스 구축을 위한 많은 데이터가 필요하다는 단점이 있다. 본 논문에서 제안하는 실시간 얼굴표정 인식 시스템은 얼굴영역 검출, 얼굴 특징 검출, 얼굴표정 분류, 아바타 제어의 네 가지 과정으로 구성된다. 웹캠을 통하여 입력된 얼굴영상에 대하여 정확한 얼굴영역을 검출하기 위하여 히스토그램 평활화와 참조 화이트(Reference White) 기법을 적용, HT 컬러모델과 PCA(Principle Component Analysis) 변환을 이용하여 얼굴영역을 검출한다. 검출된 얼굴영역에서 얼굴의 기하학적 정보를 이용하여 얼굴의 특징요소의 후보영역을 결정하고 각 특징점들에 대한 템플릿 매칭과 에지를 검출하여 얼굴표정 인식에 필요한 특징을 추출한다. 각각의 검출된 특징점들에 대하여 Optical Flow알고리즘을 적용한 움직임 정보로부터 특징 벡터를 획득한다. 이렇게 획득한 특징 벡터를 SVM(Support Vector Machine)을 이용하여 얼굴표정을 분류하였으며 추출된 얼굴의 특징에 의하여 인식된 얼굴표정을 아바타로 표현하였다.

• Journal of Korea Game Society
• /
• v.19 no.6
• /
• pp.99-106
• /
• 2019

This paper addresses a method to compute the closest approach distance between two ellipsoids in their inter-center direction. This is the key technique for collision detection and response between ellipsoids. We formulate a set of conditions with the inter-center distance, the contact point and the contact normal vector of the two externally-contacting ellipsoids. The equations are solved robustly and efficiently using a hybrid of Newton's method and the bisection method with root bracketing. We demonstrate the robustness and efficiency of the proposed method in various experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.13 no.3
• /
• pp.204-215
• /
• 1988

This paper deals with the adaptive state estimation which is designed specially for a tracking system containing unknown and/or radomly varying hybride noises to provide an accurate estimate of the system state. The range of discrete vectyor v in finite numbers(N) for this adaptive estimator span the entire possible range of impulse noise levels such as the binomial, the edge, the Tchebyscheff, the binomal-edge and the Tchbyscheff-edge distribution. A feed forward path consisting of zero detector and data selector is incoporated with the conventional adaptive state estimator so as to provide accurate estimations. Despite the large and randomly varying hybrid noises, results of computer simulations for the various discrete vector levels show that this adptive state estimator is turned out to be a good system with relatively small implse errors.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.11
• /
• pp.1714-1725
• /
• 1993

This paper analyzes the properties of such algorithm that corresponds to the nonlinear adaptive algorithm with additional update terms, parameterized by the scalar factors a1, a2, a3 and Presents its structure. The analysis of convergence leads to eigenvalues of the transition matrix for the mean weight vector. Regions in which the algorithm becomes stable are demonstrated. The time constant is derived and the computational complexities of MLMS algorithms are compared with those of the conventional LMS, sign, LFG, and QFG algorithms. The properties of convergence in the mean square are analyzed and the expressions of the mean square recursion and the excess mean square error are derived. The necessary condition for the CFG algorithm to be stable is attained. In the computer simulation applied to the system identification the CFG algorithm has the more computation complexities but the faster convergence speed than LMS, LFG and QFG algorithms.