1 November 1995 Feature-based neural wavelet optical character recognition system
Author Affiliations +
Optical Engineering, 34(11), (1995). doi:10.1117/12.213654
Abstract
A hybrid character recognition system that uses a feature-extraction method is proposed. The features are extracted using a wavelet transform, preclassified using a k-nearest-neighbor-based neural net and subsequently postprocessed using an optical correlator. This feature-based neural wavelet optical architecture is then tested on blurred character images.
Khan M. Iftekharuddin, Terry D. Schechinger, Kanaan Jemili, Mohammad A. Karim, "Feature-based neural wavelet optical character recognition system," Optical Engineering 34(11), (1 November 1995). http://dx.doi.org/10.1117/12.213654
JOURNAL ARTICLE
7 PAGES


SHARE
KEYWORDS
Wavelets

Feature extraction

Optical character recognition

Optical filters

Image filtering

Discrete wavelet transforms

Optical correlators

RELATED CONTENT

Buffer control technique for video coding
Proceedings of SPIE (February 17 1995)
UV/visible camera for the Clementine mission
Proceedings of SPIE (June 02 1995)
Directional complex-wavelet processing
Proceedings of SPIE (December 04 2000)

Back to Top