ML Anthology

LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition

Yoshua Bengio, Yann LeCun, Craig R. Nohl, Christopher J. C. Burges
NeCo 1995 pp. 1289-1303
doi:10.1162/NECO.1995.7.6.1289 /neco/1995/bengio1995neco-lerec/

Abstract

We introduce a new approach for on-line recognition of handwritten words written in unconstrained mixed style. The preprocessor performs a word-level normalization by fitting a model of the word structure using the EM algorithm. Words are then coded into low resolution "annotated images" where each pixel contains information about trajectory direction and curvature. The recognizer is a convolution network that can be spatially replicated. From the network output, a hidden Markov model produces word scores. The entire system is globally trained to minimize word-level errors.

PDF NeCo Semantic Scholar

Cite

Text

Bengio et al. "LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition." Neural Computation, 1995. doi:10.1162/NECO.1995.7.6.1289

Markdown

[Bengio et al. "LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition." Neural Computation, 1995.](https://mlanthology.org/neco/1995/bengio1995neco-lerec/) doi:10.1162/NECO.1995.7.6.1289

BibTeX

@article{bengio1995neco-lerec,
  title     = {{LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition}},
  author    = {Bengio, Yoshua and LeCun, Yann and Nohl, Craig R. and Burges, Christopher J. C.},
  journal   = {Neural Computation},
  year      = {1995},
  pages     = {1289-1303},
  doi       = {10.1162/NECO.1995.7.6.1289},
  volume    = {7},
  url       = {https://mlanthology.org/neco/1995/bengio1995neco-lerec/}
}