Seeded Laplacian: An interactive image segmentation approach using eigenfunctions
Lists
Only you see this
Abstract
In this paper, we cast the scribbled-based interactive image segmentation as a semi-supervised learning problem. Our novel approach alleviates the need to solve an expensive generalized eigenvector problem by approximating the eigenvectors using a more efficiently computed eigenfunctions. The smoothness operator defined on feature densities at the limit n → ∞ recovers the exact eigenvectors of the graph Laplacian, where n is the number of nodes in the graph. In our experiments scribble annotation is applied, where users label few pixels as foreground and background to guide the foreground/background segmentation. Experiments are carried out on standard data-sets which contain a wide variety of natural images. We achieve better qualitative and quantitative results compared to state-of-the-art algorithms.
BibTeX
@inproceedings{taha2015seeded,
author = {Ahmed Taha and Marwan Torki},
title = {{Seeded Laplacian: An interactive image segmentation approach using eigenfunctions}},
booktitle = {ICIP},
year = {2015},
url = {https://openreview.net/forum?id=9vQM2Ldb3Wp},
}Loading related content...