Rapid Foreground Extraction Algorithm Based on Trimap

Article Preview

Abstract:

Foreground extraction is a very important operation in the image processing of the computers. Its purpose is to extract the area that human beings are interested in from the complicated background, which is beneficial for the subsequent operations such as background exchange, changes of the perspective effect and image mosaicing and so on. However, it is actually an ill-posed problem to determine whether a pixel belongs to the foreground. It is usually hard to acquire an accurate solution from the initial image. Therefore, the foreground extraction algorithm generally needs the user interaction. This paper has put forward a kind of rapid foreground extraction algorithm with the user interaction form of Trimap. On the one hand, our Trimap is quite simple. The users are able to understand the influence of Trimap on the productive resultants visually. On the other hand, with the help of Trimap, we are able to lessen the area that needs to be calculated in a large degree, which can rapidly finish the work of foreground extraction.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 490-495)

Pages:

1821-1825

Citation:

Online since:

March 2012

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Yung-Yu Chuang, Brian Curless, David H. Salesin, Richard Szeliski. A bayesian approach to digital matting. In Proceedings of IEEE CVPR, 2001, Page(s): 264 - 271, vol. 2.

DOI: 10.1109/cvpr.2001.990970

Google Scholar

[2] Jue Wang, Michael F. Cohen. Optimized Color Sampling for Robust Matting. In Proceedings of IEEE CVPR, 2007, Page(s): 1 - 8.

Google Scholar

[3] Jue Wang, Maneesh Agrawala, Michael F. Cohen. Soft scissors: An Interactive Tool for Realtime High Quality Matting. In Proceedings of SIGGRAPH, 2007, Page(s): 9 - es.

DOI: 10.1145/1275808.1276389

Google Scholar

[4] A. Levin, D. Lischinski, and Y. Weiss. A closed form solution to natural image matting. PAMI, 30(2): 228–242, (2008).

DOI: 10.1109/tpami.2007.1177

Google Scholar

[5] Jianbo Shi, Jitendra Malik. Normalized Cut and Image Segmentation. In Proceedings of IEEE, 2000, Page(s): 888 - 905.

Google Scholar