Face recognition using a color tensor framework

Facial images are affected by multiple factors including facial geometries, expressions, viewpoints and illuminations. We apply multi-linear algebra to separate these factors and extract the people factor used for face recognition. Compared to standard PCA and its variants, the method allows for bigger changes in viewpoints and illuminations. Our method is based on the method, adding color information, using (2D)²-PCA for dimensionality reduction and centering face recognition in a color tensor framework. Good results are obtained by doing experiments on Weizman and Facepix database.