Co-Salient Object Detection From Multiple Images

In this paper, we propose a novel method to discover co-salient objects from a group of images, which is modeled as a linear fusion of an intra-image saliency (IaIS) map and an inter-image saliency (IrIS) map. The first term is to measure the salient objects from each image using multiscale segmentation voting. The second term is designed to detect the co-salient objects from a group of images. To compute the IrIS map, we perform the pairwise similarity ranking based on an image pyramid representation. A minimum spanning tree is then constructed to determine the image matching order. For each region in an image, we design three types of visual descriptors, which are extracted from the local appearance, e.g., color, color co-occurrence and shape properties. The final region matching problem between the images is formulated as an assignment problem that can be optimized by linear programming. Experimental evaluation on a number of images demonstrates the good performance of the proposed method on co-salient object detection.

Hongliang Li, Fanman Meng, and King N. Ngan, "Co-Salient Object Detection From Multiple Images", IEEE Transactions on Multimedia, vol. 15, no. 8, pp. 1896-1909, 2013. [PDF]
Evaluation results for two ICoseg image groups. Top and Bottom: Some results for image groups Red Sox and Cheetah, respectively. Row 1: Some original images. Rows 2–6: Results for FT, SR, SER, RC, and Our method, respectively.
Experimental results for image pairs. (a): Original image pairs, i.e., llama, elephant, hawksbill. (b)-(f): Results by CA [17], SER [10], RC [19], IPCO [1], and our method.
1. Source Code (MATLAB)
   Source code will be downloaded from Here
This work was supported in part by NSFC (No. 61271289), National High Technology Research and Development Program of China (863 Program, No. 2012AA011503), and The Ph.D. Programs Foundation of Ministry of Education of China (No. 20110185110002).