Grain size characterization in Aluminum alloys can be correlated with thermo-mechanical processing properties. In order to predict the processing characteristics of these alloys under certain combinations of strain, deformation and temperature, the metallographic measure of the grain size can be used. Most of the technigues that have been proposed so far do not provide reliable and reproducible quantitative metallographic measurements of the grain size due to human error. Considering that this manual task is also tedious to perform, a general color image analysis algorithm is proposed to automate the characterization process using an optical microscope with polarized light. This algorithm was tested on several ingots and on rolled aluminum samples. The results show robustness in several conditions, even when the grains can barely be seen by a human operator Other image analysis techniques have been proposed but where judged too slow or too complex, particularly when gathering data over several fields. Time constraints specific to industrial seffings were taken into account when implementing a new algorithm.