CN1797428A - Method and device for self-adaptive binary state of text, and storage medium - Google Patents
Method and device for self-adaptive binary state of text, and storage medium Download PDFInfo
- Publication number
- CN1797428A CN1797428A CN 200410104810 CN200410104810A CN1797428A CN 1797428 A CN1797428 A CN 1797428A CN 200410104810 CN200410104810 CN 200410104810 CN 200410104810 A CN200410104810 A CN 200410104810A CN 1797428 A CN1797428 A CN 1797428A
- Authority
- CN
- China
- Prior art keywords
- window
- threshold value
- threshold
- block
- image
- 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
- Image Processing (AREA)
Abstract
The invention relates to a method, device and memory medium for self-adapting document two-value conversion, comprising: uniform contents searching step for obtaining image blocks with uniform contents; block threshold value calculating step, for calculating a two-value conversion threshold value for each image block; threshold value mapping step for dividing the image into windows and mapping the calculated threshold values onto the windows covered by the image blocks; threshold value spreading step for distributing threshold values to the other windows based on the threshold values mapped onto the windows; interpolation step for dividing the windows into subwindows and making linear interpolation on the threshold values of the windows to calculate the threshold values of the subwindows; and two-value conversion step for making two-value conversion on all windows by corresponding threshold values, thus completing the two-value conversion of the image. The invention can be applied to OCR and image intensification, etc.
Description
Technical field
The application relates generally to file and picture and handles, and relates in particular to method, equipment and the storage medium of the self-adaption binaryzation that is used for document.
Background technology
The first step of the normally most of document analysis of document binaryzation system.For example, current OCR system requirements must carry out binaryzation to text before handling text.Compare with gray level image or color image information, the use of second-level message can reduce calculated load, allows to use the analytical approach of simplifying.
The threshold value of using in the document binaryzation is a such gray-scale value: when document during by binaryzation, the pixel that gray-scale value is higher than this threshold value is set to black pixel, and gray-scale value is set to white pixel less than the pixel of this threshold value.
Having proposed many overall situations or local threshold method comes file and picture is carried out binaryzation.The global threshold method is to use single threshold value to come entire image is carried out binaryzation, and there is limitation in many cases in this method, for example under the even situation of space of a whole page complexity or uneven illumination.The local threshold method is the wicket (overlapping or not overlapping) that original image is divided into fixed size, utilizes local feature to threshold value of each window calculation.And the threshold application smoothing technique is eliminated may exist between the window unsmooth.
When handling complicated situation, the local threshold method is compared with the global threshold method and is had more robustness.But file and picture comprises many zones with different structure and semantic content usually, such as picture, text and background.With any split image of the window of fixed size may not be a good method, because window may comprise the content from a plurality of objects, in this case, single threshold value is inappropriate.In other cases, should be in the subimage bigger than window calculated threshold.For example, should come the whole zone of binaryzation " scenery " picture with the single threshold value that realizes the integrality on visual integrality and the content.If carry out binaryzation according to the window that may have different threshold values, in bianry image " hole " may appear.
Therefore, wish to improve existing binarization method, to handle complicated file and picture.
Summary of the invention
Purpose of the present invention just provides a kind of like this method, and equipment and the storage medium of realizing such method.
For this reason, the present invention proposes a kind of new self-adaption binaryzation method that is used for file and picture.This method is at first carried out the express-analysis of document file page, finds out the subimage with homogeneous content.Higher to these levels then image block calculated threshold, and with threshold map to the window of corresponding fixed measure.For the window that is not covered by any image block, application window threshold spread technology considers that the threshold value of window in the adjacent area is determined threshold value.
Particularly, provide a kind of method of adaptively the gray scale file and picture being carried out binaryzation, having comprised: the homogeneous content is sought step, is used to analyze the gray scale file and picture, obtains the image block with homogeneous content; The block threshold value calculation procedure is used for each described image block is calculated a binary-state threshold; The threshold map step wherein is divided into window with described gray scale file and picture, will be mapped on the window that is completely or partially covered by any image block at the binary-state threshold that described block threshold value calculation procedure obtains; The threshold spread step is used for based on the threshold value that is mapped on the corresponding window, to other window allocation threshold; The interpolation step is used for described window is divided into subwindow respectively, and carries out the threshold value that described subwindow is calculated in linear interpolation by the threshold value to window; And the binaryzation step, be used for each described subwindow being carried out binaryzation, thereby finish the binaryzation of described gray scale file and picture with corresponding threshold value.The application also provides equipment and the storage medium that is used to realize this method.The present invention can be applied to OCR, figure image intensifying or the like.
A kind of equipment of the gray scale of binaryzation adaptively file and picture also is provided, has comprised: homogeneous content device for searching, be used to analyze the gray scale file and picture, obtain image block with homogeneous content; The block threshold value calculation element is used for each described image block is calculated a binary-state threshold; The threshold map device wherein is divided into window with described gray scale file and picture, and the binary-state threshold that will obtain in described block threshold value calculation element is mapped to completely or partially on the window that is covered by any image block; The threshold spread device is used for based on the threshold value that is mapped on the corresponding window, to other window allocation threshold; Interpolation device is used for described window is divided into subwindow respectively, and carries out the threshold value that described subwindow is calculated in linear interpolation by the threshold value to window; And the binaryzation device, be used for each described subwindow being carried out binaryzation, thereby finish the binaryzation of described gray scale file and picture with corresponding threshold value.
A kind of storage medium also is provided, has it is characterized in that, stored the program code that is used to realize said method therein.
The present invention can not only be kept for the text message of OCR well, and, use for other document analysis, can keep other logic and semantic content well, such as image, form, document layout information.
Description of drawings
Other purpose of the present invention, feature and advantage will become more clear after the detailed description of preferred embodiments reading hereinafter.The accompanying drawing part of book as an illustration is used for the diagram embodiments of the invention, and is used from explanation principle of the present invention with instructions one.In the accompanying drawings:
Fig. 1 is the process flow diagram of one embodiment of the present of invention;
Fig. 2 is the more detailed process flow diagram of diagram step S1 shown in Figure 1;
The schematic illustration of Fig. 3 window used in this invention and subwindow;
Fig. 4 is the process flow diagram of diagram step S3 shown in Figure 1;
The synoptic diagram of Fig. 5 is used to explain step S3 shown in Figure 1 and S5;
Fig. 6 is the process flow diagram of diagram application of the present invention;
The block diagram illustration of Fig. 7 can realize an example of the computer system of method and apparatus of the present invention.
Embodiment
Computer system for example
Method and apparatus of the present invention can be realized in any messaging device.Described messaging device for example is the single-chip microcomputer (SCM) of personal computer (PC), notebook computer, embedding scanner, duplicating machine, facsimile recorder etc., or the like.For those of ordinary skills, be easy to realize method and apparatus of the present invention by software, hardware and/or firmware.Especially it should be noted that, it is evident that for those of ordinary skills, for any step of carrying out this method or the combination of step, the perhaps any parts of equipment of the present invention or the combination of parts may need to use input-output device, memory device and microprocessor such as CPU etc.May not be certain to mention these equipment in the explanation to method and apparatus of the present invention below, but in fact used these equipment.
As above-mentioned messaging device, the block diagram of Fig. 7 shows giving an example of a computer system, can realize method and apparatus of the present invention therein.It should be noted that the computer system that is shown in Fig. 7 just is used for explanation, does not really want to limit the scope of the invention.
From the angle of hardware, computing machine 1 comprises a CPU 6,5, RAM of hard disk (HD) 7, a ROM 8 and an input-output device 12.Input-output device can comprise input media such as keyboard, Trackpad, tracking ball and mouse etc., and output unit is such as printer and monitor, and input-output unit is such as floppy disk, CD drive and communication port.
From the angle of software, described computing machine mainly comprises operating system (OS) 9, input/output driver 11 and various application program 10.As operating system, can use any operating system that to buy on the market, such as Windows series and based on the operating system of Linux.Input/output driver is respectively applied for and drives described input-output device.Described application program can be an Any Application, such as text processor, image processing program etc., comprising can be used in this invention and aim at the present invention's application program establishment, that can call described existing program.
Like this, in the present invention, can in the hardware of described computing machine, realize method and apparatus of the present invention by operating system, application program and input/output driver.
In addition, computing machine 1 can be connected to digital device 3 and application apparatus 2.Digital device can be used as image source, can be camera, video camera, scanner or the digitizer that is used for analog image is converted to digital picture.The result that equipment of the present invention and method obtain is output to application apparatus 2, and the latter carries out suitable operation according to described result.This application apparatus also can be implemented as the Another application (combining with hardware) that realizes in computing machine 1, be used for further handling described image.
Use example of the present invention
The present invention can be used in the document analysis system file and picture is converted to bianry image, as shown in Figure 6.Can be with the present invention with the gray level image binaryzation.In the present embodiment, use gray level image (coloured image can be converted into gray level image) to explain the present invention.The bianry image of Huo Deing can be used for OCR, form understanding system or page analysis system then like this.
Be used for file and picture is carried out the method and apparatus of self-adaption binaryzation
Briefly, the invention provides a kind of computer implemented method and apparatus, be used for file and picture is carried out self-adaption binaryzation.Fig. 1 is a main flow chart of the present invention, illustrates the new binarization method of being carried out by the equipment of present embodiment.
Equipment of the present invention comprises homogeneous content device for searching, block threshold value calculation element, threshold map device, threshold spread device, interpolation device and binaryzation device.
Described homogeneous content device for searching is configured to carry out document analysis (step S1), to extract the image block with homogeneous content from the gray scale file and picture, such as text block (comprising the inverse text block) and non-text block.
The homogeneous content device for searching that step S1 uses can be used many existing techniques in realizing.Fig. 2 illustrates the process flow diagram of giving an example of one of this technology.
As shown in Figure 2, beginning of process is the edge detection step S11 that is used for surveying the edge of the gray level image of wanting analyzed, obtains so-called " edge image " (image that the edge has been found out).The edge detection technology also is known in this area.In a width of cloth gray level image, so-called edge is exactly the elementary cell that appears at the discontinuous position of intensity profile, and this grey scale change can detect easily with derivative." image Segmentation " (image graphics science book series of Zhang Yujin work, Science Press, 2001, ISBN 7-03-007241-3) introduced the most frequently used method of coming the detected image edge with first order derivative, such as, can adopt Roberts operator, Sobel operator, Prewitt operator etc.If the gradation of image first order derivative of a certain pixel of trying to achieve is higher than a certain threshold value, promptly criterion threshold value in image border can determine that then this pixel is the edge of image point.
United States Patent (USP) 6192153B1 discloses a kind of image processing apparatus and method, and this invention is used for accurately identifying the type of the image-region of file and picture, and according to the sign result of image-region, each pixel is handled.Wherein in this invention, image processing apparatus comprises the Image Edge-Detection device, it by calculate the long-pending of each picture signal and a filtering parameter in the zone with, detect the pixel that is arranged in the image marginal portion.Wherein above-mentioned zone comprises that one is observed pixel and surrounds a plurality of edge pixels of this observation pixel.And, identify the image-region that comprises described observation pixel by an identity device according to described Image Edge-Detection result.It mainly comprises following several steps: with the data image signal input, then the digital picture black and white is reversed, then, the edge of detected image is divided into non-photo pixel and photo pixel according to each pixel characteristic with them; Then, non-photo pixel is classified, and the comparison film pixel carries out smoothly, thereby export resulting picture signal.Wherein used predetermined fixed threshold to come the detected image edge in the Image Edge-Detection step.
United States Patent (USP) 5583659 discloses a kind of multi-windowing that utilizes the image local characteristic with image thresholdization.It utilizes the brightness of topography to change, and characteristics such as the graded of image pixel adopt multi-windowing, reduces picture noise and reduces the ambiguity of image border.In the disclosed method of this patent, use Sobel operator and predetermined still image edge criteria threshold value to come the detected image edge.
Then, at step S12, find out the connected domain on the edge image.The notion of connected domain also is known, below it is illustrated.For example, " black eight connected domains " are one eight zones that is communicated with.The meaning of " deceiving " is that connected domain is determined by black pixel.That is to say that " black eight connected domains " are one eight black pixels that is communicated with.The conceptual description of " connectivity of pixels " relation between two or the more a plurality of pixel.For two pixels, become and be interconnected, they must meet some requirements aspect pixel intensity and the space adjacency.At first, for two pixels, become and be interconnected, its pixel value must be all in same sets of pixel values V.For grayscale image, V can be any grey level range, V={22 for example, and 23 ... 40}.For bianry image, can be V={1}.In order to provide the formula that is used for connective adjacency standard, at first to introduce the notion of " neighborhood ".For have coordinate (x, pixel P y), collection of pixels:
N4(p)＝{(x+1，y)，(x-1，y)，(x，y+1)，(x，y-1)}
Be called its 4-neighborhood.Its 8-neighborhood is following set:
N8(p)＝N4(p)∪{(x+1，y+1)，(x+1，y-1)，(x-1，y+1)，(x-1，y-1)}
Can obtain the definition that four connected sums eight are communicated with thus:
For two pixel p and q, its pixel value all belongs to set V, so, if it belongs to set N4 (p), then is four connections, if it belongs to set N8 (p), then is eight connections.
Then, utilize any known technology, connected domain is classified, for example be divided into text block, inverse text block and non-text block (step S13).Generally, criteria for classification is the ratio of connected domain (such as " white " or " black ") with the entire image of particular type, and they obtain by test.
Next be combining step (step S141, S142 or S143), be used for the image block with similarity is merged into bigger piece.Just, all adjacent text block are merged (step S141), and all adjacent inverse text block are merged (step S142), and the non-text block with similar characteristics that all are adjacent is merged (step S143).As a result, obtain a plurality of image blocks, they can comprise a plurality of text block and/or a plurality of inverse text block and/or a plurality of non-text block.
Get back to Fig. 1, the block threshold value calculation element is configured to: for each piece, use any available method to calculate a threshold value (step S2).For example, this threshold value can be the Otsu threshold value.
Described threshold map device is configured to the gray scale file and picture is divided into onesize window, and the threshold map (step S3) to window that the block threshold value calculation element is obtained.Described window can be an arbitrary dimension, and for example 15 * 15 pixels as shown in Figure 3, and can be divided into two types: comprise the properties window of at least one edge pixel, such as window A, D, E, J, M, O, P and Q, and the backdrop window that does not comprise edge pixel are such as all the other windows among Fig. 5.
By map operation, will be had a threshold value by the window of any text or all or part of covering of inverse text block, this threshold value equals the threshold value (step S32) of correspondence image piece.For example, as shown in Figure 5, suppose that piece B1 is text block or inverse text block, it covers two window J and K fully, and part covers two window L and M.So, not only window J and K will be endowed the threshold value of image block B1, and window L and M also will be endowed this threshold value, and no matter they are properties window or backdrop window.
For non-text block, have only by the properties window of all or part of covering of non-text block and will have the threshold value that equals corresponding non-text block threshold value (the step S31 among Fig. 4, obviously, step S32 also can be before S31).For example, suppose that the B2 among Fig. 5 is non-text block, then have only that D and E can be endowed the threshold value of piece B2 by the properties window A of all or part of covering of piece B2.
Like this, as shown in Figure 5, window J, K, L and M will have the threshold value of text block B1, and properties window A, D and E will have the threshold value of non-text block B2, and up to the present all other windows also do not have threshold value.
As can be seen from the above, in the threshold map step that the threshold map device is carried out, window that is covered by any image block and the backdrop window that is covered by non-text block are not endowed threshold value.
Therefore, the threshold spread step is configured to come also there not being other window allocation threshold (step S4) of threshold value based on the threshold value that is mapped on the corresponding window.
In threshold spread device and step S4, determine the threshold value of described other window like this: scan these windows according to predefined procedure, for each window, the threshold value of its 4-neighborhood window is average, as its threshold value (in other words, with the threshold spread of the 4-neighborhood window of each window to this window).If certain window in the 4-neighborhood window is not endowed threshold value as yet, then this window is not considered; If be endowed threshold value without any window in the 4-neighborhood window of certain window, then this window is skipped.Repeat described scanning, all have the threshold value of oneself up to each window.
In expansion process, must limit a border that window can be expanded.In other words, the threshold value of a window can not be extended to another window with diverse content.In the present invention, properties window is used for setting described extended boundary.Zone of transition from a content to another content always the edge can occur.Therefore, just define the border of content naturally according to the properties window of above-mentioned definition.
Therefore, in order to reach the effect of extended boundary, described threshold spread device is configured at first utilize described threshold spread method to determine the threshold value of backdrop window.Afterwards, use this method to determine the threshold value of properties window.For example, as shown in Figure 5, at first give threshold value by repeatedly scanning is next to all backdrop window (the blank window among the figure), scanning does not have the properties window (such as window B, C, F, G, H, I, O, P and Q) of threshold value then, gives threshold value to it.Like this, each window all has the threshold value of oneself.
Described interpolation device is configured to further described window is divided into subwindow, based on the threshold value (step S5) of the threshold calculations subwindow of window.For example, as shown in Figure 3, the gray scale file and picture can be split into the gray scale file and picture of 15 * 15 pixels, and each window can further be divided into the subwindow of 3 * 3 pixels.
Can carry out the threshold value that subwindow is calculated in linear interpolation by threshold value to window.Afterwards, described binaryzation device can carry out binaryzation to each subwindow with corresponding threshold value, thereby finishes the binaryzation (step S6) of whole gray scale file and picture.
Storage medium
Described purpose of the present invention can also be by realizing with program of operation or batch processing on any messaging device that described image source is communicated by letter with subsequent processing device aforesaid.Described messaging device, image source and subsequent processing device are known common apparatus.Therefore, described purpose of the present invention also can be only by providing the program code of realizing described method or equipment to realize.That is to say that the storage medium that stores the program code of realizing described method or equipment constitutes the present invention.
To those skilled in the art, can realize described method with any program language programming easily.Therefore, omitted detailed description at this to described program code.
Obviously, described storage medium can be well known by persons skilled in the art, and perhaps therefore the storage medium of any kind that is developed in the future also there is no need at this various storage mediums to be enumerated one by one.
Although in conjunction with concrete steps and structrual description the present invention, the present invention is not limited to details as described herein.The application should cover all variation, modification and modification without departing from the spirit and scope of the present invention.For example, described window and subwindow can be any sizes, are the operation of window and operation that window is divided into subwindow whenever carrying out before step S3 and step S5 respectively with described image segmentation.
Claims (11)
1. method of binaryzation gray scale file and picture adaptively comprises:
The homogeneous content is sought step, is used to analyze the gray scale file and picture, obtains the image block with homogeneous content;
The block threshold value calculation procedure is used for each described image block is calculated a binary-state threshold;
The threshold map step wherein is divided into window with described gray scale file and picture, will be mapped on the window that is completely or partially covered by any image block at the binary-state threshold that described block threshold value calculation procedure obtains;
The threshold spread step is used for based on the threshold value that is mapped on the corresponding window, to other window allocation threshold;
The interpolation step is used for described window is divided into subwindow respectively, and carries out the threshold value that described subwindow is calculated in linear interpolation by the threshold value to window; And
The binaryzation step is used for corresponding threshold value each described subwindow being carried out binaryzation, thereby finishes the binaryzation of described gray scale file and picture.
2. the method for claim 1, wherein described image block comprises text block, inverse text block and non-text block.
3. as claim 1 or 2 described methods, wherein, described threshold map step comprises:
For by the window of all or part of covering of any non-text block, only the properties window that comprises at least one edge pixel is given the threshold value of corresponding non-text block;
For by the window of any text block or all or part of covering of inverse text block, all windows are given the threshold value of corresponding text or inverse text block.
4. method as claimed in claim 3, wherein, described threshold spread step comprises:
At first backdrop window is carried out the threshold spread operation, then properties window is carried out the threshold spread operation, wherein, described backdrop window is the window that does not comprise edge pixel.
5. method as claimed in claim 4, wherein, described threshold spread operation comprises:
According to predetermined all relevant windows of sequential scanning, and the threshold value that has been endowed the window of threshold value in each relevant 4 neighborhood window of window averaged and determine threshold value of this relevant window.
6. equipment of binaryzation gray scale file and picture adaptively comprises:
Homogeneous content device for searching is used to analyze the gray scale file and picture, obtains the image block with homogeneous content;
The block threshold value calculation element is used for each described image block is calculated a binary-state threshold;
The threshold map device wherein is divided into window with described gray scale file and picture, and the binary-state threshold that will obtain in described block threshold value calculation element is mapped to completely or partially on the window that is covered by any image block;
The threshold spread device is used for based on the threshold value that is mapped on the corresponding window, to other window allocation threshold;
Interpolation device is used for described window is divided into subwindow respectively, and carries out the threshold value that described subwindow is calculated in linear interpolation by the threshold value to window; And
The binaryzation device is used for corresponding threshold value each described subwindow being carried out binaryzation, thereby finishes the binaryzation of described gray scale file and picture.
7. equipment as claimed in claim 6, wherein, described image block comprises text block, inverse text block and non-text block.
8. as claim 6 or 7 described equipment, wherein, described threshold map device further is configured to: for by the window of all or part of covering of any non-text block, only the properties window that comprises at least one edge pixel is given the threshold value of corresponding non-text block; For by the window of any text block or all or part of covering of inverse text block, all windows are given the threshold value of corresponding text or inverse text block.
9. equipment as claimed in claim 8, wherein, described threshold spread device further is configured to: at first backdrop window is carried out the threshold spread operation, then properties window is carried out the threshold spread operation, wherein, described backdrop window is the window that does not comprise edge pixel.
10. equipment as claimed in claim 9, wherein, described threshold spread device be further configured into: according to predetermined all relevant windows of sequential scanning, and the threshold value that has been endowed the window of threshold value in each relevant 4 neighborhood window of window averaged and determines threshold value of this relevant window.
11. a storage medium is characterized in that, has stored the program code that is used to realize the described method of one of claim 1 to 5 therein.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004101048108A CN100416597C (en) | 2004-12-23 | 2004-12-23 | Method and device for self-adaptive binary state of text, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2004101048108A CN100416597C (en) | 2004-12-23 | 2004-12-23 | Method and device for self-adaptive binary state of text, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1797428A true CN1797428A (en) | 2006-07-05 |
| CN100416597C CN100416597C (en) | 2008-09-03 |
Family
ID=36818454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2004101048108A Expired - Fee Related CN100416597C (en) | 2004-12-23 | 2004-12-23 | Method and device for self-adaptive binary state of text, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100416597C (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100428268C (en) * | 2007-04-13 | 2008-10-22 | 中国传媒大学 | Document Image Segmentation Method Based on Chinese Character Features |
| CN101398897B (en) * | 2007-09-29 | 2010-11-10 | 凌阳多媒体股份有限公司 | Adaptive gray scale extension and binary decision method |
| CN102890780A (en) * | 2011-07-19 | 2013-01-23 | 富士通株式会社 | Image processing device and image processing method |
| CN106529543A (en) * | 2016-11-02 | 2017-03-22 | 徐庆 | Method and system for dynamically calculating multi-color-grade binary adaptive threshold |
| CN106991753A (en) * | 2017-04-07 | 2017-07-28 | 深圳怡化电脑股份有限公司 | A kind of image binaryzation method and device |
| CN107609558A (en) * | 2017-09-13 | 2018-01-19 | 北京元心科技有限公司 | Character image processing method and processing device |
| WO2019227300A1 (en) * | 2018-05-29 | 2019-12-05 | 优视科技新加坡有限公司 | Page element processing method and apparatus, and storage medium and electronic device/terminal/server |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711238B (en) * | 2018-07-24 | 2020-11-20 | 台州市怡开包装有限公司 | Rat-proof intelligent cabinet |
-
2004
- 2004-12-23 CN CNB2004101048108A patent/CN100416597C/en not_active Expired - Fee Related
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100428268C (en) * | 2007-04-13 | 2008-10-22 | 中国传媒大学 | Document Image Segmentation Method Based on Chinese Character Features |
| CN101398897B (en) * | 2007-09-29 | 2010-11-10 | 凌阳多媒体股份有限公司 | Adaptive gray scale extension and binary decision method |
| CN102890780A (en) * | 2011-07-19 | 2013-01-23 | 富士通株式会社 | Image processing device and image processing method |
| CN102890780B (en) * | 2011-07-19 | 2015-07-22 | 富士通株式会社 | Image processing device and image processing method |
| CN106529543A (en) * | 2016-11-02 | 2017-03-22 | 徐庆 | Method and system for dynamically calculating multi-color-grade binary adaptive threshold |
| CN106991753A (en) * | 2017-04-07 | 2017-07-28 | 深圳怡化电脑股份有限公司 | A kind of image binaryzation method and device |
| CN107609558A (en) * | 2017-09-13 | 2018-01-19 | 北京元心科技有限公司 | Character image processing method and processing device |
| WO2019227300A1 (en) * | 2018-05-29 | 2019-12-05 | 优视科技新加坡有限公司 | Page element processing method and apparatus, and storage medium and electronic device/terminal/server |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100416597C (en) | 2008-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1276382C (en) | Method and apparatus for discriminating between different regions of an image | |
| US7177483B2 (en) | System and method for enhancement of document images | |
| Singh et al. | Local contrast and mean based thresholding technique in image binarization | |
| US5568571A (en) | Image enhancement system | |
| JP4423298B2 (en) | Text-like edge enhancement in digital images | |
| US8059892B1 (en) | Image enhancement method and apparatus | |
| JP4745296B2 (en) | Digital image region separation method and region separation system | |
| JP4745297B2 (en) | Method and system for identifying regions of uniform color in digital images | |
| US9965695B1 (en) | Document image binarization method based on content type separation | |
| JP2010525486A (en) | Image segmentation and image enhancement | |
| CN101042735A (en) | Image binarization method and device | |
| CN1755707A (en) | An Automatic Correction Method for Tilted Images | |
| CN100416597C (en) | Method and device for self-adaptive binary state of text, and storage medium | |
| US8442348B2 (en) | Image noise reduction for digital images using Gaussian blurring | |
| US10909406B2 (en) | Image processing system and method | |
| Cinque et al. | A multiresolution approach for page segmentation | |
| CN105721738B (en) | A kind of chromoscan file and picture preprocess method | |
| CN1519769A (en) | Method and appts. for expanding character zone in image | |
| CN1941838A (en) | File and picture binary coding method | |
| CN1920853A (en) | System and method for content recognition | |
| Tseng et al. | Document image binarization by two-stage block extraction and background intensity determination | |
| CN1734471A (en) | Method and device for estimating file inclination angle | |
| Salagar et al. | Analysis of PCA usage to detect and correct skew in document images | |
| KR100537827B1 (en) | Method for the Separation of text and Image in Scanned Documents using the Distribution of Edges | |
| RU2368007C1 (en) | Method for segmentation of text by colour criterion in process of copying |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20080903 Termination date: 20161223 |