An And-Or Graph Model for Face Representation, Sketching and Aging

For face modeling, an And-Or graph model was first proposed in [9] as a compositional representation for high resolution face images. In an And-Or graph, the And nodes represent coarse-to-fine decompositions and the Or-nodes represent alternative components for diversity. The And-Or graph face model, as Fig.1 illustrates, has three levels: the first level describes the general appearance of global face and hair; the second level refines the representation of the facial components (eyes, eye brows, nose, mouth) by modeling the variations of their shapes and subtle appearance; and the third level provides further details of the face components and divides the face skin into 9 zones where the wrinkles and speckles are represented. The And-Or graph provides a expressive model for face diversity and details, and thus is found to be especially efficient for applications in face sketching generation and face aging simulation.

[1]  Alan L. Yuille,et al.  Feature extraction from faces using deformable templates , 2004, International Journal of Computer Vision.

[2]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[3]  Song-Chun Zhu,et al.  A Multi-Resolution Dynamic Model for Face Aging Simulation , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[5]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[6]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Constrained Active Appearance Models , 2001, ICCV.

[8]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[9]  Hong Chen,et al.  A high resolution grammatical model for face representation and sketching , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Jongsun Kim,et al.  Effective representation using ICA for face recognition robust to local distortion and partial occlusion , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Nong Sang,et al.  An Automatic Portrait System Based on And-Or Graph Representation , 2007, EMMCVPR.