recognition · Machine learning · LDA · AdaBoost

Abstract We address the problem of automatically detecting a sparse set of 3D mesh vertices, likely to be good candidates for determining correspondences, even on soft organic objects. We focus on 3D face scans, on which sin-gle local shape descriptor responses are known to be weak, sparse or noisy. Our machine-learning approach consists of computing feature vectors containing D different local sur-face descriptors. These vectors are normalized with respect to the learned distribution of those descriptors for some given target shape (landmark) of interest. Then, an optimal func-tion of this vector is extracted that best separates this par-ticular target shape from its surrounding region within the set of training data. We investigate two alternatives for this optimal function: a linear method, namely Linear Discrim-inant Analysis, and a non-linear method, namely AdaBoost. We evaluate our approach by landmarking 3D face scans in the FRGC v2 and Bosphorus 3D face datasets. Our sys-tem achieves state-of-the-art performance while being highly generic