Image Matching via Saliency Region Correspondences

We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matching segments. Co-saliency matching score favors correspondences that are consistent with 'soft' image segmentation as well as with local point feature matching. We express the matching model via a joint image graph (JIG) whose edge weights represent intra- as well as inter-image relations. The dominant spectral components of this graph lead to simultaneous pixel-wise alignment of the images and saliency-based synchronization of 'soft' image segmentation. The co-saliency score function, which characterizes these spectral components, can be directly used as a similarity metric as well as a positive feedback for updating and establishing new point correspondences. We present experiments showing the extraction of matching regions and pointwise correspondences, and the utility of the global imag...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Alexander Toshev, Jianbo Shi, Kostas Daniilidis
• Keywords: Co-saliency Matching Score, Computer Vision, CVPR 2007, Feature Correspondences, Global Image Similarity, Image Matching, Pointwise Correspondences