A Resilient Image Matching Method with an Affine Invariant Feature Detector and Descriptor

TL;DR

This paper introduces a new image matching method combining an affine invariant feature detector and descriptor, significantly improving robustness to view point changes and other variations like illumination and compression.

Contribution

The paper presents a novel affine invariant feature detector and descriptor that together enhance image matching robustness against view point changes, outperforming existing methods.

Findings

Outperforms state-of-the-art algorithms in view point robustness

Maintains high accuracy under illumination, rotation, and compression changes

Proven through systematic experiments

Abstract

Image feature matching is to seek, localize and identify the similarities across the images. The matched local features between different images can indicate the similarities of their content. Resilience of image feature matching to large view point changes is challenging for a lot of applications such as 3D object reconstruction, object recognition and navigation, etc, which need accurate and robust feature matching from quite different view points. In this paper we propose a novel image feature matching algorithm, integrating our previous proposed Affine Invariant Feature Detector (AIFD) and new proposed Affine Invariant Feature Descriptor (AIFDd). Both stages of this new proposed algorithm can provide sufficient resilience to view point changes. With systematic experiments, we can prove that the proposed method of feature detector and descriptor outperforms other state-of-the-art feature matching algorithms especially on view points robustness. It also performs well under other conditions such as the change of illumination, rotation and compression, etc.