A complete set of rotationally and translationally invariant features based on a generalization of the bispectrum to non-commutative groups

Add to your list(s) Download to your calendar using vCal

• Imre Risi Kondor, Columbia University
• Wednesday 14 March 2007, 15:30-16:30
• Small public lecture room, Microsoft Research Ltd, 7 J J Thomson Avenue (Off Madingley Road), Cambridge.

If you have a question about this talk, please contact Oliver Williams.

Deriving translation and rotation invariant representations is a fundamental problem in computer vision with a substantial literature. I propose a new set of features which

a, are simultaneously invariant to translation and rotation; b, are sufficient to reconstruct the original image with no loss (up to a badwidth limit); c, do not involve matching with a template image or any similar discontinuous operation.

The new features are based on Kakarala`s generalization of the bispectrum to compact Lie groups and a projection onto the sphere. I validated the method on a handwritten digit recognition dataset with randomly translated and rotated digits. Paper: http://arxiv.org/abs/cs.CV/0701127

This talk is part of the Microsoft Research Machine Learning and Perception Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Guy Emerson's list
• Interested Talks
• ML
• Machine Learning Summary
• Microsoft Research Cambridge, public talks
• Microsoft Research Machine Learning and Perception Seminars
• Optics for the Cloud
• PMRFPS's
• School of Technology
• Small public lecture room, Microsoft Research Ltd, 7 J J Thomson Avenue (Off Madingley Road), Cambridge
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• personal list
• rp587
• yk373's list

Note that ex-directory lists are not shown.