Memory-based character recognition using a transformation invariant metric

@article{Simard1994MemorybasedCR,
  title={Memory-based character recognition using a transformation invariant metric},
  author={Patrice Y. Simard and Yann LeCun and John S. Denker},
  journal={Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)},
  year={1994},
  volume={2},
  pages={262-267 vol.2}
}
Memory-based classification algorithms such as radial basis functions or K-nearest neighbors often rely on simple distances (Euclidean distance, Hamming distance, etc.), which are rarely meaningful on pattern vectors. More complex better suited distance measures are often expensive and rather ad-hoc. We propose a new distance measure which: 1) can be made locally invariant to any set of transformations of the input; and 2) can be computed efficiently. We tested the method on large handwritten… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 24 CITATIONS

Handwritten character recognition using elastic matching based on a class-dependent deformation model

  • Seiichi Uchida, Hiroaki Sakoe
  • Computer Science
  • Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.
  • 2003
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Learning Data Manifolds with a Cutting Plane Method

VIEW 1 EXCERPT
CITES BACKGROUND

Self-Organizing Maps for Clustering in Document Image Analysis

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

Transformation invariant SOM clustering in Document Image Analysis

VIEW 2 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 11 REFERENCES

On-Line Recognition of Handwritten Symbols

Comparison of classifier methods: a case study in handwritten digit recognition

  • Léon Bottou, Corinna Cortes, +8 authors Vladimir Vapnik
  • Computer Science
  • Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)
  • 1994

An Efficient Method for Learning Invariances in Adaptive classifiers

  • B. 1992a
  • In International Conference on Pattern Recognition,
  • 1992

A Model for Signature Verification

  • E. Kishon, M. Clark, J. Fan
  • Technical Report 11214-91071507TM,
  • 1991

Strategies for efficient incremental nearest neighbor search

VIEW 1 EXCERPT

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

  • S G.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence,
  • 1989