In this paper we propose a robust method for recognition and pose determination of 3-D objects using range images in the eigenspace approach. Instead of computing the coefficients by a projection of the data onto the eigenimages, we determine the coefficients by solving a set of linear equations in a robust manner. The method efficiently overcomes the problem of missing pixels, noise and occlusions in range images. The results show that the proposed method outperforms the standard one in recognition and pose determination.