Document Type: Original Research Paper


Department of Mathematics and Computer Science, Amirkabir University of Technology – Tehran Polytechnic, Tehran, Iran


One of the serious issues in communication between people is hiding information from the others, and the best way for this, is to deceive them. Since nowadays face images are mostly used in three dimensional format, in this paper we are going to steganography 3-D face images and detecting which by curious people will be impossible. As in detecting face only, its texture is important, we separate texture from shape matrices, for eliminating half of the extra information. Steganography is done only for face texture, and for reconstructing a 3-D face, we can use any other shape. Moreover, we will indicate that, by using two textures, how two 3-D faces can be combined. For a complete description of the process, first, 2-D faces are used as an input for building 3-D faces, and then 3-D face and texture matrices are extracted separately from the constructed 3-D face. Finally, 3-D textures are hidden within the other images.

Graphical Abstract


[1]      A. Bas, W. A. Smith, T. Bolkart, and S. Wuhrer, “Fitting a 3-D morphable model to edges: A comparison between hard and soft correspondences,” arXiv preprint arXiv: 1602.01125, 2016.

[2]      V. Blanz and T. Vetter, “A morphable model for the synthesis of 3-D faces,” in Proc. the 26th annual conference on Computer Graphics and Interactive Techniques, Los Angeles CA, USA, 1999.

[3]      J. Kittler, P. Huber, Z. H. Feng, G. Hu, and W. Christmas, “3-D morphable face models and their applications,” in Proc. International Conference on Articulated Motion and Deformable Objects, Palma de Mallorca, Spain 2016.

[4]      A. Patel and W. Smith. “3d morphable face models revisited. In in Proc. of IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1327–1334, Florida, USA, 2009.

[5]      X. Zhu and D. Ramanan. "Face detection, pose estimation, and landmark localization in the wild," in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Rhode Island, 2012.

[6]      C. C. Chang, T. S. Chen, and K. F. Hwang, “Electronic image techniques,” Taipei: Unalis, 2000.

[7]      N. F. Johnson and S. Jajodia, “Exploring steganography: Seeing the unseen,” IEEE Computer, vol. 31, no. 2, pp. 26-34, Feb. 1998.

[8]      P. Paysan, R. Knothe, B. Amberg, S. Romdhani, and T. Vetter, “A 3-D face model for pose and illumination invariant face recognition,” in Proc. IEEE Intl. Conf. on Advanced Video and Signal based Surveillance, Genova, Italy, 2009.

[9]      V. Blanz and T. Vetter, “Face recognition based on fitting a 3-D morphable model,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 9,  pp. 1063-1074, 2003.

[10]   J. R. T. Rodríguez, “3D face modelling for 2D+3D face recognition,” Ph.D. dissertation, Dept. Electron. Eng., Univ. Surrey, Guildford, U.K., 2007.

[11]   K. Pearson, “On lines and planes of closest fit to systems of points in space,” Philosophical Magazine, vol. 2, no. 11, pp.  559-572, 1901.

[12]   W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B.P. Flanner, “Singular value decomposition,” Solution of Linear Algebraic Equation from Numerical Recipes in C, pp. 59-70, 1992.

[13]   T. P. Minka, “Automatic choice of dimensionality for PCA,” M.I.T Media Laboratory Perceptual Computing Section Technical Report, Cambridge, 2000.

[14]   H. A. Kiers, “Setting up alternating least squares and iterative majorization algorithms for solving various matrix optimization problems,” Computational Statistics and Data Analysis, vol.  41, no. 1, pp. 157-170, 2002.

[15]   C. G. Rafael and E. W. Richard. Digital Image
Processing. Prentice-Hall, Upper Saddle River, NJ,
USA, 3rd edition, 2006.

[16]   M. W. Chao, et al., “A high capacity 3D steganography algorithm,” IEEE Transactions on Visualization and Computer Graphics, vol. 15, no. 2, pp. 274-284, 2009.