Fast 3D Human Face Modeling Method Based on Multiple View 2D Images

Abstract:

This paper presents a novel approach to model 3D human face from multiple view 2D images in a fast mode. Our proposed method mainly includes three steps: 1) Face Recognition from 2D images, 2) Converting 2D images to 3D images, 3) Modeling 3D human face. To extract visual features of both 2D and 3D images, visual features adopted in 3D are described by Point Signature, and visual features utilized in 2D is represented by Gabor filter responses. Afterwards, 3D model is obtained by combining multiple view 2D images through calculating projections vector and translation vector. Experimental results show that our method can model 3D human face with high accuracy and efficiency.

• Periodical: Applied Mechanics and Materials (Volume 273)
• Pages: 796-799
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.273.796
• Online since: January 2013
• Authors: Yong Sheng Wang
• Keywords: 2D Image, 3D Modeling, Multiple View, Visual Feature

References

[1] Hassner, T. and Basri, R., Example based 3D reconstruction from single 2D images. IEEE Conference on Computer Vision and Pattern Recognition Workshop, (2006).

DOI: 10.1109/cvprw.2006.76

[2] Han, F. and Zhu, S.C., Bayesian reconstruction of 3d shapes and scenes from a single image. IEEE International Workshop on Higher-Level Knowledge in 3D Modeling and Motion Analysis, 2003, pp.12-20.

DOI: 10.1109/hlk.2003.1240854

[3] Amin, S.H. and Gillies, D., Analysis of 3D face reconstruction. IEEE 14th International Conference on Image Analysis and Processing, 2007, pp.413-418.

DOI: 10.1109/iciap.2007.4362813

[4] M. Fanany, I. Kumazawa, and M. Ohno. Face reconstruction from shading using smooth projected polygon representation nn. Proceedings of the 15th International Conference on Vision Interface, 2002, pp.308-313.

DOI: 10.1109/icip.2002.1039948

[5] D. Samaras, S. Wang, and L. Zhang. Face reconstruction across different poses and arbitrary illumination conditions. AVBPA, LNCS, 2005, pp.91-101.

DOI: 10.1007/11527923_10

[6] J. Lee, R. Machiraju, B. Moghaddam, and H. Pfister. Silhouette-based 3d face shape recovery. In Proceedings of Graphics Interface, 2003, pp.11-13.

[7] Mislav Grgic, Kresimir Delac, Sonja Grgic, SCface - surveillance cameras face database, Multimedia Tools and Applications, Vol. 51, No. 3, February 2011, pp.863-879.

DOI: 10.1007/s11042-009-0417-2

[8] Chung, K.C., Kee, S.C., Kim, S.R., 1999. Face recognition using principle component analysis of Gabor filter responses. In: Internat. Workshop on Recognition Analysis and Tracking of Faces and Gestures in Real-Time System, pp.53-57.

DOI: 10.1109/ratfg.1999.799223

[9] V. Blanz, P. Grother , P. Phillips , and T. Vetter, Face recognition based on frontal views generated from non-frontal images. In Proc. IEEE CVPR, Washington, DC, USA, 2005, pp.454-461.

DOI: 10.1109/cvpr.2005.150

[10] D. Jiang, Y. Hu , S. Yan , L. Zhang , H. Zhang , and W. Gao, Efficient 3D reconstruction for face recognition, Pattern Recognition, 2005, 38(6), pp.787-798.

DOI: 10.1016/j.patcog.2004.11.004

[11] X. Lu, R. Hsu , A. Jain , B. Kamgar-parsi , and B. Kamgar-parsi, Face recognition with 3D model-based synthesis. In Proc. ICBA, Hong Kong, (2004).

DOI: 10.1007/978-3-540-25948-0_20

[12] X. Zhang and Y. Gao, Face recognition across pose: A review. Pattern Recognition, 2009, 42(11), pp.2876-2896.

DOI: 10.1016/j.patcog.2009.04.017