Head pose estimation is an integral component of face recognition systems and human computer interfaces. To determine the head pose, face images with varying pose angles can be considered to lie on a smooth low-dimensional manifold in high-dimensional feature space. In this paper, we propose a novel supervised approach to manifold-based non-linear dimensionality reduction for head pose estimation. The Biased Manifold Embedding method is pivoted on the ideology of using the pose angle information of the face images to compute a biased geodesic distance matrix, before determining the low-dimensional embedding. A Generalized Regression Neural Network (GRNN) is used to learn the non-linear mapping, and linear multi-variate regression is finally applied on the low-dimensional space to obtain the pose angle. We tested this approach on face images of 24 individuals with pose angles varying from -90° to +90° with a granularity of 2°. The results showed significant reduction in the error of pose angle estimation, and robustness to variations in feature spaces, dimensionality of embedding and other parameters.

Original languageEnglish (US)
Title of host publicationVISAPP 2007 - Proceedings of the 2nd International Conference on Computer Vision Theory and Applications
Number of pages7
StatePublished - 2007
Event2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007 - Barcelona, Spain
Duration: Mar 8 2007Mar 11 2007


Other2nd International Conference on Computer Vision Theory and Applications, VISAPP 2007


  • Face modeling and analysis
  • Head pose estimation
  • Manifold learning
  • Non-linear dimensionality reduction
  • Regression analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software


Dive into the research topics of 'Biased manifold embedding for person-independent head pose estimation'. Together they form a unique fingerprint.

Cite this