-In this paper, a semi-automatic facial recognition algorithm is proposed in case of an insufficient training set (profile, front, half-turn). The recognition algorithm uses a polygonal 3D model that is created from the base images. The control points, in the proposed method, are transferred from the base images onto the 3D model, and they are also placed on the new image from the examination set. Then, the 3D model is used to determine the rotation angle of the head on the image, and the distances between the control points are calculated on both the new image and the model images to determine which class the new image belongs to.