Image Registration Algorithm Based on Improved SIFT

Abstract

A method is proposed to combine the Shi-Tomasi algorithm with the SFT (Scale-Invariant Feature Transform) algorithm for image registration, aiming to address the non-real-time issue of the SIFT algorithm. The method utilizes the Shi-Tomasi algorithm to extract feature points, and the more efficient PROSAC algorithm is employed to replace the traditional RANSAC algorithm for removing mismatches. Experimental results demonstrate that the proposed algorithm effectively improves matching accuracy while reducing the image matching time by 66.5%.