公开(公告)号：DE2630430A1

公开(公告)日：1977-01-20

申请号：DE2630430

申请日：1976-07-07

Applicant: IBM

Inventor： ROSENBAUM WALTER STEVEN

IPC: B41J5/30 ,  B41B27/36 ,  G06F3/12 ,  G06F7/00 ,  G06F40/191 ,  G06K15/06 ,  G09G5/36

公开(公告)号：DE2630304A1

公开(公告)日：1977-01-20

申请号：DE2630304

申请日：1976-07-06

Applicant: IBM

Inventor： ROSENBAUM WALTER STEVEN

IPC: G06F7/00 ,  G06F9/06 ,  G06F11/28 ,  G06F17/22 ,  G06F17/30 ,  G06K9/72 ,  G10L15/00 ,  G06K9/00 ,  G06F11/00

Abstract: A digital reference matrix apparatus is disclosed for verifying input alpha words from a keyboard, character recognition machine, or voice analyzer as valid linguistic expressions. The organization of the digital reference matrix is based upon the character transfer function of the input apparatus. The digital reference matrix contains a vector representation for each dictionary word in the form of a calculated vector magnitude and unique vector angle. The set of magnitudes and angles is stored in the digital reference matrix using a form of run length coding by storing a single magnitude pointer followed by the chain of unique angles for words having the same magnitude. The vector magnitude so calculated constitutes the address data for accessing the digital reference matrix. When an input word is received for verification, the word's magnitude and angle attributes are calculated and the digital reference matrix is accessed at the magnitude of the input word and the corresponding angles are searched for a match. An output signal is generated indicating whether or not the input word is valid. The organization of the digital reference matrix minimizes the size of the array needed for accurate word verification representation through the use of the combination of digital angle representation and run length compaction of the magnitude/angle verification syntax.

公开(公告)号：DE3071473D1

公开(公告)日：1986-04-10

申请号：DE3071473

申请日：1980-12-04

Applicant: IBM

Inventor： GLICKMAN DAVID ,  ROSENBAUM WALTER STEVEN

IPC: G06F17/21 ,  G06F17/22 ,  G06F17/27 ,  G06F17/30 ,  G06K9/72 ,  G06F15/20

Abstract: Method and system for reducing the computation required to match a misspelled word against various candidates from a dictionary to find one or more words that represent the best match to the misspelled word. The method consists in inventorying (steps 20-27), without regard to position, the respective characters in the misspelled words and in each of the dictionary candidate words. Then (steps 28-31) a candidate word is dismissed from additional processing if there is not a predetermined percentage match between its character content and that of the misspelled word. Such a prescan alpha content match reduces the number of candidates in contention so as to make a high resolution match computationally feasible on a real-time basis.

公开(公告)号：DE2754441A1

公开(公告)日：1978-06-29

申请号：DE2754441

申请日：1977-12-07

Applicant: IBM

Inventor： KOLPEK ROBERT ADOLPH ,  MACDUFFEE DAVID LEE ,  ROSENBAUM WALTER STEVEN

IPC: B41J5/30 ,  B41J7/96 ,  G06F3/09 ,  G06F3/12 ,  G06F11/00 ,  G06F17/22 ,  G06F17/27 ,  G06K9/72 ,  G06K15/00 ,  B41J5/10 ,  B41B27/10 ,  G06K15/02

Abstract: SYSTEM FOR AUTOMATICALLY PROOFREADING A DOCUMENT Spelling errors in a word processing system are detected and presented to the operator for correction at the end of a document page. A dictionary memory contains representations of the correct spellings for words most frequently used. As each word is typed, it is stored in a word queue where it is compared to the contents of the dictionary memory. If the compare is unequal, then the word and its location on the page is stored in an error memory. When an end of page indicator is set the printer automatically repositions the print head at the ending character of the first word in the error list. When the operator keys in the correct spelling, the printer is caused to remove the misspelled word from the page and type the correct spelling. The corresponding word in the error memory is also corrected. As each misspelled word in the error memory is corrected, the remainder of the memory is scanned and repetitions of the same spelling error are automatically corrected.

公开(公告)号：AU8100375A

公开(公告)日：1976-11-11

申请号：AU8100375

申请日：1975-05-09

Applicant: IBM

Inventor： CHAIRES ANNE MARIE ,  CICONTE JEAN MARIE ,  ETT ALLEN HAROLD ,  HILLIARD JOHN JOSEPH ,  ROSENBAUM WALTER STEVEN

IPC: G06F17/22 ,  G06F17/28 ,  G06K9/72 ,  G10L15/00 ,  G06K9/08 ,  G06K9/06

Abstract: A binary reference matrix apparatus is diclosed for verifying input alpha words from a character recognition machine as valid linguistic expressions. The organization of the binary reference matrix is based upon the character transfer function of the character recognition machine. The alphabetic character stream for each word scanned by the character recognition machine, is mapped into a vector representation through the assignment of a unique numeric value for each letter in the alphabet. The vector magnitude and angle so calculated constitute the address data for accessing the binary reference matrix. The point accessed in the matrix will have a binary value of 1 if the scanned word is valid and will have a binary value of 0 if the scanned word is invalid. The organization of the binary reference matrix minimizes the size of the array needed for accurate verification by choosing numerical values for the alphabetic characters in an inverse proportion to the characters read reliability in the character recognition machine, as determined by the empirical measurement of the character recognition machine, character transfer function.

公开(公告)号：DE2541204A1

公开(公告)日：1976-04-15

申请号：DE2541204

申请日：1975-09-16

Applicant: IBM

Inventor： WILLIS BOLLINGER GEB WILLIS EL ,  CHAIRES GEB LYONS ANNE MARIE ,  CICONTE GEB SCHELTES JEAN MARI ,  ETT ALLEN HAROLD ,  HILLIARD JOHN JOSEPH ,  KOCHER DONALD FRANCIS ,  ROSENBAUM WALTER STEVEN

IPC: G06F17/22 ,  G06K9/72 ,  G06F11/00 ,  G06K9/02

Abstract: 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.

公开(公告)号：DE2435889A1

公开(公告)日：1975-10-16

申请号：DE2435889

申请日：1974-07-25

Applicant: IBM

Inventor： CHAIRES GEB LYONS ANNE MARIE ,  CICONTE GEB SCHELTES JEAN MARI ,  HILLIARD JOHN JOSEPH ,  ROSENBAUM WALTER STEVEN ,  ETT ALLEN HAROLD

IPC: G06K9/72 ,  G06K9/00 ,  B07C3/14

Abstract: An online numeric discriminator is disclosed which performs the decision making process between strings of characters coming from a dual output optical character recognition system for use in text processing or mail processing applications. The dual output OCR uses separate recognition processes for alphabetic and numeric characters and attempts to recognize each character independently as both an alphabetic and a numeric character. The alphabetic interpretation of the scanned word is outputted as an alphabetic subfield on a first output line and the numeric interpretation of the scanned word is outputted as a numeric subfield on a second output line from the OCR. The bayesian online numeric discriminator then analyzes the two character streams by calculating a first conditional probability that the OCR perceived the alphabetic subfield given that a numeric subfield was actually scanned and a second conditional probability that the OCR perceived the numeric subfield given that an alphabetic subfield was actually scanned. These first and second conditional probabilities are then compared. If the conditional probability that the OCR read the alphabetic subfield given that the numeric subfield was actually scanned, is larger than the conditional probability that the OCR read the numeric subfield given that the alphabetic subfield was actually scanned, then the numeric subfield is selected by the discriminator as the most probable interpretation of the word scanned by the OCR.

公开(公告)号：FI934166A

公开(公告)日：1994-03-26

申请号：FI934166

申请日：1993-09-23

Applicant: IBM

Inventor： ROSENBAUM WALTER STEVEN

IPC: B07C3/14 ,  B07C3/20 ,  G06K9/00 ,  G06K9/03 ,  B07C3/10

Abstract: The invention provides a system and method for improving processing of Optical Read Character (OCR) scanned mail. Such an automatic mail processing is vested with an interactive learning capability. Ambiguous envelope address blocks and information fields are resolved using a unique mode of human/machine interaction that achieves a sustained high rate of automatic mail sortation.

公开(公告)号：DE3374093D1

公开(公告)日：1987-11-19

申请号：DE3374093

申请日：1983-06-01

Applicant: IBM

Inventor： CARLGREN RICHARD GORAN ,  REED MARTIN ANDREW ,  ROSENBAUM WALTER STEVEN

IPC: B41J3/46 ,  B41J29/50 ,  G06F3/12 ,  G06F17/21 ,  G06F40/189 ,  G06F40/191 ,  G06K15/00 ,  G06F15/20

Abstract: The combination of dictionary driven hyphenation, specialized algorithmic hyphenation and intelligent blank insertion provides improved right margin justification capability in a text processing system. When hyphenation is required for right margin justification, the system compares the word to be hyphenated to a prestored dictionary of words containing hyphenation points. When the word to be hyphenated matches one of the dictionary words the hyphenation points are retrieved and the word is split at the right margin. If the word to be hyphenated does not match one of the dictionary words, then a specialized list of prestored hyphenated suffixes and prestored statistical character digrams are compared to the word to determine the appropriate hyphenation points. Once the word has been split, the system searches the line for sets of predetermined words which may be separated from other words in the sentence by adding space to the line with a minimum of aesthetic distortion. Space is then added to the line until the line ending equals the right margin. The text is then printed.

公开(公告)号：AU3483378A

公开(公告)日：1979-10-11

申请号：AU3483378

申请日：1978-04-06

Applicant: IBM

Inventor： KETTLER HOWARD GEORGE ,  KOLPEK ROBERT ADOLPH ,  ROSENBAUM WALTER STEVEN

IPC: B41J19/32 ,  B41J19/58 ,  B41J19/64 ,  B41J25/12 ,  B41J25/22 ,  G06F3/12 ,  G06F17/21 ,  G06K15/00 ,  G06K15/08

Abstract: The aesthetic characteristics of adjacent characters are used to enhance the quality of output in a proportional spacing printer and to provide right margin justification for composing. Spacing between characters is determined on the basis of the character being printed and the preceding character already printed on the page. An intercharacter displacement memory contains a list of ideal spacing for all combinations of characters to be printed. As each character is typed, it and the previously stored preceding character address the intercharacter displacement memory. The output of the intercharacter displacement memory is the ideal value of escapement for this combination of characters and font style. The printer positions the print head prior to printing the next character, rather than positioning the print head after the previous character is printed. Line ending decisions for composing are eliminated during initial and final typing of a document by adding to the intercharacter displacement memory recommendations for altering the ideal spacing between characters, where aesthetically possible, to eliminate the need for line ending hyphenation. During initial keying, escapements for adjacent pairs of characters are totaled in a memory for ideal, shortest (tight), and longest (loose) recommended escapements. The line is automatically terminated within the justification range by a carrier return function based on the escapement totals and the selected right margin. Final playout of the page from memory alters the intercharacter escapements from the ideal values to either longer or shorter escapements depending on whether the line is to be lengthened or shortened.