LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition
- 1 November 1995
- journal article
- research article
- Published by MIT Press in Neural Computation
- Vol. 7 (6) , 1289-1303
- https://doi.org/10.1162/neco.1995.7.6.1289
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.Keywords
This publication has 5 references indexed in Scilit:
- Global optimization of a neural network-hidden Markov model hybridIEEE Transactions on Neural Networks, 1992
- Design of a neural network character recognizer for a touch terminalPattern Recognition, 1991
- The state of the art in online handwriting recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Learning representations by back-propagating errorsNature, 1986