Semi-automatic Face Image Finding Method, Which Uses the 3D Model of the Head for Recognising an Unknown Face

Olga Krutikova, Aleksandrs Glazs


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.


3D model; face recognition; insufficient training set; polygonal model

Full Text:



T. Kim, J. Kittler, “Locally linear discriminant analysis for multimodally distributed classes for face recognition”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, Issue 3, 2005, pp. 318–327.

R. Brunelli and T. Poggio, “Face recognition: features versus templates”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no 10, 1993, pp. 1042–1052.

Y. Li, S. Gong, H. Liddell, “Support vector regression and classification based multiview face detection and recognition”, Int. Conf. on Face and Gesture Recognition, 2000, pp. 300–305.

T. Vetter, V. Blanz, “A morphable model for the synthesis of 3D faces”, Proc. SIGGRAPH ’99 Proc. of the 26th annual conf. on Computer graphics and interactive techniques’, 1999, pp. 187–194.

V. Blanz, S. Romdhani, T. Vetter, “Face identification across different poses and illumination with a 3D morphable model”, Int. Conf. on Automatic Face and Gesture Recognition, 2002, pp. 202–207.

I. Kemelmacher-Shlizerman and R. Basri, “3d face reconstruction from a single image using a single reference face shape,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 2, 2011, pp. 394–405.

B. Horn and M. Brooks, “The variational approach to shape from shading,” Computer Vision, Graphics, and Image Processing, vol. 33, no. 2, 1986, pp. 174–208.

J. Huang, B. Heisele, and V. Blanz, “Component-based face recognition with 3d morphable models,” in Audio-and Video-Based Biometric Person Authentication. Springer, 2003, pp. 1055–1055.

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

Y. Taigman and L. Wolf, “Leveraging billions of faces to overcome performance barriers in unconstrained face recognition,” Arxiv preprint arXiv, 2011, pp. 1108–1122.

L. Wolf, T. Hassner, and Y. Taigman, “Effective unconstrained face recognition by combining multiple descriptors and learned background statistics,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 10, 2011 pp. 1978–1990.

G. Huang, M. Mattar, T. Berg, E. Learned-Miller et al., “Labeled faces in the wild: A database for studying face recognition in unconstrained environments,” 2008.

O. Krutikova, A. Glazs, “Development of a New Method for Adapting a 3D Model from a Minimum Number of 2D Images”, Technologies of Computer Control, 2013, vol. 14, pp. 12–17.

O. Krutikova, A. Glazs, “Semi-automatic method of face recognition based on extended training set”, in Proc. of Int. Conf. Biomedical Engineering, Lithuania, Kaunas, 2014, pp. 148–152.

O. Krutikova, A. Glazs, “Increasing the training set in face recognition tasks by using a 3D model of a face”, RTU Zinātniskie raksti Datorvadības tehnoloģijas, vol. 15, 2014, pp. 14–19.

DOI: 10.7250/tcc.2015.001


  • There are currently no refbacks.