• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.802-816
• /
• 2010

To create gesture from a new text input is an important problem in computer games and virtual reality. Recently, there is increasing interest in gesture stylization to imitate the gestures of celebrities, such as announcer. However, no attempt has been made so far to stylize a gestures using emotion such as happiness and sadness. Previous researches have not focused on real-time algorithm. In this paper, we present a system to automatically make gesture animation from SMS text and stylize the gesture from emotion. A key feature of this system is a real-time algorithm to combine gestures with emotion. Because the system's platform is a mobile phone, we distribute much works on the server and client. Therefore, the system guarantees real-time performance of 15 or more frames per second. At first, we extract words to express feelings and its corresponding gesture from Disney video and model the gesture statistically. And then, we introduce the theory of Laban Movement Analysis to combine gesture and emotion. In order to evaluate our system, we analyze user survey responses.

• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.191-197
• /
• 2010

Many does an application and application but the image analysis of face detection considerably is difficult. In order for with effect of the illumination which is irregular in the present paper America the illumination to range evenly in the face which is detected, detects a face territory, Complemented the result which detects only the front face of existing. With LAB color illumination revisions compared in Adaboost face detection of existing and 32% was visible the face detection result which improves. Bought two images which are input and executed Glassfire label rings. Compared Area critical price and became the area of above critical value and revised from RGB smooth anger and LAB images with LCFD system algorithm. The operational conversion image which is extracted like this executed a face territory detection in the object. In order to extract the feature which is necessary to a face detection used AdaBoost algorithms. The face territory remote login with the face territory which tilts in the present paper, until Multi-view face territory detections was possible. Also relationship without high detection rate seems in direction of illumination, With only the public PC application is possible was given proof user authentication field etc.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2441-2449
• /
• 2015

In this digital information era, utilization of images are essential for various media, and the edge is an important characteristical information of an object in images that includes the size, location, direction and etc. Many domestic and international studies are being conducted in order to detect these edge. Existing edge detection methods include Sobel, Prewitt, Roberts, Laplacian, LoG and etc. which apply fixed weight value. As these existing edge detection methods apply fixed weight mask to the image, edge detection characteristic appears slightly insufficient. Accordingly, in order to supplement these problems, this study used bottom-hat transformation from mathematical morphology and opening operation in improving the image and proposed an algorithm that detects for the edge after calculating mask-based gradient. And to evaluate the performance of the proposed algorithm, a comparison was made against the existing Sobel, Roberts, Prewitt, Laplacian, LoG edge detection methods, in illustrating visual images, and similarities were compared by calculating the MSE value based on the standard of each image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.4
• /
• pp.992-999
• /
• 2014

This paper presents an extensive experimental comparison of a variety of multi-label learning methods for the accurate prediction of subcellular localization of proteins which simultaneously exist at multiple subcellular locations. We compared several methods from three categories of multi-label classification algorithms: algorithm adaptation, problem transformation, and meta learning. Experimental results are analyzed using 12 multi-label evaluation measures to assess the behavior of the methods from a variety of view-points. We also use a new summarization measure to find the best performing method. Experimental results show that the best performing methods are power-set method pruning a infrequently occurring subsets of labels and classifier chains modeling relevant labels with an additional feature. futhermore, ensembles of many classifiers of these methods enhance the performance further. The recommendation from this study is that the correlation of subcellular locations is an effective clue for classification, this is because the subcellular locations of proteins performing certain biological function are not independent but correlated.

• Journal of Korea Water Resources Association
• /
• v.41 no.6
• /
• pp.605-617
• /
• 2008

This study developed a flood index which evaluates runoff characteristics. Runoff characteristics expressed in a hydrograph were reflected in the flood index in the form of characteristic factors such as a rising curve gradient, a peak discharge, a flood response time, and a flood discharge volume prior to peak. This study applied the standardization method to estimate the relative severity of the characteristic factors by transforming the distribution of characteristic factors into the standard normal distribution. The flood index developed in this study is a comprehensive flood index (CFI) which makes up for the weak points of a flash flood index (FFI) in determining relative severities. The CFI was applied to Han River basin and Selma River basin, and was compared with the FFI based on the correlation analysis and the regression analysis. The CFI could comprehensively evaluate flood runoff characteristics because the CFI is not dominated by a specific characteristic factor, and the CFI could explain more efficiently the relationship between rainfall and runoff than the FFI.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2014.02a
• /
• pp.457-457
• /
• 2014

오존발생방법은 다양한 방식으로 구현이 가능하나 대용량 장치를 만들기 위해서는 DBD (Dielectric barrier discharge) 구조의 형태의 가지고 있다. 이러한, DBD는 반도체의 MOS (Metal On Semiconductor)의 반대 구조를 가진 SOM (Semiconductor On Metal)의 형태를 가지고 있으며 대부분이 Oxidation 산화물을 가지고 구현한다. 오존발생기는 반도체 공정, 환경 및 정화 등 다양한 분야에 사용이 되고 있는 상황으로 성능개선을 위한 연구가 필요한 상황이다. 대표적으로 사용되는 물질인 $SiO_2$를 가지고 있는 상황이며 Silicon은 에너지 Bandgap이 1.1 eV로 금속위에 증착되어 통상적으로 사용되는 문턱전압은 0.7 V에 해당이 된다. 현재 점차적으로 연구가 진행되고 있는 $Al_2O_3$는 8.8 eV의 bandgap을 가지고 있으며 유전 상수가 9로 $SiO_2$인 3.9보다 높은 유전률 특징을 가지고 있다. 따라서, 본 연구는 오존 발생장치에 사용되는 방전관을 기존의 $SiO_2$에서 $Al_2O_3$ 방식으로 대체하므로써 실제적인 유전율의 값의 차이와 오존 발생시 오존변화율 증대에 관하여 연구하였다. $SiO_2$ 방전관은 Fe 메탈위에 약 3 mm정도의 두께를 binding시켜 N4L사의 PSM1700 모델 LCR meter를 사용하여 1.3 kHz시 7.2 pF의 유전율 확인 할 수 있으며 동일한 조건의 금속 메탈위에 $Al_2O_3$를 binding 시켜 측정한 결과 1.07 kHz시 10.7 pF의 유전율을 가지게 되어 40% 이상 높은 유전율을 가지게 되는 것을 확인 할 수 있다. 오존발생을 위하여 가변 주파수형 트랜스 드라이버를 통한 공진 주파수를 생성하여 방전 증폭을 위한 Amplifier를 통하여 변환률을 높이는 방식을 적용하여 MIDAC사의 I1801모델 적외선 분광기(FT-IR)를 통한 오존발생량을 측정하여 기존의 $SiO_2$의 방전관은 시간당 54 g의 오존 발생률 가지게 된다. $Al_2O_3$는 시간당 70 g 정도의 오존 발생률 가지므로 기존의 $SiO_2$ 보다 발생률 높은 것을 확인 할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.15-16
• /
• 2012

General lighting will be replaced into LED due to the high efficiency, low power consumption, long life than conventional light, moreover, since it is a basically semiconductor device that can convert the electric energy to visible light at a very high speed, using these characteristics can be performed communication modulation via the high-speed ON-OFF switching. Recently, visible light communication (VLC: Visible Light Communication) technology is received attention and there have been many researches. This paper is implemented media signal transmission by combining LED with VLC, a transmitter used the LED light-emitting device and receiver used an infrared sensor. In order to increase the efficiency of the communication system to improve the existing LED visible light communication driver of power conversion efficiency and thermal issues that is applied to the visible light communication in order to improve the speed of transmission media to research a new way of LED driver.

• The KIPS Transactions:PartD
• /
• v.12D no.4 s.100
• /
• pp.657-662
• /
• 2005

The Non-Sampling Error can happen any time by means of the intended or unintended error by the interviewer or respondent, but it is very difficult to find the error in survey database because it can hardly be computed mathematically and systematically. Until now, we have found it accidentally through the simple relation between the items or through the inspection from the random field. Therefore we introduced an heuristic methodology that can detect the interviewer's error by statistical decision-making or data mining techniques with a case study. It will be helpful so as to improve the statistical duality and provide efficient field management for the supervisor.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.2
• /
• pp.305-314
• /
• 2017

Recently, user authentication through biometric traits such as fingerprint and iris raise more and more attention especially in mobile commerce and fin-tech fields. In particular, commercialized authentication methods using fingerprint recognition are widely utilized mainly because customers are more adopted and used to fingerprint recognition applications. In the meantime, the security issues caused by fingerprint falsification bring lots of attention. In this paper, we propose a new method to improve the performance of fake fingerprint detection using CNN(Convolutional Neural Network). It is common practice to increase the amount of learning data by using affine transformation or horizontal reflection to improve the detection rate in CNN characteristics that are influenced by learning data. However, in this paper we propose an effective data augmentation method based on the database difficulty level. The experimental results confirm the validity of proposed method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.3
• /
• pp.563-568
• /
• 2007

We propose the computation reduction method of real root method that is used in the EVRC(Enhanced Variable Rate Codec) system. The real root method is that if polynomial equations have the real roots, we are able to find those and transform them into LSP. However, this method takes much time to compute, because the root searching is processed sequentially in frequency region. But, the important characteristic of LSP is that most of coefficients are occurred in specific frequency region. So, to reduce the computation time of real root, we used the met scale that is linear below 1kHz and logarithmic above. In order to compare real root method with proposed method, we measured the following two. First, we compared the position of transformed LSP(Line Spectrum Pairs) parameters in the proposed method with these of real root method. Second, we measured how long computation time is reduced. The experimental result is that the searching time was reduced by about 48% in average without the change of LSP parameters.