• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.93-100
• /
• 2009

In this paper, we propose a Difference Image Entropy based gaze direction recognition system. The Difference Image Entropy is computed by histogram levels using the acquired difference image of current image and reference images or average images that have peak positions from $-255{\sim}+255$ to prevent information omission. There are two methods about the Difference Image Entropy based gaze direction. 1) The first method is to compute the Difference Image Entropy between an input image and average images of 45 images in each location of gaze, and to recognize the directions of user's gaze. 2) The second method is to compute the Difference Image Entropy between an input image and each 45 reference images, and to recognize the directions of user's gaze. The reference image is created by average image of 45 images in each location of gaze after receiving images of 4 directions. In order to evaluate the performance of the proposed system, we conduct comparison experiment with PCA based gaze direction system. The directions of recognition left-top, right-top, left-bottom, right-bottom, and we make an experiment on that, as changing the part of recognition about 45 reference images or average image. The experimental result shows that the recognition rate of Difference Image Entropy is 97.00% and PCA is 95.50%, so the recognition rate of Difference Image Entropy based system is 1.50% higher than PCA based system.

• Journal of Advanced Marine Engineering and Technology
• /
• v.32 no.5
• /
• pp.768-774
• /
• 2008

In many areas of speech signal processing such as automatic speech recognition and packet based voice communication technique, VAD (voice activity detection) plays an important role in the performance of the overall system. In this paper, we present a new feature parameter for VAD which is the product of energy of the signal and the difference of two types of entropies. For this end, we first define a Mel filter-bank based entropy and calculate its difference from the conventional entropy in frequency domain. The difference is then multiplied by the spectral energy of the signal to yield the final feature parameter which we call PEED (product of energy and entropy difference). Through experiments. we could verify that the proposed VAD parameter is more efficient than the conventional spectral entropy based parameter in various SNRs and noisy environments.

• Journal of the Korean Magnetics Society
• /
• v.10 no.4
• /
• pp.149-153
• /
• 2000

Large magnetic entropy change in single crystalline and polycrystalline perovskite manganites La$_{0.7}$Ca$_{0.3}$MnO$_3$ has been observed as magnetic field is changed. The large magnetic entropy change is believed to be caused by the abrupt reduction in magnetization as a result of 1st order-like magnetic transition. The large magnetic entropy change and easiness of the Curie temperature manipulation in the temperature range 100 K

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.10 no.4
• /
• pp.204-210
• /
• 1998

This paper presents the development of the probability density function applicable for wave heights (peak-to-trough excursions) in finite water depth including shallow water depth. The probability distribution applicable to wave heights of a non-Gaussian random process is derived based on the concept of the maximum entropy method. When wave heights are limited by breaking wave heights (or water depth) and only first and second moments of wave heights are given, the probability density function developed is closed form and expressed in terms of wave parameters such as $H_m$(mean wave height), $H_{rms}$(root-mean-square wave height), $H_b$(breaking wave height). When higher than third moment of wave heights are given, it is necessary to solve the system of nonlinear integral equations numerically using Newton-Raphson method to obtain the parameters of probability density function which is maximizing the entropy function. The probability density function thusly derived agrees very well with the histogram of wave heights in finite water depth obtained during storm. The probability density function of wave heights developed using maximum entropy method appears to be useful in estimating extreme values and statistical properties of wave heights for the design of coastal structures.

• Korean Chemical Engineering Research
• /
• v.46 no.1
• /
• pp.56-62
• /
• 2008

Characteristics of heat transfer were investigated in a three-phase swirling fluidized bed whose diameter was 0.102 m and 2.5 m in height. Effects of gas and liquid velocities, particle size and liquid swirling ratio ($R_S$) on the immersed heater-to-bed overall heat transfer coefficient were examined. The heat transfer characteristics between the immersed heater and the bed was well analyzed by means of phase space portraits and Kolmogorov entropy(K) of the time series of temperature difference fluctuations. The phase space portraits of temperature difference fluctuations became stable and periodic and the value of Kolmogorov entropy tended to decrease with increasing the value of liquid swirling ratio from 0.1 to 0.4. The value of Kolmogorov entropy exhibited its minimum with increasing liquid swirling ratio. The value of overall heat transfer coefficient (h) showed its maximum with the variation of liquid velocity, bed porosity or liquid swirling ratio, but it increased with increasing gas velocity and particle size. The value of K exhibited its maximum at the liquid velocity at which the h value attained its maximum. The overall heat transfer coefficient and Kolmogorov entropy were well correlated in terms of dimensionless groups and operating variables.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.829-832
• /
• 2007

디지털 비디오 압축 기술은 대역폭과 저장 공간이 제한되는 멀티미디어 데이터의 효율적인 전송과 저장을 가능하게 하는 중요한 역할을 해왔다. 현재 VC-1은 차세대 DVD의 표준으로 채택되어 사용되고 있고 H.264/AVC의 대안으로 제안되고 있다. 이에 본 논문에서는 VC-1의 엔트로피 디코더에 대하여 소프트웨어 검증을 통한 최적화 알고리즘을 사용하여 하드웨어 설계 언어인 VHDL 언어를 이용하여 기술하고 ModeSim6.0a를 이용한 데이터 검증을 수행하였다.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.753-756
• /
• 1998

본 논문은 연속적인 수화 동영상에 있어서 가장 의미가 있는 손 영역을 검출하는 방법에 대한 연구이다. 부자연스러운 센서 등을 피하고 사용자 친화성과 범용성 및 실시간 구현을 도모하기 위하여 흑백 동영상의 처리가 요구된다. 농아자의 수화를 인식하기 위해 전철로서, 복잡한 배경으로부터 손 영역의 검출은 매우 중요하다. 정확한 손 영역의 검출로 수화 인식률의 개선과 영상처리의 고속화가 가능하다. 제안한 방법은 인접한 프레임간의 차 영상에 대하여 엔트로피를 측정하여 배경영상과 분리를 행한 후, 손 영역에 대한 추적을 수행하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.7
• /
• pp.1557-1564
• /
• 2010

In this paper, we propose a maximum entropy-based emotion recognition model using the individual average difference of emotional signal, because an emotional signal pattern depends on each individual. In order to accurately recognize a user's emotion, the proposed model utilizes the difference between the average of the input emotional signals and the average of each emotional state's signals(such as positive emotional signals and negative emotional signals), rather than only the given input signal. With the aim of easily constructing the emotion recognition model without the professional knowledge of the emotion recognition, it utilizes a maximum entropy model, one of the best-performed and well-known machine learning techniques. Considering that it is difficult to obtain enough training data based on the numerical value of emotional signal for machine learning, the proposed model substitutes two simple symbols such as +(positive number)/-(negative number) for every average difference value, and calculates the average of emotional signals per second rather than the total emotion response time(10 seconds).

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.7-14
• /
• 2018

Salient information extraction from multi-view videos is a very challenging area because of inter-view, intra-view correlations, and computational complexity. There are several techniques developed for keyframes extraction from multi-view videos with very high computational complexities. In this paper, we present a keyframes extraction approach from multi-view videos using entropy and complexity information present inside frame. In first step, we extract representative shots of the whole video from each view based on structural similarity index measurement (SSIM) difference value between frames. In second step, entropy and complexity scores for all frames of shots in different views are computed. Finally, the frames with highest entropy and complexity scores are considered as keyframes. The proposed system is subjectively evaluated on available office benchmark dataset and the results are convenient in terms of accuracy and time complexity.

• Journal of Advanced Navigation Technology
• /
• v.18 no.4
• /
• pp.387-392
• /
• 2014

Recently, various research for intelligent video surveillance system have been proposed, but the existing monitoring systems are inefficient because all of situational awareness is judged by the human. In this paper, shadow removal based moving object tracking method is proposed using the chromaticity and entropy image. The background subtraction model, effective in the context awareness environment, has been applied for moving object detection. After detecting the region of moving object, the shadow candidate region has been estimated and removed by RGB based chromaticity and minimum cross entropy images. For the validity of the proposed method, the highway video is used to experiment. Some experiments are conducted so as to verify the proposed method, and as a result, shadow removal and moving object tracking are well performed.