An investigation into face pose distributions

摘要: Visual perception of faces is invariant under many transformations, perhaps the most problematic which pose change (face rotating in depth). We use a variation Gabor wavelet transform (GWT) as representation framework for investigating face measurement. Dimensionality reduction using principal components analysis (PCA) enables changes to be visualised manifolds low-dimensional subspaces and provides useful mechanism these changes. The effectiveness measuring with GWT representations was examined PCA. discuss our experimental results draw few preliminary conclusions.