We present an efficient spectral method for finding consistent correspondences between two sets of features. We build the adjacency matrix M of a graph whose nodes represent the potential correspondences and the weights on the links represent pairwise agreements between potential correspondences. Correct assignments are likely to establish links among each other and thus form a strongly connected cluster. Incorrect correspondences establish links with the other correspondences only accidentally, so they are unlikely to belong to strongly connected clusters. We recover the correct assignments based on how strongly they belong to the main cluster of M, by using the principal eigenvector of M and imposing the mapping constraints required by the overall correspondence mapping (one-to-one or one-to-many). The experimental evaluation shows that our method is robust to outliers, accurate in terms of matching rate, while being much faster than existing methods.
A spectral technique for correspondence problems using pairwise constraints
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 2 ; 1482-1489 Vol. 2
2005-01-01
434885 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A Spectral Technique for Correspondence Problems Using Pairwise Constraints
British Library Conference Proceedings | 2005
|Recovering Human Body Configurations Using Pairwise Constraints between Parts
British Library Conference Proceedings | 2005
|Active Image Clustering with Pairwise Constraints from Humans
British Library Online Contents | 2014
|