Submodular Salient Region Detection

The problem of salient region detection is formulated as the well-studied facility location problem from operations research. High-level priors are combined with low-level features to detect salient regions. Salient region detection is achieved by maximizing a sub modular objective function, which m...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 2043 - 2050
Main Authors Zhuolin Jiang, Davis, Larry S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
Face
Feature extraction
Harmonic analysis
Image color analysis
Image segmentation
Linear programming
Optimization
Online AccessGet full text

Cover

More Information
Summary:The problem of salient region detection is formulated as the well-studied facility location problem from operations research. High-level priors are combined with low-level features to detect salient regions. Salient region detection is achieved by maximizing a sub modular objective function, which maximizes the total similarities (i.e., total profits) between the hypothesized salient region centers (i.e., facility locations) and their region elements (i.e., clients), and penalizes the number of potential salient regions (i.e., the number of open facilities). The similarities are efficiently computed by finding a closed-form harmonic solution on the constructed graph for an input image. The saliency of a selected region is modeled in terms of appearance and spatial location. By exploiting the sub modularity properties of the objective function, a highly efficient greedy-based optimization algorithm can be employed. This algorithm is guaranteed to be at least a (e - 1)/e 0.632-approximation to the optimum. Experimental results demonstrate that our approach outperforms several recently proposed saliency detection approaches.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.266