CN107358184A - The extracting method and extraction element of document word - Google Patents
The extracting method and extraction element of document word Download PDFInfo
- Publication number
- CN107358184A CN107358184A CN201710531861.6A CN201710531861A CN107358184A CN 107358184 A CN107358184 A CN 107358184A CN 201710531861 A CN201710531861 A CN 201710531861A CN 107358184 A CN107358184 A CN 107358184A
- Authority
- CN
- China
- Prior art keywords
- image
- pattern
- document
- word
- color
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000000605 extraction Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000003384 imaging method Methods 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 7
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 241000283216 Phocidae Species 0.000 description 34
- 238000010586 diagram Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 5
- 235000013350 formula milk Nutrition 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002845 discoloration Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
Abstract
The invention provides a kind of extracting method of document word, including step：From the image comprising document character area and pattern, the homochromy region of color identical included with pattern is extracted；Gray proces are carried out to described image, obtain its foreground area, the foreground area includes document character area and pattern；The contour shape of the pattern is extracted from foreground area, and the color of the word or file part in the contour shape is different from the color that pattern is included；The contour shape and homochromy region are merged, obtains public domain, the public domain in foreground area is removed, obtains the image of the only word containing document.Present invention also offers a kind of extraction element of document word, using computer vision and image processing techniques, suitable for scan image, is also applied for the image that imaging device obtains, it may also be used for electronic government documents image, it has wide range of applications, and has universality.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of extracting method and extraction element of document word.
Background technology
In order to improve operating efficiency, the automatic input of document essential information is realized, is the information-based weight ensured of relevant department
Want content.The automatic identification of conventional document word, the technology and product of existing comparative maturity.But on document character area
Figuratum image is covered, its document word content automatically extracts also to be hoisted with the technology maturity of identification.Illustrate, example
Such as the image of seal covering document word, because of doing for the physical factor such as inequality of exerting oneself, ink paste mass discrepancy, paper sheet thickness be uneven
Disturb, the limitation of the imaging device self-characteristic such as scanner, high photographing instrument or camera, and the imaging circumstances such as illumination, shooting angle
Influence, cause the phenomenon that the image for being stamped seal occurs that shade is uneven, image is fuzzy to exist.
Separated on seal with signature, technology, the existing personnel such as seal identification carry out correlative study, these researchs are specific
Background or some restriction occasions can obtain preferable effect.But in actual applications, in image in seal and document word
Appearance has that many places are overlapping with intersecting, and the position of seal appearance has certain randomness, seal species presentation diversity, existing side
Method universality when solving these problems is inadequate.
The content of the invention
(1) technical problems to be solved
It is an object of the invention to provide a kind of extracting method and extraction element of document word, with solve it is above-mentioned at least
One technical problem.
(2) technical scheme
An aspect of of the present present invention, there is provided a kind of extracting method of document word, including step：
From the image comprising document character area and pattern, the homochromy area of color identical included with pattern is extracted
Domain；
Gray proces are carried out to described image, obtain its foreground area, the foreground area include document character area and
Pattern；
Extract the contour shape of the pattern from foreground area, and the word or file part in the contour shape
Color is different from the color that pattern is included；
The contour shape and homochromy region are merged, obtains public domain, the public domain in foreground area is removed, obtains
The only image of the word containing document.
Alternatively, step can also be included：To word or file progress morphological operation, the breakpoint being connected thereto, and
Remove isolated noise spot.
Alternatively, described image may be pretreated to obtain by original image, and the pretreatment includes contrast enhancing
Processing.
Alternatively, the original image can be obtained by scanner or imaging device.
Alternatively, step can also be included before the homochromy region of color identical that extraction is included with pattern：By image
In RGB (primaries pattern) color space conversion be HSI (color space) color space.
Alternatively, the foreground area and background area are arranged to different colors, the different color is black
And white.
Alternatively, the gray proces include gray processing and binary segmentation is handled.
Alternatively, the formula of the gray processing processing is Gray=R*0.299+G*0.587+B*0.114, and Gray represents ash
Degree, the red channel of R representative images, the green channel of G representative images, the blue channel of B representative images；
The binary segmentation processing includes Otsu (theory of error between maximum kind), iterative method or minimum error method.
Alternatively, the extracting method of the contour shape of the pattern includes (Hough) Hough transformation.
Another aspect of the present invention, a kind of extraction element of document word is additionally provided, including：
Memory, for storing executable instruction；
Processor, for performing the executable instruction in memory, enter when performing executable instruction according to the above method
Row operation.
(3) beneficial effect
The present invention has advantages below compared to prior art：
1st, the extracting method of document word of the invention, using computer vision and image processing techniques, suitable for passing through
The image that scanner obtains, it is also applied for the image obtained by imaging devices such as high photographing instruments, it may also be used for electronic government documents image,
It has wide range of applications, and has universality.
2nd, the extracting method of document word of the invention, also takes pretreatment, uneven, fuzzy preferably to handle the depth
The image of pattern, so as to more accurately extract document character area.
3rd, the present invention also carries out morphological operation to document character area, connects the literal breakpoint of document, and remove and make an uproar
Sound point, with solve homochromy region and document character area in image exist many places it is overlapping with intersecting when, the document word of extraction breaks
The problem of discontinuously continuous.
Brief description of the drawings
Fig. 1 is the step schematic diagram of the extracting method of the document word of the embodiment of the present invention；
Fig. 2 is the schematic diagram of the image of a specific embodiment of the invention；
Fig. 3 is the schematic diagram in the pure official seal region of a specific embodiment of the invention；
Fig. 4 is the foreground area of a specific embodiment of the invention and the schematic diagram of background area；
Fig. 5 is that the document character area of a specific embodiment of the invention extracts the schematic diagram of result；
Fig. 6 is the structural representation of the extraction element of the document word of the embodiment of the present invention.
Embodiment
Based on above-mentioned technical problem, the invention provides a kind of extracting method of document word, can be directed to and include document
The image of character area and pattern is handled, and avoids interference of the pattern to document character area, isolated pure document word
Region.In addition, the extracting method of the document word uses computer vision and image processing techniques, suitable for being obtained by scanner
The image taken, it is also applied for the image obtained by imaging devices such as high photographing instruments, it may also be used for electronic government documents image, it applies model
Enclose extensively, there is universality.
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with specific embodiment, and reference
Accompanying drawing, the present invention is described in more detail.
The one side of the embodiment of the present invention, there is provided a kind of extracting method of document word, Fig. 1 are the embodiment of the present invention
The step schematic diagram of the extracting method of document word, as shown in figure 1, the method comprising the steps of：
S1, from the image comprising document character area and pattern, extraction and the color identical that is included of pattern are homochromy
Region；The color of pattern can be any color, it is only necessary to ensure there is the word or file color difference of intersection with it,
The pattern can also be the pattern of arbitrary shape, such as circle, rectangle, triangle etc. be regular or irregular shape.In addition should
Homochromy region can also include word, or other marks, and the mark can be rule flag, or irregular mark.
In general, it is also possible to that white space can be included in image.Document character area can overlap with pattern, can also be misaligned.
In view of paper sheet thickness, the font depth, printer apparatus, imaging device, illumination power, imaged viewing angle etc. it is a variety of because
The influence of element, can cause in different original images, the brightness of font prospect and paper background, contrast have differences, therefore right
Original image is pre-processed, and obtains described image.Wherein, original image can be the image obtained by scanner, pass through
The image or be electronic government documents image that the imaging devices such as high photographing instrument obtain, thus this method has a wide range of application, compared to existing
Have for technology, there is stronger universality.
In general, preprocess method includes contrast enhancement process, image de-noising method, image slant correction etc..For
The treatment effect of subsequent operation is ensured, in embodiments of the present invention, first to the RGB pattern in original image, passes through contrast
Enhancement Method is spent, the RGB pattern with high-contrast is obtained, to reduce the otherness that various extraneous factors are brought.
Next, just using the image including official seal pattern, document character area and white space for example, Fig. 2 is this
The schematic diagram of the image of a specific embodiment is invented, as shown in Fig. 2 the image includes document character area, official seal pattern and sky
White region, it will be apparent that, official seal pattern has intersection with document character area.
In order to closer to the mode of the vision system perceived color of people, more intuitively handle image, such as extract feature
Coloured silk etc. is operated, and the RGB color in image is transformed into intermediate colors model by the embodiment of the present invention：HSI color spaces,
HSI color spaces, the extraction red area consistent with official seal pattern color.
Wherein, RGB to HSI color space models transformation for mula is：
I=(R+G+B)/3
Wherein, H refers to tone, and S refers to color saturation, and I refers to brightness；The red channel of R representative images, the green of G representative images
Passage, the blue channel of B representative images.
According to《State Council is on state administrative organs and the regulation of enterprise and institution's seal》(promulgated by the State Council (1993) 21),
The generally circular red official seal pattern of official seal pattern, circle include word and pattern mark, therefore, the homochromy region in the present invention
It is rounded for red area, and also include word and pattern mark in circle.
S2, gray proces are carried out to described image with discoloration, obtain its foreground area, the foreground area includes document text
Block domain and pattern；
In the present embodiment, while obtaining foreground area, the background area including white space also obtain.Gray proces
Handled including gray processing and binary segmentation, wherein, gray processing use image turn the classical formulas of gray level image for：
Gray=R*0.299+G*0.587+B*0.114, wherein, Gray represents gray scale.
In general, binary segmentation processing includes Otsu binary segmentations method, iterative method or minimum error method.It is of the invention real
Example is applied using the classical Otsu binary segmentation methods of image processing field.Fig. 3 be an of the invention specific embodiment foreground area and
The schematic diagram of background area, as shown in figure 3, foreground area includes official seal pattern and document character area, it is expressed as white；Background
Region includes white space, is expressed as black.Black can also be arranged to foreground area in various embodiments, white is set
It is set to background area.
S3, the contour shape for extracting from foreground area the pattern, and the word or file portion in the contour shape
The color divided is different from the color that pattern is included；
In the embodiment of the present invention, the circular contour extraction result of official seal pattern, an actually circle.Therefore, use
The circular contour of the classical Hough transform method extraction official seal pattern of image processing field, and in different embodiments, can be with
Using the shape analysis method based on moment characteristics, or shape analysis method based on chain code etc..In addition, in order to avoid document is literary
Word is misdeemed as the word in official seal pattern, therefore the color of word or file part in the contour shape and thereon is not
It is red.
S4, the contour shape and homochromy region are merged, obtain public domain, remove the public domain in foreground area,
Obtain the image of the only word containing document.
According to document character area and the position relationship of official seal pattern, the image can be roughly divided into：(1) document character area
With official seal pattern overlapping intersection region, this is also the difficult point in the identification extraction process for the document character area for being stamped official seal pattern
Place；(2) pure document character area, the part that document character area removes (1) is referred to；(3) pure official seal region, refer to official seal pattern and remove
Go to the part of (1)；Wherein foregoing public domain also refers to (3) pure official seal region.
In the present embodiment, the circular contour and red area of official seal pattern are merged, is obtained in circular upper and circle
Red area, that is, obtain pattern contour shape and homochromy region intersection, carry out and operation, and because the circle on
And the word or file part in the circle is not red, therefore the public domain now obtained is red pure official seal area
Domain.For each red pixel point in public domain, the type of the pixel is analyzed, belongs to still pure official seal region, still
Belong to document character area and official seal pattern overlapping intersection region.Fig. 4 is the pure official seal region of a specific embodiment of the invention
Schematic diagram, as shown in figure 4, pure official seal region has lacked what official seal pattern overlapped with document character area relative to official seal pattern
Part.Then the public domain in foreground area is incorporated into background area again, obtains the foreground area of the only word containing document.
Now, white space and pure official seal region are included in background area, includes complete text in foreground area
Shelves character area.Finally, background area is shown as black, and the foreground area for being shown as white as extracts obtained document word
Region.
Further, morphological operation, connection document text can also be carried out to the document word in document character area
Breakpoint on word, and isolated noise spot is removed, obtain complete document character area extraction result.Fig. 5 has for the present invention one
The schematic diagram of the document character area extraction result of body embodiment, is carried as shown in figure 5, the white portion is document character area
Result is taken, document word therein is intact, shows the method for the present invention and can effectively realize document word in image
Extraction.
Another invention of the embodiment of the present invention, additionally provides a kind of extraction element of document word, and Fig. 6 is implemented for the present invention
The structural representation of the extraction element of the document word of example, as shown in fig. 6, it includes：
Memory 1, for storing executable instruction；The executable instruction is generally binary number form, by command code
Formed with address code, the operation that command code instruction processor 2 will be carried out, address code indicates processor 2 to the ground in memory 1
The data of Attended Operation are read in location.
Processor 2, for performing the executable instruction in memory 1, in execute instruction according to the document word
Extracting method is operated.
The extraction element of the document word of the present invention, using computer vision and image processing techniques, processor 2 passes through
The executable instruction in memory 1 is performed, the extracting method of above-mentioned document word can be realized, suitable for being obtained by scanner
Image, be also applied for by the imaging devices such as high photographing instrument obtain image, it may also be used for electronic government documents image, its application
Extensively, there is universality.
Particular embodiments described above, the purpose of the present invention, technical scheme and beneficial effect are carried out further in detail
Describe in detail it is bright, should be understood that the foregoing is only the present invention specific embodiment, be not intended to limit the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements done etc., it should be included in the guarantor of the present invention
Within the scope of shield.
Claims (10)
1. a kind of extracting method of document word, including step：
From the image comprising document character area and pattern, the homochromy region of color identical included with pattern is extracted；
Gray proces are carried out to described image, obtain its foreground area, the foreground area includes document character area and pattern；
Extract the contour shape of the pattern from foreground area, and in the contour shape and word or file part thereon
Color it is different from the color that pattern is included；
The contour shape and homochromy region are merged, obtains public domain, the public domain in foreground area is removed, is only contained
The image of document word.
2. the method according to claim 11, wherein, in addition to step：Morphological operation is carried out to the word or file, even
Breakpoint thereon is connect, and removes isolated noise spot.
3. according to the method for claim 1, wherein, described image is obtained by original image by pretreatment, the pre- place
Reason includes contrast enhancement processing.
4. according to the method for claim 3, wherein, the original image is obtained by scanner or imaging device.
5. according to the method for claim 1, wherein, extracting the homochromy region of color identical included with pattern also includes
Step：RGB color in image is converted into HSI color spaces.
6. according to the method for claim 1, wherein, the foreground area and background area are arranged to different colors,
The different color is black and white.
7. according to the method for claim 1, wherein, the gray proces include gray processing and binary segmentation is handled.
8. according to the method for claim 7, wherein, the formula of the gray processing processing is Gray=R*0.299+G*
0.587+B*0.114, Gray represent gray scale, the red channel of R representative images, the green channel of G representative images, B representative images
Blue channel；
The binary segmentation processing includes the theory of error, iterative method or minimum error method between maximum kind.
9. according to the method for claim 1, wherein, the extracting method of the contour shape of the pattern includes Hough transformation.
A kind of 10. extraction element of document word, it is characterised in that including：
Memory, for storing executable instruction；
Processor, it is any according to claim 1-9 when performing executable instruction for performing the executable instruction in memory
Methods described is operated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710531861.6A CN107358184A (en) | 2017-06-30 | 2017-06-30 | The extracting method and extraction element of document word |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710531861.6A CN107358184A (en) | 2017-06-30 | 2017-06-30 | The extracting method and extraction element of document word |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107358184A true CN107358184A (en) | 2017-11-17 |
Family
ID=60291717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710531861.6A Pending CN107358184A (en) | 2017-06-30 | 2017-06-30 | The extracting method and extraction element of document word |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107358184A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108146093A (en) * | 2017-12-07 | 2018-06-12 | 南通艾思达智能科技有限公司 | A kind of method for removing bill seal |
| CN108537086A (en) * | 2018-03-29 | 2018-09-14 | 广东欧珀移动通信有限公司 | Method for information display, device, storage medium and mobile terminal |
| CN108830133A (en) * | 2018-04-17 | 2018-11-16 | 平安科技（深圳）有限公司 | Recognition methods, electronic device and the readable storage medium storing program for executing of contract image picture |
| CN112598768A (en) * | 2021-03-04 | 2021-04-02 | 中国科学院自动化研究所 | Method, system and device for disassembling strokes of Chinese characters with common fonts |
| CN112990022A (en) * | 2021-03-18 | 2021-06-18 | 广州伟宏智能科技有限公司 | OCR character recognition and extraction method |
| CN113596425A (en) * | 2021-06-21 | 2021-11-02 | 深圳市沃特沃德信息有限公司 | Image processing method and device for ink screen terminal, storage medium and intelligent device |
| CN114283156A (en) * | 2021-12-02 | 2022-04-05 | 珠海移科智能科技有限公司 | Method and device for removing document image color and handwriting |
| CN114974148A (en) * | 2022-07-29 | 2022-08-30 | 广州文石信息科技有限公司 | Font display enhancement method, device, equipment and storage medium for ink screen |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1334543A (en) * | 2000-07-25 | 2002-02-06 | 佳能株式会社 | Bills processing method and device |
| CN1677435A (en) * | 2004-04-01 | 2005-10-05 | 富士施乐株式会社 | Image processing device, image processing method, and storage medium storing program therefor |
| CN1949249A (en) * | 2005-10-11 | 2007-04-18 | 株式会社理光 | Table extracting method and apparatus |
| CN101122953A (en) * | 2007-09-21 | 2008-02-13 | 北京大学 | Picture words segmentation method |
| CN101526999A (en) * | 2008-11-24 | 2009-09-09 | 北京大学 | Image and character separating and outputting device and method thereof |
| CN101567049A (en) * | 2009-05-26 | 2009-10-28 | 西安交通大学 | Method for processing noise of half tone document image |
| US7773822B2 (en) * | 2005-05-02 | 2010-08-10 | Colormax, Inc. | Apparatus and methods for management of electronic images |
| CN101894268A (en) * | 2010-07-16 | 2010-11-24 | 西安理工大学 | Seal authenticity identification method capable of eliminating receipt interference |
| CN102541480A (en) * | 2010-12-21 | 2012-07-04 | 北大方正集团有限公司 | Filtering method and device for printing |
| CN103729656A (en) * | 2014-01-22 | 2014-04-16 | 河北远东通信系统工程有限公司 | Seal imprint identification method and identification system |
| CN104112128A (en) * | 2014-06-19 | 2014-10-22 | 中国工商银行股份有限公司 | Digital image processing system applied to bill image character recognition and method |
-
2017
- 2017-06-30 CN CN201710531861.6A patent/CN107358184A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1334543A (en) * | 2000-07-25 | 2002-02-06 | 佳能株式会社 | Bills processing method and device |
| CN1677435A (en) * | 2004-04-01 | 2005-10-05 | 富士施乐株式会社 | Image processing device, image processing method, and storage medium storing program therefor |
| US7773822B2 (en) * | 2005-05-02 | 2010-08-10 | Colormax, Inc. | Apparatus and methods for management of electronic images |
| CN1949249A (en) * | 2005-10-11 | 2007-04-18 | 株式会社理光 | Table extracting method and apparatus |
| CN101122953A (en) * | 2007-09-21 | 2008-02-13 | 北京大学 | Picture words segmentation method |
| CN101526999A (en) * | 2008-11-24 | 2009-09-09 | 北京大学 | Image and character separating and outputting device and method thereof |
| CN101567049A (en) * | 2009-05-26 | 2009-10-28 | 西安交通大学 | Method for processing noise of half tone document image |
| CN101894268A (en) * | 2010-07-16 | 2010-11-24 | 西安理工大学 | Seal authenticity identification method capable of eliminating receipt interference |
| CN102541480A (en) * | 2010-12-21 | 2012-07-04 | 北大方正集团有限公司 | Filtering method and device for printing |
| CN103729656A (en) * | 2014-01-22 | 2014-04-16 | 河北远东通信系统工程有限公司 | Seal imprint identification method and identification system |
| CN104112128A (en) * | 2014-06-19 | 2014-10-22 | 中国工商银行股份有限公司 | Digital image processing system applied to bill image character recognition and method |
Non-Patent Citations (1)
| Title |
|---|
| 邱立可等: "《基于模板匹配和Tesseract的票据归类和索引》", 《计算机与现代化》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108146093A (en) * | 2017-12-07 | 2018-06-12 | 南通艾思达智能科技有限公司 | A kind of method for removing bill seal |
| CN108537086A (en) * | 2018-03-29 | 2018-09-14 | 广东欧珀移动通信有限公司 | Method for information display, device, storage medium and mobile terminal |
| CN108830133A (en) * | 2018-04-17 | 2018-11-16 | 平安科技（深圳）有限公司 | Recognition methods, electronic device and the readable storage medium storing program for executing of contract image picture |
| WO2019200802A1 (en) * | 2018-04-17 | 2019-10-24 | 平安科技（深圳）有限公司 | Contract image recognition method, electronic device and readable storage medium |
| CN112598768A (en) * | 2021-03-04 | 2021-04-02 | 中国科学院自动化研究所 | Method, system and device for disassembling strokes of Chinese characters with common fonts |
| CN112990022A (en) * | 2021-03-18 | 2021-06-18 | 广州伟宏智能科技有限公司 | OCR character recognition and extraction method |
| CN113596425A (en) * | 2021-06-21 | 2021-11-02 | 深圳市沃特沃德信息有限公司 | Image processing method and device for ink screen terminal, storage medium and intelligent device |
| CN113596425B (en) * | 2021-06-21 | 2023-02-07 | 深圳市沃特沃德信息有限公司 | Image processing method and device for ink screen terminal, storage medium and intelligent device |
| CN114283156A (en) * | 2021-12-02 | 2022-04-05 | 珠海移科智能科技有限公司 | Method and device for removing document image color and handwriting |
| CN114283156B (en) * | 2021-12-02 | 2024-03-05 | 珠海移科智能科技有限公司 | Method and device for removing document image color and handwriting |
| CN114974148A (en) * | 2022-07-29 | 2022-08-30 | 广州文石信息科技有限公司 | Font display enhancement method, device, equipment and storage medium for ink screen |
| CN114974148B (en) * | 2022-07-29 | 2022-11-18 | 广州文石信息科技有限公司 | Font display enhancement method, device, equipment and storage medium for ink screen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358184A (en) | The extracting method and extraction element of document word | |
| US8472726B2 (en) | Document comparison and analysis | |
| US10817741B2 (en) | Word segmentation system, method and device | |
| US8472727B2 (en) | Document comparison and analysis for improved OCR | |
| CN104751142B (en) | A kind of natural scene Method for text detection based on stroke feature | |
| CN108090511B (en) | Image classification method and device, electronic equipment and readable storage medium | |
| Berezhnoy et al. | Computer analysis of van Gogh’s complementary colours | |
| Harraj et al. | OCR accuracy improvement on document images through a novel pre-processing approach | |
| TW200842734A (en) | Image processing program and image processing device | |
| CN109803172B (en) | Live video processing method and device and electronic equipment | |
| CN111259891B (en) | Method, device, equipment and medium for identifying identity card in natural scene | |
| CN106033528A (en) | Method and equipment for extracting specific area from color document image | |
| CN109949333B (en) | Character and seal separation method based on color unmixing | |
| CN112101349A (en) | License plate sample generation method and device | |
| CN108711160B (en) | Target segmentation method based on HSI (high speed input/output) enhanced model | |
| CN109741273A (en) | A kind of mobile phone photograph low-quality images automatically process and methods of marking | |
| CN110569774B (en) | Automatic line graph image digitalization method based on image processing and pattern recognition | |
| CN105426847A (en) | Nonlinear enhancing method for low-quality natural light iris images | |
| CN110554991A (en) | Method for correcting and managing text picture | |
| CN103617423B (en) | Image segmentation and recognition method based on color parameter | |
| CN108388898A (en) | Character identifying method based on connector and template | |
| KR102158633B1 (en) | A method for extraction of a registered seal impression from a document | |
| CN111445402A (en) | Image denoising method and device | |
| Ancuti et al. | Image decolorization based on information theory | |
| JP2022067086A (en) | Digitalized writing processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171117 |
|
| WD01 | Invention patent application deemed withdrawn after publication |