CN107392203A - Regular picture information identifying method and system - Google Patents

Regular picture information identifying method and system Download PDF

Info

Publication number
CN107392203A
CN107392203A CN201710560794.0A CN201710560794A CN107392203A CN 107392203 A CN107392203 A CN 107392203A CN 201710560794 A CN201710560794 A CN 201710560794A CN 107392203 A CN107392203 A CN 107392203A
Authority
CN
China
Prior art keywords
regular picture
picture
regular
mother matrix
information
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
Application number
CN201710560794.0A
Other languages
Chinese (zh)
Inventor
刘红玉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SERVYOU SOFTWARE GROUP Co Ltd
Original Assignee
SERVYOU SOFTWARE GROUP Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by SERVYOU SOFTWARE GROUP Co Ltd filed Critical SERVYOU SOFTWARE GROUP Co Ltd
Priority to CN201710560794.0A priority Critical patent/CN107392203A/en
Publication of CN107392203A publication Critical patent/CN107392203A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/24Aligning, centring, orientation detection or correction of the image
    • G06V10/243Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10Character recognition

Abstract

The invention discloses a kind of regular picture information identifying method and system, method to include:The marginal information of regular picture is obtained in the image of shooting;Regular Pictures location in the picture and the deviation angle of mother matrix position are calculated according to marginal information, image is rotated according to deviation angle, makes the position of regular picture and mother matrix position consistency in image;According to the marginal information of the regular picture of acquisition, regular picture is cut out in image after rotation;Using the recognition rule defined based on mother matrix, row information identification is entered in the regular picture cut out.The regular picture information identifying method of the present invention and system, by establishing mother matrix and defining recognition rule, regular Pictures location and mother matrix position consistency are made by adjustment first, then the regular identification information in regular picture defined based on mother matrix is utilized, it is achieved thereby that also can effectively be identified for shooting inclined regular picture, the defects of prior art is present is overcome.

Description

Regular picture information identifying method and system
Technical field
The present invention relates to image procossing application field, more particularly to a kind of regular picture information identifying method and system.
Background technology
Under the promotion of the technologies such as internet, cloud computing, big data development, E-Tax system is constantly sent out to intellectuality Exhibition.Intelligent electronic tax system can embody in several respects, such as, taxpayer carries out on-line real name certification, it is necessary to upload proof The related certificate photograph of its identity, to carry out examination & verification certification, intellectuality, which is embodied in be compared from traditional manual examination and verification, to be changed into calculating Machine automatic identification;And for example, taxpayer handles tax item, including the business such as registration, the purchase of invoice neck, tax declaration, also needs Related certificate of taking pictures uploads to be accepted with auditing, and intellectuality, which is embodied in from traditional manual examination and verification, is changed into system automatic identification ratio It is right.
In the prior art, the certificate picture and text identification function having in application system, it is desirable to which the certificate photograph that user uploads is clapped Take the photograph that proper, position is appropriate, pictorial information can be correctly validated, and certificate is tilted and can not effectively identified.But actually should In, excessively high require that user shoots the mode of certificate photograph, user can be made to feel very trouble inconvenience, often to be shot repeatedly It could identify successfully.
The content of the invention
In consideration of it, it is an object of the invention to provide a kind of regular picture information identifying method and system, tilted for shooting Regular picture also can effectively identify, overcome the defects of prior art is present.
To achieve the above object, the present invention provides following technical scheme:
A kind of regular picture information identifying method, including:
The marginal information of regular picture is obtained in the image of shooting;
The regular Pictures location in the picture and the deviation angle of mother matrix position, root are calculated according to the marginal information Described image is rotated according to the deviation angle, makes the position of regular picture described in image and the mother matrix position consistency;
According to the marginal information of the regular picture of acquisition, regular picture is cut out in image after rotation;
Using the recognition rule defined based on the mother matrix, row information identification is entered in the regular picture cut out.
Alternatively, the marginal information that regular picture is obtained in the image of shooting includes:
Background removal is carried out to the image of shooting;
Binary conversion treatment and rim detection are carried out to the image after above-mentioned processing, obtain the regular picture in the picture Corner pixels coordinate, the length of side of the regular picture.
Alternatively, carried out described using the recognition rule defined based on the mother matrix in the regular picture cut out Before information identification, in addition to:
Pixel operation is zoomed in and out to the regular picture cut out according to the mother matrix, makes regular picture and the institute cut out The Pixel Dimensions for stating mother matrix are consistent.
Alternatively, the recognition rule defined based on the mother matrix is included:Define the field name of field area, field area The height of starting point pixel coordinate, the width of field area and field area;
It is described to utilize the recognition rule defined based on the mother matrix, row information identification bag is entered in the regular picture cut out Include:
According to the starting point pixel coordinate, the width of field area and the height of field area of defined field area, from Sub-pictures are cut in regular picture, the identification information in the sub-pictures.
Alternatively, also included based on the rule that the mother matrix defines:Define coordinate position error deviation amount;
It is described to utilize the recognition rule defined based on the mother matrix, row information identification tool is entered in the regular picture cut out Body includes:
According to the coordinate position error deviation amount of definition, abscissa, the offset of ordinate of field area starting point are adjusted, The sub-pictures of predetermined number are cut out from regular picture;
The identification information in each sub-pictures, obtains the recognition result of predetermined number;
One group of most recognition result of number be will appear from as final result.
Alternatively, also included based on the recognition rule that the mother matrix defines:Define zoom ratio;
It is described to utilize the recognition rule defined based on the mother matrix, row information identification is entered in the regular picture cut out also Including:
Sub-pictures are zoomed in and out according to the zoom ratio of definition, identification information in the sub-pictures after scaling processing.
Alternatively, in addition to:When recognition failures ,/180 degree/270 degree are rotated by 90 ° to the regular picture cut out, then It is secondary to be identified.
A kind of regular picture information identification system, including:
Acquisition module, for obtaining the marginal information of regular picture in the image of shooting;
Rectification module, for calculating the regular Pictures location in the picture and mother matrix position according to the marginal information Deviation angle, according to the deviation angle rotate described image, make the position of regular picture described in image and the mother matrix Position consistency;
Module is cut, for the marginal information of the regular picture according to acquisition, is cut out in image after rotation Cut regular picture;
Identification module, for using the recognition rule defined based on the mother matrix, being carried out in the regular picture cut out Information identifies.
Alternatively, the cutting module is additionally operable to, regular in the rule cut out using being defined based on the mother matrix Enter in picture before row information identification, pixel operation is zoomed in and out to the regular picture cut out according to the mother matrix, makes cutting The regular picture gone out is consistent with the Pixel Dimensions of the mother matrix.
Alternatively, the identification module is additionally operable to, when recognition failures, to regular picture rotation 180 degree/270 degree, again It is identified.
As shown from the above technical solution, regular picture information identifying method provided by the present invention and system, are being clapped first The marginal information of regular picture is obtained in the image taken the photograph, regular Pictures location and mother matrix in the picture are calculated using marginal information Deviation angle, image is rotated according to this deviation angle, make the position of regular picture and mother matrix position consistency, Ran Hougen in image According to the marginal information of regular picture, regular picture is cut out in image after rotation, further utilizes what is defined based on mother matrix Rule enters row information identification in the regular picture cut out.
The regular picture information identifying method of the present invention and system, by establishing mother matrix and defining recognition rule, pass through first Adjustment makes regular Pictures location and mother matrix position consistency, then utilizes the rule defined based on mother matrix to identify letter in regular picture Breath, it is achieved thereby that also can effectively be identified for shooting inclined regular picture, overcome the defects of prior art is present.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of flow chart of regular picture information identifying method provided in an embodiment of the present invention;
Fig. 2 is the mother matrix schematic diagram established in the embodiment of the present invention;
Fig. 3 is a kind of flow chart for regular picture information identifying method that further embodiment of this invention provides;
Fig. 4 is a kind of schematic diagram of regular picture information identification system provided in an embodiment of the present invention.
Embodiment
In order that those skilled in the art more fully understand the technical scheme in the present invention, below in conjunction with of the invention real The accompanying drawing in example is applied, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described implementation Example only part of the embodiment of the present invention, rather than whole embodiments.It is common based on the embodiment in the present invention, this area The every other embodiment that technical staff is obtained under the premise of creative work is not made, should all belong to protection of the present invention Scope.
It refer to Fig. 1, a kind of regular picture information identifying method provided in an embodiment of the present invention, including step:
S10:The marginal information of regular picture is obtained in the image of shooting.
It should be noted that in this method, the regular picture can be the various certificates with regular shape, for example occupy People's identity card, social security card etc..
In the specific implementation, this step can be carried out by following processing procedure, including step:
S100:Background removal is carried out to the image of shooting.
The regular picture obtained to shooting, background removal processing is carried out, remove background.
S101:Binary conversion treatment and rim detection are carried out to the image after above-mentioned processing, obtain the rule in the picture Then the corner pixels coordinate of picture, the length of side of the regular picture.
For the image obtained after upper step process, carry out binary conversion treatment, by binary conversion treatment by regular picture with Substantially distinguish background area.Then in the image after binary conversion treatment, regular picture is extracted according to pixel pixel value The edge in region.In the specific implementation, the pixel that pixel value is 255 can be extracted in the picture, be the edge of regular picture Point.
From the edge pixel point extracted, the angle point of regular picture is obtained, obtains corner pixels coordinate.And according to angle point Pixel coordinate, calculate the length of side of regular picture.
For example if this method is applied to identification user identity card, user identity card is rectangle, is accordingly extracted in the picture Four corner pixels coordinates of certificate, and calculate the width and height of regular picture.
S11:The regular Pictures location in the picture and the deviation angle of mother matrix position are calculated according to the marginal information Degree, described image is rotated according to the deviation angle, makes the position of regular picture described in image and the mother matrix position consistency.
In this method, for a kind of regular picture, using the regular picture shooting image of a standard as mother matrix.Specifically , shooting regular picture has the front view picture of one side of information, as mother matrix image.Such as resident identification card, for Identity card front and back, shoot front elevational view picture respectively and rear elevation view picture establishes mother matrix.
The corner pixels coordinate of the picture regular in the picture obtained according to upper step, calculate regular Pictures location and mother The deviation angle of version position.For example for being shaped as the certificate of rectangle, the mother matrix position of foundation is:The side of mother matrix respectively with water Square to or vertical direction it is parallel, refer to shown in Fig. 2, Fig. 2 is the mother matrix schematic diagram established in an embodiment.According to extraction The corner pixels coordinate of the regular picture gone out, calculate respectively each side of regular picture respectively with horizontal direction or vertical direction Angle, so as to obtain the deviation angle of regular Pictures location and mother matrix position.
Then according to the deviation angle being calculated, image is rotated, makes the position of regular picture and mother matrix position in image Unanimously.
S12:According to the marginal information of the regular picture of acquisition, the rule schema is cut out in image after rotation Piece.
According to the marginal information of the regular picture obtained in step S10, including the corner pixels coordinate of regular picture and The regular picture length of side being calculated, regular picture is cut out in image after rotation.
Preferably, in a kind of embodiment of the present embodiment method, know in step S13 in the regular picture cut out Before other information, in addition to:Pixel operation is zoomed in and out to the regular picture cut out according to the mother matrix, makes the rule cut out Then picture is consistent with the Pixel Dimensions of the mother matrix.
It has been just to scheme that upper step, which cuts gained picture, but its pixel may be inconsistent with the pixel of mother matrix, such as its Pixel is 672 × 1068, and mother matrix Pixel Dimensions are 712 × 448, it is therefore desirable to is further rotated that (rotation here is Refer to the size according to mother matrix, decide whether to be rotated by 90 ° according to the size of the width of picture and height) and scaling pixel operation, most Become eventually with reticle dimension and position consistency, provide and accurately enter for follow-up identification.
S13:Using the recognition rule defined based on the mother matrix, row information identification is entered in the regular picture cut out.
In this method, it is in advance based on mother matrix and defines recognition rule, establish rule base.
Specifically, included based on the recognition rule that mother matrix defines:Define field name, the starting point of field area of field area The height of pixel coordinate, the width of field area and field area.
This step utilizes the recognition rule defined based on mother matrix, and row information identification bag is entered in the regular picture cut out Include:According to the starting point pixel coordinate, the width of field area and the height of field area of defined field area, from rule schema Sub-pictures are cut in piece, the identification information in the sub-pictures.
In the specific implementation, OCR (optical character recognition) character recognition method can be used in son Text information is identified in picture.
Preferably, in order to improve the accuracy rate of information identification, in this method another embodiment, defined based on mother matrix Recognition rule except including:Define the field name of field area, the starting point pixel coordinate of field area, field area width and Outside the height of field area, in addition to:Define coordinate position error deviation amount.
Accordingly, letter is carried out in the regular picture cut out using the recognition rule defined based on mother matrix in this step Breath identification comprises the following steps:
S130:According to the coordinate position error deviation amount of definition, adjust the abscissa of field area starting point, ordinate it is inclined Shifting amount, the sub-pictures of predetermined number are cut out from regular picture;
S131:The identification information in each sub-pictures, obtains the recognition result of predetermined number;
S132:One group of most recognition result of number be will appear from as final result.
Such as when information is identified to certain field area in regular picture, according to the coordinate bit defined in rule file Error deviation amount is put, corrects the x coordinate value and y-coordinate value of the field area starting point, increases offset or reduces offset, point Sub-pictures are not cut out.The sub-pictures cut out and original subpicture piece will be offset together, for example there are 9 pictures altogether, entered simultaneously Row identification.9 groups of results are finally given, the one group of most result of occurrence number of selecting most to be consistent from 9 groups of results is as finally Recognition result.
It is difficult to it is further preferred that there may be larger or less word in picture, in this method, based on institute Stating the recognition rule that mother matrix defines also includes:Define zoom ratio.
It is described to utilize the recognition rule defined based on the mother matrix, row information identification is entered in the regular picture cut out also Including:Sub-pictures are zoomed in and out according to the zoom ratio of definition, identification information in the sub-pictures after scaling processing.Passing through will The larger or less word being difficult to first carries out ratio scaling, is identified again after being changed into normal size font, so Improve recognition accuracy.
In addition, in this method, also included based on the recognition rule that mother matrix defines:Minimum identification length, maximum identification length, Character correction array, field contents regular expression.The value of identification is corrected, verification operation, improve final identification information Accuracy rate.
Exemplary, the rule file defined in the present embodiment based on mother matrix is as follows:
It is further preferred that the present embodiment rule picture information identifying method also includes:When recognition failures, to cutting out Regular picture be rotated by 90 °/180 degree/270 degree, be identified again.Fig. 3 specifically is refer to, is defined using based on mother matrix Recognition rule, in the regular picture cut out carry out primary information identification after, judge whether to identify successfully, if so, then defeated Go out recognition result.If it is not, then perform step S14:/ 180 degree/270 degree are rotated by 90 ° to the regular picture cut out.Then enter again Enter step S13, be identified again.
By identification process if can not identify it is any as a result, it is possible to certificate position just place on the contrary, if by right 90 degree/180 degree/270 degree of certificate picture rotation, then the rule defined based on mother matrix is proceeded as described above to picture recognition information, So guarantee effectively to identify regular pictorial information from image.
Accordingly, Fig. 4 is refer to, the embodiment of the present invention also provides a kind of regular picture information identification system, including:
Acquisition module 30, for obtaining the marginal information of regular picture in the image of shooting;
Rectification module 31, for calculating the regular Pictures location in the picture and mother matrix position according to the marginal information The deviation angle put, described image is rotated according to the deviation angle, makes the position of regular picture described in image and the mother Version position consistency;
Module 32 is cut, for the marginal information of the regular picture according to acquisition, in image after rotation Cut out regular picture;
Identification module 33, for using the recognition rule defined based on the mother matrix, entering in the regular picture cut out Row information identifies.
As can be seen that the present embodiment rule picture information identification system, including acquisition module, rectification module, cutting module And identification module, the marginal information of regular picture is obtained in the image of shooting first, is calculated in the picture using marginal information The deviation angle of regular Pictures location and mother matrix, image is rotated according to this deviation angle, makes the position of regular picture in image With mother matrix position consistency, then according to the marginal information of regular picture, regular picture is cut out in image after rotation, enters one Step enters row information identification using based on the rule that mother matrix defines in the regular picture cut out.
The present embodiment rule picture information identification system, by establishing mother matrix and defining recognition rule, passes through adjustment first Make regular Pictures location and mother matrix position consistency, then utilize the regular identification information in regular picture defined based on mother matrix, It is achieved thereby that also can effectively be identified for shooting inclined regular picture, the defects of prior art is present is overcome.
In the present embodiment, the cutting module 32 is additionally operable to, and is being cut out using based on the rule that the mother matrix defines Regular picture in enter row information identification before, pixel operation is zoomed in and out to the regular picture cut out according to the mother matrix, The regular picture for making to cut out is consistent with the Pixel Dimensions of the mother matrix.
The identification module 33 is additionally operable to, and when recognition failures, to regular picture rotation 180 degree/270 degree, is carried out again Identification.
A kind of regular picture information identifying method provided by the present invention and system are described in detail above.Herein In apply specific case to the present invention principle and embodiment be set forth, the explanation of above example is only intended to help Assistant solves the method and its core concept of the present invention.It should be pointed out that for those skilled in the art, not On the premise of departing from the principle of the invention, some improvement and modification can also be carried out to the present invention, these are improved and modification is also fallen into In the protection domain of the claims in the present invention.

Claims (10)

  1. A kind of 1. regular picture information identifying method, it is characterised in that including:
    The marginal information of regular picture is obtained in the image of shooting;
    The regular Pictures location in the picture and the deviation angle of mother matrix position are calculated according to the marginal information, according to institute Deviation angle rotation described image is stated, makes the position of regular picture described in image and the mother matrix position consistency;
    According to the marginal information of the regular picture of acquisition, regular picture is cut out in image after rotation;
    Using the recognition rule defined based on the mother matrix, row information identification is entered in the regular picture cut out.
  2. 2. regular picture information identifying method according to claim 1, it is characterised in that described to be obtained in the image of shooting Taking the marginal information of regular picture includes:
    Background removal is carried out to the image of shooting;
    Binary conversion treatment and rim detection are carried out to the image after above-mentioned processing, obtain the angle of the regular picture in the picture Point pixel coordinate, the length of side of the regular picture.
  3. 3. regular picture information identifying method according to claim 1, it is characterised in that be based on the mother in described utilize The recognition rule of version definition, enter in the regular picture cut out before row information identification, in addition to:
    Pixel operation is zoomed in and out to the regular picture cut out according to the mother matrix, makes the regular picture that cuts out and the mother The Pixel Dimensions of version are consistent.
  4. 4. regular picture information identifying method according to claim 1, it is characterised in that the knowledge defined based on the mother matrix Not rule includes:Define the field name of field area, the starting point pixel coordinate of field area, the width and field area of field area The height in domain;
    Described to utilize the recognition rule defined based on the mother matrix, row information identification is entered in the regular picture cut out to be included:
    According to the starting point pixel coordinate, the width of field area and the height of field area of defined field area, from rule Sub-pictures are cut in picture, the identification information in the sub-pictures.
  5. 5. regular picture information identifying method according to claim 4, it is characterised in that the rule defined based on the mother matrix Then also include:Define coordinate position error deviation amount;
    It is described to utilize the recognition rule defined based on the mother matrix, the specific bag of row information identification is entered in the regular picture cut out Include:
    According to the coordinate position error deviation amount of definition, the abscissa of adjustment field area starting point, the offset of ordinate, from rule The sub-pictures of predetermined number are then cut out in picture;
    The identification information in each sub-pictures, obtains the recognition result of predetermined number;
    One group of most recognition result of number be will appear from as final result.
  6. 6. regular picture information identifying method according to claim 5, it is characterised in that the knowledge defined based on the mother matrix Rule does not include also:Define zoom ratio;
    It is described to utilize the recognition rule defined based on the mother matrix, row information identification is entered in the regular picture cut out and is also wrapped Include:
    Sub-pictures are zoomed in and out according to the zoom ratio of definition, identification information in the sub-pictures after scaling processing.
  7. 7. the regular picture information identifying method according to claim any one of 4-6, it is characterised in that also include:Work as knowledge Not Shi Bai when ,/180 degree/270 degree are rotated by 90 ° to the regular picture cut out, are identified again.
  8. A kind of 8. regular picture information identification system, it is characterised in that including:
    Acquisition module, for obtaining the marginal information of regular picture in the image of shooting;
    Rectification module, for calculating the inclined of the regular Pictures location and mother matrix position in the picture according to the marginal information Angle is moved, described image is rotated according to the deviation angle, makes the position of regular picture described in image and the mother matrix position Unanimously;
    Module is cut, for the marginal information of the regular picture according to acquisition, is cut out in image after rotation Regular picture;
    Identification module, for using the recognition rule defined based on the mother matrix, entering row information in the regular picture cut out Identification.
  9. 9. regular picture information identification system according to claim 8, it is characterised in that the cutting module is additionally operable to, Before row information identification is entered in the regular picture cut out using the rule defined based on the mother matrix, according to the mother matrix Pixel operation is zoomed in and out to the regular picture cut out, makes the Pixel Dimensions one of the regular picture and mother matrix cut out Cause.
  10. 10. regular picture information identification system according to claim 8, it is characterised in that the identification module is additionally operable to, When recognition failures, to regular picture rotation 180 degree/270 degree, it is identified again.
CN201710560794.0A 2017-07-11 2017-07-11 Regular picture information identifying method and system Pending CN107392203A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710560794.0A CN107392203A (en) 2017-07-11 2017-07-11 Regular picture information identifying method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710560794.0A CN107392203A (en) 2017-07-11 2017-07-11 Regular picture information identifying method and system

Publications (1)

Publication Number Publication Date
CN107392203A true CN107392203A (en) 2017-11-24

Family

ID=60340366

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710560794.0A Pending CN107392203A (en) 2017-07-11 2017-07-11 Regular picture information identifying method and system

Country Status (1)

Country Link
CN (1) CN107392203A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109376735A (en) * 2018-08-31 2019-02-22 百度在线网络技术(北京)有限公司 Identity information extracting method, device, electronic equipment and storage medium
CN109492637A (en) * 2018-11-06 2019-03-19 西安艾润物联网技术服务有限责任公司 Method of adjustment, identifier terminal and the readable storage medium storing program for executing of cog region
CN110415177A (en) * 2019-07-26 2019-11-05 四川长虹电器股份有限公司 A kind of image rotation sanction drawing method based on Java
CN110738602A (en) * 2019-09-12 2020-01-31 北京三快在线科技有限公司 Image processing method and device, electronic equipment and readable storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101655981A (en) * 2009-09-09 2010-02-24 谭洪舟 Method for detecting and adjusting inversion of certificate image
US8345993B1 (en) * 2007-10-24 2013-01-01 Glenn E Weeks Electronic coding system for security of identification
CN103488984A (en) * 2013-10-11 2014-01-01 从兴技术有限公司 Method and device for identifying second-generation identity cards based on intelligent mobile equipment
CN103729645A (en) * 2013-12-20 2014-04-16 湖北微模式科技发展有限公司 Second-generation ID card area positioning and extraction method and device based on monocular camera
CN106886774A (en) * 2015-12-16 2017-06-23 腾讯科技(深圳)有限公司 The method and apparatus for recognizing ID card information

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8345993B1 (en) * 2007-10-24 2013-01-01 Glenn E Weeks Electronic coding system for security of identification
CN101655981A (en) * 2009-09-09 2010-02-24 谭洪舟 Method for detecting and adjusting inversion of certificate image
CN103488984A (en) * 2013-10-11 2014-01-01 从兴技术有限公司 Method and device for identifying second-generation identity cards based on intelligent mobile equipment
CN103729645A (en) * 2013-12-20 2014-04-16 湖北微模式科技发展有限公司 Second-generation ID card area positioning and extraction method and device based on monocular camera
CN106886774A (en) * 2015-12-16 2017-06-23 腾讯科技(深圳)有限公司 The method and apparatus for recognizing ID card information

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109376735A (en) * 2018-08-31 2019-02-22 百度在线网络技术(北京)有限公司 Identity information extracting method, device, electronic equipment and storage medium
CN109492637A (en) * 2018-11-06 2019-03-19 西安艾润物联网技术服务有限责任公司 Method of adjustment, identifier terminal and the readable storage medium storing program for executing of cog region
CN110415177A (en) * 2019-07-26 2019-11-05 四川长虹电器股份有限公司 A kind of image rotation sanction drawing method based on Java
CN110738602A (en) * 2019-09-12 2020-01-31 北京三快在线科技有限公司 Image processing method and device, electronic equipment and readable storage medium

Similar Documents

Publication Publication Date Title
WO2019169532A1 (en) License plate recognition method and cloud system
CN107392203A (en) Regular picture information identifying method and system
US9519838B2 (en) Character recognition method
US8254644B2 (en) Method, apparatus, and program for detecting facial characteristic points
CN111680688A (en) Character recognition method and device, electronic equipment and storage medium
US20220309813A1 (en) Machine learning for data extraction
WO2019174133A1 (en) Electronic device, physical seal identification method, and computer readable storage medium
CN107506693A (en) Distort face image correcting method, device, computer equipment and storage medium
CN111553251B (en) Certificate four-corner defect detection method, device, equipment and storage medium
CN112926469B (en) Certificate identification method based on deep learning OCR and layout structure
CN108734235A (en) A kind of personal identification method and system for electronic prescription
CN110717492B (en) Method for correcting direction of character string in drawing based on joint features
CN106778737A (en) A kind of car plate antidote, device and a kind of video acquisition device
WO2013040933A1 (en) Identification method for valuable file and identification device thereof
CN111860527A (en) Image correction method, image correction device, computer device, and storage medium
CN109598185B (en) Image recognition translation method, device and equipment and readable storage medium
WO2018205789A1 (en) Method and apparatus for recognizing card placement direction, and image processing apparatus
US9741133B2 (en) Identifying shapes in an image by comparing Bézier curves
CN107590495A (en) Answer sheet picture method for correcting error, device, readable storage medium storing program for executing and electronic equipment
CN114694161A (en) Text recognition method and equipment for specific format certificate and storage medium
CN111611994A (en) Image extraction method, image extraction device, electronic equipment and storage medium
CN113221897B (en) Image correction method, image text recognition method, identity verification method and device
CN111325106B (en) Method and device for generating training data
US11393248B2 (en) Data detection method and device, computer equipment and storage medium
CN113627442A (en) Medical information input method, device, equipment and storage medium

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20171124