Patent US3842402A successfully refreshed from Google Patents.
US3842402A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Bayesian online numeric discriminator
Assignee: International Business Machines Corp
•
Filing: 1973-10-25
•
Granted: 1974-10-15
•
Expires: 1993-10-25
Abstract
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.
Inventors
- 👤 A Ett
- 👤 W Rosenbaum
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-29 16:51
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/26; G06V30/262
Claims Analysis
Total Claims: 3
Claim 1
Independent Claim
698 words
An apparatus for discriminating the alphabetic or numeric character of a character field scanned by an optical character recognition machine, comprising: an optical character recognition machine adapted to sequentially scan the characters in a character field, analyze the features of each character scanned, compare the features of each character scanned with a first matrix of stored features of alphabetic characters, output on a first output line the alphabetic character whose stored features most nearly match the features of each character scanned, for all characters scanned, compare the features of each character scanned with a second matrix of stored features of numeric characters and output on a second output line in synchronism with said output on said first line, a numeric character whose stored features most nearly match the features of the character scanned, for each character scanned; a first shift register connected to said first OCR output line, for sequentially loading and storing the alphabetic field which is the OCR alphabetic interpretation of the scanned character field, outputted on said first line; a second shift register connected to said second OCR output line, for sequentially loading and storing the numeric field which is the OCR numeric interpretation of the scanned character field, outputted on said second line; a first storage address register connected to said first OCR output line for sequentially storing each alphabetic character in the alphabetic field outputted on said first OCR output lidZ; a second storage address register connected to said second OCR output line for sequentially storing each numeric character in the numeric field outputted on said second OCR output line; a first storage means connected to said first and second storage address registers, having stored therein the conditional probabilities that a certain alphabetic character was inferred by the OCR given that a certain numeric character was scanned, for all combinations of alphabetic characters with numeric characters, said first storage means being accessed by the contents of said first and second storage address registers to yield the conditional probability that the numeric character stored in the second storage address register was misread by the OCR as the alphabetic character stored in the first storage address register; a second storage means connected to said first and second storage address registers, having stored therein the conditional probabilities that a certain numeric character was inferred by the OCR given that a certain alphabetic character was scanned, for all combinations of alphabetic characters with numeric characters, said second storage means being accessed by the contents of said first and second storage address registers to yield the conditional probability that the alphabetic character stored in the first storage address register was misread by the OCR as the numeric character stored in the second storage address register; a first storage output register connected to said first storage means for sequentially storing each conditional probability value accessed from said first storage means by said first storage address register; a second storage output register connected to said second storage means for sequentially storing each conditional probability value accessed from said second storage means by said second storage address register; a first multiplier means connected to said first storage output register for calculating the product of all the conditional probabilities accessed from said first storage means, said product being a first total conditional probability that all numeric characters stored in the second shift register were misread by the OCR as the alphabetic characters stored in said first shift register; a second multiplier means connected to said second storage output register for calculating the product of all the conditional probabilities accessed from said second storage means, said product being a second total conditional probability that all the alphabetic characters stored in the first shift register were misread by the OCR as the numeric characters stored in said second shift register; a comparator connected to said first and second multiplier means for comparing the magnitudes of said first and second total conditional probabilities and outputting an indication that a scanned character field is alphabetic if said second total conditional probability, is greater than said first total conditional probability, or is numeric if said first total conditional probability is greater than said second total conditional probability.
Claim 2
Independent Claim
698 words
An apparatus for discriminating the alphabetic or numeric character of a character field scanned by an optical character recognition machine, comprising: an optical character recognition machine adapted to sequentially scan the characters in a character field, analyze the features of each character scanned, compare the features of each character scanned with a first matrix of stored features of alphabetic characters, output on a first output line the alphabetic character whose stored features most nearly match the features of each character scanned, for all characters scanned, compare the features of each character scanned with a second matrix of stored features of numeric characters and output on a second output line in synchronism with said output on said first line, a numeric character whose stored features most nearly match the features of the character scanned, for each character scanned; a first shift register connected to said first OCR output line, for sequentially loading and storing the alphabetic field which is the OCR alphabetic interpretation of the scanned character field, outputted on said first line; a second shift register connected to said second OCR output line, for sequentially loading and storing the numeric field which is the OCR numeric interpretation of the scanned character field, outputted on said second line; a first storage address register connected to said first OCR output line for sequentially storing each alphabetic character in the alphabetic field outputted on said first OCR output lidZ; a second storage address register connected to said second OCR output line for sequentially storing each numeric character in the numeric field outputted on said second OCR output line; a first storage means connected to said first and second storage address registers, having stored therein the conditional probabilities that a certain alphabetic character was inferred by the OCR given that a certain numeric character was scanned, for all combinations of alphabetic characters with numeric characters, said first storage means being accessed by the contents of said first and second storage address registers to yield the conditional probability that the numeric character stored in the second storage address register was misread by the OCR as the alphabetic character stored in the first storage address register; a second storage means connected to said first and second storage address registers, having stored therein the conditional probabilities that a certain numeric character was inferred by the OCR given that a certain alphabetic character was scanned, for all combinations of alphabetic characters with numeric characters, said second storage means being accessed by the contents of said first and second storage address registers to yield the conditional probability that the alphabetic character stored in the first storage address register was misread by the OCR as the numeric character stored in the second storage address register; a first storage output register connected to said first storage means for sequentially storing each conditional probability value accessed from said first storage means by said first storage address register; a second storage output register connected to said second storage means for sequentially storing each conditional probability value accessed from said second storage means by said second storage address register; a first multiplier means connected to said first storage output register for calculating the product of all the conditional probabilities accessed from said first storage means, said product being a first total conditional probability that all numeric characters stored in the second shift register were misread by the OCR as the alphabetic characters stored in said first shift register; a second multiplier means connected to said second storage output register for calculating the product of all the conditional probabilities accessed from said second storage means, said product being a second total conditional probability that all the alphabetic characters stored in the first shift register were misread by the OCR as the numeric characters stored in said second shift register; a comparator connected to said first and second multiplier means for comparing the magnitudes of said first and second total conditional probabilities and outputting an indication that a scanned character field is alphabetic if said second total conditional probability, is greater than said first total conditional probability, or is numeric if said first total conditional probability is greater than said second total conditional probability.
Claim 3
Dependent Claim
166 words
The apparatus claimed in claim 1, which further comprises: a first gate having a data input connected to the output of said first shift register and having a control input connected to the output of said comparator, and an output connected to a system output line, for transmitting the alphabetic field which is the OCR alphabetic interpretation of the scanned character fields to said system output line, when said comparator outputs to said first gate control input an indication that the scanned character field is alphabetic; a second gate having a data input connected to the output of said second shift register, a control input connected to the output of said comparator, and an output connected to said system output line, for transmitting the numeric field which is the OCR numeric interpretatIon of the scanned character field from said second shift register to said system output line when said comparator outputs on said second gate control input an indication that the scanned character field is numeric.
References Cited (Backward Citations)
US3233219A
Cited
US3634822A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1977-10-14 | 1978-04-15 | 1978-10-15 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1981-10-14 | 1982-04-15 | 1982-10-15 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1985-10-14 | 1986-04-15 | 1986-10-15 | $7700.00 | Window Closed / Lapsed |