Abstract

A new technique for real-time optical character recognition that uses a joint transform correlator is proposed. This technique employs feature-extracted patterns for the reference image to detect a wide range of characters in one step. The proposed technique significantly enhances the processing speed when compared with the presently available joint transform correlator architectures and shows feasibility for multichannel joint transform correlation.

© 1995 Optical Society of America

Joint wavelet-transform correlator for image feature extraction

Wenlu Wang, Guofan Jin, Yingbai Yan, and Minxian Wu
Appl. Opt. 34(2) 370-376 (1995)

Improved feature extraction by use of a joint wavelet transform correlator

Boon Yi Soon, Mohammad S. Alam, and Mohammad A. Karim
Appl. Opt. 37(5) 821-827 (1998)

Fringe-adjusted joint transform correlation

Mohammad S. Alam and Mohammad A. Karim
Appl. Opt. 32(23) 4344-4350 (1993)

Preprocessed multiobject joint transform correlator

M. S. Alam, O. Perez, and M. A. Karim
Appl. Opt. 32(17) 3102-3107 (1993)

Reference phase-encoded fringe-adjusted joint transform correlation

Abdallah K. Cherri and Mohammad S. Alam
Appl. Opt. 40(8) 1216-1225 (2001)