Method and apparatus for character recognition based upon the frequency of occurrence of characters.

摘要

The invention relates to a method of processing data for recognising unknown characters of a known character set based in part upon the frequency of occurrence of said characters and to apparatus for performing the method. The method comprises the steps of scanning the unknown characters and generating image data representing the unknown characters, storing the generated image data, and applying to the stored image data discriminating tests for recognition purposes.
<??>The method is characterised by the steps of applying to the stored image data a first set of discriminatory tests for identifying whether the image data represents a first group of characters and for recognising the image data that represents characters of the first group of characters. The characters of the first group have a relatively high frequency of occurrence and the first group contains less than all of the characters of the character set. The method also includes subsequently applying to the unrecognised image data a second set of discriminatory tests for identifying whether the unrecognised image data represents a second group of characters and for recognising the image data that represents characters of the second group of characters. The characters of the second group have a lower frequency of occurrence than the characters of the first group and the second group contains at least some characters not in the first group of characters.
<??>The method may also include the step of sequentially applying to any unrecognised data from the application of the second set of discriminatory tests at least one additional set of discriminatory tests. Each additional set of discriminatory tests is for identifying the unrecognized image data that represents a respective additional group of characters and for recognizing the image data that represents characters of the respective additional group of characters. The characters of each additional group of characters have a lower frequency of occurrence than the characters of the preceding group of characters.