• 한국의학물리학회지:의학물리
• /
• 제15권2호
• /
• pp.70-76
• /
• 2004

간 영역을 다른 복부 장기들로부터 정확히 분할한 후 간 내부의 종양을 감별 분할하므로써 간암을 조기 발견하는 데 도움을 준다. 본 논문은 복부의 모포러지컬 특성을 이용하여 효과적인 완전 자동 간 분할을 수행할 수 있는 알고리즘을 제안한다. 전처리 단계로서 다봉성 히스토그램 분할을 수행하고 복부의 모폴러지 좌표를 찾기 위해 척추를 분할한다. 다음으로 간 영역을 C-class maximum a posteriori (MAP) decision과 이진 모폴러지 필터링에 의해 추출한다. 자동으로 분할된 간 영역을 평가하기 위해 영역 에러율(Average Error Rate)과 회전 이진 영역 투영 매칭법(Rotational Binary Region Projection Matching; RBRPM)에 의한 상관 계수를 사용한다. 실험 결과는 제안한 알고리즘에 의해 획득한 완전 자동 간 분할과 수동 간 분할사이에 매우 유사한 결과를 보였다.

• Journal of Astronomy and Space Sciences
• /
• 제23권3호
• /
• pp.269-288
• /
• 2006

We revised the OTFTOOL which was developed in Five College Radio Astronomy Observatory (FCRAO) for the On-The-Fly (OTF) observation. Besides the improvement of data resampling function of conventional OTFTOOL, we added a new SELF referencing mode and data pre-reduction function. Since OTF observation data have a large redundancy, we can choose and use only good quality samples excluding bad samples. Sorting out the bad samples is based on the floating level, rms level, antenna trajectory, elevation, $T_{sys}$, and number of samples. And, spikes are also removed. Referencing method can be chosen between CLASSICAL mode in which the references are taken from the OFFs observation and ELLIPSOIDAL mode in which the references are taken from the inner source free region (this is named as SELF reference). Baseline is subtracted with the source free channel windows and the baseline order chosen by the user. Passing through these procedures, the raw OTF data will be an FITS datacube. The revised-OTFTOOL maximizes the advantages of OTF observation by sorting out the bad samples in the earliest stage. And the new self-referencing method, the ELLIPSOIDAL mode, is very powerful to reduce the data. Moreover since it is possible to see the datacube at once without moving them into other data reduction programs, it is very useful and convenient to check whether the data resampling works well or not. We expect that the revised-OTFTOOL can be applied to the facilities of the OTF observation like SRAO, NRAO, and FCRAO.

• 천문학회보
• /
• 제42권2호
• /
• pp.60.2-61
• /
• 2017

A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.77 for flare classification and 0.83 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

• 한국멀티미디어학회논문지
• /
• 제18권12호
• /
• pp.1439-1444
• /
• 2015

Measuring spectral reflectance can be regarded as obtaining inherent color parameters, and spectral reflectance has been used in image processing. Model-based spectrum recovering, one of the method for obtaining spectral reflectance, uses ordinary camera with multiple illuminations. Conventional model-based methods allow to recover spectral reflectance efficiently by using only a few parameters, however it requires some parameters such as power spectrum of illuminations and spectrum sensitivity of camera. In this paper, we propose an enhanced model-based spectrum recovering method without pre-measured parameters: power spectrum of illuminations and spectrum sensitivity of camera. Instead of measuring each parameters, spectral reflectance can be efficiently recovered by estimating and using the spectrum characteristic matrix which contains spectrum parameters: basis function, power spectrum of illumination, and spectrum sensitivity of camera. The spectrum characteristic matrix can be easily estimated using captured images from scenes with color checker under multiple illuminations. Additionally, we suggest fast recovering method preserving positive constraint of spectrum by nonnegative basis function of spectral reflectance. Results of our method showed accurately reconstructed spectral reflectance and fast constrained estimation with unmeasured camera and illumination. As our method could be conducted conveniently, measuring spectral reflectance is expected to be widely used.

• 한국통신학회논문지
• /
• 제32권10C호
• /
• pp.1000-1009
• /
• 2007

본 논문에서는 공간적인 디인터레이싱을 위한 컨텐츠 기반 적응적 보간 기법을 제안한다. 제안하는 알고리즘은 전처리와 컨텐츠 분석, 컨텐츠에 따른 적응적 보간의 3 단계로 구성된다. 또한 적응적 보간 방식으로써 변형된 에지기반 라인 평균 방식과 그레디언트 기반 방향성 보간, 윈도우 매칭 방식의 세 가지 보간 방식을 제안한다. 각각의 보간 방식은 공간적인 영상 특징에 따라 다양한 성능을 나타낸다. 따라서 각각의 보간할 픽셀 영역은 그레디언트 검출을 통해 영역 특징을 분석하고 네 가지 카테고리로 분류된다. 이러한 분류 결과를 기반으로 각각에 적합한 디인터레이싱 방법을 사용함으로써 최적의 성능을 구현할 수 있다. 다양한 영상에 대한 실험을 통해 제안한 방식이 기존의 방식에 비해 가장 좋은 성능을 보임을 확인하였다.

• Journal of the Optical Society of Korea
• /
• 제4권1호
• /
• pp.66-70
• /
• 2000

The main problem of image projection on a transmission type holographic screen is color sepa-ration. And it can be overcome by using a long narrow slit type diffuser as a source of the object beam when we record the screen. But that screen is not optimized and so needs changing several conditions. To set up the system many complicate things should be taken into accounted so it is very important to analyze the basic structure by simple concepts and calculations. We designed the system so that recording and projection axis coincide in one line and showed that the analysis of the system is very simple. We did it by a 1st order paraxial approximation calculation and it was good enough to describe the system. The photo-emulsion layer shrinks after processing of the hologram. It induced unsatisfactory color matching at the viewing zone. To overcome this effect, we pre-checked the shrinkage rate of an emulsion layer by experiments and modified the recording set up to compensate for the amount of shrinkage.

• 한국통신학회논문지
• /
• 제30권10C호
• /
• pp.983-991
• /
• 2005

드라마와 같은 비디오에서 사람의 얼굴은 일반적으로 자주 등장하며 비디오 내용을 분석하기 위한 유용한 정보를 제공한다. 얼굴검출은 얼굴인식 및 얼굴영상의 DB 관리와 같은 응용분야에 중요한 역할을 한다. 본 논문에서는 비디오 등장인물 검색을 위한 얼굴검출 기법을 제안하였다. 전체 과정은 크게 세단계로 구성되며 첫 번째 장면전환 검출단계, 두 번째 얼굴영역 검출단계, 마지막으로 얼굴의 특징점인 눈과 입 검출단계로 구성되며, 색상에 기반한 얼굴영역 검출단계에서 발생된 얼굴 특징점을 눈과 입의 검출에 적용하였다. 실험결과 다양한 환경에서 성공적으로 얼굴을 검출하며, 기존의 색상기반 얼굴검출 방법에 비해 측면영상에서 $24\%$의 성능향상을 보였다.

• 한국군사과학기술학회지
• /
• 제17권2호
• /
• pp.175-181
• /
• 2014

In this paper, we propose a robust clutter pre-thresholding method using background adaptive Threshold Map for the clutter rejection in the complex coastal environment. The proposed algorithm is composed of the use of Threshold Map's and method of its calculation. Additionally we also suggest an automatic decision method of Thresold Map's update. Experimental results on some sets of real infrared image sequence show that the proposed method could remove clutters effectively without any loss of detection rate for the aim target and reduce processing time dramatically.

• 터널과지하공간
• /
• 제6권3호
• /
• pp.197-208
• /
• 1996

Due to the constraints in pre site-investigation for tunnel, it is essential to redesign the support structures suitable for rock mass conditions such as rock strength, ground water and discontinuity conditions for safe tunnel construction. For the selection of optimum support, it is very important to carry out the rock mass classification and in-situ measurement in tunnelling. In this paper, in a mountain tunnel designed by NATM in hard rock, the selectable system for optimum support has been studied. The tunnel is situated at Chun-an in Kyungbu highspeed railway line with 2 lanes over a length of 4, 020 m and a diameter of 15 m. The tunnel was constructed by drill & blasting method and long bench cut method, designed five types of standard support patterns according to rock mass conditions. In this tunnel, face mapping based on image processing of tunnel face and rock mass classification by RMR carried out for the quantitative evaluation of the characteristics of rock mass and compared with rock mass classes in design. Also, in-situ measurement of convergence and crown settlement conducted about 30 m interval, assessed the stability of tunnel from the analysis of monitoring data. Through the results of rock mass classification and in-situ measurement in several sections, the design of supports were modified for the safe and economic tunnelling.

• 정보과학회 논문지
• /
• 제42권7호
• /
• pp.868-877
• /
• 2015

영상에서 바코드 영역을 검출하는 다양한 방식들이 연구되어 왔다. 기존 방식들은 주파수 성분 특징을 이용하거나, Hough transform (HT)을 이용하여 바코드 영역을 검출한다. 하지만 이 방식들은 바코드의 기울기와 노이즈에 영향을 받는다. 또한 여러 개의 바코드가 있는 경우 정확히 검출하지 못한다. 본 논문에서는 바코드의 기울기와 노이즈에 강인하고, 복수 개의 바코드를 검출할 수 있는 방식을 제안한다. 우리는 전처리 단계로 Probabilistic Hough transform (PHT)를 이용하여 바코드 기울기, 노이즈, 그리고 개수에 상관없이 바코드가 존재할 가능성이 높은 영역을 추출한 후, 주파수 성분 분석을 통해 바코드를 찾아낸다. 구현된 시스템의 성능분석을 통해 다양한 환경에서 바코드 추출이 가능함을 확인했다.