Patent US5381241A successfully refreshed from Google Patents.
US5381241A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for discriminating between figure and text areas of an image
Assignee: Ezel Inc
•
Filing: 1992-08-11
•
Granted: 1995-01-10
•
Expires: 2012-08-11
Abstract
Abstract The present invention relates to a method for discriminating between figure areas, e.g., half-tone photographs, drawings and the like, and text areas in an image. More specifically, an image is processed to determine the difference between maximum and minimum brightnesses in convolutions thereof. When the difference between the maximum and minimum brightnesses is less than or equal to a predetermined level, the center pixel in the convolution is determined to be a half-tone pixel. A half-tone area is detected by determining areas of the image having at least a predetermined number of half-tone pixels. In another aspect of the invention, contiguous areas of the image having fewer than a predetermined number of configuration pixels are determined to be vacant areas having neither figure nor character information.
Inventors
- 👤 Seido Kawanaka
- 👤 Shiro Ida
- 👤 Hideo Takemura
- 👤 Kouji Kumetani
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 12:51
CPC Classifications
H; H04; H04N; H04N1/00; H04N1/40; H04N1/40062
Claims Analysis
Total Claims: 40
Claim 1
Independent Claim
154 words
A method for classifying areas in an image to extract a half-tone area, said method comprising the steps of: for each pixel in said image, performing convolutions of a predetermined size with said each pixel as a center pixel in said convolutions, thereby determine a maximal convolution brightness and a minimal convolution brightness for said pixel; calculating a brightness difference between said maximal and minimal convolution brightnesses of said center pixel; defining the center pixel as a half-tone pixel when said difference is less than or equal to a first predetermined value, said maximal brightness is less than or equal to a second predetermined value and said minimal brightness is greater than or equal to a third predetermined value; counting a number of half-tone pixels within a given area; and defining areas in said image as half-tone areas when said number of half-tone pixels is greater than or equal to a fourth predetermined value.
Claim 2
Independent Claim
154 words
A method for classifying areas in an image to extract a half-tone area, said method comprising the steps of: for each pixel in said image, performing convolutions of a predetermined size with said each pixel as a center pixel in said convolutions, thereby determine a maximal convolution brightness and a minimal convolution brightness for said pixel; calculating a brightness difference between said maximal and minimal convolution brightnesses of said center pixel; defining the center pixel as a half-tone pixel when said difference is less than or equal to a first predetermined value, said maximal brightness is less than or equal to a second predetermined value and said minimal brightness is greater than or equal to a third predetermined value; counting a number of half-tone pixels within a given area; and defining areas in said image as half-tone areas when said number of half-tone pixels is greater than or equal to a fourth predetermined value.
Claim 3
Dependent Claim
20 words
The method of claim 1, further comprising a step of reducing said image before performing the center pixel defining step.
Claim 4
Dependent Claim
31 words
The method of claim 2, wherein said image is reduced so that a distance between adjacent pixels in the reduced image is approximately within the range 0.5 mm to 1.0 mm.
Claim 5
Dependent Claim
28 words
The method of claim 1, further comprising a step of swelling and contracting said image, thereby deleting a character area in a peripheral region of a half-tone area.
Claim 6
Dependent Claim
24 words
The method of claim 1, wherein said area defining step comprising a step of defining a rectangle of minimal area circumscribing said half-tone areas.
Claim 7
Dependent Claim
24 words
The method of claim 1, further comprising a step of defining a rectangle of minimal area circumscribing a plurality of rectangles overlapping each other.
Claim 8
Dependent Claim
29 words
The method of claim 1, further comprising a step of deleting a rectangle from half-tone areas when said rectangle has a side which is shorter than a predetermined length.
Claim 9
Dependent Claim
46 words
The method of claim 1, wherein said area defining step comprises a step of prohibiting a rectangle from being defined as one of said half-tone areas when a proportion of a vertical side of said rectangle to a horizontal side thereof is outside a predetermined range.
Claim 10
Independent Claim
96 words
A method of classifying areas in an image to identify vacant areas, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas each having a predetermined size; counting a number of configuration pixels in each unit area; defining a vacant area candidate which includes said unit areas when said number of configuration pixels in each unit areas in said area candidate is less than or equal to a predetermined value; and defining a vacant area by a rectangle having a maximal characteristic among rectangles inscribing said area candidate.
Claim 11
Independent Claim
96 words
A method of classifying areas in an image to identify vacant areas, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas each having a predetermined size; counting a number of configuration pixels in each unit area; defining a vacant area candidate which includes said unit areas when said number of configuration pixels in each unit areas in said area candidate is less than or equal to a predetermined value; and defining a vacant area by a rectangle having a maximal characteristic among rectangles inscribing said area candidate.
Claim 12
Independent Claim
100 words
A method for classifying areas in an image to extract a vacant area, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting a number of configuration pixels in each unit area; defining a vacant area candidate which includes said unit areas when said number of configuration pixels in each unit areas in said area candidate is less than or equal to a predetermined value; and defining a vacant area by a rectangle which includes a maximum number of said unit areas among rectangles internally touching said candidate.
Claim 13
Independent Claim
100 words
A method for classifying areas in an image to extract a vacant area, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting a number of configuration pixels in each unit area; defining a vacant area candidate which includes said unit areas when said number of configuration pixels in each unit areas in said area candidate is less than or equal to a predetermined value; and defining a vacant area by a rectangle which includes a maximum number of said unit areas among rectangles internally touching said candidate.
Claim 14
Independent Claim
90 words
A method for classifying areas in an image to extract a configuration area, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas having a predetermined size; counting a number of configuration pixels in each unit area; defining a configuration area candidate including said unit areas when said number of configuration pixels of each unit area in said area candidate is greater than or equal to a predetermined value; and defining a configuration area by a rectangle circumscribed about said area candidate.
Claim 15
Independent Claim
90 words
A method for classifying areas in an image to extract a configuration area, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas having a predetermined size; counting a number of configuration pixels in each unit area; defining a configuration area candidate including said unit areas when said number of configuration pixels of each unit area in said area candidate is greater than or equal to a predetermined value; and defining a configuration area by a rectangle circumscribed about said area candidate.
Claim 16
Independent Claim
99 words
A method for classifying areas in an image to extract a configuration area, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting a number of configuration pixels in each unit area; defining a configuration area candidate including said unit areas when said number of configuration pixels of each unit area in said area candidate is greater than or equal to a predetermined value; defining a rectangle circumscribing said candidate area; and defining a configuration area including said rectangle, said configuration area being bigger than said rectangle.
Claim 17
Independent Claim
99 words
A method for classifying areas in an image to extract a configuration area, said method comprising the steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting a number of configuration pixels in each unit area; defining a configuration area candidate including said unit areas when said number of configuration pixels of each unit area in said area candidate is greater than or equal to a predetermined value; defining a rectangle circumscribing said candidate area; and defining a configuration area including said rectangle, said configuration area being bigger than said rectangle.
Claim 18
Dependent Claim
16 words
The method of claim 9, further comprising a step of reducing a size of said image.
Claim 19
Dependent Claim
15 words
The method of claim 9, further comprising a step of reducing noise in said image.
Claim 20
Dependent Claim
29 words
The method of claim 9, further comprising a step of filling a border of said image with configuration pixels, thereby excluding said border from consideration as a vacant area.
Claim 21
Dependent Claim
14 words
The method of claim 9, wherein said characteristic is an area of said rectangle.
Claim 22
Dependent Claim
18 words
The method of claim 9, wherein said characteristic is a length of a longest side of said rectangle.
Claim 23
Dependent Claim
26 words
The method of claim 9, wherein said characteristic is a total length of a longest side of said rectangle and a shortest side of said rectangle.
Claim 24
Dependent Claim
101 words
The method of claim 9, said vacant area defining step comprising the steps of: moving a corner of said rectangle in a first direction toward a non-vacant area of said image until said corner enters said non-vacant area; moving said corner an amount in a direction opposite to said first direction so that said corner is in said non-vacant area; moving said corner in a second direction toward said non-vacant area until said corner enters said non-vacant area; and moving said corner an amount in a direction opposite to said second direction so that said corner is in said non-vacant area.
Claim 25
Dependent Claim
37 words
The method of claim 9, further comprising a step of generating a density projection of said rectangle; and determining a border line between said vacant area and a non-vacant area of said image using said density projection.
Claim 26
Dependent Claim
14 words
The method of claim 20, wherein said density projection is a two-dimensional density projection.
Claim 27
Dependent Claim
13 words
The method of claim 11, further comprising a step of reducing said image.
Claim 28
Dependent Claim
18 words
The method of claim 11, said binarizing step comprising a step of calculating a histogram of said image.
Claim 29
Dependent Claim
21 words
The method of claim 11, wherein said binarizing step is performed using an optimal threshold based on a center density value.
Claim 30
Dependent Claim
20 words
The method of claim 11, wherein said binarizing step is performed using an optimal threshold selected using a mode method.
Claim 31
Dependent Claim
21 words
The method of claim 11, wherein said binarizing step is performed using an optimal threshold selected using a discrimination analysis method.
Claim 32
Dependent Claim
20 words
The method of claim 11, wherein said binarizing step is performed using an optimal threshold selected using a p-style method.
Claim 33
Dependent Claim
32 words
The method of claim 11, further comprising a step of setting pixels in a border of said binarized image to zero density, thereby eliminating said border from consideration as a configuration area.
Claim 34
Dependent Claim
22 words
The method of claim 11 further comprising a step of reducing noise in said binarized image using an isolated point reduction technique.
Claim 35
Dependent Claim
20 words
The method of claim 11 further comprising a step of reducing noise in said binarized image using a shrinking technique.
Claim 36
Dependent Claim
21 words
The method of claim 11 further comprising a step of reducing noise in said binarized image using a median filter technique.
Claim 37
Dependent Claim
21 words
The method of claim 11 further comprising a step of extracting said configuration area using said rectangle as a mask image.
Claim 38
Dependent Claim
22 words
The method of claim 32, wherein said extracting step comprises a step of switching an image signal according to said mask image.
Claim 39
Dependent Claim
24 words
The method of claim 32, wherein said extracting step comprises a step of ANDing bits in said image with bits in said mask image.
Claim 40
Dependent Claim
37 words
The method of claim 32, further comprising a step of: reducing noise in said binarized image; wherein said extracting step comprises a step of expanding said mask image to include pixels eliminated in said noise reduction step.
References Cited (Backward Citations)
US4547811A
Cited
US4400738A
Cited
US4630125A
Cited
US4729035A
Cited
US5267330A
Cited
GB2167264A
Cited
US4639775A
Cited
US4742557A
Cited
US4860371A
Cited
US4823194A
Cited
US4809343A
Cited
US4941192A
Cited
US5253082A
Cited
EP0348703A2
Cited
US4941190A
Cited
EP0362595A2
Cited
US5153925A
Cited
US5189710A
Cited
US5278919A
Cited
US5081692A
Cited
EP0527488A2
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1998-01-09 | 1998-07-11 | 1999-01-10 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-01-09 | 2002-07-11 | 2003-01-10 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-01-09 | 2006-07-11 | 2007-01-10 | $7700.00 | Window Closed / Lapsed |