Abstract
We present an off-line cursive word recognition system based completely on neural networks: reading models and models of early visual processing. The first stage (normalization) preprocesses the input image in order to reduce letter position uncertainty; the second stage (feature extraction) is based on the feedforward model of orientation selectivity; the third stage (letter pre-recognition) is based on a convolutional neural network, and the last stage (word recognition) is based on the interactive activation model.
| Original language | English |
|---|---|
| Pages (from-to) | 419-431 |
| Number of pages | 13 |
| Journal | International journal of neural systems |
| Volume | 18 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - 1 Oct 2008 |
| Externally published | Yes |
Keywords
- Convolutional neural networks
- Feedforward model
- Handwriting recognition
- Interactive activation model
- Reading models