CN106169078B - Image-recognizing method - Google Patents
Image-recognizing method Download PDFInfo
- Publication number
- CN106169078B CN106169078B CN201610551578.5A CN201610551578A CN106169078B CN 106169078 B CN106169078 B CN 106169078B CN 201610551578 A CN201610551578 A CN 201610551578A CN 106169078 B CN106169078 B CN 106169078B
- Authority
- CN
- China
- Prior art keywords
- picture
- pixel
- image
- points
- identity card
- 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.)
- Active
Links
Classifications
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Abstract
The invention discloses a kind of image-recognizing methods comprising following steps: input image parameters;Input parameter name, identification card number, address, gender, birthdate;Virtual identity, which is generated, according to step 2 demonstrate,proves picture;Take out multiple pixels at random in the picture of step 3;Absolute position where identity card name in original picture is identified by OCR technique;The pixel taken in picture according to step 4 takes the pixel of identical quantity with same position;The points of solid colour in two set got in comparison step four and step 6, similarity is equal to the points of solid colour and the ratio of all points, identity card of judgement of the similarity greater than a certain fixed value as the picture comprising nominator is set, reenters step 1 if being less than.The present invention can be avoided in user's self-timer picture leads to problems such as pixel not match computer screen shooting comprising identity card entity with copy, and then user is avoided to carry out fraud.
Description
Technical field
The utility model relates to a kind of recognition methods, more particularly to a kind of image-recognizing method.
Background technique
User needs to submit accredited from taking pictures to verify the operator and hold loan application people's during loan application
Identity card is in kind, but user often encounters following several problems when production is taken pictures certainly: one, confirming in picture comprising identity
Body;Two, copy is used;Three, computer screen is shot, pixel unmatches.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of image-recognizing methods, can be avoided user's self-timer picture
In include identity card entity, with copy, lead to problems such as pixel not match computer screen shooting, and then avoid user
Using copy driver's license etc., other include the certificate progress fraud of identification card number.
The present invention is to solve above-mentioned technical problem by following technical proposals: a kind of image-recognizing method comprising
Following steps:
Step 1: input image parameters;
Step 2: input parameter name, identification card number, address, gender, birthdate;
Step 3: virtual identity is generated according to step 2 and demonstrate,proves picture;
Step 4: multiple pixels are taken out at random in the picture of step 3;
Step 5: absolute position where identity card name in original picture is identified by OCR technique;
Step 6: the pixel taken in picture according to step 4 takes the pixel of identical quantity with same position;
Step 7: the points of solid colour, similarity are equal in two set got in comparison step four and step 6
The points of solid colour and the ratio of all points set judgement of the similarity greater than a certain fixed value and include nominator as the picture
Identity card, if be less than if reenter step 1.
Preferably, the pixel of the step 4 is 2,000 to 100,000, is adjusted according to the requirement of misclassification rate;Pixel
Selection do not include head portrait part;The color value of each pixel is adjusted according to misclassification rate.
Preferably, the step 5 is according to the absolute position of name and the ratio of the text of standard identity card and frame,
Calculate the absolute position of identity card in the picture.
Preferably, the fixed value of the step 7 is dynamically adjusted according to the requirement to algorithm precision.
The positive effect of the present invention is that: it includes identity card entity in user's self-timer picture that the present invention, which can be avoided,
With copy, lead to problems such as pixel not match computer screen shooting, and then user is avoided to use copy driver's license
Fraud is carried out Deng the certificate that other include identification card number.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, various modifications and improvements can be made.These belong to the present invention
Protection scope.
As shown in Figure 1, image-recognizing method of the present invention the following steps are included:
Step 1: input image parameters.
Step 2: input parameter name, identification card number, address, gender, birthdate.
Step 3: virtual identity is generated according to step 2 and demonstrate,proves picture.
Step 4: multiple pixels are taken out at random in the picture of step 3.
Pixel is 2,000 to 100,000, is adjusted according to the requirement of misclassification rate;The selection of pixel does not include head portrait portion
Point;The color value of each pixel is adjusted according to misclassification rate.
Step 5: absolute position where identity card name in original picture is identified by OCR technique.
According to the ratio of the text and frame of the absolute position of name and standard identity card, identity in the picture is calculated
The absolute position of card.
Step 6: the pixel taken in picture according to step 4 takes the pixel of identical quantity with same position.
Step 7: the points of solid colour, similarity are equal in two set got in comparison step four and step 6
The points of solid colour and the ratio of all points set judgement of the similarity greater than a certain fixed value and include nominator as the picture
Identity card, if be less than if reenter step 1.
The fixed value is dynamically adjusted according to the requirement to algorithm precision.
In conclusion the present invention can be avoided in user's self-timer picture comprising identity card entity, with copy, to computer screen
Curtain shooting leads to problems such as pixel match not Shang, so avoid user from using copy driver's license etc. other include identification card number
Certificate carry out fraud.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make various deformations or amendments within the scope of the claims, this not shadow
Ring substantive content of the invention.
Claims (4)
1. a kind of image-recognizing method, which is characterized in that itself the following steps are included:
Step 1: input image parameters;
Step 2: input parameter name, identification card number, address, gender, birthdate;
Step 3: virtual identity is generated according to step 2 and demonstrate,proves picture;
Step 4: multiple pixels are taken out at random in the picture of step 3;
Step 5: absolute position where identity card name in original picture is identified by OCR technique;
Step 6: the pixel taken in picture according to step 4 takes the pixel of identical quantity with same position;
Step 7: the points of solid colour, similarity are equal to color in two set got in comparison step four and step 6
The ratio of consistent points and all points sets body of judgement of the similarity greater than a certain fixed value as the picture comprising nominator
Part card, reenters step 1 if being less than.
2. image-recognizing method as described in claim 1, which is characterized in that the pixel of the step 4 is 2,000 to 100,000
It is a, it is adjusted according to the requirement of misclassification rate;The selection of pixel does not include head portrait part;The color value of each pixel is according to accidentally
Knowledge rate is adjusted.
3. image-recognizing method as described in claim 1, which is characterized in that the step 5 according to the absolute position of name with
And standard identity card text and frame ratio, calculate the absolute position of identity card in the picture.
4. image-recognizing method as described in claim 1, which is characterized in that the fixed value of the step 7 is according to algorithm essence
The requirement of accuracy dynamically adjusts.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610551578.5A CN106169078B (en) | 2016-07-14 | 2016-07-14 | Image-recognizing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610551578.5A CN106169078B (en) | 2016-07-14 | 2016-07-14 | Image-recognizing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106169078A CN106169078A (en) | 2016-11-30 |
CN106169078B true CN106169078B (en) | 2019-04-16 |
Family
ID=58065306
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610551578.5A Active CN106169078B (en) | 2016-07-14 | 2016-07-14 | Image-recognizing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106169078B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106874968B (en) * | 2016-12-21 | 2020-03-24 | 江苏国光信息产业股份有限公司 | Second-generation identity card authenticity identification method |
CN107730574B (en) * | 2017-09-29 | 2021-04-06 | 四川长虹电器股份有限公司 | Automatic identity card generation method based on powershell |
CN109684980B (en) * | 2018-09-19 | 2022-12-13 | 腾讯科技(深圳)有限公司 | Automatic scoring method and device |
CN110213483A (en) * | 2019-05-30 | 2019-09-06 | 苏宁金融服务(上海)有限公司 | A kind of view-finder matching process and device for papers-scanning |
CN110248037B (en) * | 2019-05-30 | 2022-01-07 | 苏宁金融服务(上海)有限公司 | Identity document scanning method and device |
CN111539406B (en) * | 2020-04-21 | 2023-04-18 | 招商局金融科技有限公司 | Certificate copy information identification method, server and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102189862A (en) * | 2011-03-11 | 2011-09-21 | 赵利军 | Identity card copy anti-counterfeiting method and special template |
CN102955941A (en) * | 2011-08-31 | 2013-03-06 | 汉王科技股份有限公司 | Identity information recording method and device |
KR101346328B1 (en) * | 2012-10-22 | 2013-12-31 | 인하대학교 산학협력단 | Identification distincting apparatus using degraded images and distincting apparatus using the same |
CN105139048A (en) * | 2015-08-24 | 2015-12-09 | 汪风珍 | Double-number certificate and human-certificate identification system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7206431B2 (en) * | 2002-02-22 | 2007-04-17 | Symbol Technologies, Inc. | System and method for generating and verifying a self-authenticating document |
-
2016
- 2016-07-14 CN CN201610551578.5A patent/CN106169078B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102189862A (en) * | 2011-03-11 | 2011-09-21 | 赵利军 | Identity card copy anti-counterfeiting method and special template |
CN102955941A (en) * | 2011-08-31 | 2013-03-06 | 汉王科技股份有限公司 | Identity information recording method and device |
KR101346328B1 (en) * | 2012-10-22 | 2013-12-31 | 인하대학교 산학협력단 | Identification distincting apparatus using degraded images and distincting apparatus using the same |
CN105139048A (en) * | 2015-08-24 | 2015-12-09 | 汪风珍 | Double-number certificate and human-certificate identification system |
Also Published As
Publication number | Publication date |
---|---|
CN106169078A (en) | 2016-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106169078B (en) | Image-recognizing method | |
Benitez-Quiroz et al. | Recognition of Action Units in the Wild with Deep Nets and a New Global-Local Loss. | |
US20180204052A1 (en) | A method and apparatus for human face image processing | |
AU2016225946B2 (en) | Style transfer for headshot portraits | |
CN103414844B (en) | Video jitter modification method and device | |
CN106971165B (en) | A kind of implementation method and device of filter | |
CN109416727A (en) | Glasses minimizing technology and device in a kind of facial image | |
CN102486868A (en) | Average face-based beautiful face synthesis method | |
CN105608722A (en) | Face key point-based automatic under-eye bag removing method and system | |
CN109948441B (en) | Model training method, image processing method, device, electronic equipment and computer readable storage medium | |
US20190130536A1 (en) | Image blurring methods and apparatuses, storage media, and electronic devices | |
CN110264396B (en) | Video face replacement method, system and computer readable storage medium | |
CN101901472B (en) | Method for aligning non-rigid robust batch images based on matrix rank minimization | |
WO2019223068A1 (en) | Iris image local enhancement method, device, equipment and storage medium | |
JP2019117577A (en) | Program, learning processing method, learning model, data structure, learning device and object recognition device | |
CN112214773B (en) | Image processing method and device based on privacy protection and electronic equipment | |
CN106454096A (en) | Image processing method and terminal thereof | |
CN110111243B (en) | Method and device for beautifying handwriting fonts by using AI technology | |
CN109598270A (en) | Distort recognition methods and the device, storage medium and processor of text | |
US20170315710A1 (en) | Methods and systems for creating and using electronic coloring pages | |
JP2019046239A (en) | Image processing apparatus, image processing method, program, and image data for synthesis | |
CN109669537B (en) | A kind of man-machine interactive system based on computer virtual interface | |
Suryawibawa et al. | Herbs recognition based on android using opencv | |
CN105931204A (en) | Image restoring method and system | |
CN109376618A (en) | Image processing method, device and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 1810, 56-62 Changliu Road, Pudong New District, Shanghai, 201203 Applicant after: MicroExpress (Group) Co., Ltd. Address before: Room 1810, 56-62 Changliu Road, Pudong New District, Shanghai, 201203 Applicant before: The amount of micro shortdial (Shanghai) Financial Information Services Limited |
|
GR01 | Patent grant | ||
GR01 | Patent grant |