基于姿态估计三维人脸形状重建
3D Facial Shape Reconstruction Based on Pose Estimation
DOI: 10.12677/JISP.2015.42003, PDF, HTML, XML, 下载: 3,121  浏览: 10,171  科研立项经费支持
作者: 牛晓霞, 丁玉东：燕山大学信息科学与工程学院，秦皇岛
关键词: 主成分分析；三维模型重建；稀疏模型；人脸姿态估计；径向基函数；PCA； 3D Model Reconstruction； Sparse Model； Face Pose Estimation； Radial Basis Function
摘要: 本文针对重建三维人脸模型对人脸图像姿态要求较高，提出基于单张人脸图像姿态预估计的模型重建算法。首先介绍单张人像的三维姿态估计方法，然后通过建立的人脸形状模型样本库，利用主成分分析(PCA)进行三维人脸稀疏模型的重构，最后利用径向基函数变换得到对应的密集三维人脸形状向量。试验结果表明，算法可重构精确的三维人脸形状模型，对有旋转姿态的人脸图像有很好的重建效果。
Abstract: Aiming at facial pose request in reconstructing 3D face model, a new method to reconstruct 3D face shape model from a single face image is proposed. First, the method of face pose estimation is described in detail. Then, the spare 3D face shape model is reconstructed by principal component analysis (PCA). Finally, the final 3D face shape model is obtained using radius base function. Expe-rimental results show that the proposed method can obtain precise reconstruction model and is more efficient with face image under rotated pose.
文章引用：牛晓霞, 丁玉东. 基于姿态估计三维人脸形状重建[J]. 图像与信号处理, 2015, 4(2): 20-26. http://dx.doi.org/10.12677/JISP.2015.42003

参考文献

[1] Parke, F.I. (1972) Computer generated animation of faces. Proceeding of the ACM National Conference, 1, 451-457.
[2] Rara, H.M., Farag, A.A. and Davis, T. (2011) Model-based 3D shape recovery from single images of unknown pose and illumination using a small number of feature points. IEEE International Joint Conference on Bio-metrics Compendium, Washington DC, 11-13 October 2011, 1-7.
[3] 王国胤, 龚勋, 等 (2009) 基于认知机理的三维人脸建模及应用. 重庆邮电大学学报, 4, 555-560.
[4] Pighin, F., Auslander, J., Lischinski, D., et al. (1997) Realistic facial animation using image-based 3D morphing. Technical Report UW-CSE-97-01-03, University of Washington, Washington DC.
[5] Zhao, W.Y. and Chellappa, R. (2000) SFS based view synthesis for robust face recognition. Proceedings of the FGR 2000, IEEE Computer Society, Washington DC, 285-292.
[6] Chowdhury, A.R., Chellappa, R. and Krishnamurthy, K. (2002) 3D face reconstruction from video using a generic model. 2015 IEEE In-ternational Conference on Multimedia & Expo (ICME), 1, 449-452.
[7] Zhang, R., Tsai, P.S., Cryer, J.E. and Shan, M. (1999) Shape from shading: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21, 690-706
[8] Blanz, V. and Vetter, T. (2003) Face recognition based on fitting a 3D morphable model. IEEE Transac-tions on Pattern Analysis and Machine Intelligence, 25, 1063-1074.
[9] Jiang, D.L., Hu, Y.X., Yan, S.C., et al. (2005) Efficient 3D reconstruction for face recognition. Pattern Recognition, 38, 787-798.
[10] Hu, Y.X., Jiang, D.L., Yan, S.C., Zhang, L. and Zhang, H.J. (2004) Automatic 3D reconstruction for face recognition. 6th IEEE International Conference on Automatic Face and Gesture Recognition, 17-19 May 2004, 843-848.
[11] 柴秀娟, 山世光, 卿来云, 等 (2006) 基于3D人脸重建的光照、姿态不变人脸识别. 软件学报, 3, 525-534.
[12] 王成章, 尹宝才, 等 (2007) 改进的基于形变模型的三维人脸建模方法. 自动化学报, 3, 232-239.
[13] 张志刚, 周明全, 耿国华 (2007) 基于单幅图像的人脸三维姿态估计. 计算机应用, 5, 1138-1140.
[14] Vetter, T. and Poggio, T. (1997) Linear object classes and image synthesis from a single example image. IEEE Transaction on Pattern Analysis and Machine Intelli-gence, 19, 733-742.