• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.719-725
• /
• 2007

In this paper, we present an audio-visual speech recognition system for noise-robust human-computer interaction. Unlike usual speech recognition systems, our system utilizes the visual signal containing speakers' lip movements along with the acoustic signal to obtain robust speech recognition performance against environmental noise. The procedures of acoustic speech processing, visual speech processing, and audio-visual integration are described in detail. Experimental results demonstrate the constructed system significantly enhances the recognition performance in noisy circumstances compared to acoustic-only recognition by using the complementary nature of the two signals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.503-506
• /
• 2008

The integral imaging is a promising 3D display technology since it is able to deliver continuous viewing points, full parallax, and full color view to the observers in space. In this paper, we propose a novel interactive 3D integral imaging system using a single camera. The user interface is implemented by adding a camera in the conventional integral imaging system. To show the possibility of the proposed system, we implement the optical setup and present the preliminary results

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.379-384
• /
• 2021

With people's continuous research and exploration in the field of artificial intelligence, more relatively mature artificial intelligence technology is applied in people's daily life. Mirrors are the most commonly used daily necessities in life, and it should be applied to artificial intelligence. The research results of this paper show that the smart mirror designed based on the raspberry pi displays weather, temperature, greetings, and has a human-mirror interaction function. The research method of this paper uses the Raspberry pi 3B + as the core controller and Google Assistant as the intelligent control. When connected to the network via Raspberry Pi's own WiFi, the mirror can automatically display and update time, weather and news information features. You can wake up the Google Assistant using keywords, then control the mirror to play music, remind the time, It implements the function of smart mirror voice interaction. Also, all the hardware used in this study is modular assembly. Later, it is convenient for user to assemble by himself later. It is suitable for market promotion at an affordable price.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2585-2598
• /
• 2015

Hand posture recognition has played a very important role in Human Computer Interaction (HCI) and Computer Vision (CV) for many years. The challenge arises mainly due to self-occlusions caused by the limited view of the camera. In this paper, a robust hand posture recognition approach based on 3D point cloud from two RGB-D sensors (Kinect) is proposed to make maximum use of 3D information from depth map. Through noise reduction and registering two point sets obtained satisfactory from two views as we designed, a multi-viewed hand posture point cloud with most 3D information can be acquired. Moreover, we utilize the accurate reconstruction and classify each point cloud by directly matching the normalized point set with the templates of different classes from dataset, which can reduce the training time and calculation. Experimental results based on posture dataset captured by Kinect sensors (from digit 1 to 10) demonstrate the effectiveness of the proposed method.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.251-258
• /
• 2011

Applying face alignment after face detection exerts a heavy influence on face recognition. Many researchers have recently investigated face alignment using databases collected from images taken at close distances and with low magnification. However, in the cases of home-service robots, captured images generally are of low resolution and low quality. Therefore, previous face alignment research, such as eye detection, is not appropriate for robot environments. The main purpose of this paper is to provide a new and effective approach in the alignment of small and blurred faces. We propose a face alignment method using the confidence value of Real-AdaBoost with a modified census transform feature. We also evaluate the face recognition system to compare the proposed face alignment module with those of other systems. Experimental results show that the proposed method has a high recognition rate, higher than face alignment methods using a manually-marked eye position.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.3
• /
• pp.98-105
• /
• 2009

It is important for firms to help customers find the products or information they need in order to increase sales and promote return visits to their websites. Hence, the presentation of product information is very important in e-commerce websites. In this research, we study how disposition styles can influence browsing patterns. The test results show that people are inclined to use feature information paths in the vertical disposition style and product information paths in the horizontal disposition style. With vertical disposition, users are more likely to follow feature information paths which may help them focus on comparisons across products.

• 한국정보교육학회:학술대회논문집
• /
• 2011.01a
• /
• pp.1-5
• /
• 2011

A change toward a digital society is requiring of the human quotient who had new informatization ability, and is large to education is affecting it. The digital Storytelling which effective anger to be educational of traditional Storytelling was combined with came into being in these changes. As I provide together multi-media element such as a screen and sound digital Storytelling jumps over the existing Storytelling, and to move, I easily cause an interest of student, and I stimulate intellectual faculties various of a schoolchild, and I make bidirectional enemy interaction possible. Therefore, I extract whether it is the education that it can apply on-site an elementary school of a cow in this study after analyzing digital Storytelling, and digital Storytelling designs the class that it is possible, and I will present it.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.3
• /
• pp.535-540
• /
• 2007

The hand recognition technique is widely used to the economic input method for user interfacing environment. However, the most of the techniques have the restricted with recognize that only a fixed background and a regular pattern. This restriction character has brought a difficult problem to apply at variable application class and to process restriction environment. In this paper, we propose a virtual input system that extracting about hand region information that is not restricted by background image and also that can be followed the location information. This research could be used some system demanded by input of a person such as control system at airport and pavilion and economic virtual input system in class of industrial computer and various kinds control-system.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.263-271
• /
• 2008

This paper presents a Korean conversational agent system in a mobile environment using natural language processing techniques. The aim of a conversational agent in mobile environment is to provide natural language interface and enable more natural interaction between a human and an agent. Constructing such an agent, it is required to develop various natural language understanding components and effective utterance generation methods. To understand spoken style utterance, we perform morphosyntactic analysis, shallow semantic analysis including modality classification and predicate argument structure analysis, and to generate a system utterance, we perform example based search which considers lexical similarity, syntactic similarity and semantic similarity.

• Journal of Biomedical Engineering Research
• /
• v.13 no.3
• /
• pp.181-188
• /
• 1992

This paper provides an overview of system analysis of immunology. The theoretical research in this area is aimed at an understanding of the precise manner by which the immune system controls Infec pious diseases, cancer, and AIDS. This can provide a systematic plan for immunological experimentation by means of an integrated program of immune system analysis, mathematical modeling and computer simulation. Biochemical reactions and cellular fission are naturally modeled as nonlinear dynamical processes to synthesize the human immune system! as well as the complete organism it is intended to protect. A foundation for the control of tumors is presented, based upon the formulation of a realistic, knowledge based mathematical model of the interaction between tumor cells and the immune system. Ordinary bilinear differential equations which are coupled by such nonlinear term as saturation are derived from the basic physical phenomena of cellular and molecular conservation. The parametric control variables relevant to the latest experimental data are also considered. The model consists of 12 states, each composed of first-order, nonlinear differential equations based on cellular kinetics and each of which can be modeled bilinearly. Finally, tumor control as an application of immunotherapy is analyzed from the basis established.