AUTOMATIC HUMAN IRIS COLOR CLASSIFICATION

We present an automatic iris color classification method suitable for predicting human eye color. The proposed method combines the abilities of intra-palette merging clustering technique with a thorough measurement of the iris color using the MartinSchultz scale. Intra-palette merging ensures the minimum set of group colors suitable for correctly representing the color information within human iris images, while the iris color specification presented as an eye color chart, the accuracy of the classification method. The experimental results seem to endorse the capacity of the method to obtain an automatic classification of the iris color.