US4003025A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Alphabetic character word upper/lower case print convention apparatus and method
Assignee: International Business Machines Corp
•
Filing: 1975-12-24
•
Granted: 1977-01-11
•
Expires: 1995-12-24
Abstract
Abstract The print convention apparatus and method disclosed herein effects a decision making process with respect to a determination as to whether an alphabetic character field output from an optical character reader (OCR) is related to the OCR scan of an upper case or a lower case inscription on the document scanned. The alphabetic character field (e.g., a word) is comprised of one or a series of alphabetic characters which represent the OCR's interpretation of characters printed on the scanned document. Each word output by the OCR corresponds to a field (i.e., word) of characters imprinted on the scanned document. The electrical signals representative of the upper and lower case alphabetic characters and rejects including conflicts outputted from the OCR are applied to a character occurrence probability storage apparatus which contains precomputed empirical probabilities therein that: (1) a given character recognition is the result of the scan of an upper case character; and (2) a given character recognition is the result of the scan of a lower case character. In addition, the storage apparatus includes probability values for character conflicts and rejects. As the series of alphabetic character signals from the OCR output are applied character-by-character to the character occurrence probability storage apparatus (e.g., a read-only store), a running sum of the respective probabilities for the upper case and lower case print conventions is developed so that, following the input of the final character, reject or conflict within a word to the aforesaid apparatus, an appropriate upper or lower case determination can be made for all of the characters within the word. This determination corresponds with the print convention of the word inscribed on the scanned document. A corresponding upper or lower case flag is correspondingly generated with the print convention determination, and associated with the alphabetic character word output from the print convention apparatus for further text processing. In one embodiment of the invention the probability for each OCR output alphabetic character being an upper or lower case character is stored in respective upper and lower case character occurrence probability storage devices after having been precomputed as the product of two probability factors; i.e., (1) a first probability factor with respect to the likelihood that the OCR recognition resulted from the scan of an upper or lower case character, and (2) a second probability factor with respect to the likelihood of a given character occurring in a specified language (e.g., English) document. In another embodiment of the invention, the character occurrence probability storage devices are functionally replaced by a read-only store having an address position for each upper and lower case alphabetic character outputted by the OCR including conflicts and rejects, and a precomputed numerical probability value associated with each address position to represent the quotient of: (1) the probability that a given character is related to an upper case print convention; and (2) the probability that the same character is related to a lower case print convention.
Inventors
- 👤 John Joseph Hilliard
- 👤 Philip Joseph Mullan
- 👤 Walter Steven Rosenbaum
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-29 12:25
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/26; G06V30/262
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
391 words
An apparatus for discriminating upper and lower case alphabetic character fields appearing on the output line of an optical character recognition machine (OCR) as a series of character defining electrical signals, comprising: a read-only store having an input and an output, said store containing respective upper and lower case P U (α n ) and P L (α n ) print convention probability values therein for conflict, reject and alphabetic characters outputted by the OCR and in accordance with the equations ##EQU3## where P U (α n ) is representative of the probability tht said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; (U(i) is the 1-26 ith upper case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; first circuit means connected said OCR output line to the input of said store whereby a sequence of signals indicative of a field of characters outputted by said OCR, address said store serially a character at a time, to thereby make available serially at said store output, probability values corresponding to the aforesaid serially outputted character signals; an adder having an input and an output; second circuit means connecting said store output to the input of said adder, whereby probability values corresponding to the aforesaid serially outputted character signals are added algebraically; and last means connected to the output of said adder to detect the polarity of the print convention probability value algebraic sum following the read-out by said OCR to said store of all characters within a field, to thereby designate the upper/lower case print convention of the characters within the field.
Claim 2
Independent Claim
391 words
An apparatus for discriminating upper and lower case alphabetic character fields appearing on the output line of an optical character recognition machine (OCR) as a series of character defining electrical signals, comprising: a read-only store having an input and an output, said store containing respective upper and lower case P U (α n ) and P L (α n ) print convention probability values therein for conflict, reject and alphabetic characters outputted by the OCR and in accordance with the equations ##EQU3## where P U (α n ) is representative of the probability tht said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; (U(i) is the 1-26 ith upper case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; first circuit means connected said OCR output line to the input of said store whereby a sequence of signals indicative of a field of characters outputted by said OCR, address said store serially a character at a time, to thereby make available serially at said store output, probability values corresponding to the aforesaid serially outputted character signals; an adder having an input and an output; second circuit means connecting said store output to the input of said adder, whereby probability values corresponding to the aforesaid serially outputted character signals are added algebraically; and last means connected to the output of said adder to detect the polarity of the print convention probability value algebraic sum following the read-out by said OCR to said store of all characters within a field, to thereby designate the upper/lower case print convention of the characters within the field.
Claim 3
Dependent Claim
94 words
An apparatus according to claim 1 additionally comprising a gate-buffer for storing coded signals representative of the field of characters outputted by said OCR; control means for effecting a transfer of said signals to said gate-buffer substantially concurrently with the development of the print convention probability value algebraic sum; and means controlled by the aforesaid last means to be responsive to the polarity of the probability value algebraic sum for appending an upper or a lower case flag to the character field stored in said gate-buffer consequent upon said polarity being plus or minus.
Claim 4
Dependent Claim
341 words
A process for discriminating upper and lower case character fields appearing on the output line of an OCR as a series of character defining electrical signals, comprising the steps of: storing in a read-only store respective upper and lower case P U (α n ) and P L (α n ) print convention probability values for characters outputted by the OCR and in accordance with the equations ##EQU4## where P U (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; U(i) is the 1-26 ith upper case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occuring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; addressing the input of said read-only store with said series of electrical signals so as to produce at the output of said read-only store, probability values corresponding to character defining electrical signals applied to the input; detecting blank character positions between adjacent characters outputted by the OCR so as to group a series of electrical signals within a character field between two successive blank character positions; adding algebraically the probability values for character defining electrical signals within a character field; and detecting the polarity of the print convention probability value algebraic sum to thereby designate the upper/lower case print convention of the characters within the character field.
Claim 5
Dependent Claim
341 words
A process for discriminating upper and lower case character fields appearing on the output line of an OCR as a series of character defining electrical signals, comprising the steps of: storing in a read-only store respective upper and lower case P U (α n ) and P L (α n ) print convention probability values for characters outputted by the OCR and in accordance with the equations ##EQU4## where P U (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; U(i) is the 1-26 ith upper case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occuring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; addressing the input of said read-only store with said series of electrical signals so as to produce at the output of said read-only store, probability values corresponding to character defining electrical signals applied to the input; detecting blank character positions between adjacent characters outputted by the OCR so as to group a series of electrical signals within a character field between two successive blank character positions; adding algebraically the probability values for character defining electrical signals within a character field; and detecting the polarity of the print convention probability value algebraic sum to thereby designate the upper/lower case print convention of the characters within the character field.
Claim 6
Dependent Claim
54 words
A process according to claim 3 additionally including the steps of storing a field of character defining electrical signals in a buffer connected to the OCR output line, and flagging the character field in the buffer upper or lower case print convention consequent upon the polarity of the print convention probability value algebraic sum.
Claim 7
Dependent Claim
424 words
A process for discriminating upper and lower case character fields appearing on the output line of an OCR as a series of character defining electrical signals, comprising the steps of: storing in a first storage unit case P U (α n ) print convention probability values for characters outputted by the OCR; storing in a second storage unit lower case P L (α n ) print convention probability values for characters outputted by the OCR; said print convention probability values being stored in accordance with the equations ##EQU5## where P U (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; U(i) is the 1-26 ith upper case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; addressing the inputs of said first and said second storage units with said series of electrical signals so as to produce at the outputs of said first and said second storage units, upper and lower case probability values, respectively, corresponding to character defining electrical signals applied to the aforesaid inputs; detecting blank character positions between adjacent characters outputted by the OCR so as to group a series of electrical signals within a character field between two successive blank character positions; adding the upper case probability values appearing at the output of said first storage unit; adding the lower case probability values appearing at the output of said second storage unit; inverting one of the aforesaid probability value sums; comparing the other one of the aforesaid probability value sums with the inverted sum to thereby designate by + and - algebraic sign the upper and lower case print convention, respectively, of the characters within the character field; and flagging the character field print convention in accordance with the algebraic sign notation.
Claim 8
Dependent Claim
424 words
A process for discriminating upper and lower case character fields appearing on the output line of an OCR as a series of character defining electrical signals, comprising the steps of: storing in a first storage unit case P U (α n ) print convention probability values for characters outputted by the OCR; storing in a second storage unit lower case P L (α n ) print convention probability values for characters outputted by the OCR; said print convention probability values being stored in accordance with the equations ##EQU5## where P U (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; U(i) is the 1-26 ith upper case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; addressing the inputs of said first and said second storage units with said series of electrical signals so as to produce at the outputs of said first and said second storage units, upper and lower case probability values, respectively, corresponding to character defining electrical signals applied to the aforesaid inputs; detecting blank character positions between adjacent characters outputted by the OCR so as to group a series of electrical signals within a character field between two successive blank character positions; adding the upper case probability values appearing at the output of said first storage unit; adding the lower case probability values appearing at the output of said second storage unit; inverting one of the aforesaid probability value sums; comparing the other one of the aforesaid probability value sums with the inverted sum to thereby designate by + and - algebraic sign the upper and lower case print convention, respectively, of the characters within the character field; and flagging the character field print convention in accordance with the algebraic sign notation.
Claim 9
Independent Claim
520 words
An apparatus for discriminating upper and lower case alphabetic character fields appearing on the output line of an optical character recognition machine (OCR) as a series of electrical signals, comprising: A first store having an input and an output, said first store containing upper case P U (α n ) print convention probability values therein for conflict, reject and alphabetic characters outputted by the OCR and in accordance with the equation ##EQU6## where P U (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; U(i) is the 1-26 ith upper case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; a second store having an input and an output, said second store containing lower case P L (α n ) print convention probability values therein for conflict, reject and alphabetic characters outputted by the OCR and in accordance with the equation ##EQU7## where P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; first circuit means connecting said OCR output line to the inputs of said first and second stores whereby a sequence of signals indicative of a field of characters outputted by said OCR, address said stores serially a character at a time, to thereby make available serially at each of said first and second store outputs, print convention probability values corresponding to the aforesaid serially outputted character signals; a first adder having an input and an output; second circuit means connecting said first store output to the input of said first adder, whereby upper case print convention probability values corresponding to the aforesaid serially outputted character signals are added algebraically in said first adder; a second adder having an input and an output; third circuit means connecting said second store output to the input of said second adder, whereby lower case print convention probability values corresponding to the aforesaid serially outputted character signals are added algebraically in said second adder; an inverter connected to the output of said second adder, and an algebraic probability value comparator connected to the output of said first adder and to the output of said inverter so as to detect the polarity of the print convention probability value algebraic sum comparison following the read-out by said OCR to said first and said second stores of all characters within a field, and to thereby designate the upper/lower case print convention of the characters in the field.
Claim 10
Independent Claim
520 words
An apparatus for discriminating upper and lower case alphabetic character fields appearing on the output line of an optical character recognition machine (OCR) as a series of electrical signals, comprising: A first store having an input and an output, said first store containing upper case P U (α n ) print convention probability values therein for conflict, reject and alphabetic characters outputted by the OCR and in accordance with the equation ##EQU6## where P U (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of an upper case alphabetic character; U(i) is the 1-26 ith upper case alphabetic character; P c [α n |U(i)] is the confusion probability of U(i) being read as α n ; P[U(i)] is the probability of U(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; a second store having an input and an output, said second store containing lower case P L (α n ) print convention probability values therein for conflict, reject and alphabetic characters outputted by the OCR and in accordance with the equation ##EQU7## where P L (α n ) is representative of the probability that said OCR recognition (α n ) resulted from the scan of a lower case alphabetic character; L(i) is the 1-26 ith lower case alphabetic character; P c [α n |L(i)] is the confusion probability of L(i) being read as α n ; and P[L(i)] is the probability of L(i) occurring on the document scanned by said OCR in view of the language of the field of characters inscribed on the aforesaid document; first circuit means connecting said OCR output line to the inputs of said first and second stores whereby a sequence of signals indicative of a field of characters outputted by said OCR, address said stores serially a character at a time, to thereby make available serially at each of said first and second store outputs, print convention probability values corresponding to the aforesaid serially outputted character signals; a first adder having an input and an output; second circuit means connecting said first store output to the input of said first adder, whereby upper case print convention probability values corresponding to the aforesaid serially outputted character signals are added algebraically in said first adder; a second adder having an input and an output; third circuit means connecting said second store output to the input of said second adder, whereby lower case print convention probability values corresponding to the aforesaid serially outputted character signals are added algebraically in said second adder; an inverter connected to the output of said second adder, and an algebraic probability value comparator connected to the output of said first adder and to the output of said inverter so as to detect the polarity of the print convention probability value algebraic sum comparison following the read-out by said OCR to said first and said second stores of all characters within a field, and to thereby designate the upper/lower case print convention of the characters in the field.
Claim 11
Dependent Claim
91 words
an apparatus according to claim 6 additionally comprising a gate-buffer for storing coded signals representative of the field of characters outputted by said OCR; control means for effecting a transfer of said signals to said gate-buffer substantially concurrently with the development of the print convention probability value algebraic sum; and means controlled by said comparator, responsive to the polarity of the probability value algebraic sum therefrom, for appending an upper or a lower case flag to the character field stored in said gate-buffer consequent upon the polarity output from said comparator.
References Cited (Backward Citations)
US3634822A
Cited
US3651459A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1980-01-11 | 1980-07-12 | 1981-01-11 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1984-01-11 | 1984-07-12 | 1985-01-11 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1988-01-11 | 1988-07-12 | 1989-01-11 | $7700.00 | Window Closed / Lapsed |