• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.968-976
• /
• 2003

In this paper, we propose a novel method for lip recognition. Lip model is built based on the concatenated gray level distribution model, and the recognition problem is simplified as the minimization problem of matching object function. The Down Hill Simplex Algorithm is used for the minimization with the proposed novel method for setting initial condition, which can refrain Iteration from converging to local minima. The proposed algorithm shows extracting lip shape from the test image where Active Shape Model fails.

• Proceedings of the KOSOMBE Conference
• /
• v.1991 no.11
• /
• pp.57-60
• /
• 1991

A new approach to texture classification for ultrasound liver diagnosis using run difference matrix was developed. The run difference matrix consists of the gray level difference along with distance. From this run difference matrix, we defined several parameters such as LDE, LDEL, NUF, SMO, SMG, SHP etc. and three vectors namely DOD, DGD and DAD. Each parameter value calculated in fatty cirrhotic, chronic hepatitic and normal liver mage was plotted in two dimensional plane. We compared our results with run length method. There are several advantages of run difference matrix method over the run lengths. 1) It is more sensitive to small difference of gray level distribution. 2) The parameters provide more statistically significant value. Images were classified with the extracted parameters to each diseases using neural networks. In preliminary clinical exprements, this approach showed satisfying results.

• The Plant Pathology Journal
• /
• v.27 no.2
• /
• pp.103-109
• /
• 2011

The fungal genus Cercospora is one of the most ubiquitous groups of plant pathogenic fungi, and gray leaf spot caused by C. zeae-maydis is one of the most widespread and damaging foliar diseases of maize in the world. While light has been implicated as a critical environmental regulator of pathogenesis in C. zeae-maydis, the relationship between light and the development of disease is not fully understood. Recent discoveries have provided new insights into how light influences pathogenesis and morphogenesis in C. zeae-maydis, particularly at the molecular level. This review is focused on integrating old and new information to provide an updated perspective of how light influences pathogenesis, and provides a working model to explain some of the underlying molecular mechanisms. Ultimately, a thorough molecular-level understanding of how light regulates pathogenesis will augment efforts to manage gray leaf spot by improving host resistance and disease management strategies.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.273-274
• /
• 2006

칼라기반 영상 검색에서 칼라의 색상 정보를 이용하는 기법에 많은 연구가 진행되고 있다. 본 논문에서는 칼라의 색상 정보와 명암 정보인 Gray-level의 특징자를 이용해서 영상을 검색하는 시스템을 제안한다. 칼라영상의 RGB 각각의 픽셀 값들을 R값, G값, B값의 크기순으로 배열하고 칼라 그레이-레벨을 구한 뒤 양자화 한다. 이러한 칼라의 특징 정보를 사용함으로써 이미지의 확대, 축소, 회전에도 강인한 검색을 할 수 있음을 실험을 통하여 성능의 우수함을 보였다.

• Journal of Korean Port Research
• /
• v.12 no.2
• /
• pp.291-302
• /
• 1998

A digital image processing technique which is able to be used for getting the velocity vector distribution of a surface of the spilt oil in the ocean without contacting the flow itself. This technique is based upon the PIV(Particle Imaging Velocimetry) technique and its system mainly consists of a high sensitive camera, a CCD camera, an image grabber, and a host computer in which an image processing algorithm is adopted for velocity vector acquisition. For the acquisition of the advective velocity vector of floating matters on the ocean, a new multi-frame tracking algorithm is proposed, and for the acquisition of the diffusion velocity vector distribution of the spilt oil onto the water surface, a high sensitive gray-level cross-correlation algorithm is proposed.

• Journal of information and communication convergence engineering
• /
• v.20 no.1
• /
• pp.58-64
• /
• 2022

Breast ultrasonic reading is critical as a primary screening test for the early diagnosis of breast cancer. However, breast ultrasound examinations show significant differences in diagnosis based on the difference in image quality according to the ultrasonic equipment, experience, and proficiency of the examiner. Accordingly, studies are being actively conducted to analyze the texture characteristics of normal breast tissue, positive tumors, and malignant tumors using breast ultrasonography and to use them for computer-assisted diagnosis. In this study, breast ultrasonography was conducted to select 247 ultrasound images of 71 normal breast tissues, 87 fibroadenomas among benign tumors, and 89 malignant tumors. The selected images were calculated using a statistical method with 21 feature parameters extracted using the gray level co-occurrence matrix algorithm, and classified as normal breast tissue, benign tumor, and malignancy. In addition, we proposed five feature parameters that are available for computer-aided diagnosis of breast cancer classification. The average classification rate for normal breast tissue, benign tumors, and malignant tumors, using this feature parameter, was 82.8%.

• Coupled systems mechanics
• /
• v.10 no.6
• /
• pp.545-560
• /
• 2021

An in situ experiment imaged via X-ray computed tomography was performed on a continuous glass fiber mat reinforced epoxy resin composite. The investigated dogbone specimen was subjected to uniaxial cyclic tension. The reconstructed scans (i.e., gray level volumes) were registered via Digital Volume Correlation. The calculated maximum principal strain fields and correlation residual maps exhibited strain localization areas within the material bulk, thus indicating damage inception and growth toward the specimen surface. Strained bands and areas of elevated correlation residuals were mainly concentrated in the narrowest gauge section of the investigated specimen, as well as on the specimen ligament edges. Gray level residuals were laid over the corresponding mesostructure to highlight and characterize damage development within the material bulk.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.410-413
• /
• 2011

본 논문에서는 도로 영상에서 검출된 자동차 영상을 종류별 분류를 위해 효과적인 질감 특징정보 기반의 자동차 종류별 분류 방안을 제안한다. 제안한 연구에서는 운전자의 안전운전지원을 위해 도로상에서 검출된 자동차 영역과 자신의 차량과 거리를 추정하기 위해 검출된 자동차의 종류를 인식할 필요가 있다. 즉, 인식된 자동차의 종류에 따라 차량 간 거리를 추정에 필요한 파라미터로 사용할 수 있기 때문이다. 따라서 본 연구에서는 검출된 자동차 영상들로부터 GLCM(gray-level co-occurrence matrix)의 7가지의 특징정보들을 추출하고 SVM을 사용하여 학습 한 후 자동차의 종류(승용, 화물, 버스)를 분류하는 방법을 제안한다. GLCM은 영상이 가진 질감 정보를 효율적으로 분석함으로써 영역의 밝기 변화 정도, 거침 정도, 픽셀 분포 정도 등을 표현하기 때문에 영상내의 포함된 영역을 분류하는데 효과적이다. 제안한 방법을 실제 자동차 규모별 분류에 적용한 결과 약 83%의 분류 성공률을 제시하였다.

• Journal of Internet Computing and Services
• /
• v.13 no.4
• /
• pp.53-62
• /
• 2012

Object segmentation is a demanding research area and not a trivial problem of image processing and computer vision. Tremendous segmentation algorithms were addressed on gray-scale (or biomedical) images that rely on numerous image features as well as their strategies. These works in practice cannot apply to natural color images because of their negative effects to color values due to the use of gray-scale gradient information. In this paper, we proposed a new approach for color object segmentation by modifying a geometric active contour model named distance regularized level set evolution (DRLSE). Its speed function will be designed to exploit as much as possible color gradient information of images. Finally, we provide experiments to show performance of our method with respect to its accuracy and time efficiency using various color images.

• Proceedings of the Optical Society of Korea Conference
• /
• 1997.08a
• /
• pp.56-56
• /
• 1997