US5444797A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for automatic character script determination
Assignee: Fujifilm Business Innovation Corp
•
Filing: 1993-04-19
•
Granted: 1995-08-22
•
Expires: 2013-04-19
Abstract
Abstract An automatic script determining apparatus automatically determines the gross script-type of the text image of a document. A connected component generating means generates connected components from the pixels comprising the text image. A bounding box generating means generates a bounding box surrounding each connected component. A centroid determining means determines a centroid for each bounding box. A script feature determining means determines the locations, relative to the centroid, of one or more predetermined types of features, for each bounding box. A script determining means determines a distribution of the located script features for the entire text image, and compares the determined spatial distribution to predetermined distribution for at least one script-type to determine the script type of the text image.
Inventors
- 👤 A. Lawrence Spitz
- 👤 David A. Hull
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-01 11:46
CPC Classifications
G; G06; G06V; G06V10/00; G06V10/40; G06V30/00; G06V30/10; G06V30/24; G06V30/242
Claims Analysis
Total Claims: 27
Claim 1
Independent Claim
265 words
An automatic script determining apparatus for determining a script-type of a script text portion of an image on a document, the script text portion including alphanumeric elements, phonetic elements, ideographic elements or pictographic elements, the script text portion comprising a plurality of characters, the apparatus comprising: a scanner for scanning the script text portion and outputting a digital data signal representative of the script text portion, the digital data signal comprising a plurality of signal portions, each signal portion comprising data representative of a corresponding one of the plurality of pixels of the script text portion; a memory for storing the digital data signal; and a controller for determining the script-type of the script text portion of the image, comprising: connected component generating means for determining a plurality of connected components from the plurality of signal portions, each character of the script text portion comprising at least one of the plurality of connecting components; bounding box determining means for determining a corresponding bounding box around the plurality of signal portions for each one of the plurality of connected components; centroid determining means for determining a centroid of each corresponding bounding box; feature determining means for locating script features, corresponding to at least one predetermined type of script feature, for each corresponding bounding box; spatial distribution determining means for determining a spatial distribution of the located script features of the plurality connected components; comparison means for comparing the determined spatial distribution to predetermined spatial distributions; and output means for outputting a signal indicative of a determined script type of the script text portion of the document.
Claim 2
Dependent Claim
265 words
An automatic script determining apparatus for determining a script-type of a script text portion of an image on a document, the script text portion including alphanumeric elements, phonetic elements, ideographic elements or pictographic elements, the script text portion comprising a plurality of characters, the apparatus comprising: a scanner for scanning the script text portion and outputting a digital data signal representative of the script text portion, the digital data signal comprising a plurality of signal portions, each signal portion comprising data representative of a corresponding one of the plurality of pixels of the script text portion; a memory for storing the digital data signal; and a controller for determining the script-type of the script text portion of the image, comprising: connected component generating means for determining a plurality of connected components from the plurality of signal portions, each character of the script text portion comprising at least one of the plurality of connecting components; bounding box determining means for determining a corresponding bounding box around the plurality of signal portions for each one of the plurality of connected components; centroid determining means for determining a centroid of each corresponding bounding box; feature determining means for locating script features, corresponding to at least one predetermined type of script feature, for each corresponding bounding box; spatial distribution determining means for determining a spatial distribution of the located script features of the plurality connected components; comparison means for comparing the determined spatial distribution to predetermined spatial distributions; and output means for outputting a signal indicative of a determined script type of the script text portion of the document.
Claim 3
Dependent Claim
53 words
The automatic script determining apparatus of claim 1, wherein the at least one predetermined type of script feature comprises at least one of concavities, black passes, white passes, black and white passes, shape measures, connected component populations, bounding box aspect ratios, bounding box area populations, connected component positions and connected component projection profiles.
Claim 4
Dependent Claim
22 words
The automatic script determining apparatus of claim 1, wherein the at least one predetermined type of script feature is upward opening concavities.
Claim 5
Dependent Claim
33 words
The automatic script determining apparatus of claim 3, wherein the spatial distribution determining means determines a vertical distribution of the upward opening concavities of the text portion relative to each corresponding bounding box.
Claim 6
Dependent Claim
37 words
The automatic script determining apparatus of claim 3, wherein the spatial distribution determining means determines the vertical distribution of the upward opening concavities relative to the centroid of a corresponding one of the plurality of bounding boxes.
Claim 7
Dependent Claim
21 words
The automatic script determining apparatus of claim 1, wherein the at least one predetermined type of script feature is black passes.
Claim 8
Dependent Claim
32 words
The automatic script determining apparatus of claim 6, wherein the spatial distribution determining means determines a vertical distribution of the black passes relative to the corresponding bounding box for each connected component.
Claim 9
Dependent Claim
30 words
The automatic script determining apparatus of claim 7, wherein the spatial distribution determining means determines the vertical distribution of the black passes relative to the centroid of each bounding box.
Claim 10
Dependent Claim
35 words
The automatic script determining apparatus of claim 1, wherein the spatial distribution determining means determines spatial distribution of the at least one predetermined script feature relative to the corresponding bounding box for each connected component.
Claim 11
Dependent Claim
34 words
The automatic script determining apparatus of claim 9, wherein the spatial distribution determining means determines spatial distribution of the at least one predetermined script feature relative to the centroid of the corresponding bounding box.
Claim 12
Dependent Claim
181 words
An automatic script determining apparatus for determining a script-type of a script of a document, the script including alphanumeric elements, phonetic elements, ideographic elements or pictographic elements, the document comprising an image comprising a plurality of pixels and having a text portion, the text portion comprising a plurality of characters, the apparatus comprising: input means for inputting a digital data signal representative of the text portion, the digital data signal comprising a plurality of signal portions, each portion corresponding to one of the plurality of pixels; connected component generating means for generating a plurality of connected components from the plurality of signal portions, each character of the text portion comprising at least one of the plurality of connected components; feature determining means for identifying script features within the text portion, corresponding to at least one predetermined type of script feature, based on the plurality of connected components; and script determining means for comparing a distribution of the identified script features with at least one predetermined script feature distribution and determining the script type of the text portion based on the comparison.
Claim 13
Dependent Claim
181 words
An automatic script determining apparatus for determining a script-type of a script of a document, the script including alphanumeric elements, phonetic elements, ideographic elements or pictographic elements, the document comprising an image comprising a plurality of pixels and having a text portion, the text portion comprising a plurality of characters, the apparatus comprising: input means for inputting a digital data signal representative of the text portion, the digital data signal comprising a plurality of signal portions, each portion corresponding to one of the plurality of pixels; connected component generating means for generating a plurality of connected components from the plurality of signal portions, each character of the text portion comprising at least one of the plurality of connected components; feature determining means for identifying script features within the text portion, corresponding to at least one predetermined type of script feature, based on the plurality of connected components; and script determining means for comparing a distribution of the identified script features with at least one predetermined script feature distribution and determining the script type of the text portion based on the comparison.
Claim 14
Dependent Claim
26 words
The automatic script determining apparatus of claim 11, wherein the at least one predetermined script feature is upward opening concavities in the plurality of connected components.
Claim 15
Dependent Claim
39 words
The automatic script determining apparatus of claim 11, wherein the feature determining means comprises: a bounding box determining means for determining a bounding box of the plurality of signal portions for each one of the plurality of connected components.
Claim 16
Dependent Claim
30 words
The automatic script determining apparatus of claim 13, wherein the at least one predetermined script feature is black passes in the bounding boxes of the a plurality of connected components.
Claim 17
Dependent Claim
49 words
The automatic script determining apparatus of claim 13, wherein the feature determining means further comprises: a centroid determining means for determining a centroid for each bounding box; and feature locating means for locating the identified script features within each bounding box relative to the centroid of each bounding box.
Claim 18
Dependent Claim
31 words
The automatic script determining apparatus of claim 15, wherein the script determining means comprises a spatial distribution means for determining a spatial distribution of the located features normalized to the centroid.
Claim 19
Dependent Claim
26 words
The automatic script determining apparatus of claim 16, wherein the at least one predetermined script feature comprises upwardly facing concavities in the plurality of connected components.
Claim 20
Dependent Claim
29 words
The automatics script determining apparatus of claim 16, wherein the at least one predetermined script feature comprises black passes in the bounding boxes of the plurality of connected components.
Claim 21
Dependent Claim
53 words
The automatic script determining apparatus of claim 11, wherein the at least one predetermined script feature comprises at least one of connected component concavities, black passes, white passes, black and white passes, shape measures, connected component populations, bounding box aspect ratios, bounding box area populations, connected component positions and connected component projection profiles.
Claim 22
Independent Claim
134 words
A method for automatically determining a script-type of a script text portion of a document, the script text portion including alphanumeric elements, phonetic elements, ideographic elements or pictographic elements, the script text portion comprising a plurality of characters, the method comprising the steps of: determining a plurality of connected components from a plurality of pixels comprising the script text portion, each character of the script text portion comprising at least one of the plurality of connected components; determining locations of script features of the script text portion based on the plurality of connected components corresponding to at least one preselected type of script feature; comparing a spatial distribution of the located script features with at least one predetermined script feature spatial distribution; and determining the script-type based on the comparison of the comparison step.
Claim 23
Independent Claim
134 words
A method for automatically determining a script-type of a script text portion of a document, the script text portion including alphanumeric elements, phonetic elements, ideographic elements or pictographic elements, the script text portion comprising a plurality of characters, the method comprising the steps of: determining a plurality of connected components from a plurality of pixels comprising the script text portion, each character of the script text portion comprising at least one of the plurality of connected components; determining locations of script features of the script text portion based on the plurality of connected components corresponding to at least one preselected type of script feature; comparing a spatial distribution of the located script features with at least one predetermined script feature spatial distribution; and determining the script-type based on the comparison of the comparison step.
Claim 24
Dependent Claim
27 words
The method for automatically determining the script type of claim 21, wherein the at least one preselected script feature is upward facing concavities in the bounding boxes.
Claim 25
Dependent Claim
75 words
The method for automatically determining the script type of claim 20, wherein the step of determining locations of script feature comprising the steps of determining, for each one of the plurality of connected components, a corresponding bounding box enclosing each said one connected component; determining a centroid for each corresponding bounding box; and locating the script features of each one of the plurality of connected components relative to the centroid for the corresponding bounding box.
Claim 26
Dependent Claim
26 words
The method for automatically determining the script-type of claim 22, wherein the at least one preselected script feature is black passes in each corresponding bounding box.
Claim 27
Dependent Claim
65 words
The method for automatically determining the script-type of claim 20, further comprising the step of selecting, as the at least one preselected script feature, at least one script feature from the group comprising connected component concavities, black passes, white passes, black and white passes, shape measures, connected component populations, bounding box aspect ratios, bounding box area populations, connected component positions and connected component projection profiles.
References Cited (Backward Citations)
US3755780A
Cited
US4516262A
Cited
US4802230A
Cited
US5048100A
Cited
US5181259A
Cited
US5253307A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1998-08-21 | 1999-02-20 | 1999-08-22 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-08-21 | 2003-02-20 | 2003-08-22 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-08-21 | 2007-02-20 | 2007-08-22 | $7700.00 | Window Closed / Lapsed |