• 한국멀티미디어학회논문지
• /
• 제12권8호
• /
• pp.1128-1141
• /
• 2009

게임 산업이 성장하면서 게임 그래픽 분야는 가장 빠르게 발전하고 있으며 지금은 실제 사진과 컴퓨터 그래픽을 구분하기 힘든 정도로 그래픽 기술은 양적으로나 질적으로 성장했다. 그러나 이러한 발전에도 불구하고 새롭게 출시되는 게임에 등장하는 캐릭터는 정서를 표현하지 않거나 소극적으로 표현하고 있다. 일반적으로 사람들은 얼굴의 표정이나 얼굴의 색(안색)에서 많은 정서 정보를 인지하는 것은 누구나 아는 사실이다. 그러므로 컴퓨터의 게임 환경에서 등장하는 캐릭터에게도 얼굴의 색의 변화를 통하여 유저에게 게임의 사실적인 느낌을 줄 수 있다. 본 논문에서는 기존의 맥박과 피부 온도만을 이용한 방법과는 다른 인간의 정서 이론을 기반한 정서 모형과 애니메이션의 정서표현 색 그리고 성격이론을 기반한 정서의 반응 속도를 결합하여 게임 캐릭터의 얼굴의 색을 동적으로 변화시켜 정서를 표현할 수 있는 얼굴 색 적응 기술 (Facial Color Adaptive Technique: FCAT)를 제안한다. 실제 얼굴 색 적응 기술을 이용하여 만든 얼굴색 모형(Facial Color Model : FCM)과 애니메이션 콘텐츠의 정서표현을 비교한 결과 정서 표현 색상과 변화율이 애니메이션과 유사하게 시뮬레이션 되었다. 또한 2차원 이미지뿐만 아니라 3차원 이미지에도 적용이 가능함을 확인 하였다.

• 한국정보전자통신기술학회논문지
• /
• 제6권4호
• /
• pp.249-254
• /
• 2013

In the area of computer vision, face recognition is being intensively researched. It is generally known that before a face is recognized it must be localized. Skin-color information is an important feature to segment skin-color regions. To extract skin-color regions the skin-color model based on multi-layer perceptron has been proposed. Extracted regions are analyzed to emphasize ellipsoidal regions. The results from this study show good accuracy for our vehicle driver face detection system.

• Journal of Astronomy and Space Sciences
• /
• 제14권1호
• /
• pp.1-17
• /
• 1997

The results of a restricted numerical simulation for the color gradients within globular clusters have been presented. The standard luminosity function of M3 and Salperter's initial mass functions were used to generate model clusters as a fundamental population. Color gradients with the sample clusters for both King and power law cusp models of surface brightness distributions are discussed in the case of using the standard luminosity function. The dependence of color gradients on several parameters for the simulations with Salpter's initial mass functions, such as slope of initial mass functions, cluster ages, metallicities, concentration parameters of King model, and slopes of power law, are also discussed. No significant radial color gradients are shown to the sample clusters which are regenerated by a random number generation technique with various parameters in both of King and power law cusp models of surface brightness distributions. Dynamical mass segregation and stellar evolution of horizontal branch stars and blue stragglers should be included for the general case of model simulations to show the observed radial color gradients within globular clusters.

• 한국멀티미디어학회논문지
• /
• 제25권9호
• /
• pp.1367-1374
• /
• 2022

In this paper, we propose an automatic cosmetic foundation recommendation system that suggests a good foundation product based on the user's skin color. The proposed system receives and preprocesses user images and detects skin color with OpenCV and machine learning algorithms. The system then compares the performance of the training model using XGBoost, Gradient Boost, Random Forest, and Adaptive Boost (AdaBoost), based on 550 datasets collected as essential bestsellers in the United States. Based on the comparison results, this paper implements a recommendation system using the highest performing machine learning model. As a result of the experiment, our system can effectively recommend a suitable skin color foundation. Thus, our system model is 98% accurate. Furthermore, our system can reduce the selection trials of foundations against the user's skin color. It can also save time in selecting foundations.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.323-330
• /
• 2009

This paper presents the selection, examination, and user test (SEUT) procedure to determine the ideal color scheme for a 4D model. This systematic procedure can be performed iteratively to obtain the color scheme that would be most appropriate for construction purposes. To verify the proposed procedure, an example case with two iterations is presented. Ten color schemes were examined and 48 users tested during the two iterations, and the result shows that the SEUT procedure is an effective method for determining the ideal color scheme for 4D models.

• 융합정보논문지
• /
• 제11권11호
• /
• pp.277-287
• /
• 2021

본 연구의 목적은 퍼스널컬러를 정량적으로 진단할 수 있는 모델을 구축하는 것이다. 현재 사용되고 있는 대표적인 퍼스널컬러용 색채 시스템들은 퍼스널컬러 진단 유형을 지나치게 단순화하거나, 진단 유형간의 객관화된 차이를 구별하기 어렵다는 한계를 가진다. 이를 보완한 새로운 색채 시스템을 개발하기 위해 논리적 배색이 가능한 PCCS 색체계를 도입하고, 색이 가지는 주요 4속성을 토대로 재분류하였다. 기존 색채 시스템보다 다양한 20개의 진단 유형을 제안하였으며, 정량적 방법을 피험자와의 어울림 정도를 평가하여 최적화된 유형을 찾을 수 있게 하였다. 평가 결과를 기호화하여 대입하면 피험자에게 맞는 유형이 도출되는 매트릭스를 고안하여 실험자의 개별 역량과 주관의 개입을 최소화하였다. 최종적으로 속성진단, 기호화, 계절진단의 세 단계로 이루어진 퍼스널컬러의 정량적 진단 모델을 구축하였다. 이는 기존 진단 방법에 다양성, 신뢰성, 정확성을 부여할 것이라 볼 수 있다.

• 산업공학
• /
• 제10권1호
• /
• pp.47-55
• /
• 1997

This paper deals with an assembly process of the TFT glasses and the color filters in LCD manufacturing. Two specific problems are presented and solved. One is a matching problem to find the best matches between a set of TFT glasses and a set of color filters, which result in the maximum number of good LCD assemblies. A simple mathematical model is constructed for this problem and an optimal solution can be obtained using an existing algorithm. The other is a main problem that requires a determination of an economic lot size of the color filters which are going to be assembled with a given set of TFT glasses. A Bayesian dynamic forecasting model is developed to predict the defective patterns of color filters. Based on the predicted defective rate of color filters, the minimum lot size of the color filters can be determined to minimize the probability of losing good TFT glasses and color filters.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.304-306
• /
• 2007

Methods of Object recognition from camera image are to compare features of color. edge or pattern with model in a general way. SIFT(scale-invariant feature transform) has good performance but that has high complexity of computation. Using simple color histogram has low complexity. but low performance. In this paper we represent a model as a color cooccurrence histogram. and we improve performance using pyramid matching. The color cooccurrence histogram keeps track of the number of pairs of certain colored pixels that occur at certain separation distances in image space. The color cooccurrence histogram adds geometric information to the normal color histogram. We suggest object recognition by pyramid matching of color cooccurrence histogram.

• 한국실내디자인학회논문집
• /
• 제15권6호
• /
• pp.221-228
• /
• 2006

The purpose of this research is to investigate the tendency of color preference for the elderly in housing. For this, a questionnaire survey was carried out with color chips and 9 photos of the living rooms which were chosen among apartment model houses in Pusan. Preference of color usage was measured by SD scale developed by advertising adjectives for the model houses. The result of this study are as follows: 1) The preferred color image was characterized as soft, warm and simple. The main factors of color image were identified and named as 'dignity factor' and 'personality factor'. 2) The elderly preferred G generally, but R for dominant color of the living room. They distinguished their attitudes about the color by the purpose of color usage. 3) For colors of architectural components of the living room, preferred colors were narrowed Y, YR and R for wall, art wall and floor. Beige was the most popular color in the living room for the elderly. This research can contribute to the basic data of color planning for the elderly housing.

• 한국실내디자인학회논문집
• /
• 제21권5호
• /
• pp.85-97
• /
• 2012

This study is aimed to identify the color characteristics of the current Korean Brand Apartment, focused on the color of kitchens and dining rooms in the cyber model houses. The Brands which were selected for this study ranked from first to fifth in the contractor ranking and now account for 64 percent of the apartments in sale in Seoul and Gyeonggi Province. In addition, the size between $99m^2$ and $165m^2$ were selected, because it was most preferred at the 2011 survey for user preference on the size of apartment. As this study is for the colors shown on the monintor, colors were extracted from the images of web site with L*, a*, b*. And then, they were converted to Munsell values through computer program, which values were used to identify the color characteristics of hue, tone and to apply the theory of Moon Spencer. The result of the study on the color characteristics of the kitchen and dining room of the five brands' apartments is as follows. Regarding the color use, most of the brands used Y and YR color while as the accent color, P, PB and G were used. This result of main color use for hue was same as the guideline by the literature review, but color for tone showed the difference between brands and the difference between sizes. Next, regarding the color combination, first ambiguity of color harmony was shown the most. And the larger the size was, the more the contrast of color harmony was shown. It means that the color tone had close relation with the sizes of households.