Abstract In a method for automatic character recognition, character strings marked by word start and word end are formed from the discrete characters calculated with the assistance of a character classifier. These character strings are checked with stored comparison strings of a context lexicon with respect to identity or similarity. The context lexicon is continuously updated by continuous read-in of strings containing no rejection characters, whereby the repeated read-in of identical strings is counted. Current strings are compared to the strings of the context lexicon and that string which is optimum with respect to similarity and frequency is selected for further evaluation. A correction provided with reference to the context comparison is only executed when the substitution transposition is probable based on the classifier characteristic for the characters under consideration.
A method for automatic character recognition, comprising the steps of: acquiring character strings by scanning and automatic character recognizing an image pattern, each character string being marked by a word start and a word end; generating a lexicon by determining which character strings contain no rejection characters and storing and continuously updating the character strings containing no rejection characters, and recording a frequency of occurrence of identical character strings; comparing each of the character strings to be checked, including character strings having rejection and substitution characters, to the stored character strings of the lexicon, and identifying a plurality of identical or optimally similar lexicon character strings corresponding to the character string being checked; selecting a lexicon character string that is optimum with respect to similarity and frequency to the character string being checked; and executing a correction, if necessary, of the character string being checked by comparison to the lexicon character string when a correction is probable for the character string being checked.
Claim 2
Independent Claim
163 words
A method for automatic character recognition, comprising the steps of: acquiring character strings by scanning and automatic character recognizing an image pattern, each character string being marked by a word start and a word end; generating a lexicon by determining which character strings contain no rejection characters and storing and continuously updating the character strings containing no rejection characters, and recording a frequency of occurrence of identical character strings; comparing each of the character strings to be checked, including character strings having rejection and substitution characters, to the stored character strings of the lexicon, and identifying a plurality of identical or optimally similar lexicon character strings corresponding to the character string being checked; selecting a lexicon character string that is optimum with respect to similarity and frequency to the character string being checked; and executing a correction, if necessary, of the character string being checked by comparison to the lexicon character string when a correction is probable for the character string being checked.