Efficient properties-based learning for mismatch removal

Abstract

Mismatch removal is a critical step of feature matching, which is a prerequisite of many vision-based tasks. This paper aims to develop a general and robust method for mismatch removal. To this end, we propose an efficient learning-based mismatch removal method that can significantly improve outlier identification in terms of both accuracy and efficiency. The key idea of our approach is to use a set of properties to describe the putative matches and feed the match representations to a supervised learning procedure learning a binary classifier for mismatch removal. The efficient properties mainly include three aspects: consistency of neighborhood elements, weighted consistency of neighborhood topology, and the stability of correspondence. Different from existing consistency of neighborhood topology, we adopt a weighted strategy to emphasize the effect of different properties with respect to the identified correspondence. The match representations combine the spatial positions of the correspondences with their descriptor reliabilities, which can effectively enlarge the distributions between outliers and inliers. To handle large proportions of outliers, we design a simple strategy to obtain a subset with high ratio inliers guiding the match representations construction process. This strategy can also boost the number of true correspondences without sacrificing the accuracy. Extensive experiments demonstrate our superiority over the state-of-the-art methods.