Independent components of face images : A representation for face recognition

@inproceedings{Bartlett1997IndependentCO,
  title={Independent components of face images : A representation for face recognition},
  author={Marian Stewart Bartlett and Terrence and J.. and Terrence J. Sejnowski},
  year={1997}
}
Methods for obtaining representations of face images based on independent component analysis (ICA) are presented. A global ICA representation is compared to a global representation based on principal component analysis (PCA) for recognizing faces m o s s changes in lighting and changes in pose. For each set of face images, a set of statistically independent source images was found through an unsupervised learning algorithm that maximized the mutual information between the input and the output… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 77 CITATIONS, ESTIMATED 23% COVERAGE

337 Citations

02040'99'03'08'13'18
Citations per Year
Semantic Scholar estimates that this publication has 337 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
SHOWING 1-9 OF 9 REFERENCES

Eigenfaces for Recognition

  • MJ McKeown, S Makeig, +4 authors TJ Sejnowski
  • Analysis of fMRI data by Decomposition into…
  • 1991

Face , gender and emotion recognition using Holons

  • Cottrell Metcalfe
  • Advances in Neuml Information Processing Systems…
  • 1991
1 Excerpt

Unsupervised learning

  • M. Stewart Bartlett, T. Sejnowski
  • Neural Computation
  • 1989

Similar Papers

Loading similar papers…