Patent US5369715A successfully refreshed from Google Patents.
US5369715A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Optical character recognition system
Assignee: Sharp Corp
•
Filing: 1991-04-26
•
Granted: 1994-11-29
•
Expires: 2011-04-26
Abstract
Abstract A histogram is prepared using the heights of characters in an input alphanumeric character image data set. Based on this histogram, reference line characters are detected from the character row. The upper and lower extracting ordinates of each character in the character row are obtained. Then, the average of each of the upper and lower extracting ordinates in the character row is determined as the ordinate of a reference line for the character row. Thus obtained reference line is used for character recognition.
Inventors
- 👤 Hideaki Tanaka
- 👤 Toshiaki Morita
- 👤 Yoshihiro Kitamura
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-31 20:55
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/14; G06V30/146
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
169 words
An optical character recognition system, comprising: means for reading images of a character row to generate an image data set representing characters of said character row; means for forming a center line which runs through said character row; means for determining characters which are crossed by said center line to be included in said character row; means for preparing a graph which indicates the frequency distribution of the heights of said determined characters; means for extracting characters from said determined characters, based on said graph, the ordinates of the data of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; means for calculating and selecting the average of the upper extracting ordinates of said extracted characters as the ordinate of one of said reference lines, and the average of the lower extracting ordinates of said extracted characters as the ordinate of the other of said reference lines; and means for using said reference lines for character recognition.
Claim 2
Dependent Claim
169 words
An optical character recognition system, comprising: means for reading images of a character row to generate an image data set representing characters of said character row; means for forming a center line which runs through said character row; means for determining characters which are crossed by said center line to be included in said character row; means for preparing a graph which indicates the frequency distribution of the heights of said determined characters; means for extracting characters from said determined characters, based on said graph, the ordinates of the data of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; means for calculating and selecting the average of the upper extracting ordinates of said extracted characters as the ordinate of one of said reference lines, and the average of the lower extracting ordinates of said extracted characters as the ordinate of the other of said reference lines; and means for using said reference lines for character recognition.
Claim 3
Dependent Claim
195 words
An optical character recognition system, comprising: means for reading images of a character row to generate an image data set representing characters of said character row; means for forming a center line which runs through said character row; means for determining characters which are crossed by said center line to be included in said character row; means for preparing a graph which indicates the frequency distribution of the heights of said determined characters; means for extracting characters from said determined characters, based on said graph, the ordinates of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; means for dividing said character row into a plurality of segments; means for calculating and selecting the average of the upper extracting ordinates of extracted characters included in one of said segments as the ordinate of one of said reference lines in said one segment, and the average of the lower extracting ordinates of the extracted characters included in said one segment as the ordinate of the other of said reference lines in said one segment; and means for using said reference lines for character recognition.
Claim 4
Dependent Claim
195 words
An optical character recognition system, comprising: means for reading images of a character row to generate an image data set representing characters of said character row; means for forming a center line which runs through said character row; means for determining characters which are crossed by said center line to be included in said character row; means for preparing a graph which indicates the frequency distribution of the heights of said determined characters; means for extracting characters from said determined characters, based on said graph, the ordinates of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; means for dividing said character row into a plurality of segments; means for calculating and selecting the average of the upper extracting ordinates of extracted characters included in one of said segments as the ordinate of one of said reference lines in said one segment, and the average of the lower extracting ordinates of the extracted characters included in said one segment as the ordinate of the other of said reference lines in said one segment; and means for using said reference lines for character recognition.
Claim 5
Dependent Claim
148 words
An optical character recognition method comprising the steps of: acquiring an image data set representing characters of a character row; forming a center line which runs through said character row; determining characters which are crossed by said center line to be included in said character row; preparing a graph which indicates the frequency distribution of the heights of said determined characters; extracting characters from said determined characters, based on said graph, the ordinates of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; calculating and selecting the average of the upper extracting ordinates of said extracted characters as the ordinate of one of said reference lines, and the average of the lower extracting ordinates of said extracted characters as the ordinate of the other of said reference lines; and using the reference lines for character recognition.
Claim 6
Dependent Claim
148 words
An optical character recognition method comprising the steps of: acquiring an image data set representing characters of a character row; forming a center line which runs through said character row; determining characters which are crossed by said center line to be included in said character row; preparing a graph which indicates the frequency distribution of the heights of said determined characters; extracting characters from said determined characters, based on said graph, the ordinates of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; calculating and selecting the average of the upper extracting ordinates of said extracted characters as the ordinate of one of said reference lines, and the average of the lower extracting ordinates of said extracted characters as the ordinate of the other of said reference lines; and using the reference lines for character recognition.
Claim 7
Dependent Claim
13 words
A method according to claim 3, wherein said character row includes alphanumeric characters.
Claim 8
Dependent Claim
13 words
A method according to claim 3, wherein said character row includes printed characters.
Claim 9
Dependent Claim
175 words
An optical character recognition method comprising the steps of: acquiring an image data set representing characters of a character row; forming a center line which runs through said character row; determining characters which are crossed by said center line to be included in said character row; preparing a graph which indicates the frequency distribution of the heights of said determined characters; extracting characters from said determined characters, based on said graph, the ordinates of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; dividing said character row into a plurality of segments; calculating and selecting the average of the upper extracting ordinates of extracted characters included in one of said segments as the ordinate of one of said reference lines in said one segment, and the average of the lower extracting ordinates of the extracted characters included in said one segment as the ordinate of the other of said reference lines in said one segment; and using the reference lines for character recognition.
Claim 10
Dependent Claim
175 words
An optical character recognition method comprising the steps of: acquiring an image data set representing characters of a character row; forming a center line which runs through said character row; determining characters which are crossed by said center line to be included in said character row; preparing a graph which indicates the frequency distribution of the heights of said determined characters; extracting characters from said determined characters, based on said graph, the ordinates of the upper and lower extreme end portions of each of said extracted characters being assumed to be respectively on reference lines; dividing said character row into a plurality of segments; calculating and selecting the average of the upper extracting ordinates of extracted characters included in one of said segments as the ordinate of one of said reference lines in said one segment, and the average of the lower extracting ordinates of the extracted characters included in said one segment as the ordinate of the other of said reference lines in said one segment; and using the reference lines for character recognition.
Claim 11
Dependent Claim
13 words
A method according to claim 6, wherein said character row includes alphanumeric characters.
Claim 12
Dependent Claim
13 words
A method according to claim 6, wherein said character row includes printed characters.
References Cited (Backward Citations)
US4251799A
Cited
US4377803A
Cited
US4918740A
Cited
JPS63216189A
Cited
US4860376A
Cited
JPS6429986A
Cited
US4926492A
Cited
JPH01231186A
Cited
US4998285A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-11-28 | 1998-05-30 | 1998-11-29 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-11-28 | 2002-05-30 | 2002-11-29 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-11-28 | 2006-05-30 | 2006-11-29 | $7700.00 | Window Closed / Lapsed |