EP0527488A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Area classification method of an image
Assignee: Yozan Inc
•
Filing: 1992-08-12
•
Granted: —
•
Expires: 2012-08-12
Abstract
Abstract A area classification method of an image for extracting half-tone area, configuration area and vacant area. Half-tone is area defined according to number of half-tone pixels. Half-tone pixel is found when a convolution has pixels of predetermined deference in brightness and predetermined range of brightness. Configuration area is defined according to number of configuration pixels and horizontal rectangle circumscribed about a candidate of a configuration area. Vacant area is defined according to number of configuration pixels and horizontal rectangle circumscribed about a candidate of a vacant.
Inventors
- 👤 Seido Kawanaka
- 👤 Shiro Ida
- 👤 Hideo Takemura
- 👤 Kouji Kumetani
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 12:29
CPC Classifications
H; H04; H04N; H04N1/00; H04N1/40; H04N1/40062
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
110 words
An area classification method of an image for extracting half-tone area comprising steps of: calculating brightness differences between maximal and minimal brightness of pixels in each convolution of said image, said convolution having predetermined size; defining the center pixel of said convolution as a half-tone pixel when said difference is equal to a predetermined value or less, said maximal brightness is predetermined value or less and said minimal brightness is predetermined value or more; and defining areas in said image and counting number of said half-tone pixels so that area of said areas are defined as a half-tone area when said number of half-tone pixels is predetermined value or more.
Claim 2
Dependent Claim
24 words
An area classification method as claimed in Claim 1, further comprising a step of diminishing said image before the step of defining half-tone pixels.
Claim 3
Dependent Claim
33 words
An area classification method as claimed in Claim 2 , wherein said image is contracted so that distance between adjacent pixels in a contracted image is approximately from 0.5 mm to 1.0 mm.
Claim 4
Dependent Claim
28 words
An area classification method as claimed in Claim 1, further comprising a step of swelling and contracting for deleting character area in the peripheral of said half-tone area.
Claim 5
Dependent Claim
34 words
An area classification method as claimed in Claim 1, further comprising a step of defining a horizontal rectangle as a half-tone area, said rectangle circumscribed about an area consisting of adjacent said half-tone areas.
Claim 6
Dependent Claim
36 words
An area classification method as claimed in Claim 1, further comprising a step of defining a rectangle as a half-tone area, said rectangle circumscribed about an area consisting of a plurality of rectangles overlapping each other.
Claim 7
Dependent Claim
30 words
An area classification method as claimed in Claim 1, further comprising a step of deleting a rectangle from half-tone areas when said rectangle has shorter side than a predetermined length.
Claim 8
Dependent Claim
38 words
An area classification method as claimed in Claim 1, further comprising a step of deleting a rectangle from half-tone areas when said rectangle has a proportion of vertical side to horizontal side is not within a predetermined value.
Claim 9
Dependent Claim
82 words
An area classification method of an image for extracting vacant area comprising steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting number of configuration pixels in each unit area; defining a candidate of vacant area consisting of said unit areas when said number of configuration pixels of said unit area is predetermined value or less; and defining a vacant area by a rectangle with longest longer side among rectangles being inscribed said candidate.
Claim 10
Dependent Claim
84 words
An area classification method of an image for extracting vacant area comprising steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting number of configuration pixels in each unit area; defining a candidate of vacant area consisting of said unit areas when said number of configuration pixels of said unit area is predetermined value or less; and defining a vacant area by a rectangle with maximum number of unit areas among rectangles internally touching said candidate.
Claim 11
Dependent Claim
78 words
An area classification method of an image for extracting configuration area comprising steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting number of configuration pixels in each unit area; defining a candidate of configuration area consisting of said unit areas when said number of configuration pixels of said unit area is predetermined value or more; and defining a configuration area by a horizontal rectangle circumscribed about said candidate area.
Claim 12
Dependent Claim
84 words
An area classification method of an image for extracting configuration area comprising steps of: binarizing said image; dividing said image into a plurality of unit areas with predetermined size; counting number of configuration pixels in each unit area; defining a candidate of configuration area consisting of said unit areas when said number of configuration pixels of said unit area is predetermined value or more; defining a horizontal rectangle circumscribed about said candidate area; and defining a configuration area including and bigger than said rectangle.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.