Share Email Print
cover

Proceedings Paper

Natural image matting through overlapping neighborhood propagation
Author(s): Hongjing Peng; Jiang Duan; Jianhua Yuan; Dinghong Shao
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The Laplacian based matting methods are attracting a lot of attention due to their elegant and high quality closedform solution. In this paper, we develop an alternative Laplacian construction for matting task by using local linear learning model, and naturally derive its nonlinear extension by incorporating Kernel Ridge Regression algorithm. Our Laplacian matrix construction approaches are based on the assumption that the alpha matte of each pixel point can be reconstructed from its neighbors' alpha values in each of overlapping windows. In this way the induced Laplacians can better exploit neighborhood intrinsic structure to constrain the propagation of foreground and background labels. Experimental results demonstrate the proposed approaches produce very high accuracy matte values, of which our nonlinear method even outperforms other Laplacian based matting methods on many test images.

Paper Details

Date Published: 13 January 2012
PDF: 8 pages
Proc. SPIE 8350, Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies, 83501C (13 January 2012); doi: 10.1117/12.921084
Show Author Affiliations
Hongjing Peng, Nanjing Univ. of Technology (China)
Jiang Duan, Nanjing Univ. of Technology (China)
Jianhua Yuan, Nanjing Univ. of Technology (China)
Dinghong Shao, Nanjing Univ. of Technology (China)


Published in SPIE Proceedings Vol. 8350:
Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies
Safaa S. Mahmoud; Zhu Zeng; Yuting Li, Editor(s)

© SPIE. Terms of Use
Back to Top