ML Anthology

Handwritten Word Recognition Using Contextual Hybrid Radial Basis Function Network/Hidden Markov Models

Bernard Lemarié, Michel Gilloux, Manuel Leroux
NeurIPS 1995 pp. 764-770
/neurips/1995/lemarie1995neurips-handwritten/

Abstract

A hybrid and contextual radial basis function networklhidden Markov model off-line handwritten word recognition system is presented. The task assigned to the radial basis function networks is the estimation of emission probabilities associated to Markov states. The model is contex(cid:173) tual because the estimation of emission probabilities takes into account the left context of the current image segment as represented by its pred(cid:173) ecessor in the sequence. The new system does not outperform the previ(cid:173) ous system without context but acts differently.

PDF NeurIPS Semantic Scholar

Cite

Text

Lemarié et al. "Handwritten Word Recognition Using Contextual Hybrid Radial Basis Function Network/Hidden Markov Models." Neural Information Processing Systems, 1995.

Markdown

[Lemarié et al. "Handwritten Word Recognition Using Contextual Hybrid Radial Basis Function Network/Hidden Markov Models." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/lemarie1995neurips-handwritten/)

BibTeX

@inproceedings{lemarie1995neurips-handwritten,
  title     = {{Handwritten Word Recognition Using Contextual Hybrid Radial Basis Function Network/Hidden Markov Models}},
  author    = {Lemarié, Bernard and Gilloux, Michel and Leroux, Manuel},
  booktitle = {Neural Information Processing Systems},
  year      = {1995},
  pages     = {764-770},
  url       = {https://mlanthology.org/neurips/1995/lemarie1995neurips-handwritten/}
}