• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.1149-1152
• /
• 2005

Detecting faces in images with complex backgrounds is a difficult task. Our approach, which obtains state of the art results, is based on a generative neural network model: the Constrained Generative Model (CGM). To detect side view faces and to decrease the number of false alarms, a conditional mixture of networks is used. To decrease the computational time cost, a fast search algorithm is proposed. The level of performance reached, in terms of detection accuracy and processing time, allows to apply this detector to a real word application: the indexation of face images on the Web.

• Journal of Life Science
• /
• v.21 no.7
• /
• pp.947-952
• /
• 2011

A number of epidemiological studies have identified human papillomavirus (HPV) types 1, 2, 3, 4, 7, 10, 27, 57, and 65 in cutaneous common warts. However, identification of the HPV subtype by conventional polymerase chain reaction (PCR) is time consuming with its multi-step laboratory process. In this study, we aim to develop a specific one-step multiplex polymerase chain reaction method which capably identifies six different HPV genotypes related to common warts. By HPV DNA sequence analysis, 6 pairs of specific primers were designed from the intergenic regions of genes L1 to E6, and from genes E2 to L2. DNA sequence analysis with the L1 gene sequence of the sample was performed to measure the specificity of multiplex PCR. HPV-1, -2, -3, -4, -27, and -57 were identified without cross amplification in 109 out of 129 samples. The sensitivity and specificity of our set of primers in detecting HPV were 85% and 99.5%, respectively. For the 20 samples where HPV type was not identifiable by our batch of primer sets, multiplex PCR with an additional set of HPV primers was done, where 7 were found positive for HPV-7 or -65. Our results demonstrate that the newly designed multiplex PCR can rapidly detect the specific HPV subtype involved in common warts with high accuracy.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.1
• /
• pp.49-59
• /
• 2011

Recently, ToA and TDoA estimation are favorable among all of estimation techniques because they have the best accuracy in estimating position. ToA and TDoA estimation are typical techniques based on time. So, it is important to have the time syncronization and offset between a target node and several reference nodes. If they don't have the time syncronization between a reference node and target node or have a time offset among reference nodes, the positioning error will increase due to the ranging error. The conventional positioning algorithm does not have a accurate device's position because ranging error is added the calc dation of the position. In this paper, we propose a hybrid method of ToA and TDoA ll increase due. We use MHP pulse that has orthogonal pulse instead of the existing pulse to transmit and receive pulses between a target node and reference nodes. We can estimate the target node's position by ToA and TDoA estimation to transmit and receive MHP pulses only once. When the proposed Hybrid method iteratively calculate the distance, we can select the ranging technique to have more accurate position. The simulation results confirm the enhancement of the Hybrid method.

• The KIPS Transactions:PartD
• /
• v.10D no.5
• /
• pp.837-844
• /
• 2003

The software reliability have to be improved as one major method to enhance the quality of developed software, and its defect is detected and modified through testing as a direct way to meet the purpose before releasing. Once its reliability grows up to the target and it is released to public. there nay be operational reliability problem. The operational software reliability trend nay be different depending on the condition whether it is universal or dedicated. And its reliability estimation is changed based on the condition if it follows uniform testing efforts or Weibull testing efforts. I study the operational reliability trend of dedicated software, applying two case testing efforts for the released item.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.1
• /
• pp.78-87
• /
• 1989

In this paper, a spatio-temporal gradient (STG) method with generalized least square estimation (GLSE) is proposed for the detection of an object motion in an image sequence corrupted by white Gaussian noise. The proposed method is applied to an automatic target tracker using a high speed 16-bit microprocessor in order to track one moving target in real time. Experimental results show that the proposed method has much better performance over the conventional one with least square estimation (LSE).

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.589-596
• /
• 2013

With the increase of social crime rate, the interest on the intelligent security system is also growing. This paper proposes a detection system of monitoring whether abnormal behavior is being carried in the images captured using CCTV. After detection of an object via subtraction from background image and morpholgy, this system extracts an abnormal behavior by each object's feature information and its trajectory. When an object is loitering for a while in CCTV images, this system considers the loitering as an abnormal behavior and sends the alarm signal to the control center to facilitate prevention in advance. Especially, this research aims at detecting a loitoring act among various abnormal behaviors and also extends to the detection whether an incoming object is identical to one of inactive objects out of image.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.12
• /
• pp.1775-1784
• /
• 2002

Fingerprint recognition technology is used in many biometrics field accordingly essential feature of fingerprint image and the study is progressing. However development is not perfect in performance of the fingerprint recognition and application of the usual life. In the paper, we study various necessity of preprocessing according to algorithm and circumstances of authentication system in automatic information machine. We prove that system circumstance and optation of fingerprints image effectively is the important factor by using optical fingerprint input device and scanning the fingerprint in ID card. And then we present correct and fast computation method for improving image and feature extraction of fingerprint. Also we study effective algorithm implementation of total system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.182-183
• /
• 2018

Most of the photographs or images of the present age have pixels of various colors that can not be recognized by human eyes. For a specific purpose, pixel-based image processing is inevitable rather than passive investigation using the human eye in order to find areas of color similar to the target color. In this paper, we try to detect all the pixels of the same color or the same color in the image. We will also try to find pixels within the error range that are similar in color to the color we are looking for.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.12
• /
• pp.1009-1018
• /
• 2003

In a park or street, we can see many people Jogging or walking with their dogs chasing their masters. In the previous study, an entertainment robot, CARTRI that imitates the dog's behavior was created. The robot's task was chasing a moving goal that was recognized as the master. The physical structure of the CARTRI robot was three-wheel type locomotion system. The sensor system which could detect the position of the master in the outdoor space, was consists of a signal transmitter which was held by the master and five ultrasonic receivers which were mounted on the robot. In the experiment, the robot could chase a human walking in outdoor space like a park. But it could not avoid obstacles and its behavior was only goal-chasing behavior because of the limit of the sensor system. In this study, an improved RF-ultrasonic sensor system which can detect both goal and obstacle is developed in order to enable the CARTRI robot to carry out various behavior. The sensor system has increased angle resolution by using eight ultrasonic receivers instead of five in the previous study. And it can detect obstacle by using reflective type ultrasonic sensors. The sensor system is designed so that detection of goal and obstacle could be conducted in one sampling period. The Performance of the developed sensor system is evaluated through experiments.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.2
• /
• pp.222.1-222.1
• /
• 2012

JEM-EUSO (Extreme Universe Space Observatory on-board the Japanese Experiment Module)는 국제우주정거장(International Space Station)의 일본 실험 모듈인 'KIBO'에 우주 망원경을 설치하여, 100 EeV이상의 초고에너지 우주선 관측을 수행함으로써, 초고에너지의 스펙트럼, 구성성분과 기원을 연구하는 국제공동연구 프로젝트이다. 구경 2.5 m로 60도의 광시야각을 가지는 대형 굴절 망원경을 통해서, 지구 대기에 우주선 shower로부터 발생한 형광 신호를 관측하려고 한다. 이 프로젝트는 2016~2017년에 발사되어, 5년 이상의 임무 수행을 목표로 하고 있으며, 그 전단계로 Prototype 시스템을 가지고 지상실험인 EUSO-TA와 고도 40 km에서 수행할 EUSO-Balloon실험을 준비하고 있다. 먼저, 망원경의 prototype을 2012년 12월쯤 미국 유타에 있는 Telescope Array(TA) 실험에 설치하여 우주선 또는 임의로 인가한 광원에 의해서 생성된 shower를 TA의 Fluorescence Detector와 함께 측정하여, 시스템 calibration과 더불어 지상에 검출된 우주선을 연구할 계획이다. 그 이듬해인 2013년 여름에는 Balloon에 망원경의 Engineering model을 실어서, 대기고도 40 km아래에서 우주선에 의해 생성되는 shower를 개발한 트리거 시스템을 통해서 검출하고, 대기권에 존재하는 UV background 광원들을 측정하여 우주선을 연구할 예정이다. 한국 그룹은 JEM-EUSO을 위해서 개발한 디지털 신호처리 및 트리거 장치의 제작 중에 있으며, 위의 실험들을 위해 망원경과 함께 조립하여 테스트를 수행할 계획이다.