Paper Info
Title
Seeded Laplaican: An Eigenfunction Solution for Scribble Based Interactive Image Segmentation.
Abstract
In this paper, we cast the scribble-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 efficiently computed eigenfunctions. The smoothness operator defined on feature densities at the limit n tends to infinity recovers the exact eigenvectors of the graph Laplacian, where n is the number of nodes in the graph. To further reduce the computational complexity without scarifying our accuracy, we select pivots pixels from annotations. In our experiments, we evaluate our approach using both human scribble and robot user annotations to guide the foreground/background segmentation. We developed a new unbiased collection of five annotated images datasets to standardize the evaluation procedure for any scribble-based segmentation method. We experimented with several variations, including different feature vectors, pivot count and the number of eigenvectors. Experiments are carried out on datasets that contain a wide variety of natural images. We achieve better qualitative and quantitative results compared to state-of-the-art interactive segmentation algorithms.
Year
Venue
Field
2017
arXiv: Computer Vision and Pattern Recognition
Scale-space segmentation,Computer science,Image segmentation,Artificial intelligence,Laplacian matrix,Computer vision,Feature vector,Pattern recognition,Segmentation,Generalized eigenvector,Pixel,Machine learning,Computational complexity theory
DocType
Volume
Citations 
Journal
abs/1702.00882
0
PageRank 
References 
Authors
0.34
13
2
Name
Order
Citations
PageRank
Ahmed Taha1125.61
Marwan Torki236721.68