International Business Machines Corporation

Ellen Willis Bollinger

Walter S Rosenbaum

John Joseph Hilliard

Allen Harold Ett

Jean Marie Ciconte

Anne Marie Chaires

Donald Francis Kocher

A cluster storage apparatus is disclosed for outputting groups of valid alpha words as potential candidates for the correct form of an alpha word misrecognized by a character recognition machine. Groups of alpha words are arranged in the cluster storage apparatus such that adjacent locations contain alpha words having similar character recognition misread propensities. Alpha words which have been determined to be misrecognized, are input to the cluster storage apparatus. Numerical values assigned to the characters of which the input word is composed, are used to calculate the address of that group of valid alpha words having similar character recognition misread propensities. The cluster storage apparatus then outputs the accessed groups of alpha words for subsequent processing. The organization of the cluster storage apparatus minimizes the difference in address between alpha words with similar character recognition misread propensities by assigning high numeric values to highly reliable characters, as determined by measuring the character transfer function of the character recognition machine.

Cluster storage apparatus for post processing error correction of a

A data processing system is disclosed for selecting the correct form of a garbled input word misread by an optical character reader so as to change the number of characters in the word by character splitting or concatenation. Dictionary words are stored in the system, having characters which are flagged for segmentation or concatenation OCR misread propensity. The OCR word and a dictionary word are loaded into a pair of associated shift registers, aligning their letters on one end. The dictionary word characters are inspected for error propensity flags. When a splitting propensity, for example, is found for a character, special conductional probability values are accessed from a storage and a calculation is performed of the probability that the first character of the dictionary word was split by the OCR into the first and second characters of the OCR word. This regional context probability is compared with the probability of a simple substitution error for the characters. If the probability of segmentation is larger, the OCR characters in the first shift register are shifted one space with respect to the dictionary word characters in the second shift register so that subsequent character pairs to be compared are properly matched. The greater calculated probability is combined in a running product. The dictionary word with the largest running product is output by the system as the most likely correct form of the garbled OCR input word. In addition to optical character recognition, the system disclosed may be applied to correcting segmentation errors in phoneme-characters output from a speech analyzer. In addition to optical character recognition, the system disclosed may be applied to correcting character substitutions, transpositions, additions, and omissions inadvertently typed on a keyboard.

Regional context maximum likelihood error correction for OCR, keyboard,

Growing community of inventors

Poughkeepsie, NY, United States of America

Ellen Willis Bollinger