Affine image matching using Delaunay Triangles

Abstract

This paper proposes a matching algorithm based on Delaunay Triangulation for accurate matching between affined images. This method is suitable for images rotated, scaled, translated and affined. During the matching process, triangle nets based on Delaunay theory are constructed from feature points extracted from the images. We try to find geometric invariants from the triangle nets when the images are affine transformed. The geometric relations of triangles in the nets are utilized for the matching task. The experimental results show that an ideal matching accuracy and correction rate can be achieved using this algorithm.