• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.397-398
• /
• 2006

본 논문에서는 이미지 검색을 위해 가장 기본적인 요소인 이미지 색상에 따른 칼라 분포정보를 이용하고 다양한 요소에 따라 가중치를 부여한 칼라기반의 검색 기술자를 제안하였고 실험적 평가를 통하여 제안 기술자의 성능을 평가하였다. 칼라 히스토그램을 통한 이미지 검색 기술자를 설계하는데 있어 칼라모델은 HSV, 웨이블릿 변환 필터는 D9/7, 웨이블릿 분해는 2 레벨을 적용하였을 때 가장 좋은 검색효율성을 보였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.191-194
• /
• 2009

본 논문에서는 효율적인 다시점 비디오 부호화를 위해 히스토그램(histogram)을 이용한 다시점 비디오의 휘도(luminance)와 색차(chrominance)성분 보상 기법을 제안한다. 다시점 비디오는 카메라의 기하학적인 위치 차이와 여러 대의 카메라가 동일한 특성을 가지도록 완벽히 조정되지 못함으로 인해 동일한 시간대에 촬영된 인접한 시점 영상 간에 휘도와 색상의 차이가 발생할 수 있다. 이러한 특성은 인접한 카메라로부터 획득된 영상을 참조하여 시점간 움직임 예측 시에 오정합의 원인이 되어 부호화 효율을 떨어뜨리게 된다. 본 논문에서는 효율적인 다시점 비디오 부호화를 위해 시점간의 히스토그램을 비교하여 정합하는 휘도 및 색차 보상 기법을 수행한다. 일정한 시간 대역(time interval)에서 다시점 비디오의 평균 누적 히스토그램을 이용하여 참조 영상을 생성하고 각 시점별로 정합 함수를 통해 다시점 영상 간의 휘도와 색상의 불일치성을 보상한다. 제안하는 조명 보상 기법을 통하여 다시점 비디오 부호화 효율을 높일 수 있었다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2007.05a
• /
• pp.35-38
• /
• 2007

맛을 인지하는데 있어 색채가 끼치는 영향에 대한 선행 연구들에 의하면 사람은 특정 색이 상기시켜주는 맛을 기억하고 있고, 맛과 그 강도를 예측하고 판단하는데 있어 색에 크게 의지하고 있음을 알 수 있다. 본 연구에서는 사람들이 음식물 색에 대한 경험의 종류와 정도에 따라 색채로부터 연상되는 맛에 대한 특성을 파악하기 위해 2회에 걸친 실험을 진행하였다. 실험 1에서는 색상환에 고르게 분포한 여섯 가지 대표 색을 가진 초콜렛 샘플을 준비하고 피험자들에게 단맛과 쓴맛의 정도에 대해 각각 평가하도록 하였다(N=20). 실험 2에서는 실험 1의 색을 활용하되, 이를 알약에 적용한 후 동일한 평가를 진행하였다(N=20). 실험 결과, 맛에 대한 경험이 풍부한 난색 계열에서는 단맛, 쓴맛에 대한 일관된 경향을 나타냈지만, 그렇지 않은 파랑색에 대해서는 분산된 반응을 나타났다. 본 연구의 결과는 경험의 정도에 따라 색으로부터 연상되는 공감각적 특성에 대한 통찰력을 제공하며 효과적인 식품 패키지 디자인에 참고로 활용될 수 있을 것이다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.10
• /
• pp.579-585
• /
• 2003

Recently most of 3D graphics rendering Processors have the pixel cache storing depth data and color data to reduce the memory latency and the bandwidth requirement. In this paper, we propose the effective pixel cache for improving the performance of a rendering processor. The proposed cache system stores the depth data selectively based on the result of Z-test and the color data are stored into the auxiliary buffer. Simulation results show that the 16Kbyte proposed cache system provides better performance than the 32Kbyte conventional cache.

• Archives of design research
• /
• no.16
• /
• pp.89-98
• /
• 1996

The purpose of this study is to offer proposals of the practical color schemes based on the use of color systems. This study focused on the .\lunsell color system, the Ostwald color system and the ISCC ~BS color names i and then selected the Ostwald color harmony and the Judd color hallTIOny in order to establish the general principles of color schemes. The method of color schemes is worked by' the 10 i hues circle of the .\Iunsell color system and the tone system of the ISCC :\BS color names, because our i country have been adopted the "vIunsell color system for the use of color education and the KS. This method is to make the balanced color schemes easily and effectively through color education ..olor education ..

• Korea Science and Art Forum
• /
• v.37 no.3
• /
• pp.125-134
• /
• 2019

This study was conducted to organize a program to classify and analyze the characteristics of images for the automation of background music selection in the video content production process. The results and contents of the study are as follows: video characteristics are selected as subject category, emotion, pixel motion speed, color, and character material. Subject categories and feelings were extracted using Microsoft's Azure Video Indexer, Pixel Movement Speed was an Optional flow, Color was an Image Histogram for Image, and character materials was CNN(Convolutional Neural Network). The results of this study are significant in that video analysis was conducted to match background music in the recent content production process of 'Internet One-person Broadcasting Creators'.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.55-58
• /
• 2007

인체의 여러 요소들의 상호균형을 중요시하는 한의학 이론은 의학적 가치가 높이 평가되고 있지만 이를 뒷받침할 만한 체계적이고 과학적인 제시가 부족한 것이 현실이다. 이에 본 논문에서는 한의학의 사진(四診)중 망진(望診) 이론을 영상공학적 기술과 융합하여 손바닥 영상 분석을 통해 간단하게 질환을 진단할 수 있는 방법에 대해 제안하고자 한다. 특히 현대인의 스트레스로 인해 늘어가고 있는 간질환자의 증가에 대비하여 정상인과 간 질환이 있는 환자간의 손바닥 색상을 비교, 분석을 하고자 한다. 이를 위해 본 논문에서는 한의학적으로 간 질환자는 정상인보다 RGB값 및 K값이 상대적으로 낮게 나타난다는 것을 규명하기 위해 정상인과 간 질환자의 손바닥 영상 분석을 통해 RGB값 및 K값의 검출로 두 개체 집단간의 유의성을 실험으로 입증함으로써 간 질환이 의심스러울 경우 조기진단에 도움을 주고자 한다.

• The Korean Journal of Vision Science
• /
• v.20 no.4
• /
• pp.453-459
• /
• 2018

Purpose : This study was to investigate the change of accommodative functions by different color density and color of colored lenses. Methods : Participant had a normal NPC and no dyschromatopsia, phoria and eye disease, also had no histories of eye surgery in 31 students of university. Their accommodative functions were measured according to 50%, 80% density of the gray, blue, brown lens and non-colored lenses. Tests of accommodative functions performed include amplitude of accommodation, accommodative facility, relative accommodation, and accommodative lag. Results : The amplitude of accommodation and accommodation lag were increased when wearing the colored lens. Negative relative accommodation was more increased when wearing the colored lens than achromatic. Positive relative accommodation increased when wearing the blue color lens density by 50%. Also, accommodation facility increased when wearing the colored lens, but, as the density of the color increased, the accommodation facility was decreased. Conclusion : As since the accommodation function changes according to density of the colored lenses, working distance and environment of the wearing colored lens should be considered when selecting density and color of colored lenses.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.4
• /
• pp.48-54
• /
• 2020

Cracks in reinforced concrete structures are the most common type of damage and are used as important analytical data to understand the fracture behavior characteristics of structures. Currently, there is a problem that most of the crack investigation relies on visual inspection, therefore many researchers have proposed image analysis techniques to improve the problem. In this study, we proposed a crack evaluation method to be applied at an indoor experimental level using image analysis method. The image analysis technique using color is for distinguishing a boundary surface between objects existing in an image, and is a method for separating similar colors into one region based on a predefined color. In this study, to improve the accuracy of image analysis, blue paint was applied to the concrete surface and bending experiments were performed. The image analysis method was able to measure the crack width with superior accuracy compared to the crack diameter, and at the same time, it was also possible to analyze the deflection of the beam. Both the crack and deformation were able to confirm the accuracy similar to the existing measurement method, and it was found that the image analysis method was very excellent in terms of applicability.

• Journal of KIISE:Software and Applications
• /
• v.27 no.2
• /
• pp.193-200
• /
• 2000

The extraction of face regions is required for Head Gesture Interface which is a natural user interface. Recently, many researchers are interested in using color information to detect face regions in image sequences. Two most widely used color models, HSI color model and YIQ color model, were selected for this study. Actually H-component of HSI and I-component of YIQ are used in this research. Given the difference in the color component, this study was aimed to compare the performance of face region detection between the two models. First, we search the optimum range of facial color for each color component, examining the detection accuracy of facial color regions for variant threshold range about facial color. And then, we compare the accuracy of the face box for both color models by using optimal facial color and motion information. As a result, a range of $0^{\circ}{\sim}14^{\circ}$ in the H-component and a range of $-22^{\circ}{\sim}-2^{\circ}$ in the I-component appeared to be the most optimum range for extracting face regions. When the optimal facial color range is used, I-component is better than H-component by about 10% in accuracy to extract face regions. While optimal facial color and motion information are both used, I-component is also better by about 3% in accuracy to extract face regions.