In this paper an eye localization algorithm which uses elliptical Gabor filters and local minima to detect eye pupils on a face image is proposed. First, face is detected in a given image. Then this face image is converted into gray-scale. Finally eye pupils are localized using elliptical Gabor filters and local minimum points. The method is tested on our combined data set using images form "ScFace", Hong Kong University "Face", "Karolinska Faces" and "MUCT" databases. For eye localization, a success rate of %89 for 569 images is achieved.