A new image representation algorithm inspired by image submodality models, redundancy reduction, and learning in biological vision

@article{Balakrishnan2005ANI,
  title={A new image representation algorithm inspired by image submodality models, redundancy reduction, and learning in biological vision},
  author={Nikhil Balakrishnan and Karthik Hariharakrishnan and Dan Schonfeld},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2005},
  volume={27},
  pages={1367-1378}
}
We develop a new biologically motivated algorithm for representing natural images using successive projections into complementary subspaces. An image is first projected into an edge subspace spanned using an ICA basis adapted to natural images which captures the sharp features of an image like edges and curves. The residual image obtained after extraction of the sharp image features is approximated using a mixture of probabilistic principal component analyzers (MPPCA) model. The model is… CONTINUE READING
9 Extracted Citations
20 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 20 references

Color Perception

  • R. Kentridge, C. Heywood, J. Davidoff
  • The Handbook of Brain Theory and Neural Networks…
  • 2003
Highly Influential
4 Excerpts

Contour and Surface Perception

  • H. Neumann, E. Mingolla
  • The Handbook of Brain Theory and Neural Networks…
  • 2003
Highly Influential
5 Excerpts

Gabor Wavelets and Statistical Pattern Recognition

  • J. Daugman
  • The Handbook of Brain Theory and Neural Networks…
  • 2003
Highly Influential
5 Excerpts

Fast ICAMatlabPackage

  • A.Hyvärinen
  • http://www.cis.hut.fi/ projects/ica/fastlab, Apr…
  • 2003
2 Excerpts

Netlab Neural Network Software

  • I. Nabney, C. Bishop
  • http://www.ncrg.aston.ac.uk/netlab, July 2003.
  • 2003
1 Excerpt

Similar Papers

Loading similar papers…