Robust Spatial Matching as Ensemble of Weak Geometric Relations

Existing spatial matching methods permit geometrically-stable image matching, but still involve a difficult trade-off between flexibility and discriminative power. To address this issue, we regard spatial matching as an ensemble of geometric relations on a set of feature correspondences. A geometric relation is defined as a set of pairs of correspondences, in which every correspondence is associated with every other correspondence if and only if the pair satisfy a given geometric constraint. We design a novel, unified collection of weak geometric relations that fall into four fundamental classes of geometric coherences in terms of both spatial contexts and between-image transformations. The spatial similarity reduces to the cardinality of the conjunction of all geometric relations. The flexibility of weak geometric relations makes our method robust as regards incorrect rejections of true correspondences, and the conjunctive ensemble provides a high discriminative power in terms of mismatches. Extensive experiments are conducted on five datasets. Besides significant performance gain, our method yields much better scalability than existing methods, and so can be easily integrated into any image retrieval process.