US5844991A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Script identification from images using cluster-based templates
Assignee: CALIFORIA UNIVERSITY OF REGENTS OF
•
Filing: 1995-08-07
•
Granted: 1998-12-01
•
Expires: 2015-08-07
Abstract
Abstract A computer-implemented method identifies a script used to create a document. A set of training documents for each script to be identified is scanned into the computer to store a series of exemplary images representing each script. Pixels forming the exemplary images are electronically processed to define a set of textual symbols corresponding to the exemplary images. Each textual symbol is assigned to a cluster of textual symbols that most closely represents the textual symbol. The cluster of textual symbols is processed to form a representative electronic template for each cluster. A document having a script to be identified is scanned into the computer to form one or more document images representing the script to be identified. Pixels forming the document images are electronically processed to define a set of document textual symbols corresponding to the document images. The set of document textual symbols is compared to the electronic templates to identify the script.
Inventors
- 👤 Judith G. Hochberg
- 👤 Patrick M. Kelly
- 👤 Timothy R. Thomas
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 20:33
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/24; G06V30/242; G06V30/244; G06V30/2445
Claims Analysis
Total Claims: 20
Claim 1
Independent Claim
151 words
A computer-implemented method for identifying a script used to create a document, including the steps of: scanning into said computer a set of training documents for each script to be identified to store a series of exemplary images representing said each script; electronically processing pixels forming said exemplary images to electronically define a set of textual symbols corresponding to said exemplary images; assigning each textual symbol to a cluster of textual symbols that most closely represents said textual symbol; forming a representative electronic template for each said cluster; scanning into said computer a document having a script to be identified to form one or more of document images representing said script to be identified; electronically processing pixels forming said document images to electronically define a set of document textual symbols corresponding to said document images; and comparing said set of document textual symbols to said electronic templates to identify said script.
Claim 2
Dependent Claim
151 words
A computer-implemented method for identifying a script used to create a document, including the steps of: scanning into said computer a set of training documents for each script to be identified to store a series of exemplary images representing said each script; electronically processing pixels forming said exemplary images to electronically define a set of textual symbols corresponding to said exemplary images; assigning each textual symbol to a cluster of textual symbols that most closely represents said textual symbol; forming a representative electronic template for each said cluster; scanning into said computer a document having a script to be identified to form one or more of document images representing said script to be identified; electronically processing pixels forming said document images to electronically define a set of document textual symbols corresponding to said document images; and comparing said set of document textual symbols to said electronic templates to identify said script.
Claim 3
Dependent Claim
26 words
A computer implemented method for identifying a script according to claim 1, where said set of training documents includes representative font types from said each script.
Claim 4
Dependent Claim
84 words
A computer implemented method for identifying a script according to claim 1, wherein said step of defining a set of textual symbols further includes the steps of: electronically examining scanned images to locate sets of contiguous black pixels, where each one of said sets defines a region; electronically defining a bounding box comprising the smallest set of rectangular pixel coordinates that encloses each said region; rescaling each said bounding box to a rescaled box to form a textual symbol defined within said rescaled box.
Claim 5
Dependent Claim
84 words
A computer implemented method for identifying a script according to claim 2, wherein said step of defining a set of textual symbols further includes the steps of: electronically examining scanned images to locate sets of contiguous black pixels, where each one of said sets defines a region; electronically defining a bounding box comprising the smallest set of rectangular pixel coordinates that encloses each said region; rescaling each said bounding box to a rescaled box to form a textual symbol defined within said rescaled box.
Claim 6
Dependent Claim
93 words
A computer implemented method for identifying a script according to claim 1, wherein the step of assigning each said textual symbol to a cluster of textual symbols further includes the steps of: determining the similarity between each said textual symbol and each said cluster of textual symbols; assigning said textual symbol to an existing cluster with which said textual symbol has at least a predetermined minimum similarity; and assigning said textual symbol to a new cluster when said textual symbol does not have at least said predetermined minimum similarity with an existing cluster.
Claim 7
Dependent Claim
93 words
A computer implemented method for identifying a script according to claim 2, wherein the step of assigning each said textual symbol to a cluster of textual symbols further includes the steps of: determining the similarity between each said textual symbol and each said cluster of textual symbols; assigning said textual symbol to an existing cluster with which said textual symbol has at least a predetermined minimum similarity; and assigning said textual symbol to a new cluster when said textual symbol does not have at least said predetermined minimum similarity with an existing cluster.
Claim 8
Dependent Claim
93 words
A computer implemented method for identifying a script according to claim 3, wherein the step of assigning each said textual symbol to a cluster of textual symbols further includes the steps of: determining the similarity between each said textual symbol and each said cluster of textual symbols; assigning said textual symbol to an existing cluster with which said textual symbol has at least a predetermined minimum similarity; and assigning said textual symbol to a new cluster when said textual symbol does not have at least said predetermined minimum similarity with an existing cluster.
Claim 9
Dependent Claim
93 words
A computer implemented method for identifying a script according to claim 4, wherein the step of assigning each said textual symbol to a cluster of textual symbols further includes the steps of: determining the similarity between each said textual symbol and each said cluster of textual symbols; assigning said textual symbol to an existing cluster with which said textual symbol has at least a predetermined minimum similarity; and assigning said textual symbol to a new cluster when said textual symbol does not have at least said predetermined minimum similarity with an existing cluster.
Claim 10
Dependent Claim
41 words
A computer implemented method for identifying a script according to claim 1, wherein said representative electronic template is formed with each pixel value determined from a representative value from corresponding pixel values in said textual symbols assigned to said image cluster.
Claim 11
Dependent Claim
41 words
A computer implemented method for identifying a script according to claim 2, wherein said representative electronic template is formed with each pixel value determined from a representative value from corresponding pixel values in said textual symbols assigned to said image cluster.
Claim 12
Dependent Claim
41 words
A computer implemented method for identifying a script according to claim 3, wherein said representative electronic template is formed with each pixel value determined from a representative value from corresponding pixel values in said textual symbols assigned to said image cluster.
Claim 13
Dependent Claim
41 words
A computer implemented method for identifying a script according to claim 4, wherein said representative electronic template is formed with each pixel value determined from a representative value from corresponding pixel values in said textual symbols assigned to said image cluster.
Claim 14
Dependent Claim
41 words
A computer implemented method for identifying a script according to claim 5, wherein said representative electronic template is formed with each pixel value determined from a representative value from corresponding pixel values in said textual symbols assigned to said image cluster.
Claim 15
Dependent Claim
41 words
A computer implemented method for identifying a script according to claim 8, wherein said representative electronic template is formed with each pixel value determined from a representative value from corresponding pixel values in said textual symbols assigned to said image cluster.
Claim 16
Dependent Claim
53 words
A computer implemented method for identifying a script according to claim 1, further including the steps of: determining the reliability of each said cluster of textual symbols to correctly identify script forming said set of training documents; and identifying templates having a low reliability to correctly identify said script forming said test documents.
Claim 17
Dependent Claim
53 words
A computer implemented method for identifying a script according to claim 2, further including the steps of: determining the reliability of each said cluster of textual symbols to correctly identify script forming said set of training documents; and identifying templates having a low reliability to correctly identify said script forming said test documents.
Claim 18
Dependent Claim
53 words
A computer implemented method for identifying a script according to claim 3, further including the steps of: determining the reliability of each said cluster of textual symbols to correctly identify script forming said set of training documents; and identifying templates having a low reliability to correctly identify said script forming said test documents.
Claim 19
Dependent Claim
53 words
A computer implemented method for identifying a script according to claim 5, further including the steps of: determining the reliability of each said cluster of textual symbols to correctly identify script forming said set of training documents; and identifying templates having a low reliability to correctly identify said script forming said test documents.
Claim 20
Dependent Claim
53 words
A computer implemented method for identifying a script according to claim 9, further including the steps of: determining the reliability of each said cluster of textual symbols to correctly identify script forming said set of training documents; and identifying templates having a low reliability to correctly identify said script forming said test documents.
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) | 2001-11-30 | 2002-06-01 | 2002-12-01 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-11-30 | 2006-06-01 | 2006-12-01 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-11-30 | 2010-06-01 | 2010-12-01 | $7700.00 | Window Closed / Lapsed |