Image co-saliency detection by propagating superpixel affinities

Image co-saliency detection is a valuable technique to highlight perceptually salient regions in image pairs. In this paper, we propose a self-contained co-saliency detection algorithm based on superpixel affinity matrix. We first compute both intra and inter similarities of superpixels of image pai...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE International Conference on Acoustics, Speech and Signal Processing pp. 2114 - 2118
Main Authors Zhiyu Tan, Liang Wan, Wei Feng, Chi-Man Pun
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2013
Subjects
all-pair Sim-Rank
Bipartite graph
bipartite graph matching
co-saliency measure
Educational institutions
Image co-saliency detection
Image color analysis
Matrix decomposition
Reliability
Sparse matrices
superpixel affinity propagation
Vectors
Online AccessGet full text

Cover

More Information
Summary:Image co-saliency detection is a valuable technique to highlight perceptually salient regions in image pairs. In this paper, we propose a self-contained co-saliency detection algorithm based on superpixel affinity matrix. We first compute both intra and inter similarities of superpixels of image pairs. Bipartite graph matching is applied to determine most reliable inter similarities. To update the similarity score between every two superpixels, we next employ a GPU-based all-pair SimRank algorithm to do propagation on the affinity matrix. Based on the inter superpixel affinities we derive a co-saliency measure that evaluates the foreground cohesiveness and locality compactness of superpixels within one image. The effectiveness of our method is demonstrated in experimental evaluation.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2013.6638027