Component-based face recognition with 3D morphable models

We present a novel approach to pose and illumination invariant face recognition that combines two recent advances in the computer vision field: component-based recognition and 3D morphable models. First, a 3D morphable model is used to generate 3D face models from three input images from each person in the training database. The 3D models are rendered under varying pose and illumination conditions to build a large set of synthetic images. These images axe then used to train a component-based face recognition system. The resulting system achieved 90% accuracy on a database of 1200 real images of six people and significantly outperformed a comparable global face recognition system. The results show the potential of the combination of morphable models and component-based recognition towards pose and illumination invariant face recognition based on only three training images of each subject.