Online color camera calibration

This paper presents a practical approach to online color camera calibration under changing illumination conditions. Calibration is based on a color camera model and color constancy. In the first stage of the calibration a reconstruction of the current illuminant is performed based on an image taken from a scene with a calibrated color set. Using the updated power spectrum distribution of the current illumination the output camera values are corrected. Based on the corrected camera output values reconstruction of the reflectance spectrum of a random color object is performed and color features of the object can be determined under a required illuminant color temperature. The simulation experiments of the algorithm and results of tests on real images are discussed and the performance of the calibration is evaluated. The approach provides a real time color camera calibration procedure for many applications of machine vision