US4776024A
Expired / Lapsed
US
⏱️ 0.0 years remaining
System for segmenting character components
Assignee: International Business Machines Corp
•
Filing: 1987-05-21
•
Granted: 1988-10-04
•
Expires: 2007-05-21
Abstract
Abstract A system and method for electronically segmenting character components on character-containing documents involving first scanning a document and quantizing the image information obtained by the scanning into two levels, e.g., black and white, by 1 and 0 bits, and from the quantized information, m-bit OR groups are generated by sequentially ORing every m-th bit in a first direction of the quantized image, where m is an integer equal to or greater than two. The black (character) bits in each of the m-bit OR groups are counted and processed using the steps of: sequentially calculating sums of n consecutive count values by shifting one by one the count values obtained by the counting along a second direction perpendicular to the first direction; and then, segmenting character components by comparing the sums with a predetermined threshold value. The ORing operations can be performed conveniently by employing the OR instruction provided in a typical microprocessor and can attain substantially the same accuracy as conventional OCR systems employing an m×n mask.
Inventors
- 👤 Shin Katoh
- 👤 Hiroyasu Takahashi
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 16:40
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/14; G06V30/148; G06V30/15
Claims Analysis
Total Claims: 18
Claim 1
Independent Claim
173 words
A method for segmenting character components in electronic images obtained from electronically scanning character-containing documents comprising the steps of: quantizing image information, obtained by scanning an area of a character-containing document, into two levels, black and white, using 1 and 0 bits; generating lines of m-bit OR groups from said quantized information by sequentially ORing every m-th bit with its following m-th bit in each line of bits in a first direction of the quantized image, where m is an integer equal to or greater than two; counting the number of black bits in each of said m-bit OR groups and producing a set of count values based thereon arranged in accordance with said generated lines; sequentially calculating sums of n consecutive count values, by shifting the count values obtained by said counting, along a second direction perpendicular to said first direction, and summing n values after each shift, where n is an integer equal to or greater than two; and segmenting character components by comparing said sums with a predetermined threshold value.
Claim 2
Independent Claim
173 words
A method for segmenting character components in electronic images obtained from electronically scanning character-containing documents comprising the steps of: quantizing image information, obtained by scanning an area of a character-containing document, into two levels, black and white, using 1 and 0 bits; generating lines of m-bit OR groups from said quantized information by sequentially ORing every m-th bit with its following m-th bit in each line of bits in a first direction of the quantized image, where m is an integer equal to or greater than two; counting the number of black bits in each of said m-bit OR groups and producing a set of count values based thereon arranged in accordance with said generated lines; sequentially calculating sums of n consecutive count values, by shifting the count values obtained by said counting, along a second direction perpendicular to said first direction, and summing n values after each shift, where n is an integer equal to or greater than two; and segmenting character components by comparing said sums with a predetermined threshold value.
Claim 3
Dependent Claim
97 words
A method as in claim 1, wherein said m-bit OR groups are generated by the steps of: (a) generating M-bit OR groups by dividing the bits of said quantized image into M-bit groups along said first direction, where M=2 P m and p is an integer; (b) ORing each of said M-bit groups with its following M-bit group; (c) then generating M/2-bit OR groups by dividing each of said ORed M-bit groups into halves and ORing each of said halves; and (d) repeating said foregoing steps (a), (b), and (c) to ultimately generate said m-bit OR groups.
Claim 4
Dependent Claim
19 words
A method as in claim 2, wherein said first direction is the direction in which character lines are segmented.
Claim 5
Dependent Claim
45 words
A method as in claim 1, wherein a predetermined number of said m-bit OR groups are generated by dividing the bits of said quantized image into groups, each consisting of said predetermined number of bits along said second direction, and sequentially ORing every m-th group.
Claim 6
Dependent Claim
18 words
A method as in claim 1, wherein said first direction is the direction in which characters are segmented.
Claim 7
Dependent Claim
17 words
A method as in claim 1, wherein said shifting comprises shifting said count values one by one.
Claim 8
Dependent Claim
15 words
A method as in claim 1, wherein said steps are carried out using a microprocessor.
Claim 9
Dependent Claim
59 words
A method as in claim 1, wherein said ORing step comprises: providing a set of m registers; employing an OR instruction with the first operand made to be the respective contents of each of said registers and the second operand made to be the respective scanning line data; and storing the ORed results respectively in said first operand registers.
Claim 10
Independent Claim
181 words
A system for segmenting character components in electronic images obtained from electronically scanning character-containing documents comprising: means for quantizing image information obtained by scanning an area of a character-containing document, into two levels, black and white, using 1 and 0 bits; ORing means for generating lines of m-bit OR groups from said quantized information by sequentially ORing every m-th bit with its following m-th bit in each line of bits in a first direction of the quantized image, where m is an integer equal to or greater than two; means for counting the number of black bits in each of said m-bit OR groups and producing a set of count values based thereon arranged in accordance with said generated lines; means for sequentially calculating sums of n consecutive count values, by shifting the count values obtained by said counting, along a second direction perpendicular to said first direction, and summing n values after each shift, where n is an integer equal to or greater than two; and means for segmenting character components by comparing said sums with a predetermined threshold value.
Claim 11
Independent Claim
181 words
A system for segmenting character components in electronic images obtained from electronically scanning character-containing documents comprising: means for quantizing image information obtained by scanning an area of a character-containing document, into two levels, black and white, using 1 and 0 bits; ORing means for generating lines of m-bit OR groups from said quantized information by sequentially ORing every m-th bit with its following m-th bit in each line of bits in a first direction of the quantized image, where m is an integer equal to or greater than two; means for counting the number of black bits in each of said m-bit OR groups and producing a set of count values based thereon arranged in accordance with said generated lines; means for sequentially calculating sums of n consecutive count values, by shifting the count values obtained by said counting, along a second direction perpendicular to said first direction, and summing n values after each shift, where n is an integer equal to or greater than two; and means for segmenting character components by comparing said sums with a predetermined threshold value.
Claim 12
Dependent Claim
100 words
A system as in claim 9, wherein said ORing means comprises; (a) means for generating M-bit OR groups by dividing the bits of said quantized image into M-bit groups along said first direction, where M=2 P m and p is an integer; (b) means for ORing each of said M-bit groups with its following M-bit group; (c) means for then generating M/2-bit OR groups by dividing each of said ORed M-bit groups into halves and ORing each of said halves; and (d) means for repeatedly actuating said foregoing (a), (b), and c) means to ultimately generate said m-bit OR groups.
Claim 13
Dependent Claim
19 words
A system as in claim 10, wherein said first direction is the direction in which character lines are segmented.
Claim 14
Dependent Claim
13 words
A system as in claim 9, wherein said ORing means comprises a microprocessor.
Claim 15
Dependent Claim
52 words
A system as in claim 9, wherein said ORing means comprises means for generating a predetermined number of said m-bit OR groups by dividing the bits of said quantized image into groups, each consisting of said predetermined number of bits along said second direction, and means for sequentially ORing every m-th group.
Claim 16
Dependent Claim
18 words
A system as in claim 9, wherein said first direction is the direction in which characters are segmented.
Claim 17
Dependent Claim
20 words
A system as in claim 9, wherein said calculating means comprises means for shifting said count values one by one.
Claim 18
Dependent Claim
63 words
A system as in claim 9, wherein said ORing means comprises: a set of m registers; microprocessor means for producing an OR instruction with the first operand made to be the respective contents of each of said registers and the second operand made to be the respective scanning line data; and means for storing the ORed results respectively in said first operand registers.
References Cited (Backward Citations)
US3543238A
Cited
US3432673A
Cited
US3629826A
Cited
US4527283A
Cited
US4377803A
Cited
US4466121A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1991-10-04 | 1992-04-04 | 1992-10-04 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1995-10-04 | 1996-04-04 | 1996-10-04 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 1999-10-04 | 2000-04-04 | 2000-10-04 | $7700.00 | Window Closed / Lapsed |