Graph-based transformation manifolds for invariant pattern recognition with kernel methods

  • Authors:

  • Alexei Pozdnoukhov;Samy Bengio

  • Affiliations:

  • Swiss Federal Institute of Technology Martigny, CH-1920, Switzerland;Swiss Federal Institute of Technology Martigny, CH-1920, Switzerland

  • Venue:
  • ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present here an approach for applying the technique of modeling data transformation manifolds for invariant learning with kernel methods. The approach is based on building a kernel function on the graph modeling the invariant manifold. It provides a way for taking into account nearly arbitrary transformations of the input samples. The approach is verified experimentally on the task of optical character recognition, providing state-of-the-art performance on harder problem settings.