In this paper, we propose the self-autonomous algorithm for mobile robot system. The proposed mobile robot system controlled by Personal Digital Assistant(PDA) can follow the target at regular intervals. The mobile robot can evaluate the distance between robot and target with ultrasonic sensors, transmits the distance to the PDA. The velocity and direction decided in PDA are transmitted to the mobile robot with wireless LAN communication. Considering the state, velocity-changing and distance-maintenance, of the mobile robot, driving velocity and direction are applied. For safety, the velocity of the mobile robot is changed step by step. As a result, we confirm the ability of following the target with proposed mobile robot.

This paper proposes a dynamic moment algorithm to control oscillaion before the convergence of the KR(Kernel Relaxation). The proposed dynamic moment algorithm can be controlled to convergence speed and performance according to the change of the dynamic moment by teaming training. we used SONAR data that is a neural network classifier standard evaluation data in order to do impartial performance evaluation. The proposed algorithm has been applied to the KP (kernel perceptron), KPM(kernel perceptron with margin) and KLMS(kernel lms) as the kernel method presented recently. The simulation results of proposed algorithm have better the convergence performance than those using none and static moment.

This paper proposes a method to track hand gesture and to recognize the gesture pattern using Kalman filter and continuous dynamic programming (CDP). The positions of hands are predicted by Kalman filter, and corresponding pixels to the hands are extracted by skin color filter. The center of gravity of the hands is the same as the input pattern vector. The input gesture is then recognized by matching with the reference gesture patterns using CDP. From experimental results to recognize circle shape gesture and intention gestures such as “Come on” and “Bye-bye”, we show the proposed method is feasible to the hand gesture-based human -computer interaction.

This paper proposes a new 75 fuzzy model approximation method which reduces error in nonlinear fuzzy model approximation over the V-type decision rules. Employing rational Bezier curves used in computer graphics to represent curves or surfaces, the proposed method approximates the decision rule by constructing a tractable linear equation in the highly non-linear fuzzy rule interval. This algorithm is applied to the self-adjusting air cushion for spinal cord injury patients to automatically distribute the patient's weight evenly and balanced to prevent decubitus. The simulation results indicate that the performance of the proposed method is bettor than that of the conventional TS Fuzzy model in terms of error and stability.

We proposed the intelligent system to control prosthetic robot. The proposed intelligent system was used competitive network, SOFM and LVQ, and consisted of pre-processing part and associative part. A pre-processing part was processed EMG signal and associative part was outputted signal to control prosthetic robot. To verify the effectiveness, we adapted to 2 link manipulator for korean consonant.

This paper introduce a personalized facial expression recognition system. Many previous works on facial expression recognition system focus on the formal six universal facial expressions. However, it is very difficult to make such expressions for normal person without much effort and training. And in these days, the personalized service is also mainly focused by many researchers in various fields. Thus, we Propose a novel facial expression recognition system with fuzzy neural networks and robust image processing.

This paper suggest target detection algorithm for mobile robot control using color and shape recognition. In many cases, ultrasonic sensor(USS) is used in mobile robot system to measure the distance between obstacles. But with only USS, it may have many restrictions. So we attached CCD camera to mobile robot to overcome its restrictions. If visual information is given to robot system then robot system will be able to accomplish more complex mission successfully. With acquired vision data, robot looks for target by color and recognize its shape.

In this paper, we propose a control method of an unknown nonlinear system using a dynamical neural network. The method proposed in this paper performs for a nonlinear system with unknown system, identification with using the dynamical neural network, and then a nonlinear adaptive controller is designed with these identified informations. In order to verify the effectiveness of the proposed algorithm, we simulated one-link manipulator. The simulation result showed the effectiveness of using the dynamical neural network in the adaptive control of one-link manipulator.

Intelligent Wearable Module is intelligent system that arises when a human is part of the feedback loop of a computational process like a certain control system. Applied system is mobile robot. This paper represents the mobile robot control system remote controlled by Intelligent Wearable Module. So far, owing to the development of internet technologies, lots of remote control methods through internet have been proposed. To control a mobile robot through internet and guide it under unknown environment, We propose a control method activated by Intelligent Wearable Module. In a proposed system, PDA acts as a user interface to communicate with notebook as a controller of the mobile robot system using TCP/IP protocol, and the notebook controls the mobile robot system. Tlle information about the direction and velocity of the mobile robot feedbacks to the PDA and the PDA send new control method produced from the fuzzy inference engine.

This paper is about the Micro Accelerometer Sensor that collect the human's writing patterns so as to process its signals. Finally, we pursue the accuracy of digital data about the writing pattern and hope to discuss the possibility of the Micro Accelerometer Sensor Besides, we researched the compensation of signal distortion due to tiIt and analyzed the noise error in order to improve its accuracy.

In this paper, the efficient transmission technique of real time video data over 3G wireless networks is presented. To understand the transmission characteristic of 3G networks on real time video data, we implemented the data transport structure of 3G wireless networks. Also this research is based on current 3G wireless network specification of 3GPP, 3GPP2 standard organization to evaluate the result over real 3G wireless network environment. The retransmission by radio link layer results in the delay factor. To implement video data transmission efficiently, we Propose to use both no-retransmission and forward error correction method.

P2P implies direct exchange between peers. If you have something I want, 1 go directly to you and obtain il. There is one of the most advantages of formation of community in P2P. For a specified purpose through P2P, the Peers who make temporary a group delivery a request efficient and safe. And the resources can be jointed common, cooperation and communication. When P2P is developed more, we can expect more formation of online community and development. But to be a safe of personal ID and password in internet, it should be possible to make a key-exchange. In the paper, it suggest P2P security system suitable to personal security that Kerberos be transformed. The user who make community in P2P, have Kerberos Server, and using Physical Address of Ethernet card in personal computer, authenticate users.

Rapid Prototyping(RP) systems, that fabricate objects with slicers, typically bear staircase artifacts when slices has a certain degree of thickness. A tangential cutting algorithm is developed in order to remove surface distortion as well as to generate smooth laser-cutting trajectory. For this, an energy function is defined with tangential line length and distance between tangential line and middle contour. Then, the energy is minimized to generate effective tangential line segments. The proposed algorithm is tested and verified on 3D object samples and the results show that the generated tangential lines effectively approximate layer surface and make laser trajectory smooth.

Watershed Segmentation with Multiple Merging Conditions in Region Growing Process The watershed segmentation method holds the merits of edge-based and region-based methods together, but still shows some problems such as over segmentation and merging fault. We propose an algorithm which overcomes the problems of the watershed method and shows efficient performance for .general images, not for specific ones. The algorithm segments or merges regions by thresholding the depths of the catchment basins, the similarities and the sizes of the regions. The experimental results shows the reduction of the number of the segmented regions that are suitable to human visual system and consciousness.

In this paper, we consider the hamiltonian properties of m ${\times}$ n mesh networks with two wrap-around edges. We describe sufficient condition that at least two edges should be added to a mesh to make it hamiltonian-connected. We propose two graphs, M1(ｍ,n) and M2(ｍ,n). These are obtained by adding one and two edges respectively in the ｍ${\times}$ｎ mesh. We show the hamiltonian properties of M1(ｍ,n) and prove that M2(m, n) is hamiltonian-connected using the hamiltonian properties of M1(ｍ,n).

본 논문은 IIPv6 기반의 Mobile Ad-hoc Networks 환경에서 화상회의 도구 같은 멀티캐스트 응용을 서비스하는데 이용될 수 있는 IPv6 기반의 자동네트워킹 기술을 제시한다. IPv6 유니캐스트 자동설정 기능을 이용하여 이동단말의 유니캐스트 주소를 자동으로 설정할 수 있고, 멀티캐스트 자동설정 기능을 이용하여 멀티캐스트 주소 할당을 필요로 하는 응용에게 멀티캐스트 주소를 쉽게 할당할 수 있으므로 Mobile Ad-hoc Networks 환경에서의 사용자는 이러한 자동네트워킹 기술을 통해 멀티 캐스트 서비스를 쉽게 이용할 수 있다.

XML is widely used to provide information on the web. Since accessing XML documents depends on their structures, it is difficult to extract necessary information from documents having different structures. We constructed an ontology of a small application domain and implemented an universal DTD generator from the ontology. The universal DTD can be used in extracting necessary information from the various XML document types representing an identical idea.

In this paper, we present the design and implementation of a Fault Tolerant VOD system. The system uses the double striping policy that a original file is sequentially striped to multiple streaming server with constant data block size and the data block of one streaming server is re-striped to the other streaming server. When a fault occurs in one streaming server, automatically the other streaming server will service.

This paper intends to provide convenience to the disabled, losing the use of their limbs, through voice recognition technology. The voice recognition part of this system recognizes voice by DTW (Dynamic Time Warping) Which is most Widely used in Speaker dependent system. Specially, S/N rate was improved through Wiener filter in the pre-treatment phase while considering real environmental conditions; the result values of 12th order feature pattern per frame are extracted by DTW algorithm using LPC and Cepsturm in feature extraction process. Furthermore, miniaturization is pursued using TMS320C32, 71's the floating-point DSP, for the hardware part. Currently, 90% of hardware porting has been completed, but we can confirm that the recognition rate was 96% as a result of performing the DTW algorithm in PC.

This paper has been studied a new approach using neural network to detect false laser marks. In the proposed approach, input images are segmented into R, G and B colors and implements mask areas respectively. And then average and variation values of the each mask area are extracted for the learning process to minimize input nodes. Using this technique, the new input data is obtained and implemented to the back-propagation algorithm using multi layer perception. This paper reduces the computational complexity necessary and shows better effectiveness to inspect false laser marks.

본 논문은 세종계획의 일환으로 개발되었던 '남북한 언어 비교 사전 검색 시스템'을 개선한 것이다. '남북한 비교 사전 검색 프로그램'은 남북한의 언어 격차를 해소하고자 일반인에게 남북한의 언어정보를 검색할 수 있도록 개발된 시스템이다. 본 논문은 또한 일반인들이 남북한이 이질성을 가진 단어에 관심을 가지고 있는 점에 착안하여 이질성을 가진 단어를 검색할 수 있도록 별도로 '남북한 이질화된 언어 검색 시스템'을 개발하였다. '남북한 언어 비교 사전 검색 시스템'은 Microsoft Visual C++로 개발되었으며 Database는 Microsoft Access를 사용하였다.

한국 방언 검색 프로그램은 21세기 세종계획 프로젝트의 한민족 언어 정보화 분과에서 개발한 것으로 남한의 방언과 북한의 방언 및 해외 동포가 살고 있는 지역에서 사용되고 있는 한국어 방언을 컴퓨터로 검색 할 수 있도록 한 것이다. 한국 방언 검색 프로그램은 검색된 방언들의 정보를 HTML 문서로 화면에 표시할 수 있도록 되어 있으며, 방언의 각 지역별 사용 분포를 지도를 통해 확인할 수 있도록 되어 있다. 본 논문에서는 한국 방언 검색 프로그램의 기능과 방언 지도의 도시를 위한 지도 도시 알고리즘에 대해서 논한다.

K-means clustering algorithm is a very popular clustering technique, which is used in the field of information retrieval. In this paper, We deal with the problem of K-means Algorithm from the view of creating the centroids and suggest a method reflecting document feature and considering the context of each document to determine the new centroids during the process of forming new centroids. For experiment, We used the automatic document summarizer to summarize the Reuter21578 newslire test dataset and achieved 20% improved results to the recall metrics.

국어 어문 규정 검색 프로그램은 21세기 세종계획 프로젝트의 한민족 언어 정보화 분과에서 개발한 것으로, 한글 맞춤법, 표준어 규정, 외래어 표기법, 국어의 로마자 표기법 등의 어문 규정과 검색어에 대한 어문 규정 설명을 HTML 문서로 보여준다. 본 논문에서는 국어 어문 규정을 검색하기 위한 데이터베이스의 구조와 국민 어문 규정 검색 프로그램의 검색 방법에 대해서 논한다.

A grid computing environment is one in which applications can be built over multiple resource nodes at widespread geographic locations. Grid environments seek to integrate and enable access to widely distributed compute resources. The compute resources in a grid environment are typically heterogeneous, with varying qualify and availability Hence, how computations are allocated to individual resources is extremely important in the design of a grid. This paper j\ulcorners concerned with resource management for metacomputing. We describe a resource management architecture using the two-level resource broker.

This thesis introduces a buffer management method that could be used to provide better sound quality for Internet phone terminals. Proposed method used the fuzzy system for dynamically adjust the number of jitter This method actively responds to both the compression algorithms that are used by the terminals, as well as to the received data to provide an improvement in sound quality. In order to confirm the validity of the suggested algorithm, comparisons of the performance have been made between the existing buffer management method and this intelligent method in various network settings.

This paper designs Accounting structure for local users to policy base in Grid environment that integrate distributed Supercomputing resources geographically. Policy base virtual user Accounting system controls unnecessary increase of discrete Computing each local Accounting information. Also, This paper described method to manage do resources of each local system to policy base and presented way to process expense cost when used resources.

The paper proposed the intelligent inference method which keeps MV(Mobile vehicle) a little way off from men and makes it follow them using fuzzy controller Recognizing positions of MV and Men and distance between them was used to infer movement angle and speed of the MV with multi-ultrasonic sensor and USB camera The very important thing Is that the MV needs to obtain surrounding Information from the sensor and the camera, then It needs to represent those circumstances MV was controlled by inference from the speed and angle which are obtained from sensor and camera. Traveling simulation with a real MV was performed repeatedly to verify the usefulness of the fuzzy logic algorithm which was proposed in this paper. And a successful result of the experiment demonstrated the excellence of the fuzzy logic controller.

Recently. the effort to make a robot alike human is increasing. The robot helps house work or make a service in restaurant is not a dream. In this paper, we studied home robot serves a beverage. Each 4 beverage has different color. (And robot can serve a drink to master with its color.) It can be applicable to other works need to recognize target object with color. Perhaps, This looks simple but it's idea can be a basis for more complex work.

Human's brain action can divide by recognition and intelligence. recognition is sensing voice, image and smell and Intelligence is logical judgment, inference, decision. To this concept, Define function of cerebral cortex, and apply the result. Current expert system is lack, that reasoning by cerebral cortex and thalamus, hoppocampal and so on. In this paper, With human's brain action, wish to embody human's action artificially Embody brain mechanism using Modular Neural Network, Applied this result to snake robot.

As the increased use of computer, wired/wireless/mobile Internet, security in using Internet becomes a more important problem. Thus, biometric technology using physical and behavior characteristics of a person is hot issue. Many different types of biometric technologies of a person such as fingerprint, face, iris, vein, DNA, brain wave, palm, voice, dynamic signature, etc. had already been studied but remained unsuccessful because they do not meet social demands. However, recently many of these technologies have been actively revived and researchers have developed new products on various commercial fields. Dynamic signature verification technology is to verify the signer by calculating his writing manner, speed, angle, and the number of strokes, order, the down/up/movement of pen when the signer input his signature with an electronic pen for his authentication. Then signature verification system collects mentioned above various feature information and compares it with the original one and simultaneously analyzes to decide whether signature is forgery or true. The prospect of signature verification technology is very promising and its use will be wide spread in terms of economy, security, practicality, stability and convenience.

This paper addresses incremental learning method for regression. SVM(support vector machine) is a recently proposed learning method. In general training a support vector machine requires solving a QP (quadratic programing) problem. For very large dataset or incremental dataset, solving QP problems may be inconvenient. So this paper presents an incremental support vector learning method for function approximation problems.

The brain of the human is the best model for the artificial intelligence and is studied by many natural, medical scientists and engineers. In the engineering department, the brain model becomes a main subject in the area of development of a system that can represent and think like human. In this paper, we approach and define the function of the brain biologically and especially, make a model for the function of cerebral cortex, known as a part that performs behavior inference and decision for sensitive information from the thalamus. Therefore, we try to make a model for the transfer process of the brain. The brain takes the sensory information from sensory organ, proceeds behavior inference and decision and finally, commands behavior to the motor nerves. We use the modular neural network in this model. finally, we would like to design the intelligent system that can sense, recognize, think and decide like the brain by learning the information process in the brain with the modular neural network.

The aim of this work is the real-time road edge detection using the fast processing of Cellular Analogic Parallel Processing Networks(CAPPN). The CAPPN is composed of 2D analog cell way. If the dynamic programming is implemented with the CAPPN, the optimal path can be detected in parallel manner Provided that fragments of road edge are utilized as the cost inverse(benefit) in the CAPPN-based optimal path algorithm, the CAPPN determines the most plausible path as the road edge line. Benefits of the proposed algorithm are the fast processing and the utilization of optimal technique to determine the road edge lines.

최근 인터넷 사용자가 늘어나면서 클러스터링 기반의 대형 서버가 등장하게 되었고 또한 분산파일시스템(DFS)에 대한 관심이 커지게 되었다. 기존 분산파일 시스템들은 파일시스템 측면의 많은 기능들이 제공되고 뛰어난 성능을 발휘하지만 사용자 인터페이스 및 관리 측면에서 본다면 미흡한 점이 많다. 본 논문에서는 분산파일 시스템의 종류와 플랫폼에 상관없이, 사용하기 쉬운 DFS Management System을 설계하고 구축한다. 전체 시스템 구조를 파악 할 수 있도록 GUI 환경을 제공하며, 모듈화/계층화 구조로 설계하는데 기존 DFS와 연동하기 위한 하부 통신모듈이 포함된다. 본 논문에서는 Java기반으로 DFS Management System을 구축하였으며, Coda DFS가 설치된 클러스터링 서버와 연동하여 시험하였다.

As the use of world wide web is increasing, the number of connections to servers is increasing also. These interactions increase the load of networks and servers. therefore efficient caching strategies for web documents are needed to reduce server load and network traffics by migrating copies of server files closer to the clients that use those files. As One idea of caching policy, we propose a Weighted Disk Cache Replacement Policy(WDCRP) which analyses user's interaction to WWW and adds weight value to each web document. Especially the WDCRP takes account of the history data of cache log, the characteristics of Web requests and the importance of user interactive-actions.

최근에 인터넷 및 웹의 급속한 발전과 더불어 S/W 개발의 새로운 방법으로 컴포넌트가 대두되고 있다. 이는 빠른 시간 안에 원하는 소프트웨어 제품을 적은 비용과 최소한의 노력으로 생산할 수 있어 효율적인 시스템 개발 및 소프트웨어 재사용에 많은 이점을 가질 수 있다 그러나 현재 사용되고 있는 COM, CORBA등은 프로그램 작성뿐만 아니라, 분산 시스템 하의 서로 다른 플랫폼에서 운영상의 문제점들이 발생하게 되었다. 본 논문에서 제시한 EJB 방식의 아키텍쳐 시스템은 서로 다른 네트워크 환경과 이기종의 시스템에 존재하는 프로그램 객체들을 동일 시스템에서 사용하는 것처럼 통합을 가능하게 해주고 있다. 그리고 사례연구를 통하여 웹 컴포넌트의 모델분석과 설계를 하여 빈(Bean)을 생성하였으며, 결론으로 COM., CORBA Component(CCM), EJB기반 컴포넌트를 비교하였다.

The informal specification technique lacks abstraction and preciseness. On the other hand, the formal specification technique makes the developer difficult to express and understand the software specification, because it contains mathematical expression. This paper proposes DSC(Domain Specification Component) to solves these problems. DSC supports the understanding of problem domain and improves reusability with selecting the strong point of informal and formal specification technique. We applied the proposed DSC to CMIP-based network management manager software. And we analyzed the effects of the reusability and confirmed the increase of the reusability.

This paper has been designed and implemented of web security system using RF card A security mechanism that was proposed in this paper provides web services on card reader reads RF card of user only. In this paper, user authentication and server authentication was provided by challenge/response mechanism. Also, this system was provides confidentiality of communication messages.

In this paper, we consider the problem of embedding Fibonacci linear array, Fibonacci mesh, Fibonacci tree into Fibonacci circulants and between Fibonacci cubes and Fibonacci circulants. We show that the Fibonacci linear array of order n , Ln is a subgraph of the Fibonacci circulants of order n , En with En◎ Ln,n≥0 , the Fibonacci mesh of order (nt,n2), M(n,.nT)with S2n.1 f( M(n.れ)닌 M(n.1.n.1)), 52れ 늰( M(n.n.1)띤 M(H.n-1)) and the Fibonacci tree-lof order n, FT/sub n/ with ∑/sub n+3/⊇ FTn , n≥0, the Fibonacci tree-ll of order n , Tれ with ∑/sub n/⊇ Tn Fu퍼hermore, 낀e show that the Fibonacci cubes of order n , rn is subgraph of the Fibonacci circulants of order n , En and inversely rn can be embedded into En with expansion 1, dilation n -2 and congestion.

This paper describes an implementation of fast face detection algorithm. This algorithm can robustly detect human faces with unknown sizes and positions in complex backgrounds. This paper provides a powerful face detection algorithm using skin color segmenting. Skin Color is modeled by a Gaussian distribution in the HSI color space among different persons within the same race, Oriental. The main feature of the Algorithm is achieved face detection robust to illumination changes and a simple adaptive thresholding technique for skin color segmentation is employed to achieve robust face detection.

This paper introduces a new distributed QoS (Quality of Service) control system for clusters of web servers. The proposed system can employ not only network bandwidth but also other metrics such as processor load, memory usage, and storage access load that affect the overall system performance. Moreover, it controls over clustered\ulcorner workstations in of-der to utilize idle resources among workstations. This architecture maximizes overall usage of cluster of web servers while it provides predictable and differentiated performance for each contents volume. We implemented a prototype of introduced system, and the test results showed the proposed method can control QoS in a cluster server system.

This paper describes remote control RS232 communication using internet service, safety of exchange data and internet traffic by Denial of Service Attacks. In case of Denial of service Attacks, it makes connection of internet service failed. So in this Paper, this solution was examined and implemented for receiving data in safety against Denial of Service Attacks by LabVIEW program of National Instruments.

This paper proposes a efficient way to use Database that is constructed about attack-pattern. For IDS that activate confrontation, we reconstruct by Layered Attack Tree after constructing attack pattern by Attack Tree. And then this paper has designed IDS that Layered Attack Tree is applied, verified them.

This paper has been studied some security issues o( stream control transmission protocol and designed some functional requirement for IPsec and IKE to facilitate their use for securing SCTP. In particular, some additional support in the form of new ID type in IKE and some implementation choices in the IPsec processing to accomodate for the multiplicity of source and destination addresses associated with a single SCTP association.

Nowadays, many users use internet and many set-top box needs browser for Internet. so we need to develop a Java Virtual Machine to improve browser's performance. This paper has been studied a Java Virtual Machine based on Real-Time 05 Vxwroks. Java Virtual Machine handles Java byte-code quickly in Browser So, this paper has designed module and interfaces for Embedded Browser and Implemented them.

We described a real-time 3D computer vision system called MIMIC(Motion interface f Motion information Capture system) that can capture and save motion of an actor. This system analyzes input images from vision sensors and searches feature information like a head, hands, and feet. Moreover, this estimates intermediated joints as an elbow and hee using feature information and makes 3D human model having 20 joints. This virtual human model mimics the motion of an actor in real-time. Therefore this system can realize the movement of an actor unaffectedly because of making intermediated joint for complete human body contrary to other marker-free motion capture system.

We propose the new algorithm for scene segmentation. The proposed system consists motion estimation module and motion segmentation module. The former estimates 2D-motion value for each pixel position from two images transformed by wavelet. The latter determine scene segments well fitting on dominant affine motion models. What distinguishes proposed algorithm from other methods is that it needs not other post-processing for scene segmentation. We can manipulate both multimedia data and objects in virtual environment using proposed algorithm.

In this paper, content-based retrieval for region of interest(ROI) has been described, using maximum bin color. From a given query image, the object of interest is selected by a user. Using maximum bin color of the selected object, candidate regions are extracted from database images. The final regions of interest are determined by comparing the normalized histograms of the selected object and each candidate region.

Automatic video partitioning is the first step for content-based indexing and retrieval of video data. In this paper, an efficient algorithm for scene change detection is proposed, where cumulative histogram and edge information are utilized. Experimental results have shown the effectiveness of the proposed algorithm.

Gesture recognitions needed for various applications and is now gaining in importance as one method of enabling natural and intuitive human machine communication. In this paper, we propose a real time hand-signal recognition system in 3-dimensional space performs robust, real-time tracking under varying illumination. As compared with the existing method using classical pattern matching, this system is efficient with respect to speed and also presents more systematic way of defining hand-signals and developing a hand-signal recognition system. In order to verify the proposed method, we developed a virtual driving system operated by hand-signals.

In this paper, 3D image display system is constructed under PC environment and programed based on modular programming by using visual C)1. The hole procedures are composed of data preparation, 3D display over transformation and scaling.

If one can easily modify the existing motion data to a new motion in making an animation movie, he can save a lot of time for graphic design. To implement this kind of system, we propose a PC-based system composed of low cost commercial animation tool (3D Studio Max) for visualization of the animation and motion editing module that handles optimization process during the motion transform. Researchers studying advanced motion transform techniques only have to focus on the mathematical manipulation of the motion data

In this paper we concentrate on overall direction of the gaze based on a head pose for human computer interaction. To decide a gaze direction of user in a image, it is important to pick up facial feature exactly. For this, we binarize the input image and search two eyes and the mouth through the similarity of each block ( aspect ratio, size, and average gray value ) and geometric information of face at the binarized image. We create a imaginary plane on the line made by features of the real face and the pin hole of the camera to decide the head orientation. We call it the virtual facial plane. The position of a virtual facial plane is estimated through projected facial feature on the image plane. We find a gaze direction using the surface normal vector of the virtual facial plane. This study using popular PC camera will contribute practical usage of gaze tracking technology.

This paper proposes a new approach to extract contour of moving object from compressed video stream. We segment the area of moving object by using motion vector and extract the motion object block from it. And then we describe the connectivity direction of outline moving block, detect the edge related to connectivity direction in the block and finally obtain the contour by connecting the edges. This can divide the moving object only with motion vector and detect the exact contour on the basis of the edge automatically. Also, we can reduce spending time using motion block and remove the noise with directional edge. The experimental results demonstrate the accurate and effective qualify of the proposed method.

This paper presents a remote mobile robot system that transmits streaming video and audio over the lossy packet networks such as (Wireless) LAN. The error resilient video and audio packets are transmitted on the RTP/UDPfP Protocol stack. The mobile robot can be accessed by a certified user from the remoted area. Thus, the movement of mobile robot can be controlled by the operator observing the working surroundings.