Abstract
We propose a new machine learning paradigm called Multilayer Graph Transformer Network that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as input and produce graphs as output. A complete check reading system based on this concept is described. The system combines convolutional neural network character recognizers with graph-based stochastic models trained cooperatively at the document level. It is deployed commercially and reads million of business and personal checks per month with record accuracy.
Original language | English (US) |
---|---|
Pages (from-to) | 151-154 |
Number of pages | 4 |
Journal | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
Volume | 1 |
State | Published - 1997 |
Event | Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger Duration: Apr 21 1997 → Apr 24 1997 |
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering