• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.2
• /
• pp.14-20
• /
• 2003

This paper presents a text extraction method of camera based document image. It is more difficult to recognize camera based document image in comparison with scanner based image because of segmentation problem due to variable lighting condition and versatile fonts. Both document binarization and character extraction are important processes to recognize camera based document image. After converting color image into grey level image, gray level normalization is used to extract character region independent of lighting condition and background image. Local adaptive binarization method is then used to extract character from the background after the removal of noise. In this character extraction step, the information of the horizontal and vertical projection and the connected components is used to extract character line, word region and character region. To evaluate the proposed method, we have experimented with documents mixed Hangul, English, symbols and digits of the ETRI database. An encouraging binarization and character extraction results have been obtained.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.2
• /
• pp.92-99
• /
• 2014

This paper proposes the method of facial expression recognition based on decision tree structure. In the image of facial expression, ASM(Active Shape Model) and LBP(Local Binary Pattern) make the local features of a facial expressions extracted. The discriminant features gotten from local features make the two facial expressions of all combination classified. Through the sum of true related to classification, the combination of facial expression and local region are decided. The integration of branch classifications generates decision tree. The facial expression recognition based on decision tree shows better recognition performance than the method which doesn't use that.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2008.06a
• /
• pp.80-80
• /
• 2008

바이오 센서 응용 연구에 많이 사용되는 금(Au) 나노 입자를 이용한 국소 표면 플라즈몬 공명(Localized Surface Plasmon Resonance, LSPR)에 의한 산란광을 검출하는데 주로 이용되는 암시야(dark field) 현미경 검출 방식에 관한 전산모사를 통하여 입사광의 입사 방식에 따른 산란광 세기를 정량적으로 분석하였다. 전산모사 기법으로는 국소 표면 플라즈몬 공명의 동역학적인 현상을 모사할 수 있는 유한차분시간영역(Finite Difference Time Domain, FDTD) 기법을 이용하였는데, 이러한 기법이 암시야 현미경 전산 모사에 유효함을 우선적으로 검증하였다. 암시야 현미경 검출 방식의 모사에서 입사 광원의 반사 입사 방식과 투과 입사 방식을 비교하였고, 각각의 방식에 서 입사광의 입사각에 따른 산랑광 세기를 계산하였다. 이러한 전산모사를 통하여 프리즘을 통한 내부 전반사(Total Internal Reflection, TIR) 방식에서 입사 광원의 임계각 근처에서 많이 발생하는 에바네슨트 장(evanescent field)을 결합하는 경우 산란광 세기가 증가함을 관찰하였고, 이러한 세기의 변화를 프레넬(Fresnel) 방정식에 의해 계산된 에바네슨트 장의 세기 분포와 비교 분석하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.855-858
• /
• 2004

본 논문에서는 원영상 영역내 포함된 우성의 에지에 대한 구체적 정보를 이용하기 위하여 Haar 웨이블릿을 이용한 에지영상 추출한다. 추출된 에지영상에 얼굴영역을 검출하기위해 이진화된 영상에 설정된 임계값을 통하여 얻은 이진영상으로부터 얼굴영역을 검출하기 위하여 얼굴의 일반적인 구조적 정보와 처리시간이 빠른 수평, 수직히스토그램 분석법을 이용하였다. 얼굴영역을 분리한 영상에 얼굴영역의 특징벡터를 구하기 위하여 26개의 특징벡터를 사용한 효율적인 고차 국소 자동 상관함수를 사용하였다. 계산된 특징벡터는 BP 신경망의 학습을 통하여 얼굴인식을 위한 데이터로 사용하여 제안된 알고리즘에 의한 인식률향상과 속도 향상을 입증한다.

• The Korean Journal of Nuclear Medicine
• /
• v.36 no.3
• /
• pp.166-176
• /
• 2002

Purpose: The purpose of this study is to investigate the effects of visual activation and quantitative analysis of regional cerebral blood flow. Visual activation was known to increase regional cerebral blood flow in the visual cortex in occipital lobe. We evaluated that change in the distribution of $^{99m}Tc-HMPAO$ (Hexamethyl propylene amine oxime) to reflect in regional cerebral blood flow. Materials and Methods: The six volunteers were injected with 925 MBq (mean ages: 26.75 years, n=6, 3men, 3women) underwent MRI and $^{99m}Tc-HMPAO$ SPECT during a rest state with closed eyes and visual stimulated with 8 Hz LED. We delineate the legion of interest and calculated the mean count per voxel in each of the fifteen slices to quantitative analysis. The ROI to whole brain ratio and regional index was calculated pixel to pixel subtraction visual non-activation image from visual activation image and constructed brain map using a statistical parameter map (SPM99). Results: The mean regional cerebral blood flow was increased due to visual stimulation. The increase rate of the mean regional cerebral blood flow which of the activation region in primary visual cortex of occipital lobe was $32.50{\pm}5.67%$. The significant activation sites using a statistical parameter of brain constructed a rendering image and image fusion with SPECT and MRI. Conclusion: Visual activation was revealed significant increase through quantitative analysis in visual cortex. Activation region was certified in Talairach coordinate and primary visual cortex (Ba17),visual association area (Ba18,19) of Brodmann.

• Journal of radiological science and technology
• /
• v.37 no.4
• /
• pp.295-305
• /
• 2014

This study is to provide accurate information as medical imaging equipment to check for the presence of body disease US equipment. We investigated the status of medical US equipment performance in Daegu and criteria US phantom (ATS-539) for US equipment performance measurements. The results in this study, 1. US phantom measurement results: The test passed rate were 88.6% and the failed rate were 11.4%. 2. The difference between the group of mean and the pass/failed groups were statistically significant. Focal zone and 4 mm functional resolution in the two items that are not present the passing standard. 3. The difference was statistically significant number of years and used equipment and pass the failed equipment (4.13 vs 7.25 years). We investigated the performance status of US equipment used in the clinical area in Daegu. The basis for the two items are not present this proposed passing standard. Equipment performance was associated with the number of years of using US equipment. It is necessary to maintain the best performance of the equipment phantom measurements for performance testing of US equipment.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.5
• /
• pp.465-473
• /
• 2002

Images are easily corrupted by noise during the data transmission, data capture and data processing. A technical method of noise analyzing and adaptive filtering for reducing of quantum noise in radiography is presented. By adjusting the characteristics of the filter according to local statistics around each pixel of the image as moving windowing, it is possible to suppress noise sufficiently while preserve edge and other significant information required in reading. We have proposed adaptive weighted median(AWM) filters based on local statistics. We show two ways of realizing the AWM filters. One is a simple type of AWM filter, whose weights are given by a simple non-linear function of three local characteristics. The other is the AWM filter which is constructed by homogeneous factor(HF). Homogeneous factor(HF) from the quantum noise models that enables the filter to recognize the local structures of the image is introduced, and an algorithm for determining the HF fitted to the detection systems with various inner statistical properties is proposed. We show by the experimented that the performances of proposed method is superior to these of other filters and models in preserving small details and suppressing the noise at homogeneous region. The proposed algorithms were implemented by visual C++ language on a IBM-PC Pentium 550 for testing purposes, the effects and results of the noise filtering were proposed by comparing with images of the other existing filtering methods.

• Communications of the Korean Mathematical Society
• /
• v.21 no.3
• /
• pp.409-417
• /
• 2006

자연현상의 복잡한 대상의 연구에서 출발한 프랙탈의 연구는 물리학에서 특히 열역학에서의 기법을 활용한 다중프랙탈의 연구로까지 그 영역이 확대되었다. 이 논문에서는 프랙탈과 다중프랙탈의 여러 가지 성질과 그 응용에 대한 최근 결과를 소개한다

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.37 no.11
• /
• pp.991-998
• /
• 2013

A numerical study is carried out for natural convection in an enclosure with an inner hot cylinder at the center. The top wall is cold, the bottom and both side walls of the enclosure are adiabatic, and the cylinder is heated. The bottom wall is heated locally at the middle. The ratio (w) is defined by as the width of the bottom wall to that of the heated local area. The immersed boundary method (IBM) is used to model an inner circular cylinder based on the finite volume method (FVM). This study investigates the effect of w on natural convection in an enclosure with an inner heated cylinder for Rayleigh numbers of $10^6$. At $6Ra=10^6$, thermal and flow fields show time-dependent characteristics after their full development.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.1
• /
• pp.54-62
• /
• 2019

In this paper, a stress-strain model for high-strength confined concrete is proposed using compressive fracture energy. In the compression test performed by author in Reference [6], an acrylic bar with strain gauges was embedded in the center of the specimen to measure the local strain distribution. It was found from the test that the local strain measurement by this acrylic rod is very effective. The local fracture zone length was defined based on the local strain distribution measured by the acrylic rod. Specifically, it was defined as the length where the local strain increases more than twice of the strain corresponding to maximum stress. In addition, the stress-strain relationship of confined concrete with compressive fracture energy is proposed on the assumption that the amount of energy absorbed by the compressive members subjected to the given lateral confining pressure is constant regardless of the aspect ratio and size. The proposed model predicts even results from other researchers accurately.