Issue No. 06 - June (2008 vol. 30)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2008.50
Zijian Xu , Moody's Corporation, Wall Street Analytics
Hong Chen , Brion Technologies Incorporated
Song-Chun Zhu , University of California, Los Angeles, Los Angeles
Jiebo Luo , Kodak Research Labs, Rochester
We present a hierarchical-compositional face model as a three-layer And-Or graph to account for the structural variabilities over multiple resolutions. In the And-Or graph, an And-node represents a decomposition of certain graphical structure expanding to a set of Or-nodes with associated relations; an Or-node functions as a switch variable pointing to alternative And-nodes. Faces are represented hierarchically: layer one treats each face as a whole; layer two refines the local facial parts jointly as a set of individual templates; layer three divides face into 15 zones and models facial features like eyecorners or wrinkles. Transitions between layers are realized by measuring the minimum-description-length given the face image complexity. Diverse face representations are formed by drawing from hierarchical dictionaries of faces, parts and skin features. A sketch captures the most informative part of a face in a concise and potentially robust representation. However, generating good facial sketches is challenging because of the rich facial details and large structural variations, especially in the high-resolution images. The representing power of our generative model is demostrated by reconstructing high-resolution face images and generating cartoon sketches. Our model is useful for applications such as face recognition, non-photorealisitc rendering, super-esolution, and low-bit rate face coding.
Image Processing and Computer Vision, Hierarchical, Statistical
J. Luo, S. Zhu, Z. Xu and H. Chen, "A Hierarchical Compositional Model for Face Representation and Sketching," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 30, no. , pp. 955-969, 2008.