• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.163-172
• /
• 2005

When tracking a human face in the moving pictures with complex background under irregular lighting conditions, the detected face can be larger including background or smaller including only a part of the face. Even background can be detected as a face area. To solve these problems, this paper proposes a new face tracking method using a block difference image and a Kalman estimator. The block difference image allows us to detect even a small motion of a human and the face area is selected using the skin color inside the detected motion area. If the pixels with skin color inside the detected motion area, the boundary of the area is represented by a code sequence using the 8-neighbor window and the head area is detected analysing this code. The pixels in the head area is segmented by colors and the region most similar with the skin color is considered as a face area. The detected face area is represented by a rectangle including the area and its four vertices are used as the states of the Kalman estimator to trace the motion of the face area. It is proved by the experiments that the proposed method increases the accuracy of face detection and reduces the fare detection time significantly.

• 전기의세계
• /
• v.43 no.1
• /
• pp.13-19
• /
• 1994

전자식 안정기는 최근 에너지 절약 정책과 관련하여 조명기기분야의 관심의 대상이 되었고, 절전 효율이 높은 고품질의 전자식 안정기에 대한 연구 개발 및 보급이 점점 더 확대되고 있는 추세이다. 일반적으로 전자식 안정기는 수십 KHz의 고주파에서 형광등을 구동시킴으로써 빛의 깜박거림과 가청잡음이 없으며, 저주파(60Hz)에서 사용하는 재래식 안정기(choke coil 방식)에 비해 높은 절전 효과를 얻을 수 있다[1-4]. 특히, 빌딩 사무실의 경우 낮에도 창가의 형광등이 켜져 있어서 막대한 전력을 낭비하고 있는 실정이므로, 일조량에 따른 자동 전력 조절이 가능한 전자식 형광등의 출현이 기대되고 있다. 전자식 안정기의 보급 확대를 위해서는 절전 효과 뿐만 아니라, 품질 문제, 수명 문제등을 고려하여야 하는 바, 예를 들면 순간 점등으로 방전초기의 sputtering 현상에 의한 lamp의 수명 단축, 미소 입력전압 변동에 따른 급격한 광출력의 변화로 절전 효과의 상실과 이상동작에 의한 스위칭 소자의 파괴 현상, 고주파 스위칭시 발생되는 전력손실과 noise등에 대한 대책이 요구되고 있다. 이러한 점을 개선하기 위해 추가되는 회로는 전자식 안정기 시스템을 더욱 복잡하게 만들고, 경제적으로 원가 부담을 주기 때문ㅇ 고품질의 전자식 안정기를 보급하는데 어려운 점으로 부각되고 있다. 본 고에서는 이러한 문제를 해결하기 위하여 조광기능을 포함한 다양한 제어회로와 보호회로를 조광기능을 포함한 다양한 제어회로와 보호회로를 1 chip에 수용하는 고품질의 전자식 안정기 제어용 집적회로에 대해서 기술하고자 한다.되어 나아갈 기술의 조류에도 부합하는 형태라 하겠다. 그러나 이 방식은 기 언급한 바와 같이 분산처리를 관장하는 운영체계의 개발에 상당한 고전이 따르리라 보여지며, 또한 보다 상세한 연구가 선행되어야 하겠지만 개발된 상용의 통신 프로토콜로서는 병렬처리의 성능을 극대화 하기에는 여러가지 제약이 있을 것으로 예측된다.기기들이 어떻게 응용되고 있는지 살펴보기로 하자. real informations would be available. Results are compared with those of optimal power flows.기능시험을 완료했으며 실제 line-of-sight(LOS) 시스템 구현에 적용중이다. 시대를 살아 갈 회원들이다. '컨텐츠의 시대'가 개막되는 것이며, 신세기통신과 SK텔레콤은 선의의 경쟁 과 협력을 통해 이동인터넷 서비스의 컨텐츠를 개발해 나가게 될 것이다. 3배가 높았다. 효소 활성에 필수적인 물의 양에 따른 DIAION WA30의 라세미화 효율에 관하여 실험한 결과, 물의 양이 증가할수록 그 효율은 감소하였다. DIAION WA30을 라세미화 촉매로 사용하여 아이소옥탄 내에서 라세믹 나프록센 2,2,2-트리플로로에틸 씨오에스터의 효소적 DKR 반응을 수행해 보았다. 그 결과 DIAION WA30을 사용하지 않은 경우에 비해 반응 전환율과 생성물의 광학 순도는 급격히 향상되었다. 전통적 광학분할 반응의 최대 50%라는 전환율의 제한이 본 연구에서 찾은 DIAION WA30을 첨가함으로써 성공적으로 극복되었다. 또한 고체 염기촉매인 DIAION WA30의 사용은 라세미화 촉매의

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.2
• /
• pp.17-26
• /
• 2001

The Purpose of this study is to provide an effective way of developing GIS to UIS at the local level. For this purpose, the study typologically reviews the developing processes of UIS and utilizes a case study as research method. As the case, the study selects three types of UIS such as FM based UIS(Kwacheon), Urban Planning based UIS(Cheungju), and LIS based UIS(Taegu Nam-Gu). Based on these three UISs, the study concludes as follows. First, the developing process of GIS to UIS began with isolated approach through integrated model and finally to internet UIS. Second, UISs follows similar processes to that of GIS construction. Third, local governments focus on the development of FM based UIS of which construction budget is financed by the central government. Based on these findings, the study provides policy alternatives for the successful construction of UIS.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.2
• /
• pp.65-73
• /
• 2008

The characterization process for the accurate color reproduction in mobile phone with camera and LCD is popular. The camera and LCD characterization, gamut mapping process is necessary to map the camera's input color stimulus, CIEXYZ value, into the LCD's output color stimulus. Each characterization is the process estimating the relation between input and output signals. In case of LCD, because of output device, the output color stimulus for the arbitrary input signal can be measured by spectro-radiometer However, in the camera, as the input device, the characterization is an inaccurate and needs the manual works in the process obtaining the output signal because the input signal can not be generated. Moreover, after gamut mapping process, the noise is increased because the optimized gamma tone curve of camera for the noise is distorted by the characterization. Thus, this paper proposed the system of obtaining the output signal of camera and the method of gamma correction for the noise. The camera's output signal is obtained by RGB values of patches from captured the color chart image. However, besides the illumination, the error for the location of the chart in the viewfinder is generated when many camera modules are captured the chart. The method of correcting the position to correct the error from manual works. The position of camera is estimated by captured image. This process and moving of camera is accomplished repeatedly, and the optimized position can be obtained. Moreover, the lightness curve of camera output is corrected partly to reduce the noise from the characterization process.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.5
• /
• pp.423-431
• /
• 2016

In general LPR(License Plate Recognition) in outdoor image is not so simple differently from in the image captured from manmade environment, because of geometric shape distortion and large illumination changes. this paper proposes three techniques for LPR in outdoor images captured from CCTV. At first, a serially connected multi-stage Adaboost LP detector is proposed, in which different complementary features are used. In the proposed detector the performance is increased by the Haar-like Adaboost LP detector consecutively connected to the MB-LBP based one in serial manner. In addition the technique is proposed that makes image processing easy by the prior determination of LP type, after correction of geometric distortion of LP image. The technique is more efficient than the processing the whole LP image without knowledge of LP type in that we can take the appropriate color to gray conversion, accurate location for separation of text/numeric character sub-images, and proper parameter selection for image processing. In the proposed technique we use DBN(Deep Belief Network) to achieve a robust character recognition against stroke loss and geometric distortion like slant due to the incomplete image processing.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.15 no.1
• /
• pp.159-171
• /
• 2012

This study has developed a technology for river basin including the management of the data related with riverbed and the analysis of the riverbed maintenance based on the high-resolution imagery data and LiDAR (Light Detection and Raging) in order to enhance the utilization of river management by using RIMGIS(River Information Management GIS) and to acquire the advanced operation for river management. Using the detailed river topographical map specially designed in the form of LiDAR or high-resolution images, riverbed data and river bank channel information that are dynamically changed were informationized and established in the RIMGIS DB. At this stage, a monitoring techniques that is established in the river management system associated with RIMGIS and minimized the impact of riverbed maintenance (fluctuations) has been studied. In addition, functions and data structure of RIMGIS containing the information of geography and management of the river have been supplemented to make an improvement of the real-time management of the river. Furthermore, a technology that is capable of supplementing RIMGIS has been developed, making it feasible to maintain the river in use of structural method including an structural scheme of cross-section of the river by providing the information of riverbed and cross-section of the river. This is considered to solve an issue of insufficient data on accuracy and based on a lack of information of the river based on the two-dimensional lines, making it feasible to (steadily) improve the function of RIMGIS and to operate management tasks. Therefore, it is highly expected to enhance aforementioned technology of the river information management as a great foundation that maximizes the utilization of the river management to support RIMGIS for the development of national river management data.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.4
• /
• pp.189-203
• /
• 2013

The purpose of this study is to build a GIS database that can utilized to provide a multi-dimensional analysis of aquatic health ecosystem. Especially, it was to build a GIS database for comprehensive analysis using the aquatic ecosystem health. So we collected data on aquatic ecosystem health assessment, Korea Reach File(KRF), Stream Naturalness and Water Environmental Information System, and detailed analysis of the collected data was performed. In addition, the core objects were extracted from individual data and a related entity was derived by pulling out the items associated with thematic characteristics and classifying them. The establishment of GIS database makes it possible to support the decision making for the user to quickly understand the information of water environment. Therefore, the database will provide the information for the effective management on water environment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.3D
• /
• pp.433-439
• /
• 2011

The frost depth(frost penetration) is used to install anti-frost heave layers in pavement designs. The freezing index is calculated by an annual accumulated value of multiplying the period of time with temperatures below zero, and the corresponding temperature. Therefore, the DAAT(daily average air temperature) calculation method may play an effect on the FI(freezing index). The Weather Observatory used to supply 4 average air temperatures per day, but currently supplies 8 per day. With this study, we divided the southern part(below FI=$350^{\circ}C{\cdot}day$) of the Korean peninsula into 6 areas according to site conditions(low embankment, embankment-cutting slope, and the cutting slope) and established a field measurement system for 15 positions to check the effects on the result of FI according to differing DAAT calculation methods. The air temperatures obtained by the field measurement system was used to calculate and compare the FI. As a result, the freezing index calculated based on the $DAAT_4(T_4)$ is normally greater by 3% than the one on $DAAT_8(T_8)$. In addition, the calibration equation for the freezing index using air temperatures was proposed through the research.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.2
• /
• pp.319-333
• /
• 2017

The construction of long sub-sea tunnel does not provide the favorable condition for the installation of ventilation system to be used during construction due to the constrained construction space. For the ventilation system required during construction, the artificial island where ventilation shaft is located is constructed at some location along the sub-sea tunnel route, which requires a high construction cost. Therefore, it is intended, as much as possible technically, to minimize the construction of artificial island. However, this requires a longer distance between ventilation shafts, there-by causing increased air leakage at the ventilation duct connection points due to the higher fan pressure being required to deliver ventilation air. Previously the air leakage was studied as an important issue. In this study experiments were carried out to develop the improved duct connection method considering various conditions such as, tunnel length, etc. Additionally, its performance results with leakage rates are shown and compared to the "S" class leakage rate of SIA. As a result, the new duct coupling type of improved method is analyzed as applicable to such a 30 km long tunnel with the leakage rate of $1.46mm^2/m^2$, which is better performance than SIA leakage rates.