BROWSE
Detail
Conference Paper
Target Normalized Matting
Cited - time in 
Share 
Share
- Authors
- Jae Hwan Kim, Man Kyu Sung
- Issue Date
- 2008-10
- Citation
- Pacific Graphics (PG)2008, pp.1-6
- Language
- English
- Type
- Conference Paper
- Abstract
- In this paper, we present an improved method of current closed-form solution for digital image matting. This method, which we call the target normalized matting, adopts the normalized cut technique where the objective function is normalized with the total degree of color similarity of foreground regions. Unlike current closedform solution, our method measures the total dissimilarity between the foreground and the background regions as well as the total similarity within foreground regions. This approach not only leads to better separation between foreground and background regions, but also works better under given insufficient constraints in the background than the previous closed-form solution. In addition, we employ a quadratic programming approach to solve the objective function to obtain a globally optimal matting result. Our algorithm has been verified through several sample images.
- KSP Keywords
- Color Similarity, Image Matting, Improved method, Normalized cut, Objective function, Programming approach, closed-form solution, digital image, quadratic programming(QP)