Image Matching via Saliency Region Correspondences
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
Abstract
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 image similarity in the context of place recognition.Keywords
This publication has 7 references indexed in Scilit:
- Using Multiple Segmentations to Discover Objects and their Extent in Image Collections2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Matching Widely Separated Views Based on Affine Invariant RegionsInternational Journal of Computer Vision, 2004
- Multiclass spectral clustering2003
- Viewpoint invariant texture matching and wide baseline stereo2002
- Feature-based correspondence: an eigenvector approachImage and Vision Computing, 1992
- An eigendecomposition approach to weighted graph matching problemsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1988