• Journal of Biomedical Engineering Research
• /
• v.20 no.4
• /
• pp.427-433
• /
• 1999

The purpose of the study is to develop an improved pitch extraction method that can be used in a variety of speech applications such as high-puality compression and vocoding, and recognition and synthesis of speech. To do so, we develop a new electroglottograph (EGG) measurement system that is based on the four modulation-demodulation type spot electrodes for detecting the EGG signals. Then, the glottal closure instant(GCI) is determined from the EGG signals on a real-time basis. We can obtain the pitch contour using the information on the GCI. It turns out that the new pitch contour algorithm (PCA) operates more reliably as compared to the conventional speech-only-based algorithm. In addition, we study the speech source models and glottal vibratory patterns for Koreans by measuring and analyzing the diversified vibration patterns of the vocal from the EGG signals.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.187-189
• /
• 2004

This paper presents the system widely used for extraction of human body recognition system in the field of bio-metric identification. The Human body recognition system is used in many fields. This biological is appled to the human recognition in banking and the access control with security. The important algorithm of the identification software usese hand lines and hand shape geometry. We used the simple algorithm and recognizing the person by their hand image from the input camera. The geometrical characteristics in hand shape such as length of finger to whole hand length thickness of finger to length, etc are used.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.04a
• /
• pp.100-105
• /
• 1998

지문 검증은 생체 측정학의 다양한 인증 시스템 중에서 기술의 적용 범위 및 사용의 편의성 등에서 가장 우수한 개인 인증 방법이다. 이러한 지문 인식 과정 중에서 Segmentation은 가장 기초적이지만 이후의 처리과정에 지대한 영향을 미칠 수 있는 과정이다. 특히 잡음이 많은 영상, 회전된 영상, 깨끗하지 못한 영상 등은 Segmentation 방법에 따라 원래의 영상이 훼손될 소지가 많다. 그래서 전자와 같은 지문의 경우, 한계 영역을 가변적으로 설정하여 전경 영상을 선택하는 것이 좋은 방법이다. 이 방법의 특징은 블록의 크기를 잘게 나누어 전경 후보자 영상 여러 개를 만들어서, 그 중에서 전경 영상 하나를 선택할 때, 가변적인 한계 영역을 설정하여, 가장 양호한 전경 영상을 선택할 수 있게 하는 것과, 필터링 적용을 통한 노이즈 제거 방법을 적용하는 것이다. 이 방법을 적용함으로써, 양호한 전경 영상을 선택할 수 있었고, 노이즈까지도 깨끗이 제거하여, 정확히 지문 부분만을 분할(Segmentation) 할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.1957-1960
• /
• 2003

최근 개인의 정보보호에 관한 관심이 높아져 가고 있으며 자신의 정보보호를 위해 스마트카드가 사용되어지고 있는 추세이다. 기존의 스마트카드는 카드 주체를 확인하는 과정으로 PIN(Personal Identity number) 제출을 요구한다. 본 논문에서 이러한 사용자의 확인 과정에 사용되는 PIN 대신 생체인식 중 서명을 스마트카드에 저장하였으며 이를 이용하여 사용자 인증을 위한 시스템에 대해 연구하였다. 본 논문은 스마트카드의 패스워드의 분실이나 강제에 의한 도용을 방지하고 사용자에 좀더 익숙하고 안전한 서비스를 보장 받게 될 것이다.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.263-271
• /
• 2008

This study is about the criminal information system of police cooperation organization between European nations. The criminal information system of police cooperation organization between European nations is the organization created by the sign of the Europol convention in 26 July 1995 and the effectuation in 1 October 1998 for European nations' cooperative confrontation with frequent international terror, international organization crime, drug trafficking, illegal immigrant smuggling, and other critical crimes. From the beginning, this organization established the criminal information system for overcoming the working limits of previous international police organization. This system consists of information system, work file, and index system and enables every national unit or other law enforcement agents to collect, exchange, and utilize the information. Additionally, it try to keep in step with the rapidly change time, such as the integration with CMS, the establishment of correspondence system against cyber crime, and the introduction of biometric database. The criminal information system of the Europol gives important suggestions to the police cooperation organization between nations, besides prevention and suppression against the international crimes in Europe.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.9
• /
• pp.363-370
• /
• 2022

Grasping a target object among clutter objects without collision requires machine intelligence. Machine intelligence includes environment recognition, target & obstacle recognition, collision-free path planning, and object grasping intelligence of robot hands. In this work, we implement such system in simulation and hardware to grasp a target object without collision. We use a RGB-D image sensor to recognize the environment and objects. Various path-finding algorithms been implemented and tested to find collision-free paths. Finally for an anthropomorphic robot hand, object grasping intelligence is learned through deep reinforcement learning. In our simulation environment, grasping a target out of five clutter objects, showed an average success rate of 78.8%and a collision rate of 34% without path planning. Whereas our system combined with path planning showed an average success rate of 94% and an average collision rate of 20%. In our hardware environment grasping a target out of three clutter objects showed an average success rate of 30% and a collision rate of 97% without path planning whereas our system combined with path planning showed an average success rate of 90% and an average collision rate of 23%. Our results show that grasping a target object in clutter is feasible with vision intelligence, path planning, and deep RL.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.10
• /
• pp.928-933
• /
• 2012

In this paper, the IR and compass sensors for the underwater system were used. The walls of the water tank have been recognized and avoided treating the walls as obstacles by the bio-mimetic underwater robot. This paper is consists of two parts: 1.The hardware part for the IR and compass sensors and 2.The software part for obstacle avoidance algorithm while the bio-mimetic robot is swimming with the obstacle recognition. Firstly, the hardware part controls through the RS-485 communications between a microcontroller and the bio-mimetic underwater robot. The software part is simulated for obstacle recognition and collision avoidance based upon the data from IR and compass sensors. Actually, the bio-mimetic underwater robot recognizes where is the obstacle as well as where is the bio-mimetic robot itself while it is moving in the water. While the underwater robot is moving at a constant speed recognizing the wall of water tank as an obstacle, an obstacle avoidance algorithm is applied for the wall following swimming based upon the IR and compass sensor data. As the results of this research, it is concluded that the bio-mimetic underwater robot can follow the wall of the water tank efficiently, while it is avoiding collision to the wall.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.275-276
• /
• 2016

In this paper, we were implemented the application to induce correct posture by recognizing the incorrect posture of the user. Implemented system uses kinect sensors to determine the user's position information, it has been developed posture determination algorithm that can determine the four wrong posture and correct posture. In addition to PC in order to improve the user convenience and accessibility, to implement real-time monitoring application that can determine the user's position in the smartphone. For the system of performance evaluation of and promote the attitude determination experiment to target the five college students, the experimental results sensitivity and specificity of it it was found that the attitude determination performance is excellent at 0.956.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.467-469
• /
• 2016

Car smart key system is a technology that allows you to turn activate / deactivate the auto lock through the contact form of electronic keys on the remote control and turn on the ignition by pressing the button. Smart key system is regarded as one of the essential options of the car as it is increasingly convenient to user, but there is no response yet for an attack to this situation. Therefore, in this paper, through an analysis of the amplification attack of a smart key we propose a way to stop the amplification attack and stop the car seized in case the car door opened due to the amplification attack.

• Journal of Korea Multimedia Society
• /
• v.15 no.6
• /
• pp.722-730
• /
• 2012

Recently, eye image information has been widely used for iris recognition or gaze detection in biometrics or human computer interaction. According as long distance camera-based system is increasing for user's convenience, the noises such as eyebrow, forehead and skin areas which can degrade the accuracy of eye detection are included in the captured image. And fast processing speed is also required in this system in addition to the high accuracy of eye detection. So, we compared the most widely used algorithms for eye detection such as AdaBoost eye detection algorithm, adaptive template matching+AdaBoost algorithm, CAMShift+AdaBoost algorithm and rapid eye detection method. And these methods were compared with images including light changes, naive eye and the cases wearing contact lens or eyeglasses in terms of accuracy and processing speed.