Global training of document processing systems using graph transformer networks
- 22 November 2002
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 489-494
- https://doi.org/10.1109/cvpr.1997.609370
Abstract
We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradient-based learning algorithms to systems composed of modules that take graphs as inputs and produce graphs as output. Training is performed by computing gradients of a global objective function with respect to all the parameters in the system using a kind of back-propagation procedure.A complete check reading system based on these concepts is described. The system uses convolutional neural network character recognizers, combined with global training techniques to provide record accuracy on business and personal checks. It is presently deployed commercially and reads million of checks per month.Keywords
This publication has 5 references indexed in Scilit:
- LeRec: A NN/HMM Hybrid for On-Line Handwriting RecognitionNeural Computation, 1995
- Weighted rational transductions and their application to human language processingPublished by Association for Computational Linguistics (ACL) ,1994
- Original approach for the localisation of objects in imagesIEE Proceedings - Vision, Image, and Signal Processing, 1994
- Integrating time alignment and neural networks for high performance continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989