A critical review of image registration methods

Abstract

Image registration is the process of precisely overlaying two (or more) images of the same area through geometrically aligning common features (or control points) identified in the images. It mainly consists of four steps: feature detection, feature matching, transformation function estimation and image resampling. Image registration is usually applied in photogrammetry, remote sensing, computer vision, pattern recognition and medical image registration. This article presents a review of image registration techniques. We emphasise on feature point detection and matching. The goal of this article is to provide the readers an overview of such techniques, a perspective on the technical advances and a reference to relevant research.

Ähnliche Arbeiten