A Study of Two Image Representations for Head Pose Estimation

Traditional appearance-based head pose estimation methods use the holistic face appearance as the input and then employ subspace analysis methods to extract low-dimensional features for classification. However, the face appearance may be more related to the unique identity of an individual rather than head poses. In this paper, we presented a comparative study of two image representations which aim to specifically describe head pose variations. The histogram of oriented gradient (HOG) based method relies on the gradient orientation distribution. The GaFour method exploits asymmetry in the intensities of each row of the face image, using a Gabor filter and Fourier transform to represent the face images. We compare the two image representations combined with two linear subspace methods (PCA and LDA). Experiments on two public face databases (CMU-PIE and CAS-PEAL) show that both HOG+LDA and GaFour+LDA give good results and HOG+LDA provides the best performance with a lower feature dimension.