CN109410026A - Identity identifying method, device, equipment and storage medium based on recognition of face - Google Patents
Identity identifying method, device, equipment and storage medium based on recognition of face Download PDFInfo
- Publication number
- CN109410026A CN109410026A CN201810131476.7A CN201810131476A CN109410026A CN 109410026 A CN109410026 A CN 109410026A CN 201810131476 A CN201810131476 A CN 201810131476A CN 109410026 A CN109410026 A CN 109410026A
- Authority
- CN
- China
- Prior art keywords
- image
- information
- card
- face
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of identity identifying method based on recognition of face, device, equipment and storage mediums, which comprises obtains the image of client camera acquisition in real time;ID card information is extracted, identity card direct picture and identity card verso images is captured, obtains effective text information of single identity card;Effective text information of the identity card is sorted out, the ID card information of classification is exported;Networking comparison is carried out to the ID card information of the face image and the classification to verify, and judges its consistency;When the ID card information by the classification carries out online checking, user information exists;And the face image it is consistent with the identity card facial image that online checking returns when, ID card information is true;Otherwise, ID card information is false;Comparison is obtained to verify result and export.The above method improves the safety of ID card information, using intelligent comparison, quickly determines the consistency of personal information in object to be identified and identity card.
Description
Technical field
The present invention relates to information security fields, more particularly to the identity identifying method based on recognition of face, device, equipment and
Storage medium.
Background technique
By the advantage of internet, online credit is also becoming a kind of trend, the completion loan Shen that can be stayed indoors
Every step please, the application condition including understanding all kinds of loans, prepares application material, until submitting loan application, all may be used
To be efficiently completed on the internet.In network credit operation, the verification of client identity cannot be passed through as traditional business
Client provides identity document, and service management personnel are completed by visually carrying out rough comparison.
Authentication based on recognition of face becomes inevitable, however the prior art has the following disadvantages, and knows to facial image
Not rate is lower, when face shape is unstable, especially when face samples by countenance, exterior light photograph, face's overcover etc. in many ways
When the influence of face factor, will increase face recognition difficulty can not quickly filter identity card when cooperation identity card carries out authentication
In personal information and it is fast read reading characters information, comparison recognition speed is slow.
Summary of the invention
Based on this, it is necessary in view of the deficiencies of the prior art, provide a kind of identity identifying method based on recognition of face, dress
It sets, equipment and storage medium.
A kind of identity identifying method based on recognition of face, which comprises obtain the acquisition of client camera in real time
Image, face image is obtained from described image;ID card information is extracted, identity card direct picture and identity card reverse side are captured
Image carries out capable positioning, binaryzation, noise remove, slant correction, the space of a whole page to identity card direct picture and identity card verso images
Analysis, Character segmentation, obtain effective text information of single identity card;Effective text information of the identity card is pressed into surname
Name, address, nationality, identification card number are sorted out, and the ID card information of classification is exported;To the face image and the classification
ID card information carries out networking comparison and verifies, and the networking comparison is verified as connection citizen identity information check system to the face
Portion's image and the ID card information of the classification are verified, and judge its consistency;When the ID card information by the classification
Online checking is carried out, user information exists;And the face image it is consistent with the identity card facial image that online checking returns when,
ID card information is true;Otherwise, ID card information is false;Comparison is obtained to verify result and export.
In one of the embodiments, before the real-time image for obtaining the acquisition of client camera further include: to institute
The face posture of acquisition angle, illumination, blocks influence factor progress screenshot environment pre-detection, and issues prompt so that user matches
It closes.
In one of the embodiments, before the real-time image for obtaining the acquisition of client camera further include: pass through
The output regulation button of the client receives the first instruction input to adjust the presumptive area, according to first instruction
Adjust the presumptive area.
The real-time image for obtaining the acquisition of client camera in one of the embodiments, is obtained from described image
After taking face image further include: the position that the face image is located in described image is detected, when the face image is located at
When other than the presumptive area in described image, by issuing prompt so that the face returns in presumptive area.
It is described in one of the embodiments, that capable positioning, two are carried out to identity card direct picture and identity card verso images
Value, noise remove, slant correction, printed page analysis, Character segmentation, the effective text information for obtaining single identity card specifically walk
Suddenly include:
Coarse positioning is carried out to effective information according to position of effective text information in identity card;
According to the average gray of the be expert at pixel in boundary in effective text information row this characteristic smaller than background, to thick fixed
The text information of position carries out precise positioning, generates the picture element matrix of pending filtering processing, and the picture element matrix is precise positioning
Region, the formula of use are as follows: by gray value in image less than or equal to lower boundary LT point be labeled as foreground point, gray value be greater than etc.
It is labeled as background dot in the point of coboundary HT, wherein LT=T*r, HT=255- (255-T) * r, T are level where slicing operation
Maximum gradation value, r are empirical values, r=0.6, to prevent from will be present the background trade of different at the boundary of precise positioning, together
Reason obtains the lower boundary, left margin, right margin in precise positioning region;
Gaussian filtering is carried out to precise positioning region using 3 pixels × 3 pixels gaussian filtering template, weakens the dry of background information
Disturb and remove noise;
Binaryzation is carried out to precise positioning region using dynamic threshold, obtains the bianry image in precise positioning region, and to accurate
The bianry image of localization region carries out individual character segmentation, obtains single effective text information.
A kind of identification authentication system based on recognition of face, described device include: face's acquiring unit, for obtaining in real time
The image of client camera acquisition, obtains face image from described image;Identity information acquiring unit, for extracting identity
Demonstrate,prove information, capture identity card direct picture and identity card verso images, to identity card direct picture and identity card verso images into
Every trade positioning, binaryzation, noise remove, slant correction, printed page analysis, Character segmentation obtain effective text of single identity card
Word information;Identity information sorts out unit, for effective text information of the identity card to be pressed name, address, nationality, identity card
Number sorted out, exports the ID card information of classification;Unit is verified in comparison, for the body to the face image and the classification
Part card information carries out networking comparison and verifies, and the networking, which compares, verifies as connection citizen identity information check system to the face
Image and the ID card information of the classification are verified, and judge its consistency;When the ID card information by the classification into
Row online checking, user information exist;And the face image it is consistent with the identity card facial image that online checking returns when, body
Part card information is true;Otherwise, ID card information is false;As a result output unit, for obtaining comparison verification result and exporting.
Face's acquiring unit is also used to face's acquiring unit and is also used to being adopted in one of the embodiments,
The face posture of collection angle, illumination, blocks influence factor progress screenshot environment pre-detection, and issues and prompt so that user cooperates.
In one of the embodiments, face's acquiring unit be also used to adjust by the output of the client by
Button receives the first instruction input to adjust the presumptive area, adjusts the presumptive area and detection according to first instruction
The face image is located at the position in described image, other than the presumptive area that the face image is located in described image
When, by issuing prompt so that the face returns in presumptive area.
A kind of computer equipment, including memory and processor are stored with computer-readable instruction in the memory, institute
When stating computer-readable instruction and being executed by the processor, so that the processor executes the above-mentioned identity based on recognition of face and recognizes
The step of card method.
A kind of storage medium being stored with computer-readable instruction, the computer-readable instruction are handled by one or more
When device executes, so that the step of one or more processors execute the above-mentioned identity identifying method based on recognition of face.
The above-mentioned identity identifying method based on recognition of face, device, equipment and storage medium, by obtaining client in real time
The image of camera acquisition, obtains face image from described image, extracts ID card information, capture identity card direct picture and
Identity card verso images carry out capable positioning to identity card direct picture and identity card verso images, binaryzation, noise remove, incline
Oblique correction, printed page analysis, Character segmentation, obtain effective text information of single identity card, by effective text of the identity card
Word information is sorted out by name, address, nationality, identification card number, exports the ID card information of classification;To the face image and
The ID card information of the classification carries out networking comparison and verifies, and the networking comparison is verified as connection citizen identity information check system
System verifies the ID card information of the face image and the classification, judges its consistency;When passing through the classification
ID card information carries out online checking, and user information exists, and the identity card face that the face image and online checking return
When image is consistent, ID card information is true;Otherwise, ID card information is false;It obtains comparison to verify result and export, reducing makes
The error rate compared with identity card personal information craft typing and naked eyes, improves the safety of ID card information, using intelligence
Way of contrast quickly determines the consistency of personal information in object to be identified and identity card, completes authentication.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.
Fig. 1 is the flow chart of the identity identifying method based on recognition of face in one embodiment of the invention;
Fig. 2 be one embodiment of the invention in identity card direct picture and identity card verso images carry out capable positioning, binaryzation,
Noise remove, slant correction, printed page analysis, Character segmentation obtain the process of effective text information method of single identity card
Figure;
Fig. 3 is the structural block diagram of the identification authentication system based on recognition of face in one embodiment of the invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.
As shown in Figure 1, in one embodiment it is proposed that a kind of identity identifying method based on recognition of face, this is based on
The identity identifying method of recognition of face can specifically include following steps:
Step 101, the image for obtaining the acquisition of client camera in real time, obtains face image from image;
The terminal device of client can be mobile phone, IPAD etc., the camera real-time image acquisition of these equipment, and processor is real-time
The image is got from camera, processor here obtains the photo that image is not camera shooting, only camera shadow
As the realtime graphic in region, after getting realtime graphic, such as face mask data, face feature data, including eyes, nose
Son, mouth, but do not need specifically to identify face, this step only needs to identify face from background, just
In being further processed.
Step 102, ID card information is extracted, captures identity card direct picture and identity card verso images, just to identity card
Face image and identity card verso images carry out capable positioning, binaryzation, noise remove, slant correction, printed page analysis, Character segmentation,
Obtain effective text information of single identity card;
Frame calibration is carried out to the camera of client, i.e., sets one in center in each frame image that camera captures
Size is the red frame of 580*580, can simplify algorithm in this way, accelerates processing progress, recognition efficiency is improved, due to identity card
Direct picture includes face information, therefore chooses a large amount of facial image, and these facial images are demarcated into positive sample, non-face
Whether image calibration distinguishes containing facial image the identity card direct picture and identity of user by model inspection at negative sample
Verso images are demonstrate,proved, can detect that facial image is identity card direct picture, otherwise are identity card verso images.
To distinguish the identity card direct picture and identity card verso images of user, simply and effectively solve to identity card
The problem of positive information extracts carries out relevant treatment to identity card direct picture and identity card verso images respectively, to obtain body
Effective text information of part card.ID card information position is fixed in ID Card Image, thus to identity card direct picture and
When effective information in the verso images of identity card is identified using to identity card direct picture and identity card verso images into
The pretreatments such as row positioning, binaryzation, noise remove, slant correction, printed page analysis, Character segmentation, image binaryzation is exactly will figure
As the gray value of upper pixel is set as 0 or 255, that is, whole image is showed to the process of apparent black and white effect,
In Digital Image Processing, the binaryzation of image is greatly reduced data volume in image, so as to highlight the profile of target, has
It is further processed conducive to image, skew correction, image denoising, the pre- place such as image enhancement then is carried out to image
Reason, printed page analysis, information column positioning, row segmentation and Character segmentation, Chinese character are made of a stroke, and each every stroke of pen is all
It being made of the pixel in some connected domains, the connected domain of upright Chinese character has feature, when intercharacter stroke has adhesion,
Multiple characters form a connected domain, need the average word of basis wide, are cut by projective analysis method, obtain the knot of cutting
Fruit obtains character structure information, word to be identified to obtain effective text information of single identity card.
Step 103, effective text information of the identity card is sorted out by name, address, nationality, identification card number,
Export the ID card information sorted out;
ID card information is identified and sorted out by name, address, nationality, identification card number, and using the ID card information of classification as item
Corresponding field is compared in part inquiry public security bureau's demographic database.
Step 104, it carries out networking comparison to the ID card information of the face image and the classification to verify, the networking
Comparison, which is verified, tests the ID card information of the face image and the classification for connection citizen identity information check system
Card, judges its consistency;When the ID card information by the classification carries out online checking, user information exists;And the face
When portion's image is consistent with the identity card facial image that online checking returns, ID card information is true;Otherwise, ID card information is
It is false;
After the character information on identity card surface is identified, name and ID card No. are input to citizenship information automatically
Inquired in network verification system, if inquired in library there are the name and ID card No., system if return with this name and
The consistent certificate information of ID card No. specifically includes: name, identification card number, address, nationality, birthdate, face
Photo etc..And using face recognition technology by identity card facial image and online checking in identity card facial image compare
It is right, judge its consistency.
Step 105, comparison is obtained to verify result and export.
Comparison query result is verified, and verification type includes response results verification, database result verification and log knot
Fruit verification obtains interface data corresponding with verification type, interface data is matched with preset correction result data, is obtained
To whether matched check results, can be automatically performed the verification of result by system, improve the efficiency of result verification and reduce false drop
Rate, and the result after output verification.
In one embodiment, before the image for obtaining the acquisition of client camera in real time further include: to people collected
Face posture angle, illumination, blocks influence factor progress screenshot environment pre-detection, and issues and prompt so that user cooperates.
Video is transferred by camera, then carries out Face detection, living body detection is carried out to face, to people collected
Face posture angle, illumination, is blocked influence factor progress screenshot environment pre-detection, and is used by voice prompting device, display screen prompt
Family cooperation.
In one embodiment, before the image for obtaining the acquisition of client camera in real time further include: pass through client
Regulation button is exported, the first instruction input is received to adjust presumptive area, presumptive area is adjusted according to the first instruction.
First instruction is the control instruction of photographer, as photographer clicks the adjusting knob of terminal device to make a reservation for
The adjusting in region, the adjusting of presumptive area includes that big minor adjustment and position are adjusted, when the display screen that adjusting knob is terminal device
When on image for showing the cyclic structure of presumptive area, photographer can draw cyclic structure on a display screen directly to carry out
Position adjusts and big minor adjustment, specifically, can be according to redefining presumptive area, later behaviour after the above-mentioned adjusting of photographer
Make to carry out according to the presumptive area newly set.
In one embodiment, in real time obtain client camera acquisition image, from image obtain face image it
Afterwards further include: detection face image is located at the position in image, when other than the presumptive area that face image is located in image, leads to
Sending prompt is crossed so that face returns in presumptive area.
Presumptive area is to preset, and can be passively arranged, for example, being such as defaulted as in terminal mobile device screen
Between 3X3 inches region be presumptive area, its size and region can also be actively set by user.Get realtime graphic
Afterwards, face is identified from image, and is detected in the presumptive area whether face is located in image, when except presumptive area
When, but when detecting that face is not located in presumptive area, i.e. control rotating drive mechanism drives mobile phone, is prompted by issuing
So that face returns in presumptive area.Recognition of face is the common knowledge and conventional techniques of the communications field, such as artificial mind
Through network technique, support vector machines method, PCA identification, Elastic Matching method, the eigenfaces based on KL transformation, it is based on integral image
Characteristic method etc., the present embodiment not -- repeat.
As shown in Fig. 2, in one embodiment, to identity card direct picture and identity card verso images carry out capable positioning,
Binaryzation, noise remove, slant correction, printed page analysis, Character segmentation, the effective text information for obtaining single identity card are specific
Step includes:
Step S201 carries out coarse positioning to effective information according to position of effective text information in identity card;
Due to text information position effective in identity card be it is fixed, can be according to effective text information in identity card
Position substantially positions effective information, i.e. coarse positioning, if than the wide and Gao Douwei 0.9 of whole picture ID Card Image, origin
In the upper left corner, then it is the upper left corner that identity card number, which is normally at (0.38,0.83), wide by 0.48, in high 0.145 rectangle, is obtained
Effective text information of identity card.
Step S202, according to the average gray of the be expert at pixel in boundary in effective text information row it is smaller than background this
One characteristic carries out precise positioning to the text information of coarse positioning, generates the picture element matrix of pending filtering processing, picture element matrix is
Precise positioning region, the formula of use are as follows: the point by gray value in image less than or equal to lower boundary LT is labeled as foreground point, gray scale
Point of the value more than or equal to coboundary HT is labeled as background dot, and wherein LT=T*r, HT=255- (255-T) * r, T are slicing operation institute
In the maximum gradation value of level, r is empirical value, r=0.6, to prevent from will be present the background trade of different at precise positioning
Boundary similarly obtains coboundary, the left margin, right margin in precise positioning region;
The pixel in each individual character image-region is handled respectively, extracts useful information, is selected according to branch's feature of pixel
Seed origin is selected, the region growing algorithm based on pixel distribution characteristics is used from seed origin, gradually to neighborhood pixels
Point advances and reads, until having handled all pixels.Region growing algorithm based on pixel distribution characteristics traverses pixel
Point obtains character structure information, identifies and determines point, there is the relatively black or relatively white point of a part in image very
It is easy to be considered as prospect either background dot, this partial dot, which is referred to as, determines point, needs first to determine point in initial phase
It is identified, calculates time-consuming to reduce.It is assumed that T is maximum gray scale corresponding to level where main stratum level i.e. slicing operation
Value, r is empirical value, and r=0. 6 enables lower boundary LT=T*r, HT=255- (255-T) * r, then point of the gray value less than or equal to LT is
Relatively black point is labeled as foreground point, and point of the gray value more than or equal to coboundary HT is relatively white point, is labeled as background
Point similarly obtains the top in precise positioning region to prevent from will be present the background trade of different at the boundary of precise positioning
Boundary, left margin, right margin.
Step S203 carries out gaussian filtering, institute to precise positioning region using 3 pixels × 3 pixels gaussian filtering template
Stating gaussian filtering is the weighted average of pixel in the neighborhood that is determined with template with each of template scan image pixel
Gray value goes the value of alternate template central pixel point, weakens interference and the removal noise of background information;
For some isolated strokes or black region still having, average stroke width is calculated first, if these are lonely
The area of vertical stroke or black region is less than square of average stroke width, then it is assumed that it is noise, if it is less than twice
Average stroke width square, and be all larger than from their central pixel point to the length on eight directions to boundaries average
The width of stroke, then it is assumed that it is also noise, by noise removal, therefore using 3 pixels × 3 pixels gaussian filtering template to essence
Quasi- localization region carries out gaussian filtering, weakens interference and the removal noise of background information, gaussian filtering be exactly to entire image into
The average weighted process of row, the value of each pixel are all weighted by other pixel values in itself and neighborhood average
After obtain.The concrete operations of gaussian filtering are with an each of template (or convolution, mask) scan image pixel, use
The weighted average gray value of pixel goes the value of alternate template central pixel point in the neighborhood that template determines.
Step S204 carries out binaryzation to precise positioning region using dynamic threshold, obtains the two-value in precise positioning region
Image, and individual character segmentation is carried out to the bianry image in precise positioning region, obtain single effective text information.
The dynamic binarization threshold for obtaining image slices vegetarian refreshments is used to carry out binaryzation to the gray scale picture after smoothing processing
Processing, further denoising improves later period matched accuracy.
As shown in figure 3, in one embodiment, providing a kind of identification authentication system based on recognition of face, the device
Include:
Face's acquiring unit obtains face image for obtaining the image of client camera acquisition in real time from described image;
Identity information acquiring unit is right for extracting ID card information, capture identity card direct picture and identity card verso images
Identity card direct picture and identity card verso images carry out capable positioning, binaryzation, noise remove, slant correction, printed page analysis, word
Symbol segmentation, obtains effective text information of single identity card;
Identity information sorts out unit, for effective text information of the identity card to be pressed name, address, nationality, identification card number
Sorted out, exports the ID card information of classification;
Unit is verified in comparison, is carried out networking comparison for the ID card information to the face image and the classification and is verified, institute
Networking comparison is stated to verify to connect citizen identity information check system to the ID card information of the face image and the classification
It is verified, judges its consistency;When the ID card information by the classification carries out online checking, user information exists;And
When the face image is consistent with the identity card facial image that online checking returns, ID card information is true;Otherwise, identity card is believed
Breath is false;
As a result output unit, for obtaining comparison verification result and exporting.
In one embodiment, face's acquiring unit is also used to face's acquiring unit and is also used to collected
Face posture angle, illumination, blocks influence factor progress screenshot environment pre-detection, and issues and prompt so that user cooperates.
In one embodiment, face's acquiring unit is also used to the output regulation button by the client, connects
The first instruction input is received to adjust presumptive area, the presumptive area is adjusted according to first instruction and detects the face and scheme
Position of the image position in described image passes through sending when other than the presumptive area that the face image is located in described image
Prompt is so that the face returns in presumptive area.
In one embodiment it is proposed that a kind of computer equipment, including memory and processor, deposited in the memory
Computer-readable instruction is contained, when the computer-readable instruction is executed by the processor, so that the processor executes institute
The step in the above-mentioned identity identifying method based on recognition of face is realized when stating readable instruction.
In one embodiment it is proposed that a kind of storage medium for being stored with computer-readable instruction, the computer can
When reading instruction is executed by one or more processors, so that one or more processors execute the above-mentioned identity based on recognition of face
Step in authentication method.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
Some exemplary embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but
It cannot be construed as a limitation to the scope of the present invention.It should be pointed out that for the ordinary skill people of this field
For member, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to of the invention
Protection scope.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of identity identifying method based on recognition of face, which is characterized in that the described method includes:
The image for obtaining the acquisition of client camera in real time, obtains face image from described image;
ID card information is extracted, identity card direct picture and identity card verso images are captured, to identity card direct picture and identity
Card verso images carry out capable positioning, binaryzation, noise remove, slant correction, printed page analysis, Character segmentation, obtain single body
Effective text information of part card;
Effective text information of the identity card is sorted out by name, address, nationality, identification card number, exports the body of classification
Part card information;
It carries out networking comparison to the ID card information of the face image and the classification to verify, the networking comparison is verified to connect
It connects citizen identity information check system to verify the ID card information of the face image and the classification, judges that it is consistent
Property;When the ID card information by the classification carries out online checking, user information exists;And the face image and networking core
Look into return identity card facial image it is consistent when, ID card information is true;Otherwise, ID card information is false;
Comparison is obtained to verify result and export.
2. the method according to claim 1, wherein it is described it is real-time obtain client camera acquisition image it
Before further include:
To in acquired image, face posture angle, illumination, blocks influence factor progress screenshot environment pre-detection, and issues
It prompts so that user cooperates.
3. the method according to claim 1, wherein it is described it is real-time obtain client camera acquisition image it
Before further include:
By the output regulation button of the client, the first instruction input is received to adjust presumptive area, according to described first
Instruction adjusts the presumptive area.
4. the method according to claim 1, wherein it is described it is real-time obtain client camera acquisition image,
After obtaining face image in described image further include:
The position that the face image is located in described image is detected, when the face image is located at the fate in described image
When other than domain, by issuing prompt so that the face image returns in presumptive area.
5. according to the method described in claim 4, it is characterized in that, described to identity card direct picture and identity card verso images
Capable positioning, binaryzation, noise remove, slant correction, printed page analysis, Character segmentation are carried out, the effective of single identity card is obtained
Text information includes:
Coarse positioning is carried out to effective information according to position of effective text information in identity card;
According to the average gray of the be expert at pixel in boundary in effective text information row this characteristic smaller than background, to thick fixed
The text information of position carries out precise positioning, generates the picture element matrix of pending filtering processing, and the picture element matrix is precise positioning
Region, the formula of use are as follows: by gray value in image less than or equal to lower boundary LT point be labeled as foreground point, gray value be greater than etc.
It is labeled as background dot in the point of coboundary HT, wherein LT=T*r, HT=255- (255-T) * r, T are level where slicing operation
Maximum gradation value, r are empirical values, r=0.6, to prevent from will be present the background trade of different at the boundary of precise positioning, together
Reason obtains coboundary, the left margin, right margin in precise positioning region;
Gaussian filtering is carried out to the precise positioning region using 3 pixels × 3 pixels gaussian filtering template, weakens background information
Interference and removal noise, the gaussian filtering be with each of template scan image pixel, with template determination
The weighted average gray value of pixel goes the value of alternate template central pixel point in neighborhood;
Binaryzation is carried out to precise positioning region using dynamic threshold, obtains the bianry image in precise positioning region, and to accurate
The bianry image of localization region carries out individual character segmentation, obtains single effective text information.
6. a kind of identification authentication system based on recognition of face, which is characterized in that the face identification device includes:
Face's acquiring unit obtains face image for obtaining the image of client camera acquisition in real time from described image;
Identity information acquiring unit is right for extracting ID card information, capture identity card direct picture and identity card verso images
Identity card direct picture and identity card verso images carry out capable positioning, binaryzation, noise remove, slant correction, printed page analysis, word
Symbol segmentation, obtains effective text information of single identity card;
Identity information sorts out unit, for effective text information of the identity card to be pressed name, address, nationality, identification card number
Sorted out, exports the ID card information of classification;
Unit is verified in comparison, is carried out networking comparison for the ID card information to the face image and the classification and is verified, institute
Networking comparison is stated to verify to connect citizen identity information check system to the ID card information of the face image and the classification
It is verified, judges its consistency;When the ID card information by the classification carries out online checking, user information exists;And
When the face image is consistent with the identity card facial image that online checking returns, ID card information is true;Otherwise, identity card is believed
Breath is false;
As a result output unit, for obtaining comparison verification result and exporting.
7. device according to claim 6, which is characterized in that face's acquiring unit is also used to face collected
Posture angle, illumination, blocks influence factor progress screenshot environment pre-detection, and issues and prompt so that user cooperates.
8. device according to claim 6, which is characterized in that face's acquiring unit is also used to through the client
Output regulation button, receive the first instruction input to adjust presumptive area, the fate adjusted according to first instruction
Domain and the detection face image are located at the position in described image, when the face image is located at the fate in described image
When other than domain, by issuing prompt so that the face returns in presumptive area.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor is executed as described in any one of claims 1 to 5
The step of method.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors are executed such as the step of any one of claims 1 to 5 the method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810131476.7A CN109410026A (en) | 2018-02-09 | 2018-02-09 | Identity identifying method, device, equipment and storage medium based on recognition of face |
PCT/CN2018/105173 WO2019153739A1 (en) | 2018-02-09 | 2018-09-12 | Identity authentication method, device, and apparatus based on face recognition, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810131476.7A CN109410026A (en) | 2018-02-09 | 2018-02-09 | Identity identifying method, device, equipment and storage medium based on recognition of face |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109410026A true CN109410026A (en) | 2019-03-01 |
Family
ID=65463950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810131476.7A Pending CN109410026A (en) | 2018-02-09 | 2018-02-09 | Identity identifying method, device, equipment and storage medium based on recognition of face |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109410026A (en) |
WO (1) | WO2019153739A1 (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110443184A (en) * | 2019-07-31 | 2019-11-12 | 上海海事大学 | ID card information extracting method, device and computer storage medium |
CN110533568A (en) * | 2019-10-09 | 2019-12-03 | 重庆特斯联智慧科技股份有限公司 | A kind of public security method of servicing and its system based on dual-identity authentication |
CN110889326A (en) * | 2019-10-16 | 2020-03-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Human body detection-based queue-jumping behavior monitoring and warning system, method, device and storage medium |
CN111405365A (en) * | 2020-03-12 | 2020-07-10 | 北京文香信息技术有限公司 | Identity authentication method, device, system and storage medium |
CN111553312A (en) * | 2020-05-13 | 2020-08-18 | 中国银行股份有限公司 | Business handling method and device |
CN111626274A (en) * | 2020-07-30 | 2020-09-04 | 四川骏逸富顿科技有限公司 | Social security card identification method and identification system thereof |
CN111783757A (en) * | 2020-06-01 | 2020-10-16 | 成都科大极智科技有限公司 | OCR technology-based identification card recognition method in complex scene |
CN111784498A (en) * | 2020-06-22 | 2020-10-16 | 北京海益同展信息科技有限公司 | Identity authentication method and device, electronic equipment and storage medium |
CN111915423A (en) * | 2020-07-18 | 2020-11-10 | 湖南三湘银行股份有限公司 | Bank on-line video recording system |
CN112906741A (en) * | 2019-05-21 | 2021-06-04 | 北京嘀嘀无限科技发展有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
CN113449673A (en) * | 2021-07-09 | 2021-09-28 | 中国银行股份有限公司 | Certificate identification and verification method and device |
CN113688362A (en) * | 2021-08-25 | 2021-11-23 | 中国工商银行股份有限公司 | Identity card information security processing method and device |
CN114005160A (en) * | 2021-10-28 | 2022-02-01 | 建湖县公安局 | Access control system and method based on identity two-dimensional code and artificial intelligence |
CN115471919A (en) * | 2022-09-19 | 2022-12-13 | 江苏至真健康科技有限公司 | Filing method and system based on portable mydriasis-free fundus camera |
CN116156426A (en) * | 2023-04-20 | 2023-05-23 | 环球数科集团有限公司 | Personnel organization management system applying LDSW technology |
CN116189181A (en) * | 2022-11-11 | 2023-05-30 | 杭州海量信息技术有限公司 | Image normalization method and system for identity card OCR |
CN116281070A (en) * | 2023-03-30 | 2023-06-23 | 山东大舜医药物流有限公司 | Medicine sorting system and method based on big data |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110969143A (en) * | 2019-12-19 | 2020-04-07 | 深圳壹账通智能科技有限公司 | Evidence obtaining method and system based on image recognition, computer equipment and storage medium |
CN111324878A (en) * | 2020-02-05 | 2020-06-23 | 重庆特斯联智慧科技股份有限公司 | Identity verification method and device based on face recognition, storage medium and terminal |
CN111291711A (en) * | 2020-02-25 | 2020-06-16 | 山东超越数控电子股份有限公司 | Python-based deep learning face recognition method, equipment and readable storage medium |
CN111461131B (en) * | 2020-04-16 | 2023-04-18 | 上海东普信息科技有限公司 | Identification method, device, equipment and storage medium for ID card number information |
CN111768346B (en) * | 2020-05-12 | 2023-09-01 | 北京奇艺世纪科技有限公司 | Correction method, device, equipment and storage medium for identity card back image |
CN111898601A (en) * | 2020-07-14 | 2020-11-06 | 浙江大华技术股份有限公司 | Identity card element extraction method and device |
CN111860314B (en) * | 2020-07-20 | 2024-05-17 | 浪潮云信息技术股份公司 | Electronic license verification method, device and system based on image recognition |
CN113129020A (en) * | 2021-05-18 | 2021-07-16 | 中国银行股份有限公司 | 5G message identity authentication system and method based on Internet of things |
CN113688815A (en) * | 2021-06-01 | 2021-11-23 | 无锡启凌科技有限公司 | Medicine packaging text computer recognition algorithm and device for complex illumination environment |
CN113449663B (en) * | 2021-07-06 | 2022-06-03 | 深圳中智明科智能科技有限公司 | Collaborative intelligent security method and device based on polymorphic fitting |
CN113793196A (en) * | 2021-08-31 | 2021-12-14 | 宁夏百川电力股份有限公司 | Electricity doctor sells electricity management system based on cloud calculates |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104680161A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Digit recognition method for identification cards |
CN106991421A (en) * | 2017-03-22 | 2017-07-28 | 湖南联信科技有限公司 | A kind of ID card information extraction system |
CN107145873A (en) * | 2017-05-12 | 2017-09-08 | 江苏鸿信***集成有限公司 | ID Card Image identification checking method and system based on recognition of face and OCR |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103218599A (en) * | 2013-03-26 | 2013-07-24 | 苏州福丰科技有限公司 | System and method for authenticating generation II identity card based on face recognition |
AU2017101064A4 (en) * | 2017-08-04 | 2017-08-31 | Id-Checkr Pty Ltd | A system and method of extracting data (ie. text and/or image) from an identity card via a user’s mobile (smart) phone (or computer or tablet) for automatic verification of that user’s digital identity online for an agent (or another user) (“id-checkr”). |
CN107609529A (en) * | 2017-09-22 | 2018-01-19 | 芜湖星途机器人科技有限公司 | Robot face identification method |
-
2018
- 2018-02-09 CN CN201810131476.7A patent/CN109410026A/en active Pending
- 2018-09-12 WO PCT/CN2018/105173 patent/WO2019153739A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104680161A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Digit recognition method for identification cards |
CN106991421A (en) * | 2017-03-22 | 2017-07-28 | 湖南联信科技有限公司 | A kind of ID card information extraction system |
CN107145873A (en) * | 2017-05-12 | 2017-09-08 | 江苏鸿信***集成有限公司 | ID Card Image identification checking method and system based on recognition of face and OCR |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112906741A (en) * | 2019-05-21 | 2021-06-04 | 北京嘀嘀无限科技发展有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
CN110443184B (en) * | 2019-07-31 | 2022-09-30 | 上海海事大学 | Identity card information extraction method and device and computer storage medium |
CN110443184A (en) * | 2019-07-31 | 2019-11-12 | 上海海事大学 | ID card information extracting method, device and computer storage medium |
CN110533568A (en) * | 2019-10-09 | 2019-12-03 | 重庆特斯联智慧科技股份有限公司 | A kind of public security method of servicing and its system based on dual-identity authentication |
CN110889326A (en) * | 2019-10-16 | 2020-03-17 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Human body detection-based queue-jumping behavior monitoring and warning system, method, device and storage medium |
CN110889326B (en) * | 2019-10-16 | 2022-07-01 | 中科南京人工智能创新研究院 | Human body detection-based queue-jumping behavior monitoring and warning system, method, device and storage medium |
CN111405365A (en) * | 2020-03-12 | 2020-07-10 | 北京文香信息技术有限公司 | Identity authentication method, device, system and storage medium |
CN111553312A (en) * | 2020-05-13 | 2020-08-18 | 中国银行股份有限公司 | Business handling method and device |
CN111783757A (en) * | 2020-06-01 | 2020-10-16 | 成都科大极智科技有限公司 | OCR technology-based identification card recognition method in complex scene |
CN111784498A (en) * | 2020-06-22 | 2020-10-16 | 北京海益同展信息科技有限公司 | Identity authentication method and device, electronic equipment and storage medium |
CN111915423A (en) * | 2020-07-18 | 2020-11-10 | 湖南三湘银行股份有限公司 | Bank on-line video recording system |
CN111626274B (en) * | 2020-07-30 | 2020-10-27 | 四川骏逸富顿科技有限公司 | Social security card identification method |
CN111626274A (en) * | 2020-07-30 | 2020-09-04 | 四川骏逸富顿科技有限公司 | Social security card identification method and identification system thereof |
CN113449673A (en) * | 2021-07-09 | 2021-09-28 | 中国银行股份有限公司 | Certificate identification and verification method and device |
CN113688362A (en) * | 2021-08-25 | 2021-11-23 | 中国工商银行股份有限公司 | Identity card information security processing method and device |
CN114005160B (en) * | 2021-10-28 | 2022-05-17 | 建湖县公安局 | Access control system and method based on identity two-dimensional code and artificial intelligence |
CN114005160A (en) * | 2021-10-28 | 2022-02-01 | 建湖县公安局 | Access control system and method based on identity two-dimensional code and artificial intelligence |
CN115471919A (en) * | 2022-09-19 | 2022-12-13 | 江苏至真健康科技有限公司 | Filing method and system based on portable mydriasis-free fundus camera |
CN115471919B (en) * | 2022-09-19 | 2023-09-12 | 江苏至真健康科技有限公司 | Filing method and system based on portable mydriasis-free fundus camera |
CN116189181A (en) * | 2022-11-11 | 2023-05-30 | 杭州海量信息技术有限公司 | Image normalization method and system for identity card OCR |
CN116189181B (en) * | 2022-11-11 | 2024-01-23 | 杭州海量信息技术有限公司 | Image normalization method and system for identity card OCR |
CN116281070A (en) * | 2023-03-30 | 2023-06-23 | 山东大舜医药物流有限公司 | Medicine sorting system and method based on big data |
CN116156426A (en) * | 2023-04-20 | 2023-05-23 | 环球数科集团有限公司 | Personnel organization management system applying LDSW technology |
CN116156426B (en) * | 2023-04-20 | 2023-06-30 | 环球数科集团有限公司 | Personnel organization management system applying LDSW technology |
Also Published As
Publication number | Publication date |
---|---|
WO2019153739A1 (en) | 2019-08-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109410026A (en) | Identity identifying method, device, equipment and storage medium based on recognition of face | |
US10755084B2 (en) | Face authentication to mitigate spoofing | |
RU2711050C2 (en) | Image and attribute quality, image enhancement and identification of features for identification by vessels and faces and combining information on eye vessels with information on faces and / or parts of faces for biometric systems | |
WO2018086543A1 (en) | Living body identification method, identity authentication method, terminal, server and storage medium | |
CN105450411B (en) | The method, apparatus and system of authentication are carried out using card feature | |
US6661907B2 (en) | Face detection in digital images | |
US20030021448A1 (en) | Method for detecting eye and mouth positions in a digital image | |
WO2019061658A1 (en) | Method and device for positioning eyeglass, and storage medium | |
US20130202159A1 (en) | Apparatus for real-time face recognition | |
US11670069B2 (en) | System and method for face spoofing attack detection | |
CN108154132A (en) | A kind of identity card text extraction method, system and equipment and storage medium | |
CN108830175A (en) | Iris image local enhancement methods, device, equipment and storage medium | |
CN108446642A (en) | A kind of Distributive System of Face Recognition | |
CN108334870A (en) | The remote monitoring system of AR device data server states | |
CN108921006B (en) | Method for establishing handwritten signature image authenticity identification model and authenticity identification method | |
CN108446639A (en) | Low-power consumption augmented reality equipment | |
CN108520208A (en) | Localize face recognition method | |
Szczepański et al. | Pupil and iris detection algorithm for near-infrared capture devices | |
CN107657201A (en) | NEXT series of products characteristics of image identifying systems and its recognition methods | |
CN112800941B (en) | Face anti-fraud method and system based on asymmetric auxiliary information embedded network | |
Mr et al. | Developing a novel technique to match composite sketches with images captured by unmanned aerial vehicle | |
Mr et al. | Developing a novel technique for face liveness detection | |
US20220058409A1 (en) | Methods and systems for authenticating a user | |
Campadelli et al. | A color based method for face detection | |
CN111723612A (en) | Face recognition and face recognition network training method and device, 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 | ||
REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1262911 Country of ref document: HK |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |