Robust head pose estimation via semi-supervised manifold learning with ℓ1-graph regularization

Abstract

In this paper, a new ℓ1-graph regularized semi-supervised manifold learning (LRSML) method is proposed for robust human head pose estimation problem. The manifold is constructed under Biased Manifold Embedding (BME) framework which computes a biased neighborhood of each point in the feature space with ℓ1-graph regularization. The construction process of ℓ1-graph is assumed to be unsupervised without harnessing any data label information and uncovers the underlying ℓ1-norm driven sparse reconstruction relationship of each sample. The LRSML is more robust to noises and has the potential to convey more discriminative information compared to conventional manifold learning methods. Furthermore, utilizing both labeled and unlabeled information improve the pose estimation accuracy and generalization capability. Numerous experiments show the superiority of our method over several current state of the art methods on publicly available dataset.