Patent US5790701A successfully refreshed from Google Patents.
US5790701A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Character recognition apparatus using edge images
Assignee: Toshiba Corp
•
Filing: 1995-06-05
•
Granted: 1998-08-04
•
Expires: 2015-06-05
Abstract
Abstract A character recognition apparatus comprises a photoelectric conversion section that converts image information including the characters to be recognized into multi-valued image information according to image density, an edge extracting circuit that creates edge image information indicating the outline of image density on the basis of the multi-valued image information from the photoelectric conversion section, and a recognition circuit that computes a distribution of a direction component so as to create a feature vector and recognizes characters on the basis of the direction feature vector.
Inventors
- 👤 Toru Shijo
- 👤 Yoshikatu Nakamura
- 👤 Toru Homma
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-03 07:04
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/18; G06V30/182
Claims Analysis
Total Claims: 6
Claim 1
Independent Claim
177 words
A character recognition apparatus comprising: means for converting image information including characters to be recognized into multi-valued image information according to image density; first formation means for forming multi-valued differentiation information by differentiating the multi-valued image information in an X-direction and a Y-direction; second formation means for forming multi-valued edge information pertaining to the X-direction and the Y-direction based upon the multi-valued differentiation information, said second formation means including: means for detecting whether the multi-valued differentiation information has a "+" peak or a "-" peak; third formation means for forming direction component information on a pixel by detecting a presence or an absence of edges extending in the X-direction and the Y-direction based upon the multi-valued edge information; fourth formation means for dividing a character region into a plurality of narrow regions and forming directional feature vectors each representing a number of direction components present in one narrow region of the plurality of narrow regions; and means for performing character recognition by detecting a similarity between the directional feature vectors and reference directional feature vectors stored beforehand.
Claim 2
Dependent Claim
177 words
A character recognition apparatus comprising: means for converting image information including characters to be recognized into multi-valued image information according to image density; first formation means for forming multi-valued differentiation information by differentiating the multi-valued image information in an X-direction and a Y-direction; second formation means for forming multi-valued edge information pertaining to the X-direction and the Y-direction based upon the multi-valued differentiation information, said second formation means including: means for detecting whether the multi-valued differentiation information has a "+" peak or a "-" peak; third formation means for forming direction component information on a pixel by detecting a presence or an absence of edges extending in the X-direction and the Y-direction based upon the multi-valued edge information; fourth formation means for dividing a character region into a plurality of narrow regions and forming directional feature vectors each representing a number of direction components present in one narrow region of the plurality of narrow regions; and means for performing character recognition by detecting a similarity between the directional feature vectors and reference directional feature vectors stored beforehand.
Claim 3
Dependent Claim
193 words
A character recognition apparatus comprising: means for converting image information including characters to be recognized into multi-valued image information according to image density; first formation means for forming multi-valued differentiation information by differentiating the multi-valued image information in an X-direction and a Y-direction; second formation means for forming multi-valued edge information pertaining to the X-direction and the Y-direction based upon the multi-valued differentiation information; third formation means for forming direction component information on a pixel by detecting a presence or an absence of edges extending in the X-direction and the Y-direction based upon the multi-valued edge information, said third formation means including: means for determining a direction code by checking whether the multi-valued differentiation information includes a "+" or a "-" peak, and means for converting the direction code into said direction component information; fourth formation means for dividing a character region into a plurality of narrow regions and forming directional feature vectors each representing a number of direction components present in one narrow region of the plurality of narrow regions; and means for performing character recognition by detecting a similarity between the directional feature vectors and reference directional feature vectors stored beforehand.
Claim 4
Dependent Claim
193 words
A character recognition apparatus comprising: means for converting image information including characters to be recognized into multi-valued image information according to image density; first formation means for forming multi-valued differentiation information by differentiating the multi-valued image information in an X-direction and a Y-direction; second formation means for forming multi-valued edge information pertaining to the X-direction and the Y-direction based upon the multi-valued differentiation information; third formation means for forming direction component information on a pixel by detecting a presence or an absence of edges extending in the X-direction and the Y-direction based upon the multi-valued edge information, said third formation means including: means for determining a direction code by checking whether the multi-valued differentiation information includes a "+" or a "-" peak, and means for converting the direction code into said direction component information; fourth formation means for dividing a character region into a plurality of narrow regions and forming directional feature vectors each representing a number of direction components present in one narrow region of the plurality of narrow regions; and means for performing character recognition by detecting a similarity between the directional feature vectors and reference directional feature vectors stored beforehand.
Claim 5
Dependent Claim
189 words
A character recognition apparatus comprising: means for converting image information including characters to be recognized into multi-valued image information according to image density; first formation means for forming multi-valued differentiation information by differentiating the multi-valued image information in an X-direction and a Y-direction; second formation means for forming multi-valued edge information pertaining to the X-direction and the Y-direction based upon the multi-valued differentiation information, said second formation means including: means for detecting an isolated edge by checking the multi-valued edge information and for adding a probable edge which forms a pair with reference to the isolated edge; third formation means for forming direction component information on a pixel by detecting a presence or an absence of edges extending in the X-direction and the Y-direction based upon the multi-valued edge information; fourth formation means for dividing a character region into a plurality of narrow regions and forming directional feature vectors each representing a number of direction components present in one narrow region of the plurality of narrow regions; and means for performing character recognition by detecting a similarity between the directional feature vectors and reference directional feature vectors stored beforehand.
Claim 6
Dependent Claim
189 words
A character recognition apparatus comprising: means for converting image information including characters to be recognized into multi-valued image information according to image density; first formation means for forming multi-valued differentiation information by differentiating the multi-valued image information in an X-direction and a Y-direction; second formation means for forming multi-valued edge information pertaining to the X-direction and the Y-direction based upon the multi-valued differentiation information, said second formation means including: means for detecting an isolated edge by checking the multi-valued edge information and for adding a probable edge which forms a pair with reference to the isolated edge; third formation means for forming direction component information on a pixel by detecting a presence or an absence of edges extending in the X-direction and the Y-direction based upon the multi-valued edge information; fourth formation means for dividing a character region into a plurality of narrow regions and forming directional feature vectors each representing a number of direction components present in one narrow region of the plurality of narrow regions; and means for performing character recognition by detecting a similarity between the directional feature vectors and reference directional feature vectors stored beforehand.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-08-03 | 2002-02-02 | 2002-08-04 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-08-03 | 2006-02-02 | 2006-08-04 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-08-03 | 2010-02-02 | 2010-08-04 | $7700.00 | Window Closed / Lapsed |