An investigation into face pose distributions
- 24 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 265-270
- https://doi.org/10.1109/afgr.1996.557275
Abstract
Visual perception of faces is invariant under many transformations, perhaps the most problematic of which is pose change (face rotating in depth). We use a variation of Gabor wavelet transform (GWT) as a representation framework for investigating face pose measurement. Dimensionality reduction using principal components analysis (PCA) enables pose changes to be visualised as manifolds in low-dimensional subspaces and provides a useful mechanism for investigating these changes. The effectiveness of measuring face pose with GWT representations was examined using PCA. We discuss our experimental results and draw a few preliminary conclusions.Keywords
This publication has 15 references indexed in Scilit:
- Tracking facesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Probabilistic visual learning for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Tracking and Recognition of Face SequencesPublished by Springer Nature ,1995
- Visual learning and recognition of 3-d objects from appearanceInternational Journal of Computer Vision, 1995
- Face recognition: features versus templatesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Learning Invariance from Transformation SequencesNeural Computation, 1991
- Application of the Karhunen-Loeve procedure for the characterization of human facesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Automatic extraction of face-featuresPattern Recognition Letters, 1987
- Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filtersJournal of the Optical Society of America A, 1985
- Computer recognition of human facesPublished by Springer Nature ,1977