Graph Embedded Analysis for Head Pose Estimation

Abstract

Head pose is an important vision cue for scene interpretation and human computer interaction. To determine the head pose, one may consider the low-dimensional manifold structure of the face view points in image space. In this paper, we present an appearance-based strategy for head pose estimation using supervised graph embedding (GE) analysis. Thinking globally and fitting locally, we first construct the neighborhood weighted graph in the sense of supervised LLE. The unified projection is calculated in a closed-form solution based on the GE linearization. We then project new data (face view images) into the embedded low-dimensional subspace with the identical projection. The head pose is finally estimated by the K-nearest neighbor classification. We test the proposed method on 18,100 USF face view images. Experimental results show that, even using a very small training set (e.g. 10 subjects), GE achieves higher head pose estimation accuracy with more efficient dimensionality reduction than the existing methods.