Browse by author
Lookup NU author(s): Professor Patrick OlivierORCiD
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
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. © 2009 IEEE.
Author(s): Dong L, Tao L, Xu G, Olivier P
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: Proceedings of the 5th International Conference on Image and Graphics (ICIG)
Year of Conference: 2010
Pages: 963-968
Publisher: IEEE
URL: http://dx.doi.org/10.1109/ICIG.2009.141
DOI: 10.1109/ICIG.2009.141
Library holdings: Search Newcastle University Library for this item
ISBN: 9780769538839
