Several face recognition methods based on 3D information have been introduced [11-13]. Cartoux et al. [ ] introduced the first contributions in this field, mainly based on extracting a facial curvature representation from distance images and the features were used to match different faces. Xu et al. [48] ​​proposed automatic 3D face recognition by combining global geometric features with local shape variations and achieved recognition rates of 96.1% and 72.6% when using a gallery of 30 and 120 subjects, respectively. Medioni et al. [30] used a variant of the Iterative Closest Point (ICP) algorithm for 3D face recognition and reported a recognition rate of 98% on a gallery of 100 subjects. Huang, Blanz, and Heisele [16] reported a 3D face recognition method that uses a morphable 3D head model to synthesize training images under a variety of conditions. Zhang and Samaras [18] used Blanz and Vetter's morphable model for recognition. The method is introduced to work well in case of multiple illuminants. The Mahalanobis distance method is used for classification. Basri and Jacobs [17] proposed a technique in which a set of images of a convex Lambertian object obtained under arbitrary illumination can be accurately approximated by a 3D linear space that can be characterized analytically using surface spherical harmonics. Ansari and Abdel-Mottaleb [39] introduced a method based on stereo images that landmarks around the eyes, nose and mouth were extracted from 2D images and converted to 3D landmarks. They used the CANDIDE-3 model [40] for face recognition. A 3D model was obtained by transforming the generic face of CANDIDE-3 to match the landmarks. The eyes, mouth and nose of... half the paper... of coefficients. The results obtained from three SVM classifiers are fused to determine the final classification. The experiments were conducted on three well-known databases; these are the Georgia Tech Face Database, AT&T "The Database of Faces", and the Essex Grimace Face Database. The work presented in [4] is an extension of [2]. In [4], bit-quantized images were used to extract curve features at five different resolutions. The 15 sets of approximate coefficients are used to train 15 support vector machines, and the results are combined using majority voting. In [5], a face recognition algorithm is proposed to reduce the computation cost of [4]. To reduce the dimension of curve features, dimensionality reduction tools such as PCA and LDA method and evaluated by conducting several experiments on three different databases: ORL, Essex Grimace and Yale Face Database.