CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2012 vol.34 Issue No.12 - Dec.
Gender and Ethnicity Specific Generic Elastic Models from a Single 2D Image for Novel 2D Pose Face Synthesis and Recognition
Issue No.12 - Dec. (2012 vol.34)
Jingu Heo , Samsung Adv. Inst. of Technol., Yongin, South Korea
M. Savvides , Cylab Biometrics Center, Carnegie Mellon Univ., Pittsburgh, PA, USA
In this paper, we propose a novel method for generating a realistic 3D human face from a single 2D face image for the purpose of synthesizing new 2D face images at arbitrary poses using gender and ethnicity specific models. We employ the Generic Elastic Model (GEM) approach, which elastically deforms a generic 3D depth-map based on the sparse observations of an input face image in order to estimate the depth of the face image. Particularly, we show that Gender and Ethnicity specific GEMs (GE-GEMs) can approximate the 3D shape of the input face image more accurately, achieving a better generalization of 3D face modeling and reconstruction compared to the original GEM approach. We qualitatively validate our method using publicly available databases by showing each reconstructed 3D shape generated from a single image and new synthesized poses of the same person at arbitrary angles. For quantitative comparisons, we compare our synthesized results against 3D scanned data and also perform face recognition using synthesized images generated from a single enrollment frontal image. We obtain promising results for handling pose and expression changes based on the proposed method.
Three dimensional displays, Face recognition, Solid modeling, Shape analysis, Image reconstruction, Computational modeling, Principal component analysis, Cultural differences, face recognition, Generic elastic models, gender and ethnicity specific models, face synthesis
Jingu Heo, M. Savvides, "Gender and Ethnicity Specific Generic Elastic Models from a Single 2D Image for Novel 2D Pose Face Synthesis and Recognition", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.34, no. 12, pp. 2341-2350, Dec. 2012, doi:10.1109/TPAMI.2011.275