Co-Salient Object Detection From Multiple Images
Authors:
- 27 June 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 15 (8) , 1896-1909
Abstract
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.Keywords
This publication has 41 references indexed in Scilit:
- Object Co-Segmentation Based on Shortest Path Algorithm and Saliency ModelIEEE Transactions on Multimedia, 2012
- Scale invariant cosegmentation for image groups2011
- Object cosegmentation2011
- From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model2011
- What is an object?2010
- Measuring visual saliency by Site Entropy Rate2010
- Discriminative clustering for image co-segmentation2010
- iCoseg: Interactive co-segmentation with intelligent scribble guidance2010
- TurboPixels: Fast Superpixels Using Geometric FlowsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Learning to Detect A Salient Object2007