LeRec: a NN/HMM hybrid for on-line handwriting recognition.

Y. Bengio, Y. LeCun, C. Nohl, C. Burges

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish (US)
Pages (from-to)1289-1303
Number of pages15
JournalNeural computation
Issue number6
StatePublished - Nov 1995

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience


Dive into the research topics of 'LeRec: a NN/HMM hybrid for on-line handwriting recognition.'. Together they form a unique fingerprint.

Cite this