An Analog-Digital Character Recognition System

The importance of solving the measurement problem in character recognition systems before or collaterally with the decision problem is stressed. Measurements themselves are decision processes. In the system discussed here the measurements constitute decisions on the probable presence and most likely orientation of the edges of the character strokes in each elementary scanning area. This permits an effective and economical sequential feature detection in which the statistical variations due to printing and scanning variations are taken into account. The article concludes with a discussion of the role of the computer in recognition-logic design.

[1]  Norman M. Abramson,et al.  Learning to recognize patterns in a random environment , 1962, IRE Trans. Inf. Theory.

[2]  Worthie Doyle,et al.  Recognition of sloppy, hand-printed characters , 1960, IRE-AIEE-ACM '60 (Western).

[3]  J. S. Bomba,et al.  Alpha-numeric character recognition using local operations , 1959, IRE-AIEE-ACM '59 (Eastern).

[4]  D H HUBEL,et al.  THE VISUAL CORTEX OF THE BRAIN. , 1963, Scientific American.

[5]  W. W. Bledsoe,et al.  Discussion of problems in pattern recognition , 1959, IRE-AIEE-ACM '59 (Eastern).

[6]  I. W. Merry,et al.  Character Quality and Scanner Organization , 1961, Comput. J..

[7]  Donald B. Brick,et al.  Bayes' optimum filters derived using Wiener canonical forms , 1962, IRE Trans. Inf. Theory.