• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1998년도 Proceedings of International Workshop on Advanced Image Technology
• /
• pp.171-176
• /
• 1998

This paper resents a spatio-temporal video segmentation method. The algorithm segments each frame of video sequences captured by a static or moving camera into moving objects (foreground) and background using a statistical hypothesis test. In the proposed method, three consecutive image frames are exploited and a hypothesis testing is performed by comparing two means from two consecutive difference images, which results in a T-test. This hypothesis test yields change detection mask that indicates moving areas (foreground) and non-moving areas (background). Moreover, an effective method for extracting object mask form change detection mask is proposed.

• 대한가정학회지
• /
• 제25권2호
• /
• pp.1-11
• /
• 1987

The purpose of the study is to researdch clothing consumer behavior of men and women over age of 20 years and to find out the reasonable maximum utility on clothing behavior. The factors are eight distinguished parts such as sex, age, monthly income, occupation, floor space, number of room, number of family and place of residence. A common questionaire is introduced to survey the clothing consumption activity and the home background. Sources to measure them are gathered in the whole country including major cities. The questionaire of 915 correspondents of 368 males and 547 females is investigated for this research. Some of the data are analyzed by correlation, frequency, percentage, mean, and S.D. Others are investigated by ANOVA Test, x2-Test, and Multiple Range Test. The results from the survey are as followings: 1. Only four factors such as sex, monthly income, occupation, and floor space have a significance in the clothing consumption activity. 2. This survey reveals that many cloths have been kept in dead storage and concerns of utility have risen high. 3. This survey has shown that the correspondents have deep concerns about using colthing exchange store, clothing lending store, and trunk room to utilize dead storage clothing efficiently.

• 한방안이비인후피부과학회지
• /
• 제32권4호
• /
• pp.41-61
• /
• 2019

Background : The current medical statistics used in clinical research are the results of Fisher's significance test and the Neyman-Pearson hypothesis test, which were combined by psychologists. Also, in the philosophical background, it is related to Popper's falsificationism based hypothesis-deductive method and reduction to absurdity. Objectives : This study was designed to find complementary and alternative methods of null hypothesis and alternative hypothesis used for the clinical research methodology of Korean medicine otolaryngology. Methods : The body of this paper was divided into seven part. These are historical background, hypothesis test, hypothesis test method used in the design of clinical study, falsificationism and reduction to absurdity, problem and alternative method of the Neyman-Pearson hypothesis test, diagnosis example of sinusitis differentiation syndromes by Bayesian statistics. Through this process, we found out problems of frequentist statistics and suggested alternative methods. Result & Conclusion : As a solution to the problems of the null hypothesis and the alternative hypothesis, there are effects size, confidence interval, Bayesian statistics and Lakatos methodology of scientific research programmes.

• 스마트미디어저널
• /
• 제4권3호
• /
• pp.50-55
• /
• 2015

본 논문에서는 야간 영상 감시(night-time video surveillance)에 특화된 GMM(Gausssian mixture model)기반의 배경 모델링(background modeling)을 이용한 배경 차분(background subtraction)방법을 제안한다. 야간 영상에서는 낮 영상에 비해 배경과 객체의 구분이 뚜렷하지 않아 매우 흡사한 픽셀 값들을 이용하여 배경을 분리해야 한다. 이러한 문제점을 해결하기 위해 전처리 단계에서 조정된 범위의 히스토그램 스트레칭을 이용하여 입력 픽셀 값을 배경 모델링에 이로운 픽셀 값으로 변경해준다. 조정된 픽셀 값을 이용하여 가장 이상적인 배경을 찾기 위해 픽셀 단위로 GMM기반의 배경 모델링 방법을 적용한다. GMM을 기반으로 한 배경모델링 방법에서는 새로운 픽셀 값이 입력되었을 때 어떤 가우시안에도 속하지 않는다면 가장 낮은 가중치를 가진 가우시안 분포를 제거함으로써 이전의 축적된 배경의 정보를 무시하는 결과를 낳게 된다. 따라서 본 논문에서는 낮은 가중치의 가우시안을 제거하는 대신 기존 가우시안의 평균과 입력된 픽셀 값의 차를 이용하여 새로운 평균에 적용함으로써 기존의 쌓여진 정보를 고려한다. 실험결과 제안된 배경 모델링 방법이 기존 방법의 이점을 유지하면서 야간 영상 감지에 특화된 배경 차분 결과를 보였다.

• Journal of Audiology & Otology
• /
• 제25권4호
• /
• pp.171-177
• /
• 2021

Background and Objectives: The purpose of the present study was to validate the performance and diagnostic efficacy of the Korean digits-in-noise (K-DIN) test in comparison to the Korean speech perception-in-noise (K-SPIN) test, which is the representative speech-in-noise test in clinical practice. Subjects and Methods: Twenty-seven subjects (15 normal-hearing and 12 hearing-impaired listeners) participated. The recorded Korean 0-9 digits were used to form quasirandom digit triplets; 50 target digit triplets were presented at the most comfortable level of each subject while presenting speech-shaped background noise at various levels of signal-to-noise ratios (-12.5, -10, -5, or +5 dB). Subjects were then instructed to listen to both target and noise masker unilaterally and bilaterally through a headphone. K-SPIN test was also conducted using the same procedure as the K-DIN. After calculating their percent correct responses, K-DIN and K-SPIN results were compared using a Pearson-correlation test. Results: Results showed a statistically significant correlation between K-DIN and K-SPIN in all hearing conditions (left: r=0.814, p<0.001; right: r=0.788, p<0.001; bilateral: r=0.727, p<0.001). Moreover, the K-DIN test achieved better testing efficacy, shorter average listening time (5 min vs. 30 min), and easier performance of task according to participants' qualitative reports than the K-SPIN test. Conclusions: In this study, the Korean version of digit triplet test was validated in both normal-hearing and hearing-impaired listeners. The findings suggest that the K-DIN test can be used as a simple and time-efficient hearing-in-noise test in audiology clinics in Korea.

• 대한청각학회지
• /
• 제25권4호
• /
• pp.171-177
• /
• 2021

Background and Objectives: The purpose of the present study was to validate the performance and diagnostic efficacy of the Korean digits-in-noise (K-DIN) test in comparison to the Korean speech perception-in-noise (K-SPIN) test, which is the representative speech-in-noise test in clinical practice. Subjects and Methods: Twenty-seven subjects (15 normal-hearing and 12 hearing-impaired listeners) participated. The recorded Korean 0-9 digits were used to form quasirandom digit triplets; 50 target digit triplets were presented at the most comfortable level of each subject while presenting speech-shaped background noise at various levels of signal-to-noise ratios (-12.5, -10, -5, or +5 dB). Subjects were then instructed to listen to both target and noise masker unilaterally and bilaterally through a headphone. K-SPIN test was also conducted using the same procedure as the K-DIN. After calculating their percent correct responses, K-DIN and K-SPIN results were compared using a Pearson-correlation test. Results: Results showed a statistically significant correlation between K-DIN and K-SPIN in all hearing conditions (left: r=0.814, p<0.001; right: r=0.788, p<0.001; bilateral: r=0.727, p<0.001). Moreover, the K-DIN test achieved better testing efficacy, shorter average listening time (5 min vs. 30 min), and easier performance of task according to participants' qualitative reports than the K-SPIN test. Conclusions: In this study, the Korean version of digit triplet test was validated in both normal-hearing and hearing-impaired listeners. The findings suggest that the K-DIN test can be used as a simple and time-efficient hearing-in-noise test in audiology clinics in Korea.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.359-362
• /
• 2004

In multi-dimensional image, ICA-based feature extraction algorithm, which is proposed in this paper, is for the purpose of detecting target feature about pixel assumed as a linear mixed spectrum sphere, which is consisted of each different type of material object (target feature and background feature) in spectrum sphere of reflectance of each pixel. Landsat ETM+ satellite image is consisted of multi-dimensional data structure and, there is target feature, which is purposed to extract and various background image is mixed. In this paper, in order to eliminate background features (tidal flat, seawater and etc) around target feature (laver farm) effectively, pixel spectrum sphere of target feature is projected onto the orthogonal spectrum sphere of background feature. The rest amount of spectrum sphere of target feature in the pixel can be presumed to remove spectrum sphere of background feature. In order to make sure the excellence of feature extraction method based on ICA, which is proposed in this paper, laver farm feature extraction from Landsat ETM+ satellite image is applied. Also, In the side of feature extraction accuracy and the noise level, which is still remaining not to remove after feature extraction, we have conducted a comparing test with traditionally most popular method, maximum-likelihood. As a consequence, the proposed method from this paper can effectively eliminate background features around mixed spectrum sphere to extract target feature. So, we found that it had excellent detection efficiency.

• 한국컴퓨터정보학회논문지
• /
• 제10권2호
• /
• pp.59-68
• /
• 2005

실시간 영상에서 객체 추적은 수년간 컴퓨터 비전 및 여러 실용적 응용 분야에서 관심을 가지는 주제중 하나이다. 하지만 배경영상의 잡음을 객체로 인식하는 오류로 인하여 추출하고자 하는 객체를 찾지 못하는 경우가 있다 본 논문에서는 실시간 영상에서 적응적 배경영상을 이용하여 객체를 추출하고 추적하는 방법을 제안한다 입력되는 영상에서 배경영역의 잡음을 제거하고 조명에 강인한 객체 추출을 위하여 객체 영역이 아닌 배경영역 부분을 실시간으로 갱신함으로써 적응적 배경영상을 생성한다. 그리고 배경영상과 카메라로부터 입력되는 입력영상과의 차를 이용하여 객체를 추출한다. 추출된 객체는 내부점을 이용하여 최소사각영역을 설정하고, 이를 통해 객체를 추적한다. 아울러 제안방법의 성능에 대한 실험결과를 기존 추적알고리즘과 비교, 분석하여 평가한다.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 1999년도 춘계학술발표논문집 논문집
• /
• pp.127-132
• /
• 1999

Cardiovascular, respiratory and electrodermal responses to acute stress episodes modeled by combined presentation of intense white noise and performance of word recognition task with noise background were studied in 15 college students. Experimental procedure consisted in sessions with white noise, word recognition task presentation with noise background and test with noise background. Recorded physiological variables were analyzed in terms of their sensitivity to detect activation of sympathetic and parasympathetic branches of autonomic nervous system and thus reflect autonomic arousal level during shout-term stress-inducing experimental manipulations. It was shown that performance of effortful mental task with noise background elicited significant physiological responses typical for active coping behavior, namely electrodermal arousal and increased cardiovascular activity. this response profile was more profound as compared to white noise only or attending task in noise background. However, all physiological responses were mostly phasic, without long-term tonic changes, since almost all variables recovered to their initial baseline levels, suggesting that dominant autonomic mechanisms in transient acute stress episodes were of parasympathetic nature (withdrawal in stress with subsequent activation in restoration period), while sympathetic contribution was not long-lasting. Nevertheless, increased number of stressors and their longer exposure may result in higher profile of tonic sympathetic arousal and reduced functional role of vagal mechanisms in autonomic balance regulation.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 춘계종합학술대회
• /
• pp.608-611
• /
• 2004

본 논문에서는 고유얼굴 특성에 기반한 강건한 얼굴 인식 기술을 제안한다. 전형적인 고유얼굴 인식방법은 학습영역에서 고유얼굴을 생성시키고, 모든 학습영상을 이 얼굴공간에 투영시켜 각각의 사람마다 저장된 성분들을 비교하거나 상관시켜 특징들을 추출합니다. 복잡한 배경에 있는 얼굴들을 인식할 때 EFR방법은 얼굴인식에는 강하지만, 얼굴과 배경들 사이의 구분을 실패하게 된다 배경에서 강건한 얼굴인식을 위해서 배경패턴을 학습하며, 배경영역은 배경패턴으로부터 생성되어 얼굴영역과 함께 얼굴 인식을 위하여 사용된다. 본 논문에서 제안한 방법이 EFR방법보다 성능과 복잡한 배경하에서 매우 좋은 결과를 나타냄을 확인할 수 있었다.