CN109409060A - Auth method, system and computer readable storage medium - Google Patents
Auth method, system and computer readable storage medium Download PDFInfo
- Publication number
- CN109409060A CN109409060A CN201811123931.5A CN201811123931A CN109409060A CN 109409060 A CN109409060 A CN 109409060A CN 201811123931 A CN201811123931 A CN 201811123931A CN 109409060 A CN109409060 A CN 109409060A
- Authority
- CN
- China
- Prior art keywords
- picture
- face
- certificate
- fusion
- human face
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000004927 fusion Effects 0.000 claims abstract description 201
- 238000004590 computer program Methods 0.000 claims description 19
- 239000000284 extract Substances 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 210000003128 head Anatomy 0.000 description 14
- 238000010586 diagram Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/04—Scanning arrangements, i.e. arrangements for the displacement of active reading or reproducing elements relative to the original or reproducing medium, or vice versa
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Credit Cards Or The Like (AREA)
- Collating Specific Patterns (AREA)
- Processing Or Creating Images (AREA)
Abstract
This application involves a kind of auth method, system and computer readable storage mediums.The auth method is based on recognition of face, this method comprises: multiple face pictures of acquisition active user;Obtain the certificate picture of certificate corresponding with active user;Wherein, certificate picture includes certificate, and certificate includes user's head portrait;Multiple face pictures and certificate picture are sent to verifying equipment;Fusion treatment is carried out to multiple face pictures by verifying equipment, obtains face fusion picture;Face comparison is carried out according to face fusion picture and certificate picture, obtains the similarity between face fusion picture and certificate picture;It is verified based on identity of the similarity to active user.Directly the identity of user can be verified using configuration lower high photographing instrument using this method.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of auth method, system and computer-readable
Storage medium.
Background technique
High photographing instrument is a kind of scanning device, is usually used in the scanning to papery document or file, and the electronics shelves scanned can
It convenient for preservation, or can show so that staff carries out next step audit, facilitate the routine office work of people.
Currently, proposing the demand for carrying out active user using high photographing instrument authentication, need to acquire based on high photographing instrument
Active user facial image carry out authentication, however, built in traditional high photographing instrument camera configuration it is lower, take
Picture quality it is poor, can not be identified at all based on identity of the collected picture to user, existing method just can only
Replacement configures higher high photographing instrument, this needs to expend a large amount of cost.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, the lower high photographing instrument pair of configuration can directly be utilized by providing one kind
Auth method, system and the computer readable storage medium that the identity of user is verified.
A kind of auth method, which comprises
Acquire multiple face pictures of active user;
Obtain the certificate picture corresponding with the active user of acquisition;Wherein, the certificate picture includes certificate, described
Certificate includes user's head portrait;
Multiple face pictures and the certificate picture are sent to verifying equipment;
Fusion treatment is carried out to multiple face pictures by the verifying equipment, obtains face fusion picture;
Carry out face comparison according to the face fusion picture and the certificate picture, obtain the face fusion picture and
Similarity between the certificate picture;
It is verified based on identity of the similarity to the active user.
In one of the embodiments, further include:
The certificate information of certificate is read by card reader;
It is described by multiple face pictures and the certificate picture be sent to verifying equipment include:
The certificate information, the multiple face picture and the certificate picture are sent to verifying equipment;
It is described to include: to the face fusion picture and certificate picture progress face comparison respectively
Corresponding portrait picture is obtained according to the certificate information;
Face comparison is carried out according to the portrait picture, the face fusion picture and the certificate picture.
Multiple face pictures include at least the first picture and second picture in one of the embodiments,;It is described logical
It crosses the verifying equipment and fusion treatment is carried out to multiple face pictures, obtaining face fusion picture includes:
First picture and the second picture are divided into human face region and background area;
Adjust the exposure of the human face region of first picture;
Adjust the exposure of the background area of the second picture;
The background area of the human face region of first picture adjusted and the second picture adjusted is merged
Processing, obtains face fusion picture.
It is described in one of the embodiments, that face pair is carried out according to the face fusion picture and the certificate picture
Than the similarity obtained between the face fusion picture and the certificate picture includes:
Human face region is partitioned into from the face fusion picture and the certificate picture respectively;
The position of human face characteristic point is determined in the human face region;
Extract the corresponding face characteristic value in each position;
It is corresponding to the certificate picture according to the corresponding face characteristic value in the position each in the face fusion picture
Difference between the corresponding face characteristic value in position obtains similar between the face fusion picture and the certificate picture
Degree.
In one of the embodiments, the step of position that human face characteristic point is determined in the human face region it
Afterwards, the method also includes:
Obtain the positional relationship between preset human face characteristic point;
According to the position of the positional relationship and each human face characteristic point, coordinate registration process is carried out to human face region,
Human face region after being aligned;
The corresponding face characteristic value in each position of extracting includes:
Corresponding face characteristic value is extracted based on each human face characteristic point in the human face region after alignment.
It is described in one of the embodiments, to be partitioned into people from the face fusion picture and the certificate picture respectively
Face region includes:
Characteristic pattern is extracted to the face fusion picture and the certificate picture respectively according to different images attribute;
Each characteristic pattern is subjected to Fusion Features, respectively obtains the figure of the face fusion picture and the certificate picture
As feature;
By human face region detection model, the face fusion picture and the certificate figure are determined according to described image feature
Encirclement coordinate in piece;
Coordinate is surrounded according to corresponding, is partitioned into face area from the face fusion picture and the certificate picture respectively
Domain.
It is described in one of the embodiments, to be partitioned into people from the face fusion picture and the certificate picture respectively
Face region includes:
Characteristic pattern is extracted to the face fusion picture and the certificate picture respectively according to different images attribute;
Each characteristic pattern is subjected to Fusion Features, respectively obtains the figure of the face fusion picture and the certificate picture
As feature;
By human face region detection model, the face fusion picture and the certificate figure are determined according to described image feature
Encirclement coordinate in piece;
Coordinate is surrounded according to corresponding, is partitioned into face area from the face fusion picture and the certificate picture respectively
Domain.
In one of the embodiments, further include:
Character recognition is carried out to the certificate picture, obtains the corresponding passport NO. of the certificate;
It will be in document corresponding to passport NO. importing and the active user.
In one of the embodiments, further include:
Obtain the corresponding instrument parameter of the high photographing instrument;
When the instrument parameter is matched with the default instrument parameter being locally stored, it is described by the verifying equipment to more
A face picture carries out fusion treatment, and obtaining face fusion picture includes:
Selection carries out merging place with the default matched image procossing control of instrument parameter to multiple face pictures
Reason, obtains face fusion picture.
A kind of authentication system, including high photographing instrument and verifying equipment, in which:
The high photographing instrument is used to acquire multiple face pictures of active user;Obtain the corresponding with the active user of acquisition
Certificate picture;Wherein, the certificate picture includes certificate, and the certificate includes user's head portrait;By multiple face figures
Piece and the certificate picture are sent to verifying equipment;
The verifying equipment is used to receive the multiple face pictures and the certificate picture that the high photographing instrument is sent;Also
For carrying out fusion treatment to multiple face pictures, face fusion picture is obtained;
The verifying equipment is also used to carry out face comparison according to the face fusion picture and the certificate picture, obtains
Similarity between the face fusion picture and the certificate picture;Based on the similarity to the identity of the active user
It is verified.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Acquire multiple face pictures of active user;
Obtain the certificate picture corresponding with the active user of acquisition;Wherein, the certificate picture includes certificate, described
Certificate includes user's head portrait;
Multiple face pictures and the certificate picture are sent to verifying equipment;
Fusion treatment is carried out to multiple face pictures by the verifying equipment, obtains face fusion picture;
Carry out face comparison according to the face fusion picture and the certificate picture, obtain the face fusion picture and
Similarity between the certificate picture;
It is verified based on identity of the similarity to the active user.
Above-mentioned auth method, system and computer readable storage medium, high photographing instrument by lower configuration with have
The verifying equipment of picture processing capacity combines the authentication, it can be achieved that active user.Wherein, high photographing instrument can acquire multiple
The face picture of face including active user, and the certificate picture for the provided certificate of active user for obtaining acquisition, and will obtain
The multiple face pictures and certificate picture obtained are sent to the verifying equipment with high photographing instrument network connection, and verifying equipment can be to multiple people
Face picture carries out fusion treatment, obtains the face fusion picture of better quality, in this way, verifying equipment can be based on face fusion
Picture and certificate picture including user's head portrait carry out face comparison, obtain face in face fusion picture and certificate picture
Similarity is verified based on identity of the obtained similarity to active user.
Detailed description of the invention
Fig. 1 is the application scenario diagram of auth method in one embodiment;
Fig. 2 is the flow diagram of auth method in one embodiment;
Fig. 3 is to carry out fusion treatment to multiple face pictures by verifying equipment in one embodiment, obtains face fusion
The flow diagram of picture;
Fig. 4 is to carry out face comparison according to face fusion picture and certificate picture in one embodiment, obtains face fusion
The flow diagram of similarity between picture and certificate picture;
Fig. 5 is the flow diagram of auth method in a specific embodiment;
Fig. 6 is the configuration diagram of authentication system in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Auth method provided by the present application can be applied in application environment as shown in Figure 1.Wherein, high photographing instrument
102 are communicated with verifying equipment 104 by network by network.High photographing instrument 102 acquires multiple face pictures of active user,
And obtain the certificate picture corresponding with active user of acquisition;Multiple face pictures and certificate picture are sent to verifying equipment
104;Fusion treatment is carried out to multiple face pictures by verifying equipment 104, obtains face fusion picture;Verifying equipment 104
Face comparison is carried out according to face fusion picture and certificate picture, obtains the similarity between face fusion picture and certificate picture;
Verifying equipment 104 is verified based on identity of the similarity to active user.Verifying equipment 104 can be, but not limited to be various meters
Calculate machine equipment, including computer or server etc..
In one embodiment, as shown in Fig. 2, providing a kind of auth method, it is applied to shown in Fig. 1 in this way
Application environment in high photographing instrument 102 and verifying equipment 104 for be illustrated, comprising the following steps:
S202 acquires multiple face pictures of active user.
Wherein, active user refers to the user of authentication to be carried out, and is needing to acquire user's for user's transacting business
When identity information, the identity of active user need to just be verified, to guarantee the accuracy and safety of data.Specifically, high
Face picture can be acquired to active user by clapping instrument, and at least two face pictures of acquisition are sent to verifying equipment.High photographing instrument
The face picture of acquisition can be to be continuously shot at set time intervals, is also possible to carry out in prompt active user
Shooting obtains after facial orientation adjustment.For example, high photographing instrument can be arranged to burst mode, high photographing instrument can continuous acquisition to more
A face picture.
In one embodiment, the camera of high photographing instrument can be opened by verifying equipment triggering, further, high photographing instrument can
Can also it lead to including multiple cameras for example, high photographing instrument can acquire the face picture of active user by the first camera of unlatching
The certificate picture for second camera acquisition the provided certificate of active user opened is provided.
In one embodiment, when acquiring face picture, the camera of high photographing instrument can be configured, so that collecting
Face picture have different picture characteristics.For example, high photographing instrument when face picture is opened in acquisition first, can make camera to adopting
The middle position of the face picture of collection is focused to be shot again, since face appears in the middle position of picture, then acquiring
Face picture in face with regard to relatively sharp.
S204 obtains the certificate picture corresponding with active user of acquisition;Wherein, certificate picture includes certificate, certificate packet
Include user's head portrait.
Wherein, certificate is the electronic card for having recorded user's identity information, certificate can be resident identification card, social security card,
Common reserve fund card or E-Passport etc..Specifically, high photographing instrument can acquire corresponding certificate picture to the certificate that active user provides,
It just include user's head portrait in collected certificate picture since certificate includes user's head portrait.
For example, user resident identification card can be placed in high photographing instrument specify position on, high photographing instrument can by with
The corresponding camera in the position acquires the picture for the identity card that user provides, and includes on identity card in obtained identity card picture
User's head portrait of stamp.It is appreciated that the face picture of high photographing instrument acquisition can be used for obtaining the face information of user, acquisition
Certificate picture can be used for obtaining user's information of certificate, when the difference between the two information meets the condition of being verified
When, then determine that the authentication of active user passes through.
Multiple face pictures and certificate picture are sent to verifying equipment by S206.
Specifically, the lower feelings of quality of the lower face picture for causing to collect and certificate picture are configured in high photographing instrument
Under condition, the certificate picture of multiple face pictures of acquisition and acquisition can be sent to verifying equipment by high photographing instrument, by verifying equipment pair
After the picture of acquisition is handled, picture is obtained based on processing and carries out recognition of face.
Verifying equipment can be the equipment being connected to the network with high photographing instrument, and verifying equipment can be used for obtaining the current of typing
The identity information of user and the information for handling related service, and corresponding document is generated after the completion of manual or automatic appraise and decide, than
Such as insurance business document or charter business document.Collected face picture can be passed through wired or wireless side by high photographing instrument
Formula is transmitted to verifying equipment.
S208 carries out fusion treatment to multiple face pictures by verifying equipment, obtains face fusion picture.
Wherein, face fusion picture is compared to the higher picture of clarity of the face picture of high photographing instrument acquisition.Specifically
Ground, verifying equipment can carry out fusion treatment to multiple face pictures, obtain after the multiple face pictures for receiving high photographing instrument transmission
To face fusion picture.In one embodiment, verifying equipment can will carry out body according to the face picture and certificate image that obtain
The implementation of part verifying is packaged into the form of control, so that it may using corresponding control to the face picture of acquisition at
Reason, is verified based on identity of the picture obtained after processing to active user.
In one embodiment, multiple face pictures include at least the first picture and second picture;As shown in figure 3, step
S208 carries out fusion treatment to multiple face pictures by verifying equipment, and obtaining face fusion picture includes:
First picture and second picture are divided into human face region and background area by S302.
S304 adjusts the exposure of the human face region of the first picture.
S306 adjusts the exposure of the background area of second picture.
S308, at the background area fusion of the human face region of the first picture adjusted and second picture adjusted
Reason, obtains face fusion picture.
For multiple face pictures of high photographing instrument acquisition since depth of exposure is different, clarity is poor, therefore can be based on multiple people
Face picture adjusts corresponding exposure, and the picture of different exposures adjusted is fused together, to reinforce human face region, is cut
Weak background area forms the comparison between human face region and background area, the clarity of human face region not only can be improved, may be used also
To improve the accuracy for carrying out human face region detection based on the face fusion picture obtained after adjustment.
Specifically, verifying equipment can filter out the first picture and second picture from received multiple face pictures, and first
Picture and second picture can be two difference between picture, that is, the content of picture that high photographing instrument is continuously shot not
Greatly, but exposure there are biggish differences.Verifying equipment can adjust the brightness of pixel included by human face region in the first picture
Value, for example can be preset first value, so that human face region tends to bright effect after the display;Similarly, equipment is verified
The brightness value of pixel included by background area in adjustable second picture, for example can be preset second value, so that back
Scene area tends to relatively clear effect after the display;Then verifying equipment can be by the human face region in the first picture adjusted
Fusion treatment is carried out with the background area in second picture, obtains face fusion picture.
In one embodiment, verifying equipment can also the pixel to the stitching portion of obtained face fusion picture carried out
Filter processing, so that the pixel transition of stitching portion is more smooth, further increases the clarity of face fusion picture.
S210 carries out face comparison according to face fusion picture and certificate picture, obtains face fusion picture and certificate figure
Similarity between piece.
Wherein, similarity is used to measure the similarities and differences between the picture of two progress face comparisons.Specifically, verifying equipment can
Corresponding picture feature is extracted to face fusion picture and certificate picture respectively, picture feature is indicated in vector form, phase
It can be indicated with the distance between feature vector of face fusion picture and certificate picture like degree.In one embodiment,
The similarity between the corresponding feature vector of two pictures can be indicated with Euclidean distance, for example, the feature vector of two n dimension
(x1,x2,...,xn)、(y1,y2,...,yn) between similarity S (x, y) can be indicated by the following formula:
In one embodiment, as shown in figure 4, step S210, carries out face according to face fusion picture and certificate picture
Comparison, the similarity obtained between face fusion picture and certificate picture include:
S402 is partitioned into human face region from face fusion picture and certificate picture respectively.
Wherein, human face region is the rectangular area in face fusion picture where face.The rectangular area can be including
The region that the profile of face is constituted in face fusion picture, for example can be the minimum square for enclosing the profile of face in picture
Shape region.It is appreciated that compared to face fusion picture and certificate picture are directly carried out face comparison, from face fusion picture
Face comparison is carried out based on the human face region being separated out with being partitioned into after human face region in certificate picture, avoids human face region from accounting for whole
The ratio of a picture is smaller to be caused to compare the lower problem of accuracy, can be reduced background area in picture and be compared institute's band to face
The accuracy of face comparison can be improved in the interference come.
Step S402 in one of the embodiments, is partitioned into face from face fusion picture and certificate picture respectively
Region includes: to extract characteristic pattern to face fusion picture and certificate picture respectively according to different images attribute;By each characteristic pattern into
Row Fusion Features respectively obtain the characteristics of image of face fusion picture and certificate picture;By human face region detection model, according to
Characteristics of image determines the encirclement coordinate in face fusion picture and certificate picture;Coordinate is surrounded according to corresponding, respectively from face
Human face region is partitioned into fusion picture and certificate picture.
Wherein, image attributes includes the pixel value of each pixel, resolution ratio, color component value, tone, saturation in picture
Degree, brightness, color channel and level of image etc..Characteristic pattern is that each pixel has corresponded to a certain image attributes in picture
The probability matrix that characteristic value is constituted.The size of the resolution ratio of the characteristic pattern of different images attribute can be different.
Specifically, verifying equipment can pass through the convolution of the preparatory trained human face region detection model based on machine learning
Input layer carries out feature extraction to the picture of input, illustrates to divide from picture here by taking picture is face fusion picture as an example
Cut out the process of human face region.It is that difference is belonged to based on face fusion picture when carrying out feature extraction to face fusion picture
The feature of image attributes extracts, and obtains the characteristic pattern for belonging to different images attribute, can be right after obtaining corresponding characteristic pattern
Multiple characteristic patterns carry out Fusion Features, obtain the characteristics of image of face fusion picture.It is defeated for the characteristics of image obtained after fusion
Enter into the convolution input layer of the face region detection model, the model parameter of hidden layer based on this model, to characteristics of image
Operation is carried out, finally by the corresponding encirclement frame coordinate of output layer output face fusion picture, so that it may sit according to the encirclement frame
Mark is partitioned into human face region from face fusion picture.Similarly, the step of being partitioned into human face region from certificate picture with from
The step of being partitioned into human face region in face fusion picture is consistent, and details are not described herein.
S404 determines the position of human face characteristic point in human face region.
Wherein, human face characteristic point is key position in face, including eyes, nose, face mask, mouth, eyebrow, ear
Etc., the position of human face characteristic point is coordinate of the human face characteristic point in human face region.Specifically, people is being partitioned into from picture
Behind face region, the position of each human face characteristic point in human face region, that is, coordinate may further determine that.
In one embodiment, verifying equipment can be based on the human face characteristic point identification model of machine learning model, into one
It walks and feature is extracted to the human face region being partitioned into, the seat of each human face characteristic point in human face region is determined according to the feature of extraction
Mark, the position of each human face characteristic point in human face region is determined according to obtained coordinate.
S406 extracts the corresponding face characteristic value of each position.
Specifically, in human face region has been determined behind the corresponding position of each human face characteristic point, verifying equipment can obtain this
The corresponding characteristic value in position determined in human face region, this feature value can be what extraction in step s 404 obtained.
For example, corresponding eye feature value is extracted, for certificate for the eyes in human face region in face fusion picture
Eyes in picture in human face region extract corresponding eye feature value, similarly, for other human face characteristic points such as nose
Son, face mask, mouth etc. all extract corresponding characteristic value respectively.
S408, it is corresponding with corresponding position in certificate picture according to the corresponding face characteristic value of each position in face fusion picture
Face characteristic value between difference, obtain the similarity between face fusion picture and certificate picture.
Specifically, verifying equipment can be partitioned into human face region from face fusion picture and certificate picture, and determine people
The position of each human face characteristic point in face region extracts the corresponding characteristic value of each position, then compares identical face characteristic one by one
The corresponding characteristic value in point position, for example, will be in face fusion picture in the corresponding characteristic value of eyes and certificate picture
The corresponding characteristic value of eyes is compared, and obtains difference between the two, and is combined between every a pair of of human face characteristic point
Difference obtains the similarity between face fusion picture and certificate picture.It specifically can be according to preset weighting coefficient to every a pair
Difference between human face characteristic point is weighted summation, obtains final similarity.Can also some human face characteristic point it
Between difference be more than preset threshold when directly determine face comparison can not pass through, therefore, it is determined that authentication does not pass through.
In one embodiment, high photographing instrument can also read the certificate information of certificate by card reader;By multiple face figures
It includes: that certificate information, multiple face pictures and certificate picture are sent to verifying to set that piece and certificate picture, which are sent to verifying equipment,
It is standby;Carrying out face comparison according to face fusion picture and certificate picture includes: to obtain corresponding portrait picture according to certificate information;
Face comparison is carried out according to portrait picture, face fusion picture and certificate picture.
Wherein, for card reader for reading certificate information from certificate, certificate information includes name, gender, type of credential, card
At least one of piece number code, certificate validity period, certificate picture and portrait picture etc., card reader such as can be identity card and read
Read device etc..
Specifically, high photographing instrument can read the certificate of the provided certificate of active user by built-in or external card reader
The certificate picture of the certificate information of reading, collected multiple face pictures and acquisition is sent to verifying equipment, tested by information
Corresponding portrait picture can be obtained according to certificate information by demonstrate,proving equipment.When certificate information includes portrait picture, equipment is verified
Face comparison can be carried out to the portrait picture of acquisition, face fusion picture and certificate picture respectively, for example, these three figures can be based on
Piece is compared two-by-two, and when any group of picture comparison is obstructed out-of-date, then authentication does not pass through.When certificate information does not include portrait
When picture, verifying equipment can search from certificate database corresponding with the passport NO. according to the passport NO. in certificate information
The portrait picture found and face fusion picture and certificate picture are carried out face comparison by portrait picture.Certificate database can
To be the database of the either addressable external authoritative institution of local database.
In one embodiment, when verifying equipment determines that the certificate has failed according to the certificate validity period in certificate information
When, then it can directly assert that the authentication of active user does not pass through.
S212 is verified based on identity of the similarity to active user.
Specifically, verifying equipment is determining that human face region is wrapped based on relatively clear degree face fusion picture and certificate picture
After including the similarity between face, it can be verified based on identity of the similarity to active user, for example, when similarity is lower than
When 90%, it can determine whether that verifying does not pass through, and provide the unacceptable prompt of authentication.
In above-mentioned auth method, pass through the high photographing instrument of lower configuration and the verifying equipment phase that has picture processing capacity
In conjunction with, it can be achieved that authentication to active user.Wherein, high photographing instrument can acquire the face that multiple include the face of active user
Picture, and the certificate picture for the provided certificate of active user for obtaining acquisition, and by the multiple face pictures and certificate figure of acquisition
Piece is sent to the verifying equipment with high photographing instrument network connection, and verifying equipment can carry out fusion treatment to multiple face pictures, obtain
The face fusion picture of better quality, in this way, verifying equipment can be based on face fusion picture and including user's head portrait
Certificate picture carries out face comparison, obtains the similarity of face in face fusion picture and certificate picture, similar based on what is obtained
Degree verifies the identity of active user.
After the step of determining the position of human face characteristic point in human face region in one of the embodiments, method is also
It include: the positional relationship obtained between preset human face characteristic point;According to the position of positional relationship and each human face characteristic point, to people
Face region carries out coordinate registration process, the human face region after being aligned;Extracting the corresponding face characteristic value of each position includes: base
Each human face characteristic point in human face region after alignment extracts corresponding face characteristic value.
Due to the face picture of the collected active user of high photographing instrument be not necessarily it is proper, in human face region has been determined
It, can be special to each face according to the positional relationship between preset each human face characteristic point after the position of each human face characteristic point
The position of sign point is converted, specifically, can carry out coordinate alignment according to preset positional relationship to each human face characteristic point
Processing, so that obtaining includes more proper human face region.In this way, verifying equipment can be mentioned based on the human face region after alignment
It takes corresponding face characteristic value, then is carried out pair with the face characteristic value of each human face characteristic point in human face region in certificate picture
Than determining the similarity between face fusion picture and certificate picture.Positional relationship specifically can be under the coordinate system of setting,
Relative positional relationship between each human face characteristic point, for example, nose is in the middle position of picture, left eye and right eye are about nose
Position bilateral symmetry etc..
Auth method in one of the embodiments, further include: character recognition is carried out to certificate picture, obtains certificate
Corresponding passport NO.;It will be in document corresponding to passport NO. importing and active user.
Specifically, verifying equipment can also pass through character recognition algorithm pair after the certificate picture for getting high photographing instrument transmission
Certificate picture carries out character recognition, obtains the corresponding passport NO. of certificate, such as bank card number or resident identification card number,
And the passport NO. for obtaining identification imports in document corresponding to the user identifier with active user, to remove from manually
The process of typing passport NO. can be improved the efficiency of document processing.
Auth method in one of the embodiments, further include: obtain the corresponding instrument parameter of high photographing instrument;Work as instrument
When parameter is matched with the default instrument parameter being locally stored, fusion treatment is carried out to multiple face pictures by verifying equipment, is obtained
It include: to choose to merge multiple face pictures with the matched image procossing control of default instrument parameter to face fusion picture
Processing, obtains face fusion picture.
Wherein, instrument parameter includes aperture, field angle and focal length of the camera of high photographing instrument etc., and instrument parameter is different, is adopted
The quality of the face picture collected is also different.Different instrument parameter and corresponding image procossing control has been locally stored in verifying equipment
Corresponding relationship between part, after the instrument parameter being locally stored is sent to verifying equipment by high photographing instrument, verifying equipment can be
Local search whether there is and the matched image procossing control of the instrument parameter, selection and the matched image procossing of the instrument parameter
Control carries out fusion treatment to multiple face pictures, obtains face fusion picture.
As shown in figure 5, in a specific embodiment, auth method the following steps are included:
S502 acquires multiple face pictures of active user;
S504 obtains the certificate picture corresponding with active user of acquisition;Wherein, certificate picture includes certificate, certificate packet
Include user's head portrait;
S506 reads the certificate information of certificate by card reader;
Certificate information, multiple face pictures and certificate picture are sent to verifying equipment by S508;Multiple face pictures are at least
Including the first picture and second picture;
First picture and second picture are divided into human face region and background area by S510;
S512 adjusts the exposure of the human face region of the first picture;
S514 adjusts the exposure of the background area of second picture;
S516, at the background area fusion of the human face region of the first picture adjusted and second picture adjusted
Reason, obtains face fusion picture;
S518 obtains corresponding portrait picture according to certificate information;
S520 extracts characteristic pattern to face fusion picture and certificate picture respectively according to different images attribute;
Each characteristic pattern is carried out Fusion Features, respectively obtains the characteristics of image of face fusion picture and certificate picture by S522;
S524 is determined in face fusion picture and certificate picture by human face region detection model according to characteristics of image
Surround coordinate;
S526 surrounds coordinate according to corresponding, is partitioned into human face region from face fusion picture and certificate picture respectively.
S528 determines the position of human face characteristic point in human face region;
S530 obtains the positional relationship between preset human face characteristic point;
S532 carries out coordinate registration process to human face region, obtains according to the position of positional relationship and each human face characteristic point
Human face region after alignment;
S534 extracts corresponding face characteristic value based on each human face characteristic point in the human face region after alignment;
S536, it is corresponding with corresponding position in certificate picture according to the corresponding face characteristic value of each position in face fusion picture
Face characteristic value between difference, obtain the similarity between face fusion picture and certificate picture;
S538 is verified based on identity of the similarity to active user.
S540 carries out character recognition to certificate picture, obtains the corresponding passport NO. of certificate when authentication passes through;
S542, will be in document corresponding to passport NO. importing and active user.
It should be understood that although each step in the flow chart of Fig. 2 to Fig. 5 is successively shown according to the instruction of arrow,
But these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these
There is no stringent sequences to limit for the execution of step, these steps can execute in other order.Moreover, Fig. 2 is into Fig. 5
At least part step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
One moment executed completion, but can execute at different times, and the execution in these sub-steps or stage sequence is also not necessarily
Be successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or
Alternately execute.
In one embodiment, as shown in fig. 6, providing a kind of authentication system 600, comprising: high photographing instrument 602 and test
Demonstrate,prove equipment 604, in which:
High photographing instrument 602 is used to acquire multiple face pictures of active user;Obtain the card corresponding with active user of acquisition
Part picture;Wherein, certificate picture includes certificate, and certificate includes user's head portrait.
High photographing instrument 602 is also used to multiple face pictures and certificate picture being sent to verifying equipment.
Fusion treatment is carried out to multiple face pictures by verifying equipment 604, obtains face fusion picture.
Verifying equipment 604 is also used to carry out face comparison according to face fusion picture and certificate picture, obtains face fusion
Similarity between picture and certificate picture.
Verifying equipment 604 is also used to verify based on identity of the similarity to active user.
In one embodiment, high photographing instrument is also used to read the certificate information of certificate by card reader;By certificate information, more
A face picture and certificate picture are sent to verifying equipment;Verifying equipment is also used to obtain corresponding portrait figure according to certificate information
Piece;Face comparison is carried out according to portrait picture, face fusion picture and certificate picture.
In one embodiment, multiple face pictures include at least the first picture and second picture;Verifying equipment is also used to
First picture and second picture are divided into human face region and background area;Adjust the exposure of the human face region of the first picture;
Adjust the exposure of the background area of second picture;By the human face region and second picture adjusted of the first picture adjusted
Background area fusion treatment, obtain face fusion picture.
In one embodiment, verifying equipment is also used to be partitioned into face from face fusion picture and certificate picture respectively
Region;The position of human face characteristic point is determined in human face region;Extract the corresponding face characteristic value of each position;According to face fusion
Difference in picture between the corresponding face characteristic value of each position face characteristic value corresponding with corresponding position in certificate picture, obtains
Similarity between face fusion picture and certificate picture.
In one embodiment, verifying equipment is also used to obtain the positional relationship between preset human face characteristic point;According to
The position of positional relationship and each human face characteristic point carries out coordinate registration process to human face region, the human face region after being aligned;
Corresponding face characteristic value is extracted based on each human face characteristic point in the human face region after alignment.
In one embodiment, verifying equipment is also used to according to different images attribute respectively to face fusion picture and certificate
Picture extracts characteristic pattern;Each characteristic pattern is subjected to Fusion Features, the image for respectively obtaining face fusion picture and certificate picture is special
Sign;By human face region detection model, the encirclement coordinate in face fusion picture and certificate picture is determined according to characteristics of image;Root
Coordinate is surrounded according to corresponding, is partitioned into human face region from face fusion picture and certificate picture respectively.
In one embodiment, verifying equipment is also used to carry out character recognition to certificate picture, obtains the corresponding card of certificate
Piece number code;It will be in document corresponding to passport NO. importing and active user.Further, the document of generation, which can be reserved for, is verifying
In equipment corresponding document storing data library.
In one embodiment, verifying equipment is also used to obtain the corresponding instrument parameter of high photographing instrument;When instrument parameter and this
When the default instrument parameter matching of ground storage, choose with the matched image procossing control of default instrument parameter to multiple face pictures
Fusion treatment is carried out, face fusion picture is obtained.
Above-mentioned authentication system 600 passes through the high photographing instrument of lower configuration and the verifying equipment that has picture processing capacity
Combine the authentication, it can be achieved that active user.Wherein, high photographing instrument can acquire the people that multiple include the face of active user
Face picture, and the certificate picture for the provided certificate of active user for obtaining acquisition, and by the multiple face pictures and certificate of acquisition
Picture is sent to the verifying equipment with high photographing instrument network connection, and verifying equipment can carry out fusion treatment to multiple face pictures, obtain
To the face fusion picture of better quality, in this way, verifying equipment can be based on face fusion picture and including user's head portrait
Certificate picture carry out face comparison, the similarity of face in face fusion picture and certificate picture is obtained, based on obtained phase
The identity of active user is verified like degree.
Specific about authentication system limits the restriction that may refer to above for auth method, herein not
It repeats again.The step of high photographing instrument in above-mentioned authentication system or verifying equipment execute can be realized by way of module,
Modules can be realized fully or partially through software, hardware and combinations thereof.Modules can be embedded in the form of hardware or
Independently of in the processor in computer equipment, can also be stored in a software form in the memory in computer equipment, with
It is called convenient for processor and executes the corresponding operation of modules.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of multiple face pictures of acquisition active user when being executed by processor;Obtain acquisition with it is current
The corresponding certificate picture of user;Wherein, the certificate picture includes certificate, and certificate includes user's head portrait;By multiple face figures
Piece and certificate picture are sent to verifying equipment;Fusion treatment is carried out to multiple face pictures by verifying equipment, face is obtained and melts
Close picture;Face comparison is carried out according to face fusion picture and certificate picture, is obtained between face fusion picture and certificate picture
Similarity;It is verified based on identity of the similarity to active user.
In one embodiment, it also performs the steps of when computer program is executed by processor and is read by card reader
The certificate information of certificate;Computer program, which is executed by processor, is sent to verifying equipment for multiple face pictures and certificate picture
It is specifically executed when step and certificate information, multiple face pictures and certificate picture is sent to verifying equipment;Computer program is located
Reason device is executed specifically to execute when carrying out the step of face comparison according to face fusion picture and certificate picture and be obtained according to certificate information
Take corresponding portrait picture;Face comparison is carried out according to portrait picture, face fusion picture and certificate picture.
In one embodiment, multiple face pictures include at least the first picture and second picture;Computer program is located
It manages device to execute through verifying equipment to multiple face pictures progress fusion treatment, obtains also realizing when the step of face fusion picture
Following steps: the first picture and second picture are divided into human face region and background area;Adjust the human face region of the first picture
Exposure;Adjust the exposure of the background area of second picture;After the human face region of the first picture adjusted and adjustment
Second picture background area fusion treatment, obtain face fusion picture.
In one embodiment, computer program, which is executed by processor, carries out people according to face fusion picture and certificate picture
Face comparison, also performs the steps of respectively when obtaining the step of the similarity between face fusion picture and certificate picture from people
Human face region is partitioned into face fusion picture and certificate picture;The position of human face characteristic point is determined in human face region;It extracts each
The corresponding face characteristic value in position;It is corresponding to certificate picture according to the corresponding face characteristic value of each position in face fusion picture
Difference between the corresponding face characteristic value in position, obtains the similarity between face fusion picture and certificate picture.
In one embodiment, computer program is executed by processor the position that human face characteristic point is determined in human face region
The step of after, also perform the steps of the positional relationship obtained between preset human face characteristic point;According to positional relationship and respectively
The position of human face characteristic point carries out coordinate registration process to human face region, the human face region after being aligned;Computer program quilt
Face area after also being performed the steps of based on alignment when the step of the corresponding face characteristic value of processor execution extraction each position
Each human face characteristic point in domain extracts corresponding face characteristic value.
In one embodiment, computer program is executed by processor divides from face fusion picture and certificate picture respectively
It is also performed the steps of when cutting out the step of human face region according to different images attribute respectively to face fusion picture and certificate figure
Piece extracts characteristic pattern;Each characteristic pattern is subjected to Fusion Features, respectively obtains the characteristics of image of face fusion picture and certificate picture;
By human face region detection model, the encirclement coordinate in face fusion picture and certificate picture is determined according to characteristics of image;According to
It is corresponding to surround coordinate, human face region is partitioned into from face fusion picture and certificate picture respectively.
In one embodiment, it is also performed the steps of when computer program is executed by processor and certificate picture is carried out
Character recognition obtains the corresponding passport NO. of certificate;It will be in document corresponding to passport NO. importing and active user.
In one embodiment, it is corresponding that acquisition high photographing instrument is also performed the steps of when computer program is executed by processor
Instrument parameter;When instrument parameter is matched with the default instrument parameter being locally stored, computer program is executed by processor logical
It crosses verifying equipment and fusion treatment is carried out to multiple face pictures, obtain also performing the steps of when the step of face fusion picture
It chooses and fusion treatment is carried out to multiple face pictures with default instrument parameter matched image procossing control, obtain face fusion figure
Piece.
Above-mentioned computer readable storage medium is set by the high photographing instrument of lower configuration with the verifying for having picture processing capacity
It is standby to combine the authentication, it can be achieved that active user.Wherein, high photographing instrument can acquire the face that multiple include active user
Face picture, and the certificate picture for the provided certificate of active user for obtaining acquisition, and by the multiple face pictures and card of acquisition
Part picture is sent to the verifying equipment with high photographing instrument network connection, and verifying equipment can carry out fusion treatment to multiple face pictures,
The face fusion picture of better quality is obtained, in this way, verifying equipment can be based on face fusion picture and including user's head
The certificate picture of picture carries out face comparison, the similarity of face in face fusion picture and certificate picture is obtained, based on what is obtained
Similarity verifies the identity of active user.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of auth method, which is characterized in that the described method includes:
Acquire multiple face pictures of active user;
Obtain the certificate picture corresponding with the active user of acquisition;Wherein, the certificate picture includes certificate, the certificate
Including user's head portrait;
Multiple face pictures and the certificate picture are sent to verifying equipment;
Fusion treatment is carried out to multiple face pictures by the verifying equipment, obtains face fusion picture;
Face comparison is carried out according to the face fusion picture and the certificate picture, obtains the face fusion picture and described
Similarity between certificate picture;
It is verified based on identity of the similarity to the active user.
2. the method according to claim 1, wherein the method also includes:
The certificate information of certificate is read by card reader;
It is described by multiple face pictures and the certificate picture be sent to verifying equipment include:
The certificate information, the multiple face picture and the certificate picture are sent to verifying equipment;
It is described to include: to the face fusion picture and certificate picture progress face comparison respectively
Corresponding portrait picture is obtained according to the certificate information;
Face comparison is carried out according to the portrait picture, the face fusion picture and the certificate picture.
3. the method according to claim 1, wherein multiple face pictures include at least the first picture and the
Two pictures;It is described that fusion treatment is carried out to multiple face pictures by the verifying equipment, obtain face fusion picture packet
It includes:
First picture and the second picture are divided into human face region and background area;
Adjust the exposure of the human face region of first picture;
Adjust the exposure of the background area of the second picture;
By the background area fusion treatment of the human face region of first picture adjusted and the second picture adjusted,
Obtain face fusion picture.
4. the method according to claim 1, wherein described according to the face fusion picture and the certificate figure
Piece carries out face comparison, and the similarity obtained between the face fusion picture and the certificate picture includes:
Human face region is partitioned into from the face fusion picture and the certificate picture respectively;
The position of human face characteristic point is determined in the human face region;
Extract the corresponding face characteristic value in each position;
According to corresponding position in each corresponding face characteristic value in position in the face fusion picture and the certificate picture
Difference between corresponding face characteristic value obtains the similarity between the face fusion picture and the certificate picture.
5. according to the method described in claim 4, it is characterized in that, described determine human face characteristic point in the human face region
After the step of position, the method also includes:
Obtain the positional relationship between preset human face characteristic point;
According to the position of the positional relationship and each human face characteristic point, coordinate registration process is carried out to human face region, is obtained
Human face region after alignment;
The corresponding face characteristic value in each position of extracting includes:
Corresponding face characteristic value is extracted based on each human face characteristic point in the human face region after alignment.
6. according to the method described in claim 4, it is characterized in that, described respectively from the face fusion picture and the certificate
Human face region is partitioned into picture includes:
Characteristic pattern is extracted to the face fusion picture and the certificate picture respectively according to different images attribute;
Each characteristic pattern is subjected to Fusion Features, the image for respectively obtaining the face fusion picture and the certificate picture is special
Sign;
By human face region detection model, determined in the face fusion picture and the certificate picture according to described image feature
Encirclement coordinate;
Coordinate is surrounded according to corresponding, is partitioned into human face region from the face fusion picture and the certificate picture respectively.
7. method according to any one of claims 1 to 6, which is characterized in that the method also includes:
Character recognition is carried out to the certificate picture, obtains the corresponding passport NO. of the certificate;
It will be in document corresponding to passport NO. importing and the active user.
8. method according to any one of claims 1 to 6, which is characterized in that the method also includes:
Obtain the corresponding instrument parameter of the high photographing instrument;
When the instrument parameter is matched with the default instrument parameter being locally stored, it is described by the verifying equipment to multiple institutes
It states face picture and carries out fusion treatment, obtaining face fusion picture includes:
It chooses and fusion treatment is carried out to multiple face pictures with the default instrument parameter matched image procossing control, obtain
To face fusion picture.
9. a kind of authentication system, including high photographing instrument and verifying equipment, it is characterised in that:
The high photographing instrument is used to acquire multiple face pictures of active user;Obtain the card corresponding with the active user of acquisition
Part picture;Wherein, the certificate picture includes certificate, and the certificate includes user's head portrait;By multiple face pictures and
The certificate picture is sent to verifying equipment;
The verifying equipment is used to receive the multiple face pictures and the certificate picture that the high photographing instrument is sent;It is also used to
Fusion treatment is carried out to multiple face pictures, obtains face fusion picture;
The verifying equipment is also used to carry out face comparison according to the face fusion picture and the certificate picture, obtains described
Similarity between face fusion picture and the certificate picture;It is carried out based on identity of the similarity to the active user
Verifying.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any item of the claim 1 to 8 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811123931.5A CN109409060A (en) | 2018-09-26 | 2018-09-26 | Auth method, system and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811123931.5A CN109409060A (en) | 2018-09-26 | 2018-09-26 | Auth method, system and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409060A true CN109409060A (en) | 2019-03-01 |
Family
ID=65465212
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811123931.5A Pending CN109409060A (en) | 2018-09-26 | 2018-09-26 | Auth method, system and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409060A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978063A (en) * | 2019-03-28 | 2019-07-05 | 厦门美图之家科技有限公司 | A method of generating the alignment model of target object |
CN110147461A (en) * | 2019-04-30 | 2019-08-20 | 维沃移动通信有限公司 | Image display method, device, terminal device and computer readable storage medium |
CN110781842A (en) * | 2019-10-29 | 2020-02-11 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
CN110909766A (en) * | 2019-10-29 | 2020-03-24 | 北京明略软件***有限公司 | Similarity determination method and device, storage medium and electronic device |
CN111476279A (en) * | 2020-03-24 | 2020-07-31 | 平安银行股份有限公司 | Similarity value-based identification method and device and computer equipment |
CN111781993A (en) * | 2020-06-28 | 2020-10-16 | 联想(北京)有限公司 | Information processing method, system and computer readable storage medium |
CN112070013A (en) * | 2020-09-08 | 2020-12-11 | 安徽兰臣信息科技有限公司 | Method and device for detecting facial feature points of children and storage medium |
CN113656842A (en) * | 2021-08-10 | 2021-11-16 | 支付宝(杭州)信息技术有限公司 | Data verification method, device and equipment |
CN113868609A (en) * | 2021-09-18 | 2021-12-31 | 深圳市爱剪辑科技有限公司 | Video editing system based on deep learning |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102902959A (en) * | 2012-04-28 | 2013-01-30 | 王浩 | Face recognition method and system for storing identification photo based on second-generation identity card |
CN106529414A (en) * | 2016-10-14 | 2017-03-22 | 国政通科技股份有限公司 | Method for realizing result authentication through image comparison |
CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技(上海)有限公司 | Similarity judgement system based on human face five-sense-organ |
CN108171032A (en) * | 2017-12-01 | 2018-06-15 | 平安科技(深圳)有限公司 | A kind of identity identifying method, electronic device and computer readable storage medium |
CN108171463A (en) * | 2017-12-01 | 2018-06-15 | 平安科技(深圳)有限公司 | A kind of long-range face label method, electronic device and computer readable storage medium |
CN108229330A (en) * | 2017-12-07 | 2018-06-29 | 深圳市商汤科技有限公司 | Face fusion recognition methods and device, electronic equipment and storage medium |
CN108322646A (en) * | 2018-01-31 | 2018-07-24 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
-
2018
- 2018-09-26 CN CN201811123931.5A patent/CN109409060A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102902959A (en) * | 2012-04-28 | 2013-01-30 | 王浩 | Face recognition method and system for storing identification photo based on second-generation identity card |
CN106529414A (en) * | 2016-10-14 | 2017-03-22 | 国政通科技股份有限公司 | Method for realizing result authentication through image comparison |
CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技(上海)有限公司 | Similarity judgement system based on human face five-sense-organ |
CN108171032A (en) * | 2017-12-01 | 2018-06-15 | 平安科技(深圳)有限公司 | A kind of identity identifying method, electronic device and computer readable storage medium |
CN108171463A (en) * | 2017-12-01 | 2018-06-15 | 平安科技(深圳)有限公司 | A kind of long-range face label method, electronic device and computer readable storage medium |
CN108229330A (en) * | 2017-12-07 | 2018-06-29 | 深圳市商汤科技有限公司 | Face fusion recognition methods and device, electronic equipment and storage medium |
CN108322646A (en) * | 2018-01-31 | 2018-07-24 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978063A (en) * | 2019-03-28 | 2019-07-05 | 厦门美图之家科技有限公司 | A method of generating the alignment model of target object |
CN110147461A (en) * | 2019-04-30 | 2019-08-20 | 维沃移动通信有限公司 | Image display method, device, terminal device and computer readable storage medium |
CN110781842A (en) * | 2019-10-29 | 2020-02-11 | 深圳市商汤科技有限公司 | Image processing method and device, electronic equipment and storage medium |
CN110909766A (en) * | 2019-10-29 | 2020-03-24 | 北京明略软件***有限公司 | Similarity determination method and device, storage medium and electronic device |
CN110909766B (en) * | 2019-10-29 | 2022-11-29 | 北京明略软件***有限公司 | Similarity determination method and device, storage medium and electronic device |
CN111476279A (en) * | 2020-03-24 | 2020-07-31 | 平安银行股份有限公司 | Similarity value-based identification method and device and computer equipment |
CN111781993A (en) * | 2020-06-28 | 2020-10-16 | 联想(北京)有限公司 | Information processing method, system and computer readable storage medium |
CN111781993B (en) * | 2020-06-28 | 2022-04-22 | 联想(北京)有限公司 | Information processing method, system and computer readable storage medium |
CN112070013A (en) * | 2020-09-08 | 2020-12-11 | 安徽兰臣信息科技有限公司 | Method and device for detecting facial feature points of children and storage medium |
CN113656842A (en) * | 2021-08-10 | 2021-11-16 | 支付宝(杭州)信息技术有限公司 | Data verification method, device and equipment |
CN113656842B (en) * | 2021-08-10 | 2024-02-02 | 支付宝(杭州)信息技术有限公司 | Data verification method, device and equipment |
CN113868609A (en) * | 2021-09-18 | 2021-12-31 | 深圳市爱剪辑科技有限公司 | Video editing system based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109409060A (en) | Auth method, system and computer readable storage medium | |
Ferrara et al. | Face demorphing | |
US11120250B2 (en) | Method, system and computer program for comparing images | |
Ferrara et al. | On the effects of image alterations on face recognition accuracy | |
Hsu et al. | Camera response functions for image forensics: an automatic algorithm for splicing detection | |
CN101783019B (en) | Subject tracking apparatus and control method therefor, image capturing apparatus, and display apparatus | |
WO2019114376A1 (en) | Document verification method, device, electronic device, and storage medium | |
BR112017016942B1 (en) | SYSTEMS AND METHODS FOR PERFORMING USER AUTHENTICATION BASED ON FINGERPRINTS WITH THE USE OF IMAGE COLLECTIONS CAPTURED USING MOBILE DEVICES | |
US8275174B2 (en) | Vein pattern management system, vein pattern registration apparatus, vein pattern authentication apparatus, vein pattern registration method, vein pattern authentication method, program, and vein data configuration | |
CN110570209A (en) | Certificate authenticity verification method and device, computer equipment and storage medium | |
US10403076B2 (en) | Method for securing and verifying a document | |
MX2012010602A (en) | Face recognizing apparatus, and face recognizing method. | |
CN108764321B (en) | Image-recognizing method and device, electronic equipment, storage medium | |
KR102145132B1 (en) | Surrogate Interview Prevention Method Using Deep Learning | |
Gonzalez et al. | Hybrid two-stage architecture for tampering detection of chipless id cards | |
CN113642639B (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
Ferrara et al. | On the impact of alterations on face photo recognition accuracy | |
CN111046755A (en) | Character recognition method, character recognition device, computer equipment and computer-readable storage medium | |
WO2021166289A1 (en) | Data registration device, biometric authentication device, and recording medium | |
US9286707B1 (en) | Removing transient objects to synthesize an unobstructed image | |
CN109325448A (en) | Face identification method, device and computer equipment | |
JP2007164401A (en) | Solid body registration device, solid body authentication device, solid body authentication system and solid body authentication method | |
JP5791361B2 (en) | PATTERN IDENTIFICATION DEVICE, PATTERN IDENTIFICATION METHOD, AND PROGRAM | |
Chiesa et al. | Advanced face presentation attack detection on light field database | |
Gonzalez et al. | Improving presentation attack detection for ID cards on remote verification systems |
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 |