US5883974A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Methods for determining font attributes of characters
Assignee: Xerox Corp
•
Filing: 1997-04-11
•
Granted: 1999-03-16
•
Expires: 2017-04-11
Abstract
Abstract Font attributes of characters or letters are estimated by an optical character recognition system using character, run or stroke-based techniques with or without character identification information.
Inventors
- 👤 Zhigang Fan
- 👤 Robert Cooperman
- 👤 Robert Shuchatowitz
- 👤 Lucy Hadden
- 👤 Emil Rainero
- 👤 Frederick Roberts, Jr.
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 20:52
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/24; G06V30/242; G06V30/244; G06V30/245
Claims Analysis
Total Claims: 14
Claim 1
Independent Claim
107 words
A method for estimating at least one run-based font attributable of a group of characters of an input image independently of any character identification information of the group of characters, comprising: forming a plurality of single-connected and well-aligned-connected runs from bitmaps of the characters of the group of characters; forming a slant histogram, the slant histogram comprising estimated slants of characters, from the plurality of runs of the group of characters; identifying at least one frequency peak of the slant histogram; and estimating at least one run-based font attribute based on the plurality of runs and at least one of the at least one identified frequency peak.
Claim 2
Independent Claim
107 words
A method for estimating at least one run-based font attributable of a group of characters of an input image independently of any character identification information of the group of characters, comprising: forming a plurality of single-connected and well-aligned-connected runs from bitmaps of the characters of the group of characters; forming a slant histogram, the slant histogram comprising estimated slants of characters, from the plurality of runs of the group of characters; identifying at least one frequency peak of the slant histogram; and estimating at least one run-based font attribute based on the plurality of runs and at least one of the at least one identified frequency peak.
Claim 3
Dependent Claim
55 words
The method of claim 1, wherein, for each character of the group of characters, the histogram forming step comprises: determining a slant for each character of the group of characters from runs for that character of the plurality of runs; forming at least one slant histogram from the determined slants for the group of characters.
Claim 4
Dependent Claim
72 words
The method of claim 2, wherein, for each character of the group of characters, the slant determining step comprises: identifying at least one topmost run and at least one bottommost run; determining a top center point of the at least one topmost run; determining a bottom center point of the at least one bottommost run; connecting the top and bottom center points to form a line; determining a slant of the line.
Claim 5
Dependent Claim
32 words
The method of claim 1, further comprising estimating, for each character of the group of characters, a stroke thickness as the length of a representative run of the runs of that character.
Claim 6
Dependent Claim
28 words
The method of claim 1, wherein the run-based font attribute estimating step comprises determining a posture based on the at least one frequency peak of the slant histogram.
Claim 7
Dependent Claim
78 words
The method of claim 5, wherein the posture determining step comprises: comparing a slant value of each of the at least one frequency peak of the slant histogram to a preset threshold; determining if at least one of the at least one frequency peak is greater than the preset threshold; and when at least one of the at least one frequency peak is greater than the preset threshold, estimating that the group of characters has an italic posture.
Claim 8
Dependent Claim
78 words
The method of claim 5, wherein the posture determining step comprises: comparing a slant value of each of the at least one frequency peak of the slant histogram to a preset threshold; determining if at least one of the at least one frequency peak is less than the preset threshold; and when at least one of the at least one frequency peak is greater than the preset threshold, estimating that the group of characters has a Roman posture.
Claim 9
Dependent Claim
118 words
The method of claim 5, wherein the posture determining step comprises: comparing a slant value of each of the at least one frequency peak of the slant histogram to a first preset threshold and a second preset threshold higher than the first preset threshold; determining, for each at least one frequency peak, if the slant value for that frequency peak is less than the first preset threshold, between the first and second preset thresholds, or greater than the second preset threshold; and estimating that the posture for the group of characters based on the slant values of the at least one frequency peak which are less than the first preset threshold and greater than the second preset threshold.
Claim 10
Dependent Claim
83 words
The method of claim 8, wherein the posture estimating step comprises: determining if a number of the slant values which are above the second preset threshold is greater than a number of the slant values which are below the first preset threshold; and when a number of the slant values which are above the second preset threshold is greater than a number of the slant values which are below the first preset threshold, estimating that the group of characters has an italic posture.
Claim 11
Dependent Claim
83 words
The method of claim 8, wherein the posture estimating step comprises: determining if a number of the slant values which are above the second preset threshold is less than a number of the slant values which are below the first preset threshold; and when a number of the slant values which are above the second preset threshold is less than a number of the slant values which are below the first preset threshold, estimating that the group of characters has a Roman posture.
Claim 12
Dependent Claim
45 words
The method of claim 1, wherein the run-based font attribute estimating step comprises estimating the at least one run-based font attribute based on the at least one run-based font attributes estimated for at least one other group of characters located near the group of characters.
Claim 13
Dependent Claim
60 words
The method of claim 11, wherein the run-based font attribute estimating step further comprises weighting, for each at least one run-based font attribute of each at least one other group of characters, that run-based font attribute based on at least one of the font attribute and a distance between the group of characters and the corresponding other group of characters.
Claim 14
Dependent Claim
46 words
The method of claim 1, wherein the run-based font attribute estimating step comprises: determining if character identification information is available; and when character identification information is available, estimating the character-based font attributes based on the plurality of identified frequency peaks and the available character identification information.
References Cited (Backward Citations)
US4897880A
Cited
US5159645A
Cited
US5278920A
Cited
US5048113A
Cited
US5369715A
Cited
US5245674A
Cited
US5253307A
Cited
US5513277A
Cited
US5359673A
Cited
US5321768A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2002-03-15 | 2002-09-14 | 2003-03-16 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2006-03-15 | 2006-09-14 | 2007-03-16 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2010-03-15 | 2010-09-14 | 2011-03-16 | $7700.00 | Window Closed / Lapsed |