16 June 1983 Hybrid Optical-Digital Image Processing System For Pattern Recognition
Author Affiliations +
Proceedings Volume 0369, Max Born Centenary Conf; (1983); doi: 10.1117/12.934407
Event: The Max Born Centenary Conference, 1982, Edinburgh, United Kingdom
The coherent optical filtering techniques provide a general concept for the classification of patterns. This paper describes the design and testing of a hybrid optical-digital image processing system and the development of methods for a statistical expansion of the correlation signal shape because a simple correlation signal intensity measurement is in most of the applications insufficient. Six different algorithms for correlation signal evaluation are investigated. A feature reduction is achieved by a multivariate analysis. For alpha-numeric patterns modified by binary random noise, rotation, scaling and shearing high classification results have been obtained.
© (1983) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
F. Merkle, T. Lorch, T. Karte, J. Donandt, "Hybrid Optical-Digital Image Processing System For Pattern Recognition", Proc. SPIE 0369, Max Born Centenary Conf, (16 June 1983); doi: 10.1117/12.934407; https://doi.org/10.1117/12.934407

Back to Top