The local normalization tends to uniformize the mean and variance of an image around a local neighborhood. This is especially useful for correct non-uniform illumination or shading artifacts.
The local normalization of f(x,y) is computed as follows:
The estimation of the local mean and variance is performed through local spatial smoothing. In this implementation, we use fast recursive Gaussian filters. The parameters of the algorithm are the sizes of the smoothing windows, σ1, and, σ2, which control the estimation of the local mean and local variance, respectively. Often σ2 should be larger than σ1.
The software provided here is a plugin for ImageJ, a general purpose image-processing and image-analysis package. It runs also on the image-processing package Fiji. ImageJ has a public domain licence; it runs on several plateforms: Unix, Linux, Windows, and Mac OS X. It doesn't take more than a couple of minutes to install.
Download Local_Norm.jar [Version 03.09.2011].
The plugin consists in one single JAR file; place it into the "plugins" folder of ImageJ.
Do not unzip the JAR file.
After restarting ImageJ, you have a new entrie in the Plugin » Filters of ImageJ, which is Local_Normalization.
Matlab version of the Local Normalization, by Guanglei Xiong, 17 Aug 2005 (Updated 07 Sep 2005)
We have also a demonstration of this algorithm running on any browser that supports Java.