US5835625A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for optical character recognition utilizing proportional nonpredominant color analysis
Assignee: International Business Machines Corp
•
Filing: 1993-01-29
•
Granted: 1998-11-10
•
Expires: 2013-01-29
Abstract
Abstract A method and apparatus for optical identification an unknown character from a plurality of known characters. Each of the known characters includes a predominant color and a nonpredominant color in preselected proportions. The unknown character has at least one geometric feature and a plurality of pixels including a predominant color and a nonpredominant color. The method and apparatus of the present invention include an examination of at least one geometric feature of the unknown character. A hypothetical identity for the unknown character is generated in response to the examination of at least one geometric feature of the unknown character. A portion of the plurality of pixels of the unknown character is sampled and a proportion between the predominant color and the nonpredominant color within the sampled portion of the plurality of pixels is determined from the sampled pixels. A comparison of the determined proportion with a preselected proportion associated with a known character corresponding to the hypothetical identity is made. The hypothetical identity is assigned to the unknown character if the determined proportion falls within the preselected range of the preselected proportion for the known character corresponding to the hypothetical identity.
Inventors
- 👤 Gregory P. Fitzpatrick
- 👤 Marvin L. Williams
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-02 20:06
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/22; G06V30/224; G06V10/00; G06V10/10; G06V10/12; G06V10/14; G06V10/143
Claims Analysis
Total Claims: 11
Claim 1
Independent Claim
245 words
A method in a data processing system for optically identifying an unknown character from a plurality of known characters, each of said plurality of known characters including a predominant color and a nonpredominant color in preselected proportions and wherein said unknown character is comprised of at least one geometric feature and a plurality of pixels including a predominant color and a nonpredominant color, said method comprising the data processing system implemented steps of: generating data using an optical scanning device to scan said unknown character, wherein said data includes at least one geometric feature and a plurality of pixels including a predominant color and a nonpredominant color of said unknown character; examining said at least one geometric feature of said unknown character using said data; generating a hypothetical identity for said unknown character in response to said examination of said at least one geometric feature using said data; sampling a portion of said plurality of pixels of said unknown character from said data and determining a proportion between said predominant color and said nonpredominant color within said sampled portion of said plurality of pixels; comparing said determined proportion with a preselected proportion for an associated one of said plurality of known characters corresponding to said hypothetical identity; and assigning said hypothetical identity to said unknown character if said determined proportion falls within a preselected range of said preselected proportion for said one of said plurality of known characters, wherein said unknown character may be identified.
Claim 2
Independent Claim
245 words
A method in a data processing system for optically identifying an unknown character from a plurality of known characters, each of said plurality of known characters including a predominant color and a nonpredominant color in preselected proportions and wherein said unknown character is comprised of at least one geometric feature and a plurality of pixels including a predominant color and a nonpredominant color, said method comprising the data processing system implemented steps of: generating data using an optical scanning device to scan said unknown character, wherein said data includes at least one geometric feature and a plurality of pixels including a predominant color and a nonpredominant color of said unknown character; examining said at least one geometric feature of said unknown character using said data; generating a hypothetical identity for said unknown character in response to said examination of said at least one geometric feature using said data; sampling a portion of said plurality of pixels of said unknown character from said data and determining a proportion between said predominant color and said nonpredominant color within said sampled portion of said plurality of pixels; comparing said determined proportion with a preselected proportion for an associated one of said plurality of known characters corresponding to said hypothetical identity; and assigning said hypothetical identity to said unknown character if said determined proportion falls within a preselected range of said preselected proportion for said one of said plurality of known characters, wherein said unknown character may be identified.
Claim 3
Dependent Claim
109 words
The method for optically identifying an unknown character according to claim 1, further comprising determining whether said nonpredominant color of said unknown character corresponds to a nonpredominant color for said associated one of said plurality of known characters corresponding to said hypothetical identity; and wherein said step of assigning said hypothetical identity to said unknown character if said determined proportion falls within a preselected range of said preselected proportion for said one of said plurality of known characters is performed only if said nonpredominant color of said unknown character corresponds to said nonpredominant color for said associated one of said plurality of known characters corresponding to said hypothetical identity.
Claim 4
Dependent Claim
21 words
The method of claim 1, wherein said nonpredominant color is associated with at least two noncontiguous pixels in said unknown character.
Claim 5
Dependent Claim
19 words
The method of claim 1, wherein said nonpredominant color is associated with pixels randomly dispersed within said unknown character.
Claim 6
Dependent Claim
268 words
A data processing system for optically identifying an unknown character from a plurality of known characters, each of said plurality of known characters including a predominant color and a nonpredominant color in preselected proportions and wherein said unknown character is comprised of at least one geometric feature and a plurality of pixels including a predominant color and a nonpredominant color, said data processing system comprising: an optical scanning device, wherein said optical scanner optically scans an unknown character to produce data including at least one geometric feature of the unknown character and a plurality of pixels including a predominant color and a nonpredominant color from the unknown character in response to optically scanning said unknown character; a memory for storing said data produced by said optical scanning device; examination means for examining said at least one geometric feature of said unknown character using said data located in said memory; generation means for generating a hypothetical identity for said unknown character in response to said examination of said at least one geometric feature; sampling means for sampling a portion of said plurality of pixels of said unknown character and determining a proportion between said predominant color and said nonpredominant color within said sampled portion of said plurality of pixels; comparison means for comparing said determined proportion with a preselected proportion for an associated one of said plurality of known characters corresponding to said hypothetical identity; and assignment means for assigning said hypothetical identity to said unknown character if said determined proportion falls within a preselected range of said preselected proportion for said one of said plurality of known characters.
Claim 7
Dependent Claim
268 words
A data processing system for optically identifying an unknown character from a plurality of known characters, each of said plurality of known characters including a predominant color and a nonpredominant color in preselected proportions and wherein said unknown character is comprised of at least one geometric feature and a plurality of pixels including a predominant color and a nonpredominant color, said data processing system comprising: an optical scanning device, wherein said optical scanner optically scans an unknown character to produce data including at least one geometric feature of the unknown character and a plurality of pixels including a predominant color and a nonpredominant color from the unknown character in response to optically scanning said unknown character; a memory for storing said data produced by said optical scanning device; examination means for examining said at least one geometric feature of said unknown character using said data located in said memory; generation means for generating a hypothetical identity for said unknown character in response to said examination of said at least one geometric feature; sampling means for sampling a portion of said plurality of pixels of said unknown character and determining a proportion between said predominant color and said nonpredominant color within said sampled portion of said plurality of pixels; comparison means for comparing said determined proportion with a preselected proportion for an associated one of said plurality of known characters corresponding to said hypothetical identity; and assignment means for assigning said hypothetical identity to said unknown character if said determined proportion falls within a preselected range of said preselected proportion for said one of said plurality of known characters.
Claim 8
Dependent Claim
77 words
The data processing system of claim 5, further comprising determination means for determining whether said nonpredominant color of said unknown character corresponds to a nonpredominant color for said associated one of said plurality of known characters corresponding to said hypothetical identity; and wherein said assignment means is utilized only if said nonpredominant color of said unknown character corresponds to said nonpredominant color for said associated one of said plurality of known characters corresponding to said hypothetical identity.
Claim 9
Dependent Claim
36 words
The data processing system of claim 6, further comprising storage means for storing data representing said predominant color, said nonpredominant color and said proportions of predominant color and nonpredominant color for said plurality of known characters.
Claim 10
Dependent Claim
21 words
The apparatus of claim 5, wherein said nonpredominant color is associated with at least two noncontiguous pixels in said unknown character.
Claim 11
Dependent Claim
19 words
The method of claim 5, wherein said nonpredominant color is associated with pixels randomly dispersed within said unknown character.
References Cited (Backward Citations)
US3938088A
Cited
US3786237A
Cited
USRE31692E
Cited
US3949363A
Cited
US4637051A
Cited
US4987603A
Cited
US5239592A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-11-09 | 2002-05-11 | 2002-11-10 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-11-09 | 2006-05-11 | 2006-11-10 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-11-09 | 2010-05-11 | 2010-11-10 | $7700.00 | Window Closed / Lapsed |