• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.147-155
• /
• 1998

장면 전환 검출 알고리듬은 매 프레임마다 프레임간의 밝기차나 히스트그램 차이를 계산하므로 계산량이 많으며, 검출 속도 또한 느리게 된다. 검색 속도의 향상을 위해 시간적 표본화 방법이 제안되었으나, 적절한 검색 간격을 선택하는 어떠한 기준이나 방법도 제시되지 않았으며, 따라서 검색 간격을 경험에 의해 선택할 수밖에 없었다. 이 논문에서는 동영상의 통계적, 특성, 장면 전환 검색 간격과 장면 전환 검출 시간의 관계를 수식으로 유도하고 실험으로 확인하였다. 또한 최적의 표본화 간격을 유도된 식으로부터 구하고, 동영상의 평균 장면 전환 간격과 관계함을 보였다. 평균 장면 전환 간격이 알려져 있지 않은 동영상에 대해서 최적 검색 간격을 추정할 수 있는 알고리듬을 제안하였다.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.774-777
• /
• 2017

사진에는 의도하지 않은 노이즈나 찍는 과정 중에 발생한 실수나 문제로 원치 않게 가려진 부분이 있을 수 있는데, 이미지 완성 어플리케이션은 사용자가 전문적인 프로그램이나 전문가의 도움 없이 노이즈나 가려진 부분을 제거할 수 있도록 하였다. 본 논문에서는 GAN(Generative Adversial Network) 모델에 노이즈가 있는 사진을 입력으로 넣어 노이즈가 제거 된 사진을 생성하도록 하였고, 생성 된 사진과 기존 이미지가 자연스럽게 합성 될 수 있도록 보정을 하여 완성 된 이미지를 출력하는 어플리케이션을 제안한다. GAN 분류 모델의 시그모이드 교차-엔트로피와 생성이미지와 원본이미지간의 평균 제곱 오차를 함께 최소화 하도록 생성 모델을 학습시켰고, 낮은 평균 제곱 오차를 가지는 완성 이미지를 생성 할 수 있었다. 이미지 보정을 통해 생성 된 이미지와 입력 이미지와의 밝기 차이를 해소시켜 좀 더 자연스러운 완성 이미지 결과를 얻을 수 있었다.

• Journal of the Korean earth science society
• /
• v.37 no.7
• /
• pp.434-447
• /
• 2016

This study analyzed mass concentrations of PM10 and PM2.5, as measured at Tae-ahn and Gang-nae, Cheongju in central Korea over the period from 2011 to 2015. Higher mass concentrations of PM10, with the exception of dustfall cases during the period of winter and spring, reflected the influence of a prevailing westerly airflow, while the level of PM10 stayed at a low level in summer, reflecting the influence of North Pacific air mass and frequent rainfall. Accordingly, cases where a daily PM10 average of $81{\mu}gm^{-3}$ or over (exceeding the status of fine dust particles being 'a little bit bad') were often observed during the period of winter and spring, with more cases occurring in parts of Tae-ahn that are located close to the sources of pollutant emission in eastern China. Dustfall usually originated from dust storms made up of particles $2.5{\mu}m$ or over in diameter. However, anthropogenic haze displayed a high composition ratio of particulate less than $2.5{\mu}m$ in diameter. Accordingly, brightness temperature difference (BTD) values from the Communication, Ocean and Meteorological Satellite (COMS) were $-0.5^{\circ}K$ or over in haze with fine particulate. PM10 mass concentrations and NOAA 19 satellite BTD for haze cases were analyzed. Though PM10 mass concentrations were found to be lower than $200{\mu}g\;m^{-3}$, the mass concentration ratio of PM2.5/PM10 was measured as higher than 0.4 and BTD was found to be distributed in the range from -0.3 to $0.5^{\circ}K$. However, the BTD of dustfall cases exceeding $190{\mu}g\;m^{-3}$, were found to be less than 0.4 and BTD was found to be distributed in the range less than $-0.7^{\circ}K$. The result of applying BTD threshold values of the large-scale transport of haze proved to fall into line with the range over which aerosols of MODIS AOD and OMI AI were distributed.

• Journal of the Korean Society of Radiology
• /
• v.11 no.4
• /
• pp.213-219
• /
• 2017

The purpose of study is provide the basic data for set up proper illuminance of examination room that put purpose of an empirical study basic data about examination environment setting of the ultrasonic examination on design the examination environment of a new ultrasonic examination. As a method, to investigate the ultrasonic environment related to illumination to take a survey on the ultrasonic examination about test object to 48 parts of six units of general hospital in Busan. As a result, All Door + Curtain showed high scores in analyzing the gender, age, examination part in the case of ultrasonic examination room shielding and LED and light source control is required in the case of kind of light source. In the ultrasonic examination environment survey, the illuminance brightness is average 10 Lux which is included illuminance brightness range recommended the WHO and CEC and illuminance brightness of ultrasonic examination waiting room(ultrasonic examination waiting room, corridor) indicate average 300~800 Lux and it satisfied hospital illumination environment more than 300 Lux recommended by KSA 3011. In conclusion, Basic data suggested that improved future ultrasonic examination environment or designed new examination room on the basis of analysis result of general background and ultrasonic examination related to environment factor.

• Journal of the Korean Society of Radiology
• /
• v.7 no.1
• /
• pp.9-15
• /
• 2013

In this study, texture feature analysis (TFA) algorithm to automatic recognition of liver disease suggests by utilizing computed tomography (CT), by applying the algorithm computer-aided diagnosis (CAD) of hepatocellular carcinoma (HCC) design. Proposed the performance of each algorithm was to comparison and evaluation. In the HCC image, set up region of analysis (ROA, window size was $40{\times}40$ pixels) and by calculating the figures for TFA algorithm of the six parameters (average gray level, average contrast, measure of smoothness, skewness, measure of uniformity, entropy) HCC recognition rate were calculated. As a result, TFA was found to be significant as a measure of HCC recognition rate. Measure of uniformity was the most recognition. Average contrast, measure of smoothness, and skewness were relatively high, and average gray level, entropy showed a relatively low recognition rate of the parameters. In this regard, showed high recognition algorithms (a maximum of 97.14%, a minimum of 82.86%) use the determining HCC imaging lesions and assist early diagnosis of clinic. If this use to therapy, the diagnostic efficiency of clinical early diagnosis better than before. Later, after add the effective and quantitative analysis, criteria research for generalized of disease recognition is needed to be considered.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1150-1159
• /
• 2006

This paper proposed a curve progress control function of the area base instead of the existing edge indication function, in order to detect the brain ventricle area by utilizing a geodesic active contour model. The proposed curve progress control function is very effective in detecting the brain ventricle area and this function is based on the average brightness of the brain ventricle area which appears brighter in MRI images. Compared numerically by using various measures, the proposed method in this paper can detect brain ventricle areas better than the existing method. By examining images of normal and diseased brain's images by brain tumor, we compared the several brain ventricle detection algorithms with proposed method visually and verified the effectiveness of the proposed method.

• Journal of Biomedical Engineering Research
• /
• v.19 no.3
• /
• pp.321-325
• /
• 1998

This paper presents a simple, practical, and efficient method for estimating the speed of sound in reflection mode in ultrasound medical imaging. Its accurate determination is indispensable in order to obtain both good resolution and correct geometrical and volumetric information about human organs such as heart and kidney. Up to now, there have been several methods available, but they all suffer from either poor performance or high complexity. The proposed method finds out an optimum focusing delay profile in such a way that the brightness in a region of interest is maximized using continuous dynamic focusing in receive under fixed transmit focusing. Experiments carried out on a real ultrasound medical phantom reveals that the method a quite simple and effective in providing good speed of sound estimation, hence improved resolution and images, adding to dignostic utility.

• Annual Conference of KIPS
• /
• 2010.11a
• /
• pp.617-620
• /
• 2010

최근 고성능 모바일 단말기와 다양한 컨텐츠가 등장하면서 유비쿼터스 환경에서의 사용자 인터페이스에 대한 관심이 높아지고 있다. 특히 모바일 프로젝터는 장소의 제한을 받지 않고 큰 화면을 다른 사람과 공유할 수 있는 장점이 있는 반면에 단말기를 직접 제어해야 하는 불편함이 있다. 본 논문에서는 모바일 환경에서 카메라를 통해 입력된 영상 정보만으로 사용자가 스크린에 비추는 레이저 포인터를 실시간으로 검출하는 알고리즘을 제안한다. 제안하는 알고리즘은 색상 감지와 움직임 감지로 나뉜다. 단일 프레임에서 영상 성분의 평균을 이용한 조건을 검사하여 레이저 포인터 색상 영역을 검출하고, 인접한 프레임과 현재 프레임과의 차를 구하며 그 차이가 임계값보다 큰 영역을 움직임 영역으로 검출한다. 마지막으로 색상 검출 영역과 움직임 검출 영역을 동시에 만족하는 영역을 최종적으로 레이저 포인터 영역으로 인식한다. 본 기법은 영상 정보만 사용하기 때문에 센서나 불필요한 장비를 착용할 필요가 없고 영상 성분 평균을 이용하므로 프로젝터 성능에 따른 조도의 변화에 강건하여 효과적인 레이저 포인터 검출이 가능하다. 실험결과는 주변 조명의 밝기에 따라 차이가 있지만 대부분 80% 이상의 검출률과 16% 미만의 오검출률의 성능으로 나타났고, 이 같은 결과는 사용자의 주관적인 만족을 보장하였다.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.367-376
• /
• 2009

In this paper, we propose a flame detection method using Haar wavelet and moving averages in outdoor infrared video sequences. Our proposed method is composed of three steps which are Haar wavelet decomposition, flame candidates detection, and their tracking and flame classification. In Haar wavelet decomposition, each frame is decomposed into 4 sub- images(LL, LH, HL, HH), and also computed high frequency energy components using LH, HL, and HH. In flame candidates detection, we compute a binary image by thresholding in LL sub-image and apply morphology operations to the binary image to remove noises. After finding initial boundaries, final candidate regions are extracted using expanding initial boundary regions to their neighborhoods. In tracking and flame classification, features of region size and high frequency energy are calculated from candidate regions and tracked using queues, and we classify whether the tracked regions are flames by temporal changes of moving averages.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.623-632
• /
• 2009

In this paper, we propose a pulmonary nodule registration for the tracking of lung nodules in sequential CT scans. Our method consists of following five steps. First, a translational mismatch is corrected by aligning the center of optimal bounding volumes including each segmented lung. Second, coronal maximum intensity projection(MIP) images including a rib structure which has the highest intensity region in baseline and follow-up CT series are generated. Third, rigid transformations are optimized by normalized average density differences between coronal MIP images. Forth, corresponding nodule candidates are defined by Euclidean distance measure after rigid registration. Finally, template matching is performed between the nodule template in baseline CT image and the search volume in follow-up CT image for the nodule matching. To evaluate the result of our method, we performed the visual inspection, accuracy and processing time. The experimental results show that nodules in serial CT scans can be rapidly and correctly registered by coronal MIP-based rigid registration and local template matching.