Investigation into face pose distributions

Shaogang Gong, Stephen McKenna, John J. Collins

Research output: Contribution to conferencePaper

57 Citations (Scopus)

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.

Original languageEnglish
Pages265-270
Number of pages6
DOIs
Publication statusPublished - 1 Dec 1996
EventProceedings of the 1996 2nd International Conference on Automatic Face and Gesture Recognition - Killington, VT, USA
Duration: 14 Oct 199616 Oct 1996

Conference

ConferenceProceedings of the 1996 2nd International Conference on Automatic Face and Gesture Recognition
CityKillington, VT, USA
Period14/10/9616/10/96

Keywords

  • Principal component analysis
  • Face detection
  • Face recognition
  • Robustness
  • Wavelet transforms
  • Solid modeling
  • Eyes
  • Lighting
  • Machine vision
  • Laboratories

Fingerprint Dive into the research topics of 'Investigation into face pose distributions'. Together they form a unique fingerprint.

  • Cite this

    Gong, S., McKenna, S., & Collins, J. J. (1996). Investigation into face pose distributions. 265-270. Paper presented at Proceedings of the 1996 2nd International Conference on Automatic Face and Gesture Recognition, Killington, VT, USA, . https://doi.org/10.1109/AFGR.1996.557275