Multi-Digit Recognition Using a Space Displacement Neural Network

  title={Multi-Digit Recognition Using a Space Displacement Neural Network},
  author={Ofer Matan and Christopher J. C. Burges and Yann LeCun and John S. Denker},
We present a feed-forward network architecture for recognizing an unconstrained handwritten multi-digit string. This is an extension of previous work on recognizing isolated digits. In this architecture a single digit recognizer is replicated over the input. The output layer of the network is coupled to a Viterbi alignment module that chooses the best interpretation of the input. Training errors are propagated through the Viterbi module. The novelty in this procedure is that segmentation is… CONTINUE READING
Highly Cited
This paper has 153 citations. REVIEW CITATIONS
84 Citations
8 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 84 extracted citations

153 Citations

Citations per Year
Semantic Scholar estimates that this publication has 153 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-8 of 8 references

ReadingHandwritten Digits : A ZIP Code Recognition System

  • O. Matan, J. Bromley, +6 authors T. Thompson
  • 1992
1 Excerpt

Connectionist Viterbi Training : A New Hybrid Method For Continuous Speech Recognition

  • M. Franzini, K. F. Lee, A. Waibel
  • In ProceedingsICASSP
  • 1990

Handwritten Zip Code

  • W. Hubbard, L. D. Jackel, H. S. Baird
  • 1990

Handwritten Zip CodeRecognition with Multilayer Networks

  • O. Matan, B. Boser, +5 authors H. S. Baird
  • Proceedings of the 10 th Internationalconference…
  • 1990

Probabilistic Interpretation of Feedforward Classi cation

  • J. S. Bridle
  • 1989
2 Excerpts

Probabilistic Interpretation of Feedforward Classification Network Outputs with Relationships to Statistical Pattern Recognition

  • J. S. Bridle
  • 1989
1 Excerpt

Similar Papers

Loading similar papers…