Image registration based on SIFT features and adaptive RANSAC transform

Scale invariant feature transform (SIFT) is one of the most applicable algorithms used in the image registration problem for extracting and matching of the features. One of the efficient methods in reducing mismatches in this algorithm is the RANdom SAmple Consensus (RANSAC) method. Besides the applicability of RANSAC, its threshold value is fixed, and it is empirically chosen. In this paper, a new method is proposed where the threshold value is calculated based on the variance between the correct matches' and of mismatches classes. Simulation results confirm the superiority of the chosen threshold in different situations in comparison with classic RANSAC algorithms in terms of CMR and FMR.