Ziv–Zakai Bounds on Image Registration

Abstract

Image registration is a fundamental and important task in image processing. The goal essentially is to estimate the transformation that aligns two images. We focus on the general rigid body transformation case. In this paper, we derive the Ziv-Zakai bounds (ZZB) on image registration by assuming an uncertainty model for the rotation and translation errors, and propose to use the ZZB as a benchmark to evaluate the registration ability of an image pair. We also compare the performance of several image registration algorithms with the derived bounds when applied to several datasets.