Image matching for repetitive patterns

Repetitive patterns exist widely in real world images, and matching images with plenty of repetitive patterns remains a challenging task. We present in this paper a novel feature matching algorithm of images with notably repetitive patterns, in which a reliable initial correspondence set is established, purified and propagated using a voting strategy, incorporating a local geometrical constraint. Experiments have demonstrated that the proposed algorithm outperforms state-of-the-art feature matching methods on matching images with plenty of repetitive patterns.