Robust non-intrusive eye location plays an important role in vision-based man-machine interaction. A modified Hausdor? distance based measure to localize the eyes is proposed, which could tolerate various changes in eye pose, shape, and scale. To eliminate the e?ects of the illumination variations, an 8-neighbour-based transformation of the gray images is proposed. The transformed image is less sensitive to illumination changes while preserves the appearance information of eyes. All the localized candidates of eyes are identified by back-propagation neural networks. Experiments demonstrate that the robust method for eye location is able to localize eyes with di?erent eye sizes, shapes, and poses under different illuminations.