Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Hough-SIFT, a novel image registration method that enhances the performance of the traditional SIFT algorithm in the presence of strong linear structures by leveraging Hough space for descriptor matching. By transforming the SIFT descriptors into Hough space, the method capitalizes on the distinctive peaks formed by linear features, which significantly improves descriptor discriminability in challenging scenarios. Experimental results show that Hough-SIFT outperforms SIFT in linear scenes while achieving comparable accuracy in standard conditions, highlighting its robustness in diverse applications such as electronic image stabilization.
Hough-SIFT transforms SIFT's descriptor matching into Hough space, significantly boosting performance in challenging linear environments where traditional methods falter.
Image registration is essential in applications such as electronic image stabilization. Scale-Invariant Feature Transform (SIFT), a widely used local keypoint detector and descriptor, typically provides accurate registration; however, it often fails in scenes with strong linear structures (e.g., shutters), where local features become ambiguous. We propose Hough-SIFT, a robust registration method that performs SIFT descriptor matching in Hough space. In this domain, linear structures form distinctive peaks that restore descriptor discriminability. Experiments demonstrate that Hough-SIFT is robust in linear scenes where SIFT frequently fails, while maintaining accuracy comparable to SIFT in normal scenes.