Methods for enhancing neural network handwritten character recognition
- 9 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. i, 695-700
- https://doi.org/10.1109/ijcnn.1991.155265
Abstract
An efficient method for increasing the generalization capacity of neural character recognition is presented. The network uses a biologically inspired architecture for feature extraction and character classification. The numerical methods used are optimized for use on massively parallel array processors. The method for training set construction, when applied to handwritten digit recognition, yielded a writer-independent recognition rate of 92%. The activation strength produced by network recognition is an effective statistical confidence measure of the accuracy of recognition. A method of using the activation strength for reclassification is described which, when applied to handwritten digit recognition, reduced substitutional errors to 2.2%.Keywords
This publication has 7 references indexed in Scilit:
- Analysis of a biologically motivated neural network for character recognitionPublished by Association for Computing Machinery (ACM) ,1991
- Stereoscopic Depth Discrimination in the Visual Cortex: Neurons Ideally Suited as Disparity DetectorsScience, 1990
- Development of feature detectors by self-organizationBiological Cybernetics, 1990
- A neural network approach to character recognitionNeural Networks, 1989
- Complete discrete 2-D Gabor transforms by neural networks for image analysis and compressionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Self-organization in a perceptual networkComputer, 1988
- An application of neural net chips: handwritten digit recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988