The Experts below are selected from a list of 1650 Experts worldwide ranked by ideXlab platform
Renaud Keriven - One of the best experts on this subject based on the ideXlab platform.
-
trimap segmentation for fast and user friendly alpha matting
Lecture Notes in Computer Science, 2005Co-Authors: Olivier Juan, Renaud KerivenAbstract:Given an image, digital matting consists in extracting a Foreground Element from the background. Standard methods are initialized with a trimap, a partition of the image into three regions: a definite Foreground, a definite background, and a blended region where pixels are considered as a mixture of Foreground and background colors. Recovering these colors and the proportion of mixture between both is an under-constrained inverse problem, sensitive to its initialization: one has to specify an accurate trimap, leaving undetermined as few pixels as possible. First, we propose a new segmentation scheme to extract an accurate trimap from just a coarse indication of some background and/or Foreground pixels. Standard statistical models are used for the Foreground and the background, while a specific one is designed for the blended region. The segmentation of the three regions is conducted simultaneously by an iterative Graph Cut based optimization scheme. This user-friendly trimap is similar to carefully hand specified ones. As a second step, we take advantage of our blended region model to design an improved matting method coherent. Based on global statistics rather than on local ones, our method is much faster than standard Bayesian matting, without quality loss, and also usable with manual trimaps.
Olivier Juan - One of the best experts on this subject based on the ideXlab platform.
-
trimap segmentation for fast and user friendly alpha matting
Lecture Notes in Computer Science, 2005Co-Authors: Olivier Juan, Renaud KerivenAbstract:Given an image, digital matting consists in extracting a Foreground Element from the background. Standard methods are initialized with a trimap, a partition of the image into three regions: a definite Foreground, a definite background, and a blended region where pixels are considered as a mixture of Foreground and background colors. Recovering these colors and the proportion of mixture between both is an under-constrained inverse problem, sensitive to its initialization: one has to specify an accurate trimap, leaving undetermined as few pixels as possible. First, we propose a new segmentation scheme to extract an accurate trimap from just a coarse indication of some background and/or Foreground pixels. Standard statistical models are used for the Foreground and the background, while a specific one is designed for the blended region. The segmentation of the three regions is conducted simultaneously by an iterative Graph Cut based optimization scheme. This user-friendly trimap is similar to carefully hand specified ones. As a second step, we take advantage of our blended region model to design an improved matting method coherent. Based on global statistics rather than on local ones, our method is much faster than standard Bayesian matting, without quality loss, and also usable with manual trimaps.
Richard Szeliski - One of the best experts on this subject based on the ideXlab platform.
-
a bayesian approach to digital matting
Computer Vision and Pattern Recognition, 2001Co-Authors: Yungyu Chuang, Brian Curless, David Salesin, Richard SzeliskiAbstract:This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a Foreground Element from a background image by estimating an opacity for each pixel of the Foreground Element. Our approach models both the Foreground and background color distributions with spatially-varying sets of Gaussians, and assumes a fractional blending of the Foreground and background colors to produce the final output. It then uses a maximum-likelihood criterion to estimate the optimal opacity, Foreground and background simultaneously. In addition to providing a principled approach to the matting problem, our algorithm effectively handles objects with intricate boundaries, such as hair strands and fur, and provides an improvement over existing techniques for these difficult cases.
Nahhas Shuruq - One of the best experts on this subject based on the ideXlab platform.
-
The Influence of Pattern and Color Interaction in Object Color Preference
2019Co-Authors: Nahhas ShuruqAbstract:University of Minnesota Ph.D. dissertation.April 2019. Major: Design, Housing and Apparel. Advisor: Barbara Martinson. 1 computer file (PDF); ix, 189xii, 152 pages.A mixed method study was conducted to examine the influence of pattern density and color contrast in object color preference for two-color combinations. This study answered four questions: What colors are selected by participants when shown a set of solid colored hues? Which density and contrast levels are preferred by participants? Which objects do participants prefer for a specific colored pattern swatch? Why? A convenience sample of 30 undergraduate design students from the College of Design at the University of Minnesota participated in this research. Four main conclusions were the result of this research: First, color influences pattern more than pattern influences color. The same pattern of the same density appears different and would be preferred for big or small objects based on its colors. Second, the most preferred combinations have medium value or chroma (middle), low chroma (muted), high value (light). The least preferred combinations have very high chroma (saturated), or low value (dark). Third, the most preferred color combinations create sufficient contrast (high or mid) between the Foreground Element and background. The least preferred color combinations create low or no contrast between the Foreground Element and background. Fourth, the participants’ responses were varied between subjective and objective. Some responses were more subjective than objective. In this case, the participants related their preferences to their personal life and experience. Other responses were more objective than subjective. In this case, the participants related their preferences to the properties of color, pattern and the object size or purpose
Yungyu Chuang - One of the best experts on this subject based on the ideXlab platform.
-
a bayesian approach to digital matting
Computer Vision and Pattern Recognition, 2001Co-Authors: Yungyu Chuang, Brian Curless, David Salesin, Richard SzeliskiAbstract:This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a Foreground Element from a background image by estimating an opacity for each pixel of the Foreground Element. Our approach models both the Foreground and background color distributions with spatially-varying sets of Gaussians, and assumes a fractional blending of the Foreground and background colors to produce the final output. It then uses a maximum-likelihood criterion to estimate the optimal opacity, Foreground and background simultaneously. In addition to providing a principled approach to the matting problem, our algorithm effectively handles objects with intricate boundaries, such as hair strands and fur, and provides an improvement over existing techniques for these difficult cases.