An improved Bayesian matting method based on image statistic characteristics

Wei Sun; Siwei Luo; Lina Wu

doi:10.1117/12.2179335

4 March 2015 An improved Bayesian matting method based on image statistic characteristics

Wei Sun, Siwei Luo, Lina Wu

Proceedings Volume 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014); 94431F (2015) https://doi.org/10.1117/12.2179335
Event: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2014, Beijing, China

Abstract

Image matting is an important task in image and video editing and has been studied for more than 30 years. In this paper we propose an improved interactive matting method. Starting from a coarse user-guided trimap, we first perform a color estimation based on texture and color information and use the result to refine the original trimap. Then with the new trimap, we apply soft matting process which is improved Bayesian matting with smoothness constraints. Experimental results on natural image show that this method is useful, especially for the images have similar texture feature in the background or the images which is hard to give a precise trimap.

Citation Download Citation

Wei Sun, Siwei Luo, and Lina Wu "An improved Bayesian matting method based on image statistic characteristics", Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 94431F (4 March 2015); https://doi.org/10.1117/12.2179335

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available