Off-line Handwriting Recognition by Recurrent Error Propagation Networks
Recent years have seen an upsurge of interest in computer handwriting recognition as a means of making computers accessible to a wider range of people. A complete system for off-line, automatic recognition of handwriting is described, which takes word images scanned from a handwritten page and produces word-level output. Normalisation and preprocessing methods are described and details of the recurrent error propagation network and Viterbi decoder used for recognition are given. Results are reported and compared with those presented by researchers using other methods.
KeywordsRecognition Rate Speech Recognition Handwriting Recognition Viterbi Decoder Cursive Script
Unable to display preview. Download preview PDF.
- E.R. Davies. Machine Vision: theory algorithms, practicalities. Micro electrics and signal processing Number 9. London Academic, 1990.Google Scholar
- D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning internal representations by error propagation. In D.E. Rumelhart and J.L. McClelland, editors, Parallel Distributed Processing: Explorations in the Microstructure of Cognition ,volume 1, chapter 8, pages 318–362. Bradford Books, 1986.Google Scholar
- Barak A. Pearlmutter. Dynamic recurrent neural networks. Technical Report CMU-CS-88-191, CMU, School of Computer Science, Pittsburgh, PA15213, December 1990.Google Scholar
- John S. Bridle. Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition. Neu rocomputing ,F 68:227–236, 1990.Google Scholar
- Robert A. Jacobs. Increased rates of convergence through learning rate adaptation. Neural Networks, 1:295–307, 1988.Google Scholar
- A.J. Robinson and F. Fallside. Phoneme recognition from the TIMIT database using recurrent error propagation networks. Technical Report TR 42, Cambridge University Engineering Department, Cambridge, UK., March 1990.Google Scholar
- H.F. Silverman and D.P. Morgan. The application of dynamic programming to connected speech recognition. IEEE ASSP Magazine ,pages 6–25, July 1990.Google Scholar
- Stig Johansson, Roger Garside, Knut Hofland, and Geoffrey Leech. The tagged LOB corpus vertical/horizontal version. Technical report, Norwegian Computing Centre for The Humanities, 1986.Google Scholar