Journal article
A new approach to hand-written character recognition
Pattern recognition, Vol.25(6), pp.655-666
06/01/1992
DOI: 10.1016/0031-3203(92)90082-T
Abstract
A novel, biologically motivated, computationally efficient approach to the classification of hand-written characters is described. Dystal (DYnamically STable Associative Learning) is an artificial neural network based on features of learning and memory identified in neurobiological research on
Hermissenda crassicornis and rabbit hippocampus. After a single pass through the training set, Dystal correctly classifies 98% of previously unseen hand-written digits. Similar training on hand-printed Kanji characters results in learning to read 40 people's handprinting of 160 characters to 99.8% accuracy (a task analogous to learning the latin characters in 40 different fonts) and reading different people's handprinting with 90% accuracy.
Details
- Title: Subtitle
- A new approach to hand-written character recognition
- Creators
- K.T. Blackwell - Environmental Research Institute of MichiganT.P. Vogl - Environmental Research Institute of MichiganS.D. Hyman - National Institutes of HealthG.S. Barbour - Environmental Research Institute of MichiganD.L. Alkon - Environmental Research Institute of Michigan
- Resource Type
- Journal article
- Publication Details
- Pattern recognition, Vol.25(6), pp.655-666
- DOI
- 10.1016/0031-3203(92)90082-T
- ISSN
- 0031-3203
- eISSN
- 1873-5142
- Publisher
- Elsevier Ltd
- Language
- English
- Date published
- 06/01/1992
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Iowa Neuroscience Institute
- Record Identifier
- 9984446443102771
Metrics
21 Record Views