• 한국지반공학회논문집
• /
• 제38권5호
• /
• pp.61-71
• /
• 2022

토색은 흙을 분류하고 물리적, 화학적, 생물학적 특성을 예측하기 위한 기초 지표로 널리 활용된다. 일반적으로 토색은 육안으로 관찰해 결정하지만 관찰자의 예민도 혹은 주관이 개입될 가능성이 높으며 많은 시간이 소요된다. 디지털 이미지 프로세싱은 디지털 이미지를 이용해 원하는 정보를 획득하는 일련의 과정으로, 이를 통해 빠르고 정확한(수치적인 혹은 통계적인) 토색 분석이 가능할 것으로 기대된다. 본 연구는 현장의 불규칙한 광조건을 고려할 수 있는 디지털 이미지 프로세싱 기반 토색 분석 기술 개발을 위한 기초단계로서 수행되었다. 자연광의 특성(조도 및 색온도)을 모사할 수 있는 디지털 이미지 촬영 스튜디오를 구축하고, 두 가지 흙 시료(주문진 표준사 및 안성 풍화토)를 대상으로 광조건을 12회 씩 바꿔가며 디지털 이미지를 촬영했다. 디지털 이미지 프로세싱을 통해 촬영된 시료의 토색을 두 가지 색 표시계(RGB, CIELAB)에 대해 추출한 결과, CIELAB 색 표시계를 활용해 현장의 불규칙한 광조건을 고려할 수 있음을 확인했다.

• 정보처리학회논문지B
• /
• 제12B권5호
• /
• pp.543-552
• /
• 2005

본 논문은 조영 영상에서 유동적인 배경의 텍스쳐 분석을 통한 DSA(Digital subtraction Angiography: 디지털 혈관조영술)기반의 관상동맥 검출방법에 대해 기술한다. DSA 방법은 조영제를 투입하기 전에 촬영된 마스크 영상과 조영제 투입 후의 혈관 대비가 나타나는 라이브 영상과의 차이를 이용하여 빠르게 혈관 영역만을 검출하는 방법이다. 이 방법의 큰 단점은 배경의 움직임에 민감하고, 두 영상간의 지역적인 배경 명암 분포의 변화에 따라 오검출이 발생할 수 있다. 따라서 본 논문에서는 배경 텍스쳐의 유사도를 분석하여 움직임의 차이가 가장 작은 영상을 선택함으로써 배경의 움직임으로 인한 구조적인 문제를 해결하고, 선택된 영상의 지역적 명암 보정을 통해 혈관 영역만을 효과적으로 추출할 수 있는 방법을 제안한다. 실험 결과에서는 성능 평가를 위하여 다섯 환자의 임상 관상동맥 조영 영상을 사용 하였다. 제안하는 방법은 기존의 방법보다 배경을 혈관으로 인식하는 오 인식률에서 약 $2\%$정도의 안정적인 결과를 보여주며, 정확도는 증가하였음을 알 수 있다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.464-467
• /
• 2007

All image data acquisition systems for example the digital camera and digital camcorder, use the image sensor to convert the image data (light) into electronic data. These image sensors are used in satellite camera for high quality and resolution image data. There are two kinds of image sensors, the one is the CCD (charge coupled device) detector sensor and the other is the CMOS (complementary metal-oxide semiconductor) image sensor. The CCD sensor control system has more complex than the CMOS sensor control system. For the high quality image data on CCD sensor, the precise timing control signal and the several voltage sources are needed in the control system. In this paper, the comparison of the CCD with CMOS sensor, the CCD sensor characteristic, and the control system will be described.

• Advances in aircraft and spacecraft science
• /
• 제6권1호
• /
• pp.69-86
• /
• 2019

This paper discusses the use of the Digital Image Correlation (DIC) technique for the displacement and strain measurements of a wet lay-up composite wing. As opposed to classical strain gages, DIC allows to conduct full field strain analysis of simple to complex structural parts. In this work, wing-up bending tests and measurements of the composite wing of the Dardo Aspect by CFM Air are carried out through an ad-hoc test rig and the Q-400 DIC system by Dantec Dynamics. Also, the results are used to validate a finite element model of the structure under investigation.

• Smart Structures and Systems
• /
• 제24권5호
• /
• pp.597-606
• /
• 2019

Damage detection based on dynamic characteristics of a structure is one of important roles in structural damage identification. It is difficult to detect local structural damage using traditional dynamic experimental methods due to a limited number of sensors used in an experiment. In this work, a non-contact test stand of fan blades is established, and a full-field noncontact test method, combined with three-dimensional digital image correlation, Bayesian operational modal analysis, and damage indices, is used to detect local damage of a fan blade under ambient excitation without use of baseline information before structural damage. The methodology is applied to detect invisible local damage on the fan blade. Such a method has a seemingly high potential as an alternative to detect local damage of blades with complex high-precision surfaces under extreme working conditions because it is a noncontact test method and can be used under ambient excitation without human participation.

• International Journal of Advanced Culture Technology
• /
• 제11권2호
• /
• pp.403-408
• /
• 2023

The widespread discussion of AI-generated content, fueled by the emergence of consumer applications like ChatGPT and Midjourney, has attracted significant attention. Among various AI applications, AI painting has gained popularity due to its mature technology, user-friendly nature, and excellent output quality, resulting in a rapid growth in user numbers. Midjourney and Stable Diffusion are two of the most widely used AI painting tools by users. In this study, the author adopts a perspective that represents the general public and utilizes case studies and comparative analysis to summarize the distinctive features and differences between Midjourney and Stable Diffusion in the context of AI character illustration. The aim is to provide informative material forthose interested in AI painting and lay a solid foundation for further in-depth research on AI-generated content. The research findings indicate that both software can generate excellent character images but with distinct features.

• Journal of Multimedia Information System
• /
• 제7권1호
• /
• pp.1-10
• /
• 2020

The image analysis is an important and predominant task for classifying the different parts of the image. The analysis of complex image analysis like histopathological define a crucial factor in oncology due to its ability to help pathologists for interpretation of images and therefore various feature extraction techniques have been evolved from time to time for such analysis. Although deep reinforcement learning is a new and emerging technique but very less effort has been made to compare the deep learning and deep reinforcement learning for image analysis. The paper highlights how both techniques differ in feature extraction from complex images and discusses the potential pros and cons. The use of Convolution Neural Network (CNN) in image segmentation, detection and diagnosis of tumour, feature extraction is important but there are several challenges that need to be overcome before Deep Learning can be applied to digital pathology. The one being is the availability of sufficient training examples for medical image datasets, feature extraction from whole area of the image, ground truth localized annotations, adversarial effects of input representations and extremely large size of the digital pathological slides (in gigabytes).Even though formulating Histopathological Image Analysis (HIA) as Multi Instance Learning (MIL) problem is a remarkable step where histopathological image is divided into high resolution patches to make predictions for the patch and then combining them for overall slide predictions but it suffers from loss of contextual and spatial information. In such cases the deep reinforcement learning techniques can be used to learn feature from the limited data without losing contextual and spatial information.

• 대한임상전기생리학회지
• /
• 제8권2호
• /
• pp.39-43
• /
• 2010

Purpose : The purpose of this study was to analyze skin reactions induced by ultraviolet irradiation using digital imagery. Methods : We recruited 15 women and ultraviolet irradiation was applied to their lumbar area. (The degree of inflammatory reaction was set on the basis of the third erythema dose. Image analysis was divided by Photoshop CS (8 bit RGB scale and gray scale). Then, images were processes using Image Pro Plus 4.5 program analyzing R, G, B, chromatic red value, luminance value and gray value. Results : As a result of analyzing changes in RGB scale, there were statistically significant differences in R, G, and chromatic red values. As a result of analyzing changes in gray scale, there were statistically significant differences in gray value. Analysis of changes in B and luminance values showed that there was no statistically significant difference. Conclusion : This study found that ultraviolet irradiation had influence on RGB and gray scale. These results suggest that changes to digital images on skin reaction by ultraviolet irradiation are related to erythema. In particular, these changes are related to R and gray values.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.156-158
• /
• 2003

Analysis of high-resolution satellite image becomes important for cartography, surveillance, and remote sensing. However, there are lots of problems to be solved for automatic analysis of high-resolution satellite image especially in urban area. The problems are originated from the increased complexity due to the unnecessary details and shadows, and time-varying illuminations. Because of such obstacles, it seems impossible to make automatic analysis. This paper proposes a way of change detection of buildings in urban area by using digital vector map. The proposed way makes the buildings on the vector map parameterized, and searches them in the preprocessed high-resolution image by using generalized Hough transform. The searched building objects are overlaid on the satellite image. The overlaid image can help to detect the change of building rapidly.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.684-689
• /
• 1987

Digital Subtraction Angiography(DSA) technique has been widely used to detect vascular diseases and hemodynamic parameters noninvasively. However, there are few quantitative studies on the factors in fluencing the resultant DSA image quality. In this paper, several important factors are suggested to improved the DSA image quality based on mathematical analysis. Experimental DSA images for different filters are shown and also discussed the difference between original and processed image quality.