Color cluster rotation
Dietrich W. R. Paulus, Laszlo Csink, Hendrik J. Niemann · 2002
The distribution of color values in color images depends on the illumination which varies widely under real-world conditions. We present a new approach for color normalization which adjusts the statistical properties of the distribution to predefined values. We introduce two algorithms based on geometric manipulations of the color cluster. Our new color rotation algorithm is tested on some natural and synthetic images.