First Order Locally Orderless Registration

First Order Locally Orderless Registration (FLOR) is a scale-space framework for image density estimation used defining similarity, mainly Image Registration. The was designed in principle to use zeroth-order information, providing estimates over three scales: scale, intensity and integration scale. We extend it take first-order information into account hint at higher-order information. show how standard similarity measures the framework. study especially Sum of Squared Differences (SSD) Normalized Cross-Correlation (NCC) but present theory Normalised Mutual Information (NMI) can be included.