• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.175-182
• /
• 2004

There is a growing interest in speaker verification, which verifies someone by his/her voices. There are many speaker vitrification algorithms such as HMM and DTW. However, it is impossible to apply these algorithms to memory limited applications because of large number of feature vectors to register or verify users. In this paper we introduces a speaker verification system using SVM, which needs a little memory usage and computation time. Also we proposed hardware architecture for SVM. Experiments were conducted with Korean database which consists of four-digit strings. Although the error rate of SVM is slightly higher than that of HMM, SVM required much less computation time and small model size.

• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.200-207
• /
• 2009

U-Healthcare is more efficient as a solving method for health problems rather than visiting the hospital. Recently, systems have been studied to offer appropriate service to user, which gather and analyze biological signals of a user and context information around the user from a variety of sensors. The existing systems for U-Healthcare are based on domain specific service so it is difficult to expand and link to other systems. Also, they lack services focusing on the specific quality of the user, because they offer a general service which targets a lot of users. To address this problem, we expand an extensibility of system using the context-awareness agent based on multi-agents. Also, we provide the suitable services which match with the context information of user to each user using the modeling toolkit JaUCE based on GUI. We design and implement U-Silvercare service to demonstrate the effectiveness of the proposed context-awareness agent and modeling toolkit.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.681-687
• /
• 2007

Face recognition technique is very popular for a personal information security and user identification in recent years. However, the face recognition system is very hard to be implemented due to the difficulty where change in illumination, pose and facial expression. In this paper, we consider that an illumination change causing the variety of face appearance, virtual image data is generated and added to the D-LDA which was selected as the most suitable feature extractor. A less sensitive recognition system in illumination is represented in this paper. This way that consider nature of several illumination directions generate the virtual training image data that considered an illumination effect of the directions and the change of illumination density. As result of experiences, D-LDA has a less sensitive property in an illumination through ORL, Yale University and Pohang University face database.

• Korean Security Journal
• /
• no.19
• /
• pp.225-244
• /
• 2009

Electronic security system is composed mainly of electronic-information-communication device, so system technology, configuration and management of the electronic security system could be affected by the change of information-communication environment. This study is to propose the future prospect on the development of technique for electronic security system through the analysis of the trend and the actual condition on the development of technique. This study is based on literature study and interview with user and provider of electronic security system, also survey was carried out by system provider and members of security integration company to come up with more practical result. Hybrid DVR technology that has multi-function such as motion detection, target tracking and image identification is expected to be developed. And 'Embedded IP camera' technology that internet server and image identification software are built in. Those technologies could change the configuration and management of CCTV system. Fingerprint identification technology and face identification technology are continually developed to get more reliability, but continual development of surveillance and three-dimension identification technology for more efficient face identification system is needed. As radio identification and tracking function of RFID is appreciated as very useful for access control system, hardware and software of RFID technology is expected to be developed, but government's support for market revitalization is necessary. Behavior pattern identification sensor technology is expected to be developed and could replace passive infrared sensor that cause system error, giving security guard firm confidence for response. The principle of behavior pattern identification is similar to image identification, so those two technology could be integrated with tracking technology and radio identification technology of RFID for total monitoring system. For more efficient electronic security system, middle-ware's role is very important to integrate the technology of electronic security system, this could make possible of installing the integrated security system.

• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1226-1232
• /
• 2004

Biometric authentication is rising technology for the security market of the next generation. But most of biometric systems are developed using only one of various biological features. Recently, there is a vigorous research for the standardization of various biometric systems. In this paper, we propose a web-based authentication system using three other verifiers based on functional, parametric, and structural approaches for one biometrics of handwritten signature, which is conformable to a specification of BioAPI introduced by BioAPI Consortium for a standardization of biometric technology. This system is developed with a client-server structure, and clients and servers consist of three layers according to the BioAPI structure. The proposed neb-based multiple authentication system of one biometrics can be used to highly increase confidence degree of authentication without additional several biological measurements, although rejection rate is a little increased. That is, the false accept rate(FAR) decreases on the scale of about 1:40,000, although false reject rate(FRR) increases about 2.7 times in the case of combining above three signature verifiers. So the proposed approach can be used as an effective identification method on the internet of an open network. Also, it can be easily extended to a security system using multimodal biometrics.

• Journal of the korean Society of Automotive Engineers
• /
• v.18 no.6
• /
• pp.63-68
• /
• 1996

차량의 자동제어는 컴퓨터, 통신, 기계, 계측등의 하드웨어와 자동제어 기술, 통신망 운영, 컴퓨터 운영등의 소프트웨어 기술의 응용을 바탕으로 하는 지능형 차량은 단순히 차량 상호간, 차량과 도로에 설치된 컴퓨터와의 통신으 통한 정보교환 기능과 더불어 운전기능 자체를 스스로 행하는 기능을 포함하고 있다. 지능형 차량 개발은 운전자 인식증진 기술, 사고회피 기술, 피해확산 방지기술, ITS(Intelligent Transport System) 연계 및 관련 Infrastructure 기술, Human-Machine Interface 기술, Sensor Fusion 기술, 레이더 기술 등을 꼽을 수 있다. 이중에서 차량의 지능화를 구현하는 가장 핵심적인 세부 기술은 CCD 카메라, 레이저 레이더, 밀리파 레이더, 생체 센서등을 들 수 있다. 본 원고에서는 위와 같이 차량의 지능화, 특히 차량 거리검지 장치를 구현코자 사용되고 있는 센서의 종류와 응용에 대하여 고찰하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1079-1082
• /
• 2017

최근에 각종 생체전위를 활용한 연구가 활발히 이루어 지고 있다 학습효과를 위해서 집중력 향상에 대한 연구는 교육분야에서 중요한 과제이다. 따라서 뇌파(eletroencephalogram)를 활용한 집중력 향상에 필요한 소프트웨어적 연구는 가치가 있는 연구로서 판단할 수 있다. 따라서 금번 연구에서는 뇌파와 컴퓨터 간 신호처리에 중점을 두고 효율적으로 데이터 프로세스를 할 수 있는 게임이라는 매체를 활용한 학습효과 증진 프로그램을 개발하고자 한다. 금번 연구에서는 학습에 필요한 인터페이스 프로그램과 뇌파 수집에 필요한 뇌파수집기를 중점으로 개발하였다.

• Journal of Biomedical Engineering Research
• /
• v.24 no.5
• /
• pp.411-419
• /
• 2003

This paper aims at developing 'gyro-mouse' which provides decent and comfortable human-computer interface that supports the usage of such software as an internet-browser in PC for the people paralyzed in upper limbs. This interface operates on information collected from head movement to get the cursor control. The interface is composed of two modules. One is hardware module in which the head horizontal and vertical angular velocities are detected and transmitted into PC. The other is a PC software that translates the received data into movement and click signals of the mouse. The ANN (artificial neural network) learns the quick nodding pattern of each user as click input so that it can provide user-friendly interface. The performance of the system was evaluated by three indices that are click recognition rate. error in cursor position control. and click rate of the moving target box. The performance result of the gyro-mouse was compared with that of the optical-mouse to assess the efficiency of the gyro-mouse. The average click recognition rate was 93%, average error in cursor position control was 1.4∼5 times of optical mouse. and the click rate with 50 pixels target box was 40%(30 clicks/min) to that of optical mouse. The click rate increased monotonously with the number of trial from 35% to 44%. The suggested system is expected to provide a new possibility to communicate with the society.

• Journal of KIISE:Software and Applications
• /
• v.30 no.9
• /
• pp.876-884
• /
• 2003

It is essential to identify both the pupil and iris boundaries for iris recognition. The circular edge detector proposed by Daugman is the most common and powerful method for the iris region extraction. The method is accurate but requires lots of computational time since it is based on the exhaustive search. Some heuristic methods have been proposed to reduce the computational time, but they are not as accurate as that of Daugman. In this paper, we propose a pupil and iris boundary finding algorithm which is faster than and as accurate as that of Daugman. The proposed algorithm searches the boundaries using the Daugman's circular edge detector, but reduces the search region using the problem domain knowledge. In order to find the pupil boundary, the search region is restricted in the maximum and minimum bounding circles in which the pupil resides. The bounding circles are obtained from the binarized pupil image. Two iris boundary points are obtained from the horizontal line passing through the center of the pupil region obtained above. These initial boundary points, together with the pupil point comprise two bounding circles. The iris boundary is searched in this bounding circles. Experiments show that the proposed algorithm is faster than that of Daugman and more accurate than the conventional heuristic methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.9
• /
• pp.643-650
• /
• 2013

In this paper, we propose a novel method for enhancing the detection speed and rate by reducing the computation in Hough Circle Transform on real-time iris detection of smartphone camera image. First of all, we find a face and eyes from input image to detect iris and normalize the iris region into fixed size to prevent variation of size for iris region according to distance from camera lens. Moreover, we carry out histogram equalization to get regular image in bright and dark illumination from smartphone and calculate minimal iris range that contains iris with the distance between corner of the left eye and corner of the right eye on the image. Subsequently, we can minimize the computation of iris detection by applying Hough Circle Transform on the range including the iris only. The experiment is carried out in two case with bright and dark illumination. Our proposed method represents that detection speed is 40% faster and detection rate is 14% better than existing methods.