US5179599A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Dynamic thresholding system for documents using structural information of the documents
Assignee: HP Inc
•
Filing: 1992-06-11
•
Granted: 1993-01-12
•
Expires: 2012-06-11
Abstract
Abstract Disclosed is a system that converts a scanned image of a complex document, wherein each pixel is represented by a gray scale level, into a bi-level image where text has been preserved and separated from the background. The system subdivides the scanned image into cells, and then creates histograms of the gray scale levels of the pixels in the cells. It creates matrices of the runs of dark pixels within the cells, and examines the runs to determine the extent of connected components. It computes the percentage of runs of each length, and computes the average gray scale level of runs of each length for the document image. It determines peaks in each of the histograms, and determines the width of the first peak within each histogram. The system uses this information to set a gray scale level threshold used to create the bi-level image.
Inventors
- 👤 Lynn J. Formanek
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-03 22:16
CPC Classifications
G; G06; G06V; G06V30/00; G06V30/10; G06V30/16; G06V30/162
Claims Analysis
Total Claims: 12
Claim 1
Independent Claim
202 words
A process for separating text information from background information in a document, said system comprising the steps of: (a) scanning said document to create a scanned image of said document, said scanned image having a gray scale value for each of a plurality of pixels within said document; (b) dividing the document into a plurality of cells; (c) constructing a histogram of said gray scale values of pixels within one of said plurality of cells; (d) determining a number of peaks of said histogram (e) determining a number of each length of dark pixels within said one of said cells; (f) if said histogram contains two peaks and a background peak of said two peaks has a gray scale level equal to or below a determined white level and a number of one dark pixel runs is greater than a predetermined number of one pixel runs value setting a threshold gray scale level for said one of said cells to a predetermined first threshold level; (g) separating said text information from said background information by re-scanning said cell using said threshold gray scale level set in step (e); and (h) repeating steps (c) through (g) for each of said plurality of cells.
Claim 2
Dependent Claim
202 words
A process for separating text information from background information in a document, said system comprising the steps of: (a) scanning said document to create a scanned image of said document, said scanned image having a gray scale value for each of a plurality of pixels within said document; (b) dividing the document into a plurality of cells; (c) constructing a histogram of said gray scale values of pixels within one of said plurality of cells; (d) determining a number of peaks of said histogram (e) determining a number of each length of dark pixels within said one of said cells; (f) if said histogram contains two peaks and a background peak of said two peaks has a gray scale level equal to or below a determined white level and a number of one dark pixel runs is greater than a predetermined number of one pixel runs value setting a threshold gray scale level for said one of said cells to a predetermined first threshold level; (g) separating said text information from said background information by re-scanning said cell using said threshold gray scale level set in step (e); and (h) repeating steps (c) through (g) for each of said plurality of cells.
Claim 3
Dependent Claim
92 words
The process of claim 1 wherein step (f) further comprises the step of: (f1) if said histogram contains two peaks and a background peak of said two peaks has a gray scale level equal to or below a predetermined white level and a number of dark two pixel runs is greater than a predetermined number of two pixel runs value setting a threshold value for said one of said cells to a value equal to one less that a gray scale value of an average run within said one of said cells.
Claim 4
Dependent Claim
86 words
The process of claim 1 wherein step (f) further comprises the step of: (f1) if said histogram contains two peaks and a background peak of said two peaks has a gray scale level equal to or below a predetermined white level and a number of one, two and three dark pixel runs is each less than a predetermined run value setting a threshold value for said one of said cells to a level below a gray scale level of a foreground peak of said two peaks.
Claim 5
Dependent Claim
96 words
The process of claim 1 wherein step (f) further comprises the step of: (f1) if said histogram contains two peaks and a background peak of said two peaks has a gray scale level equal to or below a predetermined white level and any of a number of one, two and three dark pixel runs is greater than a predetermined run value setting a threshold value for said one of said cells to a level between said gray scale level of said background peak and a gray scale level of a foreground peak of said two peaks.
Claim 6
Dependent Claim
104 words
The process of claim 1 wherein step (f) further comprises the step of: (f1) if said histogram contains one peak and a gray scale level of said peak is greater than a predetermined very dark level, setting a threshold value for said one of said cells to a level less than said gray scale level of said peak; and (f2) if said histogram contains one peak and a gray scale level of said peak is less than said predetermined very dark level, setting a threshold level for said one of said cells to a level greater than said gray scale level of said peak.
Claim 7
Dependent Claim
76 words
The process of claim 1 wherein step (f) further comprises the steps of: (f1) constructing a plurality of histograms, one for each cell of a predetermined list of neighboring cells, each said histogram being of said gray scale values of pixels within one cell of said predetermined list of neighboring cells; (f2) determining a background peak of each of said plurality of histograms; and (f3) determining a foreground peak of each of said plurality of histograms.
Claim 8
Dependent Claim
101 words
The process of claim 6 wherein step (f) further comprises the steps of: (f4) for each one of said cells in said predetermined list of neighboring cells, if said histogram for said cell contains three peaks and a middle of said three peaks has a gray scale level within a value of one of a gray scale level of a background peak of any of said neighboring cells, setting a threshold level for said one of said cells to a level between said middle peak gray scale level and a gray scale level of a foreground peak of said three peaks.
Claim 9
Dependent Claim
101 words
The process of claim 6 wherein step (f) further comprises the steps of: (f4) for each one of said cells in said predetermined list of neighboring cells, if said histogram for said cell contains three peaks and a middle of said three peaks has a gray scale level within a value of one of a gray scale level of a foreground peak of any of said neighboring cells, setting a threshold level for said one of said cells to a level between said middle peak gray scale level and a gray scale level of a background peak of said three peaks.
Claim 10
Dependent Claim
59 words
The process of claim 6 wherein step (f) further comprises the steps of: (f4) for each one of said cells in said predetermined list of neighboring cells, if said histogram for said cell contains more than three peaks, setting a threshold level for said one of said cells to an average level of a threshold of said neighboring cells.
Claim 11
Dependent Claim
93 words
The process of claim 1 wherein step (f) further comprises the steps of: (f1) if said histogram contains three peaks and a difference in gray scale level values between a middle of said three peaks and a foreground peak is less than a difference in gray scale level values between said middle of said three peaks and a background peak, setting a threshold level for said one of said cells to a level between said middle peak gray scale level and a gray scale level of said background peak of said three peaks.
Claim 12
Dependent Claim
93 words
The process of claim 1 wherein step (f) further comprises the steps of: (f1) if said histogram contains three peaks and a difference in gray scale level values between a middle of said three peaks and a background peak is less than a difference in gray scale level values between said middle of said three peaks and a foreground peak, setting a threshold level for said one of said cells to a level between said middle peak gray scale level and a gray scale level of said foreground peak of said three peaks.
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) | 1996-01-12 | 1996-07-13 | 1997-01-12 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2000-01-12 | 2000-07-13 | 2001-01-12 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2004-01-12 | 2004-07-13 | 2005-01-12 | $7700.00 | Window Closed / Lapsed |