• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.5
• /
• pp.599-606
• /
• 2019

The Arena Fragmentation Test(AFT) is one of the important tasks for designing a high-explosive warhead. In order to measure the statistics of a warhead in the test, fragments of a warhead that penetrate steel plates are detected by using complex and expensive measuring equipment. In this paper, instead of using specific hardware to measure the statistics of a warhead, we propose to use an image processing based object detection algorithm to detect fragments in AFT. To this end, we use a hard-thresholding method with a brightness feature and apply a morphology filter to remove noise components. We also propose a simple yet effective temporal filtering method to detect only the first penetrating fragments. We show that the performance of the proposed method is comparable to that of a hardware system under the same experimental conditions. Furthermore, the proposed method can produce better results in terms of finding exact positions of fragments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.70-75
• /
• 2022

Accurately measuring location is necessary to provide a variety of services. The data for indoor positioning measures the RSSI values from the WiFi device through an application of a smartphone. The measured data becomes the raw data of machine learning. The feature data is the measured RSSI value, and the label is the name of the space for the measured position. For this purpose, the machine learning technique is to study a technique that predicts the exact location only with the WiFi signal by applying an efficient technique to classification. Ensemble is a technique for obtaining more accurate predictions through various models than one model, including backing and boosting. Among them, Boosting is a technique for adjusting the weight of a model through a modeling result based on sampled data, and there are various algorithms. This study uses Xgboost among the above techniques and evaluates performance with other ensemble techniques.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.59-66
• /
• 2016

This paper presents an empirical evaluation on dimensionality reduction strategies by which dissimilarity-based classifications (DBC) can be implemented efficiently. In DBC, classification is not based on feature measurements of individual objects (a set of attributes), but rather on a suitable dissimilarity measure among the individual objects (pair-wise object comparisons). One problem of DBC is the high dimensionality of the dissimilarity space when a lots of objects are treated. To address this issue, two kinds of solutions have been proposed in the literature: prototype selection (PS)-based methods and dimension reduction (DR)-based methods. In this paper, instead of utilizing the PS-based or DR-based methods, a way of performing DBC in Eigen spaces (ES) is considered and empirically compared. In ES-based DBC, classifications are performed as follows: first, a set of principal eigenvectors is extracted from the training data set using a principal component analysis; second, an Eigen space is expanded using a subset of the extracted and selected Eigen vectors; third, after measuring distances among the projected objects in the Eigen space using $l_p$-norms as the dissimilarity, classification is performed. The experimental results, which are obtained using the nearest neighbor rule with artificial and real-life benchmark data sets, demonstrate that when the dimensionality of the Eigen spaces has been selected appropriately, compared to the PS-based and DR-based methods, the performance of the ES-based DBC can be improved in terms of the classification accuracy.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.139-146
• /
• 2008

Masked fake face detection using ordinary visible images is a formidable task when the mask is accurately made with special makeup. Considering recent advances in special makeup technology, a reliable solution to detect masked fake faces is essential to the development of a complete face recognition system. This research proposes a method for masked fake face detection that exploits reflectance disparity due to object material and its surface color. First, we have shown that measuring of albedo can be simplified to radiance measurement when a practical face recognition system is deployed under the user-cooperative environment. This enables us to obtain albedo just by grey values in the image captured. Second, we have found that 850nm infrared light is effective to discriminate between facial skin and mask material using reflectance disparity. On the other hand, 650nm visible light is known to be suitable for distinguishing different facial skin colors between ethnic groups. We use a 2D vector consisting of radiance measurements under 850nm and 659nm illumination as a feature vector. Facial skin and mask material show linearly separable distributions in the feature space. By employing FIB, we have achieved 97.8% accuracy in fake face detection. Our method is applicable to faces of different skin colors, and can be easily implemented into commercial face recognition systems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.5
• /
• pp.909-916
• /
• 2009

This paper presents the automatic vision algorithm to generate and calibrate reference phase plane to improve the accuracy of 3D measuring machine of using phase shifting projection moire method, which is not traditional N-bucket method, but is based on direct image processing method to the pattern projection image. Generally, to acquire accurate reference phase plane, the calibration specimen with well treated surface is needed, and detailed calibration method should be performed. For the cost reduction of specimen manufacturing and the calibration time reduction, on the specimen, not specially designed, with general accuracy level, an efficient calibration procedure for the reference phase generation is proposed. The proposed vision algorithm is developed to extract the line center points of the projected line pattern from acquired images, derive the line feature information consisting of its slope and intercept by using sampled feature points, and finally generate the related reference phase between line pairs. Experimental results show that the proposed method make reference phase plane with a good accuracy under noisy environment and the proposed algorithm can reduce the total cost to make high accurate calibration specimen, also increase the accuracy of reference phase plane, and reduce the complex calibration procedure to move grid via N-bucket algorithm precisely.

• The Research Journal of the Costume Culture
• /
• v.18 no.4
• /
• pp.670-686
• /
• 2010

This study aims at clarifying the action types of skin management which is base on age, marriage or not, family composition, school career, and income which are demographic variables centering around the lifestyle of middleaged and old age women. As for study method, this researcher executed literature study and questionnaire on adult women over 45 years old who dwell in Seoul and Kyounggi area. Survey period was Mar. 1, 2009 to Jun. 30. And, after distributing 1,000 copies of questionnaire, this researcher used effective 869 copies of questionnaire for analysis out of collected questionnaire, 895 copies. As for analysis method, this researcher executed DUNCAN test with factor analysis, reliability analysis, manin component analysis, K-average, multitude analysis, dispersion analysis and post verification by using SPSS 12.0 program. As for demographic feature for middle aged and old age women, 50~59 years old women were most by age as 302 persons(33.7%). It is emerging that spouse existence is very high as 674 persons(75.3%) in the answer for marriage or not, couple family to live with unmarried children is very high as 483 persons(54.0%) in the answer for family composition, leaving high school in mid-course or gradation of high school are very high as 356 persons(39.8%) in the answer for school career, income from 3 million Won under 4 million won is very high as 260 persons(29.1%) in the answer for monthly income of family members, and women to use under 50 thousand won is very high as 510 persons(57.0%) in the monthly average expense to be used for skin management. In this study, this researcher extracted total 5 factors (economic saving, displaying consumption, confidence inclination, centering around family, and leisure application) by executing factor analysis with 12 question items of lifestyle so as to grasp factor structure of lifestyle of middleaged and old age people, and whole explanatory variable quantity was 70.9%. This researcher named as economic saving type, diplaying consumption style, and type centering around leisure and family, after making multitude analysis about 5 factors analyzed by measuring lifestyle feature. As the result of structure analysis of question items of skin management(pursuit of skin management, life of skin management, and inclination of skin management), this researcher extracted total 3 factors, and whole explanatory variable quantity was 71.30%. Thus, it emerged that there is significant difference among groups.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.41-43
• /
• 2022

In order to prevent and block infectious diseases caused by the recent COVID-19 pandemic, non-contact biometric information acquisition and analysis technology is attracting attention. The invasive and attached biometric information acquisition method accurately has the advantage of measuring biometric information, but has a risk of increasing contagious diseases due to the close contact. To solve these problems, the non-contact method of extracting biometric information such as human fingerprints, faces, iris, veins, voice, and signatures with automated devices is increasing in various industries as data processing speed increases and recognition accuracy increases. However, although the accuracy of the non-contact biometric data acquisition technology is improved, the non-contact method is greatly influenced by the surrounding environment of the object to be measured, which is resulting in distortion of measurement information and poor accuracy. In this paper, we propose a context-based bio-signal modeling technique for the interpretation of personalized information (image, signal, etc.) for bio-information analysis. Context-based biometric information modeling techniques present a model that considers contextual and user information in biometric information measurement in order to improve performance. The proposed model analyzes signal information based on the feature probability distribution through context-based signal analysis that can maximize the predicted value probability.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.19 no.2
• /
• pp.19-30
• /
• 2013

Purpose: The planning and design of hospital generally requires the participation and consultation of skilled experts since it has more complex space program than any other buildings. Therefore, the BIM systems for the planning of hospital have been tried continuously. The purpose of this study is to identify the precondition for space Program validation of healthcare architecture based on BIM, which is recently receiving wide attention. Method: For this study, United States, Australia and Finland's guidelines were analyzed among the description space program validation system in 14 overseas BIM Guidelines. And the propose precondition that can be applied to healthcare architecture from among these description of space program validation items, target, process etc for General building. Result: 1) spatial program validation is the following four evaluation phase. Step 1: Standard setting phase Step 2: BIM model accuracy assessment phase Step 3: space validation phase Step 4: Performance evaluation phase 2) The standards for the building elements at Standards Setting stage is considered to the standards for the architectural elements of General building. 3) Healthcare Architecture Area calculation method is considered to be reasonable that borrowing the area calculation standard of general architecture according to the UIA of international standards. However, Be proposed of measuring method that reflect the efficiency of the design process step-by-step area calculation method. The performance assessment indicators of reflect the Hospital uniqueness have to developed. And the research needs to be carried out continuously according to the purpose for healthcare architecture of feature-oriented. Implications: In this paper like to understanding that precondition of space program validation considering the BIM. As a result, understanding to condition about step of the evaluation, the evaluation standards. Is expected to keep the focus on the development of performance indicators that reflect the uniqueness of the hospital for the efficient evaluation of the Hospital building.

• Publications of The Korean Astronomical Society
• /
• v.27 no.4
• /
• pp.281-284
• /
• 2012

We utilize AKARI's slitless spectroscopic capability to detect the $3.3{\mu}m$ polycyclic aromatic hydrocarbons (PAHs) emission and measure star formation (SF) activity for various AKARI programs. First, we obtain $2{\sim}5{\mu}m$ spectra of 20 flux-limited galaxies with mixed SED classes in order to calibrate the $3.3{\mu}m$ PAH luminosity ($L_{PAH3.3}$) as a star formation rate (SFR) indicator. We find that $L_{PAH3.3}$ correlates with $L_{IR}$ as well as with the $6.2{\mu}m$ PAH luminosity ($L_{PAH6.2}$). The correlations does not depend on SED classes. We find that ULIRGs deviate from the correlation between PAH luminosities and $L_{IR}$, while they do not for the correlation between PAH luminosities. We suggest possible effects to cause this deviation. On the other hand, how AGN activity is linked to SB activity is one of the most intriguing questions. While it is suggested that AGN luminosity of quasars correlates with starburst (SB) luminosity, it is still unclear how AGN activity is connected to SF activity based on host galaxy properties. We are measuring SFRs for the LQSONG sample consisting of reverberation mapped AGNs and PG-QSOs. This is an extension of the ASCSG program by which we investigated the connection between SB and AGN activities for Seyferts type 1s at z ~ 0.36. While we found no strong correlation between $L_{PAH3.3}$ and AGN luminosity for these Seyferts 1s, $L_{PAH3.3}$ measured from the central part of galaxies correlates with AGN luminosity, implying that SB and AGN activities are directly connected in the nuclear region.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.145-151
• /
• 2012

The pulsimeter is a representative device in the oriental medicine, which can analysis a risk factor in a cardiovascular diseases. However, most of the previous methods have the limit by the contacted sate of the brachial pulse and sensor in the measuring time, the inaccuracy of detected pulse, and the difficulty of pulse analysis. Accordingly, we propose the moving pulse image analysis based pulsimeter that can acquire a pulse of patient in real time by analyzing a moving image. then this video is shot the state change of the T.S. occurred by a pulse in capillary. In order to evaluate the performance of the our pulsimeter, we measured a respective detecting-rate about the essential 5 feature-points in the pulse analysis from the detected original pulse. As a result, the proposed method is very successful.