A robust point matching algorithm for image registration

Abstract

Accurate point matching is a crucial and challenging process in feature-based image registration, especially for images with a monotonous background, In this paper, we propose a robust point matching algorithm for image registration which integrates cyclic string matching method and a two decision criteria, i. e., the stability and accuracy of transformation error. In this algorithm, a filtering strategy is designed to eliminate dubious matches to get exactly matched point sets. The performance of the proposed algorithm is evaluated by registering two typical image pairs containing repetitive patterns. Compared with Random Sample Consensus (RANSAC), Graph Transformation Matching (GTM), the proposed algorithm obtains the highest precision and stability.