US5091964A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Apparatus for extracting a text region in a document image
Assignee: FUJIFACOM Corp 1 FUJI-MACHI HINO-SHI TOKYO JAPAN
•
Filing: 1991-04-01
•
Granted: 1992-02-25
•
Expires: 2011-04-01
Abstract
Abstract A peripheral distribution of filled pixels in a document image is calculated by projecting the filled pixels in an X-axis or a Y-axis direction. A bottom part in the peripheral distribution is detected. The document image is divided into a plurality of primary image regions in accordance with a dividing line intersecting the bottom part in the X-axis or Y-axis direction, so that the document image is classified into text regions, drawing regions and picture regions. Thus, the text regions can be extracted automatically from the document image without requiring a specific manual operation for extracting text regions by an operator.
Inventors
- 👤 Shoji Shimomura
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-28 14:12
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/40; G06V30/41; G06V30/413; H; H04; H04N; H04N1/00; H04N1/40; H04N1/40062
Claims Analysis
Total Claims: 17
Claim 1
Independent Claim
241 words
An apparatus for extracting a text region in a document image, comprising: projection calculation means for calculating a peripheral distribution of filled pixels in a document image, which contains a mixed form of text and other kind of visual information and which is represented in terms of binary data, by projecting the filled pixels in a predetermined direction, said predetermined direction being a direction extending along either one of an X-axis and a Y-axis; detection means for detecting a bottom part in the peripheral distribution calculated; dividing means for dividing said document image into a plurality of primary image regions in accordance with a line intersecting the bottom part in said predetermined direction; reduction means for reducing each of the plurality of primary image regions divided by said dividing means until the size of said primary image region reaches the size of a circumscribed rectangular frame of filled pixels to form a plurality of secondary image regions in which unfilled pixels are excluded from said primary image regions; consolidating means for consolidating a plurality of secondary image regions adjacent to one another among said plurality of secondary image regions into a single tertiary image region; and extraction means for calculating a line density of filled pixels in said tertiary image region consolidated and for extracting a text region from said document image by judging that said tertiary image region is a text region when said calculation result indicates a text image.
Claim 2
Independent Claim
241 words
An apparatus for extracting a text region in a document image, comprising: projection calculation means for calculating a peripheral distribution of filled pixels in a document image, which contains a mixed form of text and other kind of visual information and which is represented in terms of binary data, by projecting the filled pixels in a predetermined direction, said predetermined direction being a direction extending along either one of an X-axis and a Y-axis; detection means for detecting a bottom part in the peripheral distribution calculated; dividing means for dividing said document image into a plurality of primary image regions in accordance with a line intersecting the bottom part in said predetermined direction; reduction means for reducing each of the plurality of primary image regions divided by said dividing means until the size of said primary image region reaches the size of a circumscribed rectangular frame of filled pixels to form a plurality of secondary image regions in which unfilled pixels are excluded from said primary image regions; consolidating means for consolidating a plurality of secondary image regions adjacent to one another among said plurality of secondary image regions into a single tertiary image region; and extraction means for calculating a line density of filled pixels in said tertiary image region consolidated and for extracting a text region from said document image by judging that said tertiary image region is a text region when said calculation result indicates a text image.
Claim 3
Dependent Claim
36 words
An apparatus for extracting a text region in a document image as claimed in claim 1, further comprising: smoothing means for smoothing binary image data to be used for projection calculation by said projection calculation means.
Claim 4
Dependent Claim
41 words
An apparatus for extracting a text region in a document image as claimed in claim 1, wherein said extraction means further comprising: display means for displaying said tertiary image data extracted by said extraction means in the form of visual drawing.
Claim 5
Dependent Claim
40 words
An apparatus for extracting a text region in a document image as claimed in claim 1, wherein said extracting means further uses a filled-pixel density in addition to said line density when a type of a document image is judged.
Claim 6
Dependent Claim
36 words
An apparatus for extracting a text region in a document image as claimed in claim 1, further comprising: smoothing means for smoothing binary image data to be used for projection calculation by said projection calculation means.
Claim 7
Independent Claim
179 words
A method of extracting a text region in a document image, comprising the steps of: calculating a peripheral distribution of filled pixels in a document image, which contains a mixed form of text and other kind of visual information and which is represented in terms of binary data, by projecting the filled pixels in a predetermined direction, said predetermined direction being a direction extending along either one of an X-axis and a Y-axis; detecting a bottom part in the peripheral distribution calculated; dividing said document image into a plurality of primary image regions in accordance with a line intersecting the bottom part in said predetermined direction; consolidating means for consolidating a plurality of secondary image regions adjacent to one another among said plurality of secondary image regions into a single tertiary image region; and extraction means for calculating a line density of filled pixels in said tertiary image region consolidated and for extracting a text region from said document image by judging that said tertiary image region is a text region when said calculation result indicates a text image.
Claim 8
Independent Claim
179 words
A method of extracting a text region in a document image, comprising the steps of: calculating a peripheral distribution of filled pixels in a document image, which contains a mixed form of text and other kind of visual information and which is represented in terms of binary data, by projecting the filled pixels in a predetermined direction, said predetermined direction being a direction extending along either one of an X-axis and a Y-axis; detecting a bottom part in the peripheral distribution calculated; dividing said document image into a plurality of primary image regions in accordance with a line intersecting the bottom part in said predetermined direction; consolidating means for consolidating a plurality of secondary image regions adjacent to one another among said plurality of secondary image regions into a single tertiary image region; and extraction means for calculating a line density of filled pixels in said tertiary image region consolidated and for extracting a text region from said document image by judging that said tertiary image region is a text region when said calculation result indicates a text image.
Claim 9
Dependent Claim
33 words
A method of extracting a text region in a document image as claimed in claim 6, further comprising the step of smoothing binary image data to be used for calculating said peripheral distribution.
Claim 10
Dependent Claim
38 words
A method of extracting a text region in a document image as claimed in claim 6, wherein said tertiary image data extracted by said extraction means is displayed in the form of visual drawing by a display unit.
Claim 11
Dependent Claim
37 words
A method of extracting a text region in a document image as claimed in claim 6, wherein a filled-pixel density is used in addition to said line density when a type of a document image is judged.
Claim 12
Dependent Claim
33 words
An apparatus for extracting a text region in a document image as claimed in claim 6, further comprising the step of smoothing binary image data to be used for calculating said peripheral distribution.
Claim 13
Dependent Claim
250 words
A character recognizing apparatus for recognizing characters in a text region in a document image, comprising: projection calculation means for calculating a peripheral distribution of filled pixels in a document image, which contains a mixed form of text and other kind of visual information and which is represented in terms of binary data, by projecting the filled pixels in a predetermined direction extending along either one of an X-axis and a Y-axis; detection means for detecting a bottom part in the peripheral distribution calculated; dividing means for dividing said document image into a plurality of primary image regions in accordance with a line intersecting the bottom part in said predetermined direction; reduction means for reducing each of the plurality of primary image regions divided by said dividing means until the size of said primary image region reaches the size of a circumscribed rectangular frame of filled pixels to form a plurality of secondary image regions in which unfilled pixels are excluded from said primary image regions; consolidating means for consolidating a plurality of secondary image regions adjacent to one another among said plurality of secondary image regions into a single tertiary image region; and extraction means for calculating a line density of filled pixels in said tertiary image region consolidated and for extracting a text region from said document image by judging that said tertiary image region is a text region when said calculation result indicates a text image; and recognizing means for recognizing characters in said text region extracted.
Claim 14
Dependent Claim
250 words
A character recognizing apparatus for recognizing characters in a text region in a document image, comprising: projection calculation means for calculating a peripheral distribution of filled pixels in a document image, which contains a mixed form of text and other kind of visual information and which is represented in terms of binary data, by projecting the filled pixels in a predetermined direction extending along either one of an X-axis and a Y-axis; detection means for detecting a bottom part in the peripheral distribution calculated; dividing means for dividing said document image into a plurality of primary image regions in accordance with a line intersecting the bottom part in said predetermined direction; reduction means for reducing each of the plurality of primary image regions divided by said dividing means until the size of said primary image region reaches the size of a circumscribed rectangular frame of filled pixels to form a plurality of secondary image regions in which unfilled pixels are excluded from said primary image regions; consolidating means for consolidating a plurality of secondary image regions adjacent to one another among said plurality of secondary image regions into a single tertiary image region; and extraction means for calculating a line density of filled pixels in said tertiary image region consolidated and for extracting a text region from said document image by judging that said tertiary image region is a text region when said calculation result indicates a text image; and recognizing means for recognizing characters in said text region extracted.
Claim 15
Dependent Claim
35 words
A character recognizing apparatus as claimed in claim 11, wherein said extraction means further comprises display means for displaying said tertiary image data extracted by said extraction means in the form of a visual drawing.
Claim 16
Dependent Claim
33 words
A character recognizing apparatus as claimed in claim 11, wherein said extracting means further uses a filled-pixel density in addition to said line density when a type of a document image is judged.
Claim 17
Dependent Claim
30 words
A character recognizing apparatus as claimed in claim 11, further comprising smoothing means for smoothing binary image data to be used for a projection calculation by said projection calculation means.
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) | 1995-02-24 | 1995-08-26 | 1996-02-25 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1999-02-24 | 1999-08-26 | 2000-02-25 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2003-02-24 | 2003-08-26 | 2004-02-25 | $7700.00 | Window Closed / Lapsed |