Abstract

The essence of character recognition is a comparison between the unknown character and a set of reference patterns. Usually, these reference patterns are all possible characters themselves, the whole alphabet in the case of letter characters. Obviously, N analog measurements are highly redundant, since only K = log₂N binary decisions are enough to identify one out of N characters. Therefore, we devised K reference patterns accordingly. These patterns, called principal components, are found by digital image processing, but used in an optical analog computer. We will explain the concept of principal components, and we will describe experiments with several optical character recognition systems, based on this concept.

© 1979 Optical Society of America

Character Recognition by Incoherent Spatial Filtering

J. D. Armitage and A. W. Lohmann
Appl. Opt. 4(4) 461-467 (1965)

Bipolar incoherent optical pattern recognition by carrier encoding

Alan Furman and David Casasent
Appl. Opt. 18(5) 660-665 (1979)

Optical character recognition by triple correlation

Adolf W. Lohmann
Appl. Opt. 28(2) 200-201 (1989)

Pattern recognition with wavelength-multiplexed filters

S. K. Case
Appl. Opt. 18(12) 1890-1894 (1979)

Storage Capacity of an Optically Formed Spatial Filter for Character Recognition

C. B. Burckhardt
Appl. Opt. 6(8) 1359-1366 (1967)