CN1734471A - Method and apparatus for estimating file inclination - Google Patents
Method and apparatus for estimating file inclination Download PDFInfo
- Publication number
- CN1734471A CN1734471A CN 200410056571 CN200410056571A CN1734471A CN 1734471 A CN1734471 A CN 1734471A CN 200410056571 CN200410056571 CN 200410056571 CN 200410056571 A CN200410056571 A CN 200410056571A CN 1734471 A CN1734471 A CN 1734471A
- Authority
- CN
- China
- Prior art keywords
- binary picture
- scan
- data
- inclination
- angle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Editing Of Facsimile Originals (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an inclination estimation method of scanning files, which comprises the following steps: first, scanning a file to generate first scanning datum which converse to binary image; second, judging the image whether containing an image area; third, generating a binary image removal if yes; finally, calculating the inclination according to present judgment and the binary image removal.
Description
Technical field
The present invention is about a kind of evaluation method and device thereof, particularly about estimate the method and the device thereof at the angle of inclination that is produced when scanning a file.
Background technology
When duplicating or scanning document, because arbitrarily putting file, the user causes scanning crooked image sometimes.When quantity of documents was a lot of, the user must be ajusted file page by page by manual mode, and is quite time-consuming also bothersome.
In the routine techniques, the file angle of inclination can utilize the mode of software to calculate and then it is become a full member.As United States Patent (USP) the 6th, 493, No. 470 disclosed methods promptly are to utilize software program to carry out the scanning document angle of inclination function of becoming a full member.
Fundamental purpose of the present invention is to provide a kind of estimate angle that file tilts and the method that the file scan image is become a full member.
Summary of the invention
A purpose of the present invention is to provide the method at a kind of estimation one angle of inclination, and it can be used for estimating the angle of inclination that is produced when scanning a file, and then scan image is become a full member.
Another object of the present invention is to provide a kind of in order to estimating the device at an angle of inclination, the angle of inclination that it is produced in the time of can automatically estimating scanning one file, and then scan image become a full member.
In the method at the angle of inclination that is produced when estimating scanning one file according to the present invention, at first scanning document is to produce one first scan-data.Then first scan-data being converted to a gray level image (grayimage), is binary picture (binary image) according to a threshold value with greyscale image transitions again.
Judging that binary picture has does not comprise figure (graph) district, if the deletion graph area is arranged then in binary picture to produce a deletion binary picture.Utilize a predetermined discriminant approach and, calculate the angle of inclination according to the deletion binary picture.Again with one second predetermined resolution scanning document, to produce one second scan-data; And, rotate second scan-data according to the angle of inclination that calculates.
The present invention estimates in the method at angle of inclination, but the design software Automatic Program goes to calculate the angle of inclination of scanning document, and carries out the work that the file scan image is become a full member automatically.Therefore use method that the present invention estimates the angle of inclination when scanning or hard-copy file, need not utilize manual mode to remove to ajust to be scanned/file of duplicating one by one, to save time and manpower by the user.
Can be further understood via following detailed Description Of The Invention and appended diagram about the advantages and spirit of the present invention.
Description of drawings
Fig. 1 estimates the system block diagrams of file angle of inclination device for the present invention.
Fig. 2 estimates the histogrammic synoptic diagram that file angle of inclination method is utilized for the present invention.
Fig. 3 estimates the threshold operation method flow diagram of file angle of inclination method for the present invention.
Fig. 4 estimates the synoptic diagram of the mask determining method of file angle of inclination method for the present invention.
Fig. 5 estimates the flow chart of steps of file angle of inclination method for the present invention
Fig. 6 estimates the flow chart of steps of another embodiment of file angle of inclination method for the present invention.
The drawing reference numeral explanation
10: estimating device 11: controller
12: modular converter 14: judge module
16: computing module 30: mask
Embodiment
See also Fig. 1, Fig. 1 is the system block diagrams of the estimating device 10 at file of the present invention angle of inclination.Estimating device 10 of the present invention is in order to estimate the angle of inclination that is produced when scanning a file.Estimating device 10 comprises a controller 11, a modular converter 12, a judge module 14 and a computing module 16.
See also Fig. 2 and Fig. 3, the synoptic diagram of the histogram (histogram) that Fig. 2 is utilized for the modular converter 12 of Fig. 1, the operational method process flow diagram of the threshold value that Fig. 3 is utilized for Fig. 1 modular converter 12.Modular converter 12 is converted to a gray level image (gray image) with first scan-data, and foundation one threshold value is a binary picture (binary image) with this greyscale image transitions.Below will utilize a histogrammic embodiment with 256 color level that the mode of greyscale image transitions for binary picture is described.In embodiment shown in Figure 2, gray level image is divided into 256 levels, i.e. 0 to 255 level.The image number that each grade comprises promptly represents the gray level image of being changed in the shared image number of this grade.For example, after first scan-data is converted to gray level image, can obtain in the gray level image via this histogram, the image number that each grade is shared, and set a threshold value (threshold) according to this being binary picture with image transitions.
The relation of literal and background is then considered in the setting of this threshold value.In an embodiment, state one is the dark bright situation of literal of background, and state two is the dark situation of the bright literal of background; The formula of this threshold value is respectively formula one and formula two.
Formula one (state one):
Formula two (state two):
In the above-mentioned formula one, two, i represents i level, and X is the number percent that background that experimental observation gets accounts for whole literal, and H is the aggregate-value of shared number in each grade in the histogram, and T is the number of all pixels.
In an embodiment, this threshold value can be utilized software systems computing in addition.Fig. 3 shows an embodiment of the computing flow process of this threshold value; With resulting data in the gray level image histogram, import this computing flow process, the value that can try to achieve one-level is threshold.The gray level image histogram can be divided into two zones according to the threshold value, and then be binary picture with image transitions, and binary picture can be considered and has only black and two kinds of colors of white promptly 0 and 1, wherein 0 represent that color is the image of black in the binary picture, 1 represent then that color is white image in the binary picture.More than being illustrated as greyscale image transitions is an embodiment of the threshold value dynamic calculation of binary picture.The mode that depends on of relevant threshold value has many kinds, and is well known in the art, so other modes no longer describe in detail.
See also Fig. 4, Fig. 4 is the synoptic diagram of judge module 14 mask that utilizes of Fig. 1.In another embodiment, judge module 14 utilizes mask method to judge that binary picture has not comprise figure (graph) district.In embodiment shown in Figure 4 is a 3*3 mask, this mask is utilized on binary picture, if the regional corresponding mask sum of products in the binary picture during greater than a predetermined value, as greater than 4 o'clock, judges that then this piece zone is a graph area.The complexity of the method is much smaller than four connections, eight connection methods.
ρ＝xcosθ+ysinθ；0θ＜π。
In the Hough conversion, (x, the y) M of conllinear point on the coordinate plane is in (ρ, θ) coordinate plane should be the M bar sinusoidal curve that meets at same point relatively.Utilize Hough to change this characteristic, point on the deletion binary picture can be gathered (x, y) coordinate values is converted to (ρ, the θ) set of the sinusoidal curve on the plane, these sinusoidal curves will be according to the directivity of literal on its file, and major part can meet at a plurality of points with close θ value.Utilize the numerical value of these some set,, can obtain the approximate angle value (θ) that file tilts with the account form of average or proportion.
See also Fig. 5, Fig. 5 estimates the flow chart of steps of file angle of inclination method for the present invention.The evaluation method at the angle of inclination that produces when the present invention also is provided in to scan a file.The flow process of utilizing the present invention to estimate that file angle of inclination method scans a file comprises the following step:
S40: scanning this document is to produce one first scan-data;
S42: first scan-data is converted to a gray level image (gray image);
S44: is this binary picture (binary image) according to a threshold value with this greyscale image transitions;
S46: judging that this binary picture has does not comprise a figure (graph) district.If have, then carry out step S48; If not, then skip to step S50;
S48: delete this graph area certainly in this binary picture, to produce a deletion binary picture;
S50: utilize a predetermined discriminant approach, calculate this angle of inclination;
S52: with one second predetermined resolution scanning this document, to produce one second scan-data;
S54:, rotate this second scan-data according to this angle of inclination.
See also Fig. 6, Fig. 6 estimates the flow chart of steps of another embodiment of file angle of inclination method for the present invention.In another embodiment, the flow process of utilizing the present invention to estimate that file angle of inclination method scans a file comprises the following step:
S80: scanning this document produces scan-data;
S82: the resolution that reduces this scan-data;
S84: judge whether scan-data is coloured image.If skip to step S90; If not, then carry out step S86;
S86: judge whether scan-data is gray level image.If then skip to step 92; If not, then carry out step S88;
S88: judge whether scan-data is binary picture.If then skip to step 94; If not, then restart;
S90: coloured image is converted to gray level image;
S92: with greyscale image transitions is binary picture;
S94: the graph area of deletion binary picture, to produce the deletion binary picture;
S96: carry out the Hough conversion;
S98: calculate the angle of inclination value;
S100: rotation sweep data.
In embodiment shown in Figure 6, do not need scanning document twice, only need to reduce the resolution of scan-data, can calculate the angle of inclination and file is become a full member, therefore can save time and manpower.
The present invention estimates that the method at angle of inclination or device can utilize software, go to calculate the angle of inclination of scanning document automatically, and carry out the work that the file scan image is become a full member automatically.Therefore use the present invention when estimating the method at angle of inclination or being installed on scanning or hard-copy file, need not utilize manual mode to remove to ajust to be scanned/file of duplicating one by one, to save time and manpower by the user.
Via the above detailed description of preferred embodiments, hope can be known description feature of the present invention and spirit more, and is not to come category of the present invention is limited with above-mentioned disclosed preferred embodiment.On the contrary, its objective is that hope can contain in the category of scope of being arranged in of various changes and tool equivalence institute of the present invention desire application.Therefore, the category of the scope that the present invention applied for should be done the broadest explanation according to above-mentioned explanation, contains the arrangement of all possible change and tool equivalence to cause it.
Claims (21)
1. the method at estimation one angle of inclination, this angle of inclination produces in scanning one file time institute, and this method comprises the following step:
(a) scanning this document is to produce one first scan-data;
(b) this first scan-data is converted to a binary picture;
(c) judging that this binary picture has does not comprise a graph area, if this graph area of deletion is arranged then in this binary picture to produce a deletion binary picture; And
(d) utilize one to be scheduled to discriminant approach and, to calculate this angle of inclination according to this deletion binary picture.
2. as claim the 1 described method, this method also comprises:
(e) with one second predetermined resolution scanning this document, to produce one second scan-data; And
(f), rotate this second scan-data according to this angle of inclination.
3. as claim the 2 described methods, (a) step scans with one first predetermined resolution, and wherein this first predetermined resolution is less than this second predetermined resolution.
4. as claim the 1 described method, wherein (b) step comprises:
(b1) this first scan-data is converted to a gray level image; And
(b2) be this binary picture with this greyscale image transitions.
5. as claim the 4 described methods, wherein (b2) step is this binary picture according to a threshold value with this greyscale image transitions.
6. as claim the 1 described method, wherein (c) step is communicated with determining methods according to a kind of four, judges that this binary picture has not comprise this graph area.
7. as claim the 1 described method, wherein (c) step is communicated with determining methods according to a kind of eight, judges that this binary picture has not comprise this graph area.
8. as claim the 1 described method, wherein (c) step is according to a mask (mask) method, judges that this binary picture has not comprise this graph area.
9. as claim the 1 described method, wherein (d) step should comprise a Hough switch process by predetermined discriminant approach.
10. as claim the 1 described method, this method also comprises:
(g), rotate this first scan-data according to this angle of inclination.
11. as claim the 10 described methods, wherein (b) step comprises:
(bI) reduce this first scan-data, to produce this first scan-data of low resolution.
(bII) this first scan-data with low resolution is converted to a gray level image;
(bIII) be this binary picture with this greyscale image transitions.
12. the device in order to the estimation angle of inclination, this angle of inclination institute when scanning a file produces, this estimating device comprises:
One controller is in order to scan this document to produce one first scan-data;
One modular converter is in order to be converted to a binary picture with this first scan-data;
One judge module does not comprise a graph area in order to judge that this binary picture has, and then deletes this graph area to produce a deletion binary picture in this binary picture if having;
One computing module utilizes a predetermined discriminant approach and according to this deletion binary picture, calculates this angle of inclination.
13. as claim the 12 described estimating devices, wherein this controller is with one second predetermined resolution scanning this document, to produce one second scan-data; And, rotate this second scan-data according to this angle of inclination.
14. as claim the 13 described estimating devices, this controller scans with one first predetermined resolution, wherein this first predetermined resolution is less than this second predetermined resolution.
15. as claim the 12 described estimating devices, wherein modular converter is converted to a gray level image with this first scan-data, and is this binary picture with this greyscale image transitions.
16. as claim the 15 described estimating devices, wherein modular converter is this binary picture according to a threshold value with this greyscale image transitions.
17. as claim the 12 described estimating devices, wherein this judge module is communicated with determining methods according to a kind of four, judges that this binary picture has not comprise this graph area.
18. as claim the 12 described estimating devices, wherein this judge module is communicated with determining methods according to a kind of eight, judges that this binary picture has not comprise this graph area.
19. as claim the 12 described estimating devices, wherein this judge module is according to a masking method, judges that this binary picture has not comprise this graph area.
20. claim the 12 described estimating devices, wherein computing module should comprise a Hough switch process by predetermined discriminant approach.
21. as claim the 12 described estimating devices, wherein this modular converter reduces the resolution of this first scan-data earlier, to produce this first scan-data of low resolution, this first scan-data of low resolution is changed this gray level image, be this binary picture with this greyscale image transitions again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004100565713A CN100382097C (en) | 2004-08-10 | 2004-08-10 | Method and apparatus for estimating file inclination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004100565713A CN100382097C (en) | 2004-08-10 | 2004-08-10 | Method and apparatus for estimating file inclination |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1734471A true CN1734471A (en) | 2006-02-15 |
| CN100382097C CN100382097C (en) | 2008-04-16 |
Family
ID=36076886
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2004100565713A Expired - Fee Related CN100382097C (en) | 2004-08-10 | 2004-08-10 | Method and apparatus for estimating file inclination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100382097C (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101924856A (en) * | 2009-06-17 | 2010-12-22 | 北京大学 | Method and device for testing manuscript inclining angle |
| CN102282588A (en) * | 2009-04-07 | 2011-12-14 | 村田机械株式会社 | Image processing apparatus, processing method, processing program, and storing medium |
| CN105447426A (en) * | 2014-07-14 | 2016-03-30 | 株式会社理光 | Judgment device, document image management system and judgment method |
| CN108900730A (en) * | 2018-07-12 | 2018-11-27 | 四川骏逸富顿科技有限公司 | A kind of paper jam prediction technique and system for paper scanning means |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09212582A (en) * | 1996-01-31 | 1997-08-15 | Mitsumi Electric Co Ltd | Skew measuring method for scanner ocr |
| KR100247970B1 (en) * | 1997-07-15 | 2000-03-15 | 윤종용 | Direction correction method of document image |
| US6529641B1 (en) * | 1999-10-29 | 2003-03-04 | Eastman Kodak Company | Method for deskewing a scanned text image |
| JP2002259993A (en) * | 2001-03-05 | 2002-09-13 | Ricoh Co Ltd | Image tilt detecting method and its device and program |
-
2004
- 2004-08-10 CN CNB2004100565713A patent/CN100382097C/en not_active Expired - Fee Related
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102282588A (en) * | 2009-04-07 | 2011-12-14 | 村田机械株式会社 | Image processing apparatus, processing method, processing program, and storing medium |
| CN101924856A (en) * | 2009-06-17 | 2010-12-22 | 北京大学 | Method and device for testing manuscript inclining angle |
| CN105447426A (en) * | 2014-07-14 | 2016-03-30 | 株式会社理光 | Judgment device, document image management system and judgment method |
| CN105447426B (en) * | 2014-07-14 | 2018-02-02 | 株式会社理光 | Decision maker, file and picture management system and decision method |
| CN108900730A (en) * | 2018-07-12 | 2018-11-27 | 四川骏逸富顿科技有限公司 | A kind of paper jam prediction technique and system for paper scanning means |
| CN108900730B (en) * | 2018-07-12 | 2020-11-03 | 四川骏逸富顿科技有限公司 | Jam prediction method and system for paper scanning device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100382097C (en) | 2008-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5568571A (en) | Image enhancement system | |
| CN1991865A (en) | Device, method, program and media for extracting text from document image having complex background | |
| CN101042735A (en) | Image binarization method and device | |
| US7317835B2 (en) | Image processing method and apparatus | |
| DE3776078D1 (en) | METHOD FOR CONVERTING AN ORIGINAL VIDEO IMAGE WITH MANY GRAY LEVELS TO A BINARY IMAGE. | |
| CN1741039A (en) | Face organ's location detecting apparatus, method and program | |
| CN101069414A (en) | Method for suppressing blank pages in a multi-page scanning process and software therefor | |
| CN1633159A (en) | A method for removing image noise | |
| CN1607542A (en) | Image processing apparatus, image processing method, program and storage medium | |
| CN100338618C (en) | Automatic correction method for tilted image | |
| US6044179A (en) | Document image thresholding using foreground and background clustering | |
| US9332154B2 (en) | Image binarization using dynamic sub-image division | |
| CN1711558A (en) | Similar image extraction device, similar image extraction method, and similar image extraction program | |
| CN1734471A (en) | Method and apparatus for estimating file inclination | |
| CN1694119A (en) | Method for picture binaryzation | |
| US20050281483A1 (en) | Tilted angle detection for document image deskew | |
| CN1797428A (en) | Method and device for self-adaptive binary state of text, and storage medium | |
| JP4941843B2 (en) | Road marking image processing apparatus, road marking image processing method, and road marking image processing program | |
| CN1577378A (en) | Systems and methods for estimating an image marking process using scanned image attributes | |
| CN1581926A (en) | Half-tone processing method for automatic detecting image-text | |
| CN1192592C (en) | Automatic image clipping method | |
| KR100537827B1 (en) | Method for the Separation of text and Image in Scanned Documents using the Distribution of Edges | |
| CN100337463C (en) | Method for searching black and white boundary of image | |
| CN101034436A (en) | Multiple linewidth self-adapting preliminary vectorization method in vectorization process of engineering drawing | |
| CN1146814C (en) | Method for automatic detecting location of transparent draft and its device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20080416 |