• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.449-456
• /
• 2009

Image processing has been applied to steel bridge defect recognition since 1990s. Compare to human visual inspection, image processing provides a more objective and accurate way of assessment. Since shade and shadow may sometimes occur when taking bridge coating images, non-uniform illumination problems should be considered. By means of color image processing, this paper aims to mitigate the illumination effect for bridge coating assessment. Furthermore, the adaptable ellipse method (AEM) is proposed to recognize mild rust colors. Finally, AEM will be compared to the K-Means algorithm, a popular recognition method, to show its advantage.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2021년도 가을 학술논문 발표대회
• /
• pp.112-113
• /
• 2021

Since natural sand is being depleted, research is being conducted to use glass similar to sand as an aggregate. When non-reusable waste glass is crushed and used as fine aggregate, it is known that alkali of cement and silica of glass react to cause an alkali aggregate reaction. The purpose of this study is to provide basic data by studying the strength according to color to use waste glass as fine aggregate. When 10% was replaced, both flexural and compressive strength showed strength values similar to those of Plain. When replaced by 20% and 30%, the 7-day intensity was higher than that of Plain. In addition, colorless glass was found to have the highest strength among glass colors. More research is expected to be needed to become a fine aggregate of waste glass.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2013년도 추계 학술논문 발표대회
• /
• pp.190-191
• /
• 2013

In this research, the fundamental experiment for colour concrete(by using pigment) has been invested. Fundamental properties and dyeability for the colour mortar as the changing replacement ratio of pigment has been tested. For the conclusion, with the increasing ratio of pigment, the flow and compressive strength for the mortar has been decreased, For the dyeability, there's little difference when replacement ratio of dyestuff changed when the colour is red and yellow, but large difference when the blue pigment was used. Consider about the workability and strength of the mortar, the optimum pigment's replacement ratio is fixed as 2.5%.

• 한국멀티미디어학회논문지
• /
• 제2권3호
• /
• pp.308-319
• /
• 1999

본 논문에서는, clustered-dot 방법으로 해프톤된 칼라 인쇄물에 대한 새로운 역 해프토닝 방법을 제안한다. 제안한 방법은 채널 영상을 블록 단위로 나눈 후, 모아레 영역올 추출하고 평활화 단계에서 모아레 패턴의 세기에 따라 평활화 정도를 조절함으로써 기존의 방법보다 자연스럽게 평활화된 연속계조영상(continuous tone image)을 얻을수 있다. 이때 경계 정보를 함께 고려함으로써, 역 해프토닝된 영상에서 의미있는 경계가 잘 보존될 수 있도록 하였다. 실험을 통해, 제안한 방법이 경계를 잘 보존하고 모아레 패턴을 효과적으로 제거함으로써 기존의 방법보다 향상된 역 해프토닝 결과를 얻올 수 있음을 확인하였다. 제안한 방법은 디지털 도서관의 구축, 칼라 인쇄물 영상 압축, 멀티미디어 제작 동의 분야에서 효과적으로 활용될 수 있다.

• 동의생리병리학회지
• /
• 제29권4호
• /
• pp.289-294
• /
• 2015

In order to make digital processing of facial color, standardization methods of photographing and observational requirements and gloss-detecting are done through preceding papers and actual experiences. Examiner's observational informations should be contained with original and temporary color, normalcy and deviation range and gloss. And these are interrelated with time, interior and exterior temperature, emotional state, so should be recorded too. Picturing procedure should be controlled in simple and practical but objective way. Just water cleansing, 15 to 20 minute resting, prohibiton of moisturizing of examinee are common for examiner. Temperature and moisture, width, light source requirement, brightness, polarizing filter of parlor and camera-to-object distance, posture of examinee are should be recorded. In addition, pre and post-revision of color and manifestation of color space after taking images are needed coping with construction of diagnostic database.

• 한국환경과학회지
• /
• 제11권11호
• /
• pp.1183-1187
• /
• 2002

Existing retaining walls are usually made from only one cast form and any damage must be promptly repaired. However, when a part of a retaining wall is repaired, a gap can be created between the repaired and existing parts, along with an unpleasing visual effect. As such, the whole structure is often reconstructed, rather than repairing one part, resulting in construction waste and possible contamination of the environment. Accordingly, the current study proposes a construction method for a retaining wall that uses separate blocks to downsize of quantity of construction waste. In addition, by changing the color or modifying the block cover a more environmentally friendly retaining wall construction method is achieved.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2008년도 추계 학술논문 발표대회
• /
• pp.27-30
• /
• 2008

This study investigated the application of red muds, which were industrial wastes fired at 800℃, with a coloring agents. The results were summarized as following. The slumpflow, air content and unit weight volume were satisfied with each target values. The setting time was shortened on the case that 3 % of the red coloring agent and fired red mud were simultaneously replaced about 1 hour compared with the previous study which was 6 % of the red coloring agent was individually used. For the length change ratio caused by drying shrinkage and depth of neutralization on hardened concrete, they were declined when 3 % of the red coloring agent and fired red mud were simultaneously replaced compared with the previous study. On the measurement of forming colors, the case that 3 % of the red coloring agent and fired red mud were simultaneously replaced was similar to the previous study.

• 한국인공지능학회지
• /
• 제11권1호
• /
• pp.17-24
• /
• 2023

With the continuous growth in the amount of data collected and analyzed, deep learning has become increasingly popular for extracting meaningful insights from various fields. However, hardware limitations pose a challenge for achieving meaningful results with limited data. To address this challenge, this paper proposes an algorithm that leverages the characteristics of convolutional neural networks (CNNs) to reduce the size of image datasets by 20% through smoothing and shrinking the size of images using color elements. The proposed algorithm reduces the learning time and, as a result, the computational load on hardware. The experiments conducted in this study show that the proposed method achieves effective learning with similar or slightly higher accuracy than the original dataset while reducing computational and time costs. This color-centric dataset construction method using image smoothing techniques can lead to more efficient learning on CNNs. This method can be applied in various applications, such as image classification and recognition, and can contribute to more efficient and cost-effective deep learning. This paper presents a promising approach to reducing the computational load and time costs associated with deep learning and provides meaningful results with limited data, enabling them to apply deep learning to a broader range of applications.

• 전자공학회논문지SC
• /
• 제49권1호
• /
• pp.1-7
• /
• 2012

본 논문에서는 색상과 깊이 카메라로 구성된 복합형 카메라 시스템을 이용하여 3차원 영상을 구성하는 방법을 제안한다. 복합형 카메라 시스템은 3차원 영상 구성에 대하여 각 카메라가 갖는 단점을 상호 보완할 수 있다. 3차원 영상 구성에 앞서 개별적인 카메라의 내부변수 및 외부변수를 추출하며 이를 이용하여 영상 정합에 필요한 두 카메라 사이의 관계를 얻는다. 또한, 깊이 카메라의 출력과 거리 관계를 실험적으로 유도하며 정합된 영상에 대하여 좌표 변환을 통해 3차원 영상을 구성한다. 제안된 기법을 구현하기 위해 마이크로소프트사의 복합형 카메라를 이용하며 실험을 수행하며 3차원 영상 및 실제 측정치와의 비교 결과를 제시함으로써 성능을 검증한다.

• 한국건축시공학회지
• /
• 제21권6호
• /
• pp.573-581
• /
• 2021

본 연구에서는 메카노크로믹 센서의 건설 구조물 건전도 모니터링 활용 가능성을 검토하기 위한 기초 단계의 실험적 연구를 진행하였다. 콘크리트 재료의 마감 유형에 따른 메카노크로믹 센서의 변형 및 변색 특성을 파악하였다. 그결과, 콘크리트 시험체의 인장변형률이 증가할수록 메카노크로믹 센서의 변형 및 변색 반응도가 증가하는 것을 확인하였다. 또한, 콘크리트, 우레탄, 에폭시, 수성페인트 및 유성페인트의 마감 환경의 차이는 메카노크로믹 센서의 변형 및 변색 특성에 영향을 미치지 않았다.