The Community for Technology Leaders
Green Image
Issue No. 06 - June (2008 vol. 30)
ISSN: 0162-8828
pp: 955-969
Jiebo Luo , Kodak Research Labs, Rochester
Song-Chun Zhu , University of California, Los Angeles, Los Angeles
Zijian Xu , Moody's Corporation, Wall Street Analytics
Hong Chen , Brion Technologies Incorporated
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
Jiebo Luo, Song-Chun Zhu, Zijian Xu, Hong Chen, "A Hierarchical Compositional Model for Face Representation and Sketching", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 30, no. , pp. 955-969, June 2008, doi:10.1109/TPAMI.2008.50
101 ms
(Ver 3.3 (11022016))