3D and Infrared Face Reconstruction from RGB data using Canonical Correlation Analysis

M. Reiter, R. Donner, G. Langs, H. Bischof
2006 18th International Conference on Pattern Recognition (ICPR'06)  
In this paper, we apply a multiple regression method based on Canonical Correlation Analysis (CCA) to face data modelling. CCA is a factor analysis method which exploits the correlation between two high dimensional signals. We first use CCA to perform 3D face reconstruction and in a separate application we predict near-infrared (NIR) face texture. In both cases, the input data are color (RGB) face images. Experiments show, that due to the correlation between input and output signal, only a
more » ... signal, only a small number of canonical factors are needed to describe the functional relation of RGB images to the respective output (NIR images and 3D depth maps) with reasonable accuracy.
doi:10.1109/icpr.2006.24 dblp:conf/icpr/ReiterDLB06 fatcat:wyfmndxa2fbglpxqu3fwztshry