Facial Shape Recovery from a Single Image with an Arbitrary Directional Light Using Linearly Independent Representation

By the assumption that a face image under an arbitrary point light source is a linear combination of three linearly independent random vectors , we propose a novel statistical Shape From Shading (SFS) algorithm which can recover 3-D facial shape irrespective of the illumination direction, unlike most other statistical SFS algorithms. The scaled surface normal vectors , which are the products of albedos and surface normal vectors, can be represented by three linearly independent random vectors if we assume that human face is Lambertian. Thanks to this linearly independent representation, 3-D facial shape reconstruction can be accomplished by a few matrix multiplication under an arbitrary point light source. The experimental results show that the proposed algorithm shows good performance under various light conditions at low computational cost.

[1]  David J. Kriegman,et al.  The Bas-Relief Ambiguity , 2004, International Journal of Computer Vision.

[2]  Ping-Sing Tsai,et al.  Shape from Shading: A Survey , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Demetri Terzopoulos,et al.  Multilinear subspace analysis of image ensembles , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[4]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[5]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Edwin R. Hancock,et al.  A Coupled Statistical Model for Face Shape Recovery From Brightness Images , 2007, IEEE Transactions on Image Processing.

[7]  Robert J. Woodham,et al.  Photometric method for determining surface orientation from multiple images , 1980 .

[8]  Dimitris N. Metaxas,et al.  Incorporating Illumination Constraints in Deformable Models for Shape from Shading and Light Direction Estimation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Alexander A. Sawchuk,et al.  Adaptive Noise Smoothing Filter for Images with Signal-Dependent Noise , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Edwin R. Hancock,et al.  Recovering Facial Shape Using a Statistical Model of Surface Normal Direction , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Sungsoo Park,et al.  The POSTECH face database (PF07) and performance evaluation , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[12]  Paul A. Griffin,et al.  Statistical Approach to Shape from Shading: Reconstruction of Three-Dimensional Face Surfaces from Single Two-Dimensional Images , 1996, Neural Computation.

[13]  Rama Chellappa,et al.  A Method for Enforcing Integrability in Shape from Shading Algorithms , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Ira Kemelmacher-Shlizerman,et al.  Molding Face Shapes by Example , 2006, ECCV.

[15]  Rama Chellappa,et al.  Robust Estimation of Albedo for Illumination-invariant Matching and Shape Recovery , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[16]  Ran He,et al.  Face shape recovery from a single image using CCA mapping between tensor spaces , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Josef Kittler,et al.  Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.