Co-Saliency Detection Based on Hierarchical Segmentation

Zhi Liu¹     Wenbin Zou²     Lina Li¹     Liquan Shen¹     Olivier Le Meur³

Image and Video Processing LAB,Shanghai University¹
College of Information Engineering, Shenzhen University²
University of Rennes,France³

 

Abstract

Co-saliency detection, an emerging and interesting issue in saliency detection, aims to discover the common salient objects in a set of images. This paper proposes a hierarchical segmentation based co-saliency model. On the basis of fine segmentation, regional histograms are used to measure regional similarities between region pairs in the image set, and regional contrasts within each image are exploited to evaluate the intra-saliency of each region. On the basis of coarse segmentation, an object prior for each region is measured based on the connectivity with image borders. Finally, the global similarity of each region is derived based on regional similarity measures, and then effectively integrated with intra-saliency map and object prior map to generate the co-saliency map for each image. Experimental results on two benchmark datasets demonstrate the better co-saliency detection performance of the proposed model compared to the state-of-the-art co-saliency models.

 

co-saliency model

Illustration of the proposed hierarchical segmentation based co-saliency model.

Results

subjective comparison

Examples of co-saliency detection on CP dataset. From top to bottom: original images in five image pairs, binary ground truths, co-saliency maps generated using Li's model [5], Fu's model [9] and our model, respectively.

Examples of co-saliency detection on iCoseg dataset. From top to bottom: some original images in four image sets, binary ground truths, co-saliency maps generated using Fu's model [9] and our model, respectively.

 

objective comparison

>

Precision-recall curves of different saliency models on CP dataset (top) and iCoseg dataset (bottom).

Citation

Z. Liu, W. Zou, L. Li, L. Shen and O. Le Meur, "Co-Saliency Detection via Co-Salient Object Discovery and Recovery," Signal Processing Letters, IEEE, vol. 21, no. 1, pp. 88-92, Jan 2014.
@ARTICLE{6675796,
author={Zhi Liu and Wenbin Zou and Lina Li and Liquan Shen and Le Meur, O.},
journal={Signal Processing Letters, IEEE},
title={Co-Saliency Detection Based on Hierarchical Segmentation},
year={2014},
month={Jan},
volume={21},
number={1},
pages={88-92},
doi={10.1109/LSP.2013.2292873},
ISSN={1070-9908},} .

 

Downloads

"Co-Saliency Detection Based on Hierarchical Segmentation" Z. Liu, W. Zou, L. Li, L. Shen and O. Le Meur, Signal Processing Letters, IEEE, vol. 21, no. 1, pp. 88-92, Jan 2014.    [Paper]   [MATLAB Code]