×

METHOD AND CIRCUIT ARRANGEMENT FOR AUTOMATIC RECOGNITION OF CHARACTERS WITH THE HELP OF A TRANSLATION INVARIANT CLASSIFICATION MATRIX

  • US 3,815,090 A
  • Filed: 09/26/1972
  • Issued: 06/04/1974
  • Est. Priority Date: 09/27/1971
  • Status: Expired due to Term
First Claim
Patent Images

1. A method for the automatic recognition of characters within a class of characters in which the individual characters are substantially identical yet differ from each other with respect to shape, size and position within a raster of a column-by-column scanning area, whereby the scanning signal produced by a scanning process are interpreted as a function of two variables which is transformed by a set of Walsh functions in several steps to result in a translation invariant classification matrix from which an identity of the character to be recognized is derived, comprising the steps of:

  • scanning the scanning area to obtain scanning signal corresponding to the brightness of the character elements in the scanning area;

    one-dimensionally transforming the scanning signals column-bycolumn, according to the columns of the scanning area, with a set of orthogonal Walsh functions which have been extended over phase-shifted sequences in such a way that the result of the transformation of a column of scanning signals with one of the Walsh functions forms one of the elements of a onedimensionally transformed image matrix;

    transforming the elements of the one-dimensionally transformed matrix in the same manner with the transposed set of said Walsh functions to provide a two-dimensionally transformed image matrix;

    reducing the two-dimensionally transformed image matrix by determining the element of maximum value by means of maximum detectors within corresponding partial ranges of the twodimensionally transformed image matrix limited by lines and columns, which are referred to one of the phase-shifted sequences of equal order;

    forming spectrum values of a sequence spectrum by determining absolute values of the elements of the reduced twodimensionally transformed image matrix;

    comparing combinations of spectrum values with stored reference combinations of spectrum values to obtain probabilities of the identity of the character to be recognized; and

    classifying said character in determining the maximum of these probabilities by means of a maximum detector.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×