• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2737-2753
• /
• 2013

In this study, we propose a novel salient object detection strategy based on regional contrast and relative spatial compactness. Our algorithm consists of four basic steps. First, we learn color names offline using the probabilistic latent semantic analysis (PLSA) model to find the mapping between basic color names and pixel values. The color names can be used for image segmentation and region description. Second, image pixels are assigned to special color names according to their values, forming different color clusters. The saliency measure for every cluster is evaluated by its spatial compactness relative to other clusters rather than by the intra variance of the cluster alone. Third, every cluster is divided into local regions that are described with color name descriptors. The regional contrast is evaluated by computing the color distance between different regions in the entire image. Last, the final saliency map is constructed by incorporating the color cluster's spatial compactness measure and the corresponding regional contrast. Experiments show that our algorithm outperforms several existing salient object detection methods with higher precision and better recall rates when evaluated using public datasets.

• ETRI Journal
• /
• 제35권6호
• /
• pp.969-979
• /
• 2013

Various simulation applications for hair, clothing, and makeup of a 3D avatar can provide more useful information to users before they select a hairstyle, clothes, or cosmetics. To enhance their reality, the shapes, textures, and colors of the avatars should be similar to those found in the real world. For a more realistic 3D avatar color reproduction, this paper proposes a spectrum-based color reproduction algorithm and color management process with respect to the implementation of the algorithm. First, a makeup color reproduction model is estimated by analyzing the measured spectral reflectance of the skin samples before and after applying the makeup. To implement the model for a makeup simulation system, the color management process controls all color information of the 3D facial avatar during the 3D scanning, modeling, and rendering stages. During 3D scanning with a multi-camera system, spectrum-based camera calibration and characterization are performed to estimate the spectrum data. During the virtual makeup process, the spectrum data of the 3D facial avatar is modified based on the makeup color reproduction model. Finally, during 3D rendering, the estimated spectrum is converted into RGB data through gamut mapping and display characterization.

• ETRI Journal
• /
• 제36권2호
• /
• pp.224-231
• /
• 2014

In this paper, a method to extract temperature effect information using the color temperatures of video scenes with mapping to temperature effects is proposed to author temperature effects of multiple sensorial media content automatically. An authoring tool to apply the proposed method is also introduced. The temperature effects generated by the proposed method are evaluated by a subjective test to measure the level of satisfaction. The mean opinion score results show that most of the test video sequences receive an average of approximately four points (in a five-point scale), indicating that test video sequences (with the temperature effects generated by the proposed method) enhance levels of satisfaction.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.693-694
• /
• 2006

The high definition digital TV display devices need real-time gamut mapping. This paper proposes a gamut mapping algorithm that used three dimensional reduced resolution look up table and tetrahedral interpolation for real-time processing. The proposed hardware architecture is successfully implemented in FPGA and ASIC.

• 한국정보과학회논문지:시스템및이론
• /
• 제35권5호
• /
• pp.213-222
• /
• 2008

본 논문은 2D 가상 착의 시스템의 컬러 영상 분할 및 직물 텍스쳐 매핑에 관한 것이다. 제안된 시스템은 컬러 영상 분할에 의해 2D 의류 모델 영상으로부터 분할된 의류 형상 영역에, 명도 차분 맵에 기반하여 사용자가 선택한 새로운 직물 패턴을 가상적으로 착용시킬 수 있는 것이 특징이다. 제안된 시스템은 모델 의류의 색이나 명도에 상관없이, 선택된 의류 형상 영역의 음영 및 조명 특성을 유지하면서 직물 패턴이나 직물 색을 가상적으로 변경시킬 수 있다. 또한 각기 다른 스타일 혹은 전체적인 차림새를 위한 다양한 직물 패턴 조합을 신속하고 용이하게 시뮬레이션하고 비교 선택할 수 있다. 제안된 시스템은 다양한 디지털 환경에서 실시간 처리가 가능하고 비교적 자연스럽고 사실적인 가상 착의 스타일을 제공할 뿐만 아니라 수작업을 최소한으로 줄인 반자동화 처리가 가능하기 때문에 높은 실용성과 편리한 사용자 인터페이스를 제공할 수 있다. 제안된 시스템에 따르면, 실제 의복을 제작하지 않고도 직물 패턴 디자인이 의복의 외관에 미치는 영향을 시뮬레이션할 수 있으므로 직물 디자이너의 창작활동을 도와줄 수 있고, 또한 구매자의 의사결정을 지원해 B2B 또는 B2C 전자상거래 행위를 촉진할 수 있다.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2009년도 제38회 동계학술대회 초록집
• /
• pp.137-137
• /
• 2010

Copper electroplating is a very popular and important technology for depositing high-quality conductor interconnections, especially in through silicon via (TSV). As this advanced packaging technique developing, a mass of copper and chemical solution are used, so attention to these chemical materials into the utilization and costs can not be ignored. An economical and practical real-time chemical solution monitoring has not been achieved yet. Either Red-green-blue (RGB) or optical emission spectroscopy (OES) color sensor can successfully monitor the color condition of solution during the process. The reaction rate, uniformity and quality can map onto the color changing. Hidden Semi Markov model (HSMM) can establish mapping from the color change to upper indicators, and artificial neural network (ANN) can be integrated to comprehensively determine its targets, whether the solution inside the container can continue to use.

• 반도체디스플레이기술학회지
• /
• 제23권2호
• /
• pp.23-27
• /
• 2024

Underwater images are typically degraded due to color distortion, light absorption, scattering, and noise from artificial light sources. Restoration of these images is an essential task in many underwater applications. In this paper, we propose a two-phase deep learning-based method, Underwater Deep Curve Estimation (UWDCE), designed to effectively enhance the quality of underwater images. The first phase involves a white balancing and color correction technique to compensate for color imbalances. The second phase introduces a novel deep learning model, UWDCE, to learn the mapping between the color-corrected image and its best-fitting curve parameter maps. The model operates iteratively, applying light-enhancement curves to achieve better contrast and maintain pixel values within a normalized range. The results demonstrate the effectiveness of our method, producing higher-quality images compared to state-of-the-art methods.

• 한국게임학회 논문지
• /
• 제3권1호
• /
• pp.3-9
• /
• 2003

본 논문에서는 텍스쳐 매핑과 파티클 시스템을 이용하여, 눈 내리는 장면의 애니매이션을 OpenGL로 구현하는 두가지 방법을 제시하고 이들의 실행 결과를 비교 분석하였다. 하나는 glPointSize()함수를 사용하는 것이고 또 다른 하나는 glutSolidSphere()함수를 사용하는 것이다. 실행 결과 전자가 후자보다 실행 결과가 빨라서 속도가 느린 PC나 내리는 눈의 개체 수가 많은 경우에 사용하기에 더 적절한 방법이라 생각된다. 또 전자의 방법을 이용한 구현 과정에서 눈의 모앙과 눈의 색깔의 제어가 서로 상충되는 사실을 발견하고 이미지를 조작하여 그것을 해결하는 방법을 제시한다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (A)
• /
• pp.216-217
• /
• 2007

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 2002년도 추계학술발표회요약집
• /
• pp.344.1-344
• /
• 2002