Expression-Insensitive 3D Face Recognition using Sparse Representation

We present a face recognition method based on sparse representation for recognizing 3D face meshes under ex-pressions using low-level geometric features. First, to en-able the application of the sparse representation frame-work, we develop a uniform remeshing scheme to establish a consistent sampling pattern across 3D faces. To handle facial expressions, we design a feature pooling and rank-ing scheme to collect various types of low-level geometric features and rank them according to their sensitivities to facial expressions. By simply applying the sparse repre-sentation framework to the collected low-level features, our proposed method already achieves satisfactory recognition rates, which demonstrates the efficacy of the framework for 3D face recognition. To further improve results in the pres-ence of severe facial expressions, we show that by choos-ing higher-ranked, i.e., expression-insensitive, features, the recognition rates approach those for neutral faces, without requiring an extensive set of reference faces for each indi-vidual to cover possible variations caused by expressions as proposed in previous work. We apply our face recogni-tion method to the GavabDB and FRGC 2.0 databases and demonstrate encouraging results. 1