Paper Info
Title
Unsupervised Salient Object Segmentation Based on Kernel Density Estimation and Two-Phase Graph Cut
Abstract
In this paper, we propose an unsupervised salient object segmentation approach based on kernel density estimation (KDE) and two-phase graph cut. A set of KDE models are first constructed based on the pre-segmentation result of the input image, and then for each pixel, a set of likelihoods to fit all KDE models are calculated accordingly. The color saliency and spatial saliency of each KDE model are then evaluated based on its color distinctiveness and spatial distribution, and the pixel-wise saliency map is generated by integrating likelihood measures of pixels and saliency measures of KDE models. In the first phase of salient object segmentation, the saliency map based graph cut is exploited to obtain an initial segmentation result. In the second phase, the segmentation is further refined based on an iterative seed adjustment method, which efficiently utilizes the information of minimum cut generated using the KDE model based graph cut, and exploits a balancing weight update scheme for convergence of segmentation refinement. Experimental results on a dataset containing 1000 test images with ground truths demonstrate the better segmentation performance of our approach.
Year
DOI
Venue
2012
10.1109/TMM.2012.2190385
IEEE Transactions on Multimedia
Keywords
Field
DocType
Object segmentation,Image segmentation,Image color analysis,Kernel,Estimation,Educational institutions,Biological system modeling
Graph theory,Cut,Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Minimum cut,Image segmentation,Unsupervised learning,Artificial intelligence,Kernel density estimation
Journal
Volume
Issue
ISSN
14
4
1520-9210
Citations 
PageRank 
References 
53
1.38
23
Authors
6
Name
Order
Citations
PageRank
Zhi Liu179258.22
Ran Shi2707.08
Liquan Shen3122686.47
Yinzhu Xue4712.45
King Ngi Ngan52383185.21
Zhaoyang Zhang6704.15