CN106778613A - A kind of auth method and device based on the matching of face cut zone - Google Patents
A kind of auth method and device based on the matching of face cut zone Download PDFInfo
- Publication number
- CN106778613A CN106778613A CN201611168833.4A CN201611168833A CN106778613A CN 106778613 A CN106778613 A CN 106778613A CN 201611168833 A CN201611168833 A CN 201611168833A CN 106778613 A CN106778613 A CN 106778613A
- Authority
- CN
- China
- Prior art keywords
- cut zone
- user
- pore
- image
- feature
- 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 44
- 239000011148 porous material Substances 0.000 claims abstract description 161
- 238000012360 testing method Methods 0.000 claims abstract description 48
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims 1
- 230000001815 facial effect Effects 0.000 description 19
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- 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
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of auth method based on the matching of face cut zone, including：When the authentication triggering command of user is received, the test image of multiple cut zone of the face of user is obtained；Test image to each cut zone is pre-processed, and obtains the area grayscale image of optimization；Based on the advance pore rank Scale invariant features transform algorithm realized, the skin pore feature of multiple pore characteristic points in each area grayscale image is determined；The skin pore feature of each pore characteristic point in each area grayscale image is matched to the fixed reference feature of the pore characteristic point of corresponding cut zone in the feature database being obtained ahead of time respectively；According to matching result, determine whether user is validated user.The method provided using the embodiment of the present invention, can improve recognition efficiency and accuracy rate, enhance system security.The invention also discloses a kind of authentication means based on the matching of face cut zone, with relevant art effect.
Description
Technical field
The present invention relates to technical field of face recognition, more particularly to a kind of identity based on the matching of face cut zone is tested
Card method and device.
Background technology
With the fast development of science and technology, identity validation technology is also developed rapidly.Whole to mobile phone, automobile etc.
In the releasing process at end, in the releasing process applied in terminal, during mobile payment, it is required for carrying out identity testing
Card, to determine whether user identity is legal.
Existing auth method is mostly verified by user name, password etc..User name, password authentification pass through
Afterwards, you can determine that user is validated user.
In existing this method, user name, password are easily stolen by unauthorized person, so as to unauthorized person is utilized steal
The information such as user name, password can carry out illegal operation, security is relatively low.
The content of the invention
It is an object of the invention to provide a kind of auth method and device based on the matching of face cut zone, to improve
Recognition efficiency and accuracy rate, enhance system security.
In order to solve the above technical problems, the present invention provides following technical scheme：
A kind of auth method based on the matching of face cut zone, including：
When the authentication triggering command of user is received, the survey of multiple cut zone of the face of the user is obtained
Attempt picture；
Test image to each cut zone is pre-processed, and obtains the region ash of the corresponding optimization of each cut zone
Degree image, the pretreatment is processed and removal noise processed comprising gray processing；
Based on the advance pore rank Scale invariant features transform algorithm realized, multiple in each area grayscale image is determined
The skin pore feature of pore characteristic point；
Respectively by the skin pore feature of each pore characteristic point in each area grayscale image and the feature being obtained ahead of time
The fixed reference feature of the pore characteristic point of corresponding cut zone is matched in storehouse；
According to matching result, determine whether the user is validated user.
It is described according to matching result in a kind of specific embodiment of the invention, determine whether the user is legal
User, including：
If the quantity of the pore characteristic point of matching is big with the ratio of the pore characteristic point total quantity that the feature database is included
In predetermined threshold value, it is determined that the user is validated user.
It is described to be become based on the advance pore rank scale invariant feature realized in a kind of specific embodiment of the invention
Scaling method, determines the skin pore feature of multiple pore characteristic points in each area grayscale image, including：
For each area grayscale image, rolled up with the area grayscale image using multiple different size of Gaussian kernels
Product, the multiple images with different resolution of generation；
The pixel value of the image with same resolution ratio is carried out into calculus of differences；
Local most dark point is defined as candidate feature point during the image after calculus of differences will be carried out；
Using preferable pore model it is determined that candidate feature point in select pore characteristic point；
The Feature Descriptor of each pore characteristic point is generated, the skin of each pore characteristic point of the area grayscale image is obtained
Skin pore feature.
In a kind of specific embodiment of the invention, the test image to each cut zone is pre-processed,
The area grayscale image of the corresponding optimization of each cut zone is obtained, including：
The test image to each cut zone carries out gray processing treatment respectively, obtains the corresponding gray scale of each cut zone
Image；
One cut zone of selection, the pixel value of the gray level image according to the cut zone calculates the ash of the cut zone
Spend the average of image；
Noise processed is removed to the corresponding gray level image of each cut zone respectively using the average, each is obtained
The area grayscale image of the corresponding optimization of cut zone.
In a kind of specific embodiment of the invention, when it is determined that the user is not validated user, also include：
The step of test image of the multiple cut zone for repeating the face for obtaining the user, until repeating
When number of times reaches preset times threshold value, determine that the user is disabled user.
A kind of authentication means based on the matching of face cut zone, including：
Area image obtains module, for when the authentication triggering command of user is received, obtaining the user's
The test image of multiple cut zone of face；
Pretreatment module, pre-processes for the test image to each cut zone, obtains each cut zone pair
The area grayscale image of the optimization answered, the pretreatment is processed and removal noise processed comprising gray processing；
Characteristic determination module, for based on the advance pore rank Scale invariant features transform algorithm realized, determining each
The skin pore feature of multiple pore characteristic points in area grayscale image；
Characteristic matching module, for respectively by the skin pore feature of each pore characteristic point in each area grayscale image
The fixed reference feature of the pore characteristic point of cut zone corresponding to the feature database being obtained ahead of time is matched；
Legitimacy determining module, for according to matching result, determining whether the user is validated user.
In a kind of specific embodiment of the invention, the legitimacy determining module, specifically for：
The ratio of the pore characteristic point total quantity included with the feature database in the quantity of the pore characteristic point of matching is more than
During predetermined threshold value, determine that the user is validated user.
In a kind of specific embodiment of the invention, the characteristic determination module, specifically for：
For each area grayscale image, rolled up with the area grayscale image using multiple different size of Gaussian kernels
Product, the multiple images with different resolution of generation；
The pixel value of the image with same resolution ratio is carried out into calculus of differences；
Local most dark point is defined as candidate feature point during the image after calculus of differences will be carried out；
Using preferable pore model it is determined that candidate feature point in select pore characteristic point；
The Feature Descriptor of each pore characteristic point is generated, the skin of each pore characteristic point of the area grayscale image is obtained
Skin pore feature.
In a kind of specific embodiment of the invention, the pretreatment module, specifically for：
The test image to each cut zone carries out gray processing treatment respectively, obtains the corresponding gray scale of each cut zone
Image；
One cut zone of selection, the pixel value of the gray level image according to the cut zone calculates the ash of the cut zone
Spend the average of image；
Noise processed is removed to the corresponding gray level image of each cut zone respectively using the average, each is obtained
The area grayscale image of the corresponding optimization of cut zone.
In a kind of specific embodiment of the invention, also including illegalities determining module, it is used for：
When it is determined that the user is not validated user, multiple segmentations of the face for obtaining the user are repeated
The step of test image in region, until when number of repetition reaches preset times threshold value, determining that the user is disabled user.
The technical scheme provided using the embodiment of the present invention, when the authentication triggering command of user is received, can
To obtain the test image of multiple cut zone of the face of user, the test image to each cut zone is pre-processed,
The area grayscale image of optimization can be obtained, based on the advance pore rank Scale invariant features transform algorithm realized, can be true
The skin pore feature of multiple pore characteristic points in fixed each area grayscale image, respectively by each area grayscale image each
The skin pore feature of pore characteristic point is special to the reference of the pore characteristic point of corresponding cut zone in the feature database being obtained ahead of time
Levy and matched, according to matching result, it may be determined that whether user is validated user, so as to realize the checking to user identity.
The matching of the skin pore feature of the pore characteristic point included based on face cut zone gray level image is known to facial image
Not, recognition efficiency and accuracy rate can be improved, is enhanced system security.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of implementing procedure of the auth method based on the matching of face cut zone in the embodiment of the present invention
Figure；
Fig. 2 is a kind of structural representation of the authentication means based on the matching of face cut zone in the embodiment of the present invention
Figure.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiment is only a part of embodiment of the invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
A kind of auth method based on the matching of face cut zone is the embodiment of the invention provides, the method can be answered
For server, server is connected with client communication, can carry out information exchange, and use can be obtained from client by interaction
The test image of multiple cut zone of the face at family, and then the respective handling such as it is identified to test image.The method may be used also
To be applied to client, directly the respective handling such as it is identified to the test image of multiple cut zone of face by client.
By the identification to cut zone image, determine whether user is validated user, improve the security of corresponding system.
A kind of authentication based on the matching of face cut zone shown in Figure 1, being provided by the embodiment of the present invention
The implementing procedure figure of method, the method may comprise steps of：
S110：When the authentication triggering command of user is received, multiple cut zone of the face of user are obtained
Test image.
The embodiment of the present invention is verified by recognition of face to user identity.After subscriber authentication passes through, Yong Huke
The harbor of face identification device is provided with to enter, or operation is unlocked to mobile terminal, vehicle etc., or opened
Certain application installed in terminal, or move payment etc..
In actual applications, certification entrance can be provided the user, user can trigger identity and test by the certification entrance
Card process.When the authentication triggering command of user is received, the facial image of user can be obtained.Specifically, can lead to
The image capture device for crossing the setting of certification entrance relevant position gathers the facial image of user.
After obtaining the facial image of user, the face in facial image can be positioned by client, or client
Facial image is sent to server by end, the face in facial image is positioned by server, to obtain the face of user
Multiple cut zone test image.
Specifically, it is possible to use (Discriminative Response Map Fitting differentiate that response diagram is intended to DRMF
Close) method positioned, and obtains the test image of multiple cut zone of face.Left cheek, right cheek and volume can such as be obtained
The test image of first three cut zone.DRMF methods are prior art, and the embodiment of the present invention is repeated no more to this.
By taking mobile payment scene as an example, when user uses mobile payment function on mobile terminals, you can be considered as to client
End have issued authentication triggering command, and the client is mobile payment client.Client receives the authentication of user
During triggering command, the facial image of the camera collection user of mobile terminal can be called, facial feature localization is carried out to facial image,
Obtain the test image of multiple cut zone of face.The test image of multiple cut zone is sent to server by client.
Server when the authentication triggering command of user is received, can obtain the test of multiple cut zone of the face of user
Image.
S120：Test image to each cut zone is pre-processed, and obtains the corresponding optimization of each cut zone
Area grayscale image.
Wherein, pretreatment is processed and removal noise processed comprising gray processing.
After server obtains the test image of multiple cut zone of the face of user, can be to the survey of each cut zone
Attempt, as being pre-processed, such as to carry out gray processing treatment and removal noise processed, removal noise processed can smooth picture,
Reduce sharpness.Pre-processed by the test image to each cut zone, each cut zone correspondence can be obtained
Optimization area grayscale image.
In a kind of specific embodiment of the invention, step S120 may comprise steps of：
Step one：The test image to each cut zone carries out gray processing treatment respectively, obtains each cut zone pair
The gray level image answered；
Step 2：One cut zone of selection, the pixel value of the gray level image according to the cut zone calculates the cut section
The average of the gray level image in domain；
Step 3：Noise processed is removed to the corresponding gray level image of each cut zone respectively using average, is obtained
The area grayscale image of the corresponding optimization of each cut zone.
For ease of description, above three step is combined and is illustrated.
The test image to each cut zone carries out gray processing treatment respectively, can obtain each cut zone corresponding
Gray level image.Gray scale processing method is prior art, and the embodiment of the present invention is repeated no more to this.
A cut zone is selected in multiple cut zone, such as right cheek region is selected, according to the cut zone
The pixel value of gray level image, can calculate the average of the gray level image of the cut zone.Specifically, can be by the cut zone
The pixel value of gray level image sorts according to size order, obtains pixel median, then the picture for being calculated the setting regions image
Element value pixel average, pixel median and pixel mean of mean are defined as the cut zone gray level image it is equal
Value.Noise processed is removed to the corresponding gray level image of each cut zone respectively using the average, each cut section is obtained
The area grayscale image of the corresponding optimization in domain.Specifically, more than the pixel value of the average during gray level image can be lowered.
Noise processed is removed by gray level image, the quantity of pore characteristic point can be made to be maintained at certain model
Enclose, during pore Feature Points Matching, to reduce amount of calculation, improve recognition efficiency.
S130：Based on the advance pore rank Scale invariant features transform algorithm realized, each area grayscale image is determined
The skin pore feature of middle multiple pore characteristic points.
In embodiments of the present invention, a pore rank Scale invariant that can generate skin pore feature can in advance be realized
Eigentransformation algorithm, i.e. PSIFT (Pore Scale Invariant Feature Transform) algorithm, the PSIFT algorithms
It is to be proposed based on SIFT (Scale Invariant Feature Transform, Scale invariant features transform) algorithm.
In embodiments of the present invention, PSIFT algorithms have mainly done following three points improvement on the basis of SIFT algorithms：
1) local most dark point, is chosen as candidate feature point.SIFT algorithms make local most bright and local most dark point
It is candidate feature point.It is dark relative to the skin brightness of surrounding in view of pore, therefore choose local most dark in PSIFT algorithms
Point is used as candidate feature point.
2) preferable pore model, is introduced to choose pore characteristic point.It is more similar to skin pore in view of Gauss curved,
Therefore as preferable pore model after Gaussian function being made into corresponding modification, selected in candidate feature point using the preferable pore model
Take pore characteristic point.
3) Feature Descriptor of pore characteristic point, is improved, that is, increases the dimension of skin pore characteristic vector.
In actual applications, can be by image capture device actual acquisition facial image, or from image data base
Facial image is obtained, so as to obtain multiple facial images of different user.Gray processing treatment etc. is carried out to each facial image pre-
Treatment, can obtain the corresponding face gray level image sample data of each facial image.Respectively to each face gray scale of acquisition
Image sample data is analyzed, and the parameter of PSIFT algorithms can be modified.The pore feature that face gray level image is included
Point can be the pore characteristic point for characterizing diverse location in the faces such as the left corners of the mouth, the right corners of the mouth, left eye angle, right eye angle, chin.
Improved more than, SIFT algorithms can be modified as being adapted to the PSIFT algorithms of generation skin pore feature.
The process that PSIFT algorithms are realized is also the pore characteristic point and its corresponding skin pore feature included to face gray level image
Image processing process.
Based on the advance pore rank Scale invariant features transform algorithm realized, it may be determined that in each area grayscale image
The skin pore feature of multiple pore characteristic points.
In a kind of specific embodiment of the invention, step S130 may comprise steps of：
First step：For each area grayscale image, multiple different size of Gaussian kernels and the area grayscale are used
Image carries out convolution, the multiple images with different resolution of generation；
Second step：The pixel value of the image with same resolution ratio is carried out into calculus of differences；
3rd step：Local most dark point is defined as candidate feature point during the image after calculus of differences will be carried out；
4th step：Using preferable pore model it is determined that candidate feature point in select pore characteristic point；
5th step：The Feature Descriptor of each pore characteristic point is generated, each hair of the area grayscale image is obtained
The skin pore feature of hole characteristic point.
For ease of description, above-mentioned five steps are combined and is illustrated.
In embodiments of the present invention, based on the advance PSIFT algorithms realized, it may be determined that many in each area grayscale image
The skin pore feature of individual pore characteristic point.Specifically, being directed to each area grayscale image, it is possible to use multiple different size of
Gaussian kernel carries out convolution with the area grayscale image, so, can generate multiple images with different resolution.Will be with same
The pixel value of the image of one resolution ratio carries out calculus of differences, i.e., subtracted each other two-by-two, obtains carrying out the image after calculus of differences.Will
Local most dark point is defined as candidate feature point in carrying out the image after calculus of differences.Using preferable pore model it is determined that time
Select and select pore characteristic point in characteristic point, generate the Feature Descriptor of each pore characteristic point, you can obtain the area grayscale
The skin pore feature of each pore characteristic point of image.
S140：Respectively by the skin pore feature of each pore characteristic point in each area grayscale image be obtained ahead of time
The fixed reference feature of the pore characteristic point of corresponding cut zone is matched in feature database.
In embodiments of the present invention, user need to be carried out when for the first time using face identification functions to the facial image of user
Multiple cut zone images are identified by region segmentation, obtain the ginseng of the pore characteristic point of each cut zone of the user
Feature is examined, the feature database of the user is set up accordingly.The feature database of one or more users can be previously stored with server.
In step S130, it is determined that the skin pore feature of multiple pore characteristic points in each area grayscale image, can be with
It is respectively that the skin pore feature of each pore characteristic point in each area grayscale image is corresponding to the feature database being obtained ahead of time
The fixed reference feature of the corresponding pore characteristic point of cut zone is matched.
The authentication triggering command of user is being received, when obtaining the facial image of user, user can be simultaneously being obtained
Mark, the ID can be terminal iidentification, can also be that user name etc. is identified.Match the feature database for using be with
Family identifies corresponding feature database.
For each pore characteristic point in each area grayscale image, can be by the skin pore feature of the pore characteristic point
The fixed reference feature of the corresponding pore characteristic point of cut zone corresponding to feature database is matched, and judges that the two is with nearest neighbor algorithm
No matching.
In embodiments of the present invention, a matching threshold can be preset, when the skin pore of certain pore characteristic point
When the matching degree of the fixed reference feature of feature pore characteristic point corresponding to feature database is more than the matching threshold, it is determined that the two
Match somebody with somebody.
S150：According to matching result, determine whether user is validated user.
In step S140, respectively by the skin pore feature of each pore characteristic point in each area grayscale image with it is advance
After the fixed reference feature of the pore characteristic point of corresponding cut zone is matched in the feature database of acquisition, each region ash can be obtained
Each corresponding matching result of pore characteristic point in degree image.
According to matching result, it may be determined that whether user is validated user.
Specifically, can according to matching pore characteristic point absolute quantity or relative populations, determine user whether be
Validated user.
In a kind of specific embodiment of the invention, step S150 may comprise steps of：
If the ratio of the pore characteristic point total quantity that the quantity of the pore characteristic point of matching is included with feature database is more than pre-
If threshold value, it is determined that user is validated user.
According to matching result, it may be determined that the quantity of the pore characteristic point of matching, may thereby determine that the pore of matching is special
Levy the ratio of the pore characteristic point total quantity that quantity a little is included with feature database.If the ratio is more than predetermined threshold value, can be with
Think that user user corresponding with feature database is same person, it may be determined that user is validated user.
Predetermined threshold value can be set and be adjusted according to actual conditions, such as, be set to 0.8, the embodiment of the present invention pair
This is not limited.
If it is determined that user be validated user, then show that subscriber authentication passes through, can according to user instruction perform into
Single stepping.If it is determined that user is not validated user, then show subscriber authentication not over entering for user can be refused
Single stepping.
In a kind of specific embodiment of the invention, when it is determined that user is not validated user, can repeat and obtain
The step of test image of the multiple cut zone for obtaining the face of user, until when number of repetition reaches preset times threshold value, really
User is determined for disabled user.The step of test image of the multiple cut zone for repeating the face for obtaining user, Ke Yichong
Newly carry out recognition of face.When number of repetition reaches default frequency threshold value, it may be determined that user is disabled user, in this feelings
Under condition, can be with outputting alarm information.
The method provided using the embodiment of the present invention, when the authentication triggering command of user is received, can obtain
Multiple cut zone of the face of user test image, the test image to each cut zone pre-processes, can be with
The area grayscale image of optimization is obtained, based on the advance pore rank Scale invariant features transform algorithm realized, it may be determined that every
The skin pore feature of multiple pore characteristic points in individual area grayscale image, respectively by each pore in each area grayscale image
The skin pore feature of characteristic point is entered to the fixed reference feature of the pore characteristic point of corresponding cut zone in the feature database being obtained ahead of time
Row matching, according to matching result, it may be determined that whether user is validated user, so as to realize the checking to user identity.It is based on
The matching of the skin pore feature of the pore characteristic point that face cut zone gray level image is included is identified to facial image, can
To improve recognition efficiency and accuracy rate, enhance system security.
Corresponding to above method embodiment, the embodiment of the present invention additionally provide it is a kind of based on face cut zone matching
Authentication means, a kind of authentication means and above-described one kind based on the matching of face cut zone described below
Auth method based on the matching of face cut zone can be mutually to should refer to.
Shown in Figure 2, the device is included with lower module：
Area image obtains module 210, for when the authentication triggering command of user is received, obtaining the people of user
The test image of multiple cut zone of face；
Pretreatment module 220, pre-processes for the test image to each cut zone, obtains each cut zone
The area grayscale image of corresponding optimization, pretreatment is processed and removal noise processed comprising gray processing；
Characteristic determination module 230, for based on the advance pore rank Scale invariant features transform algorithm realized, it is determined that often
The skin pore feature of multiple pore characteristic points in individual area grayscale image；
Characteristic matching module 240, for respectively by the skin pore of each pore characteristic point in each area grayscale image
Feature is matched to the fixed reference feature of the pore characteristic point of corresponding cut zone in the feature database being obtained ahead of time；
Legitimacy determining module 250, for according to matching result, determining whether user is validated user.
The device provided using the embodiment of the present invention, when the authentication triggering command of user is received, can obtain
Multiple cut zone of the face of user test image, the test image to each cut zone pre-processes, can be with
The area grayscale image of optimization is obtained, based on the advance pore rank Scale invariant features transform algorithm realized, it may be determined that every
The skin pore feature of multiple pore characteristic points in individual area grayscale image, respectively by each pore in each area grayscale image
The skin pore feature of characteristic point is entered to the fixed reference feature of the pore characteristic point of corresponding cut zone in the feature database being obtained ahead of time
Row matching, according to matching result, it may be determined that whether user is validated user, so as to realize the checking to user identity.It is based on
The matching of the skin pore feature of the pore characteristic point that face cut zone gray level image is included is identified to facial image, can
To improve recognition efficiency and accuracy rate, enhance system security.
In a kind of specific embodiment of the invention, legitimacy determining module 250, specifically for：
The ratio of the pore characteristic point total quantity included with feature database in the quantity of the pore characteristic point of matching is more than default
During threshold value, determine that user is validated user.
In a kind of specific embodiment of the invention, characteristic determination module 230, specifically for：
For each area grayscale image, rolled up with the area grayscale image using multiple different size of Gaussian kernels
Product, the multiple images with different resolution of generation；
The pixel value of the image with same resolution ratio is carried out into calculus of differences；
Local most dark point is defined as candidate feature point during the image after calculus of differences will be carried out；
Using preferable pore model it is determined that candidate feature point in select pore characteristic point；
The Feature Descriptor of each pore characteristic point is generated, the skin of each pore characteristic point of the area grayscale image is obtained
Skin pore feature.
In a kind of specific embodiment of the invention, pretreatment module 220, specifically for：
The test image to each cut zone carries out gray processing treatment respectively, obtains the corresponding gray scale of each cut zone
Image；
One cut zone of selection, the pixel value of the gray level image according to the cut zone calculates the ash of the cut zone
Spend the average of image；
Noise processed is removed to the corresponding gray level image of each cut zone respectively using average, each segmentation is obtained
The area grayscale image of the corresponding optimization in region.
In a kind of specific embodiment of the invention, also including illegalities determining module, it is used for：
When it is determined that user is not validated user, the test chart of multiple cut zone of the face for obtaining user is repeated
The step of picture, until when number of repetition reaches preset times threshold value, determining that user is disabled user.
Each embodiment is described by the way of progressive in this specification, and what each embodiment was stressed is and other
The difference of embodiment, between each embodiment same or similar part mutually referring to.For being filled disclosed in embodiment
For putting, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is referring to method part
Illustrate.
Professional further appreciates that, with reference to the unit of each example of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, generally describes the composition and step of each example according to function in the above description.These
Function is performed with hardware or software mode actually, depending on the application-specific and design constraint of technical scheme.Specialty
Technical staff can realize described function to each specific application using distinct methods, but this realization should not
Think beyond the scope of this invention.
The step of method or algorithm for being described with reference to the embodiments described herein, directly can be held with hardware, processor
Capable software module, or the two combination is implemented.Software module can be placed in random access memory (RAM), internal memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In field in known any other form of storage medium.
Specific case used herein is set forth to principle of the invention and implementation method, and above example is said
It is bright to be only intended to help and understand technical scheme and its core concept.It should be pointed out that common for the art
For technical staff, under the premise without departing from the principles of the invention, some improvement and modification can also be carried out to the present invention, these
Improve and modification is also fallen into the protection domain of the claims in the present invention.
Claims (10)
1. it is a kind of based on face cut zone matching auth method, it is characterised in that including：
When the authentication triggering command of user is received, the test chart of multiple cut zone of the face of the user is obtained
Picture；
Test image to each cut zone is pre-processed, and obtains the area grayscale figure of the corresponding optimization of each cut zone
Picture, the pretreatment is processed and removal noise processed comprising gray processing；
Based on the advance pore rank Scale invariant features transform algorithm realized, multiple pores in each area grayscale image are determined
The skin pore feature of characteristic point；
Respectively by the skin pore feature of each pore characteristic point in each area grayscale image and the feature database being obtained ahead of time
The fixed reference feature of the pore characteristic point of corresponding cut zone is matched；
According to matching result, determine whether the user is validated user.
2. it is according to claim 1 based on face cut zone matching auth method, it is characterised in that described
According to matching result, determine whether the user is validated user, including：
If the ratio of the pore characteristic point total quantity that the quantity of the pore characteristic point of matching is included with the feature database is more than pre-
If threshold value, it is determined that the user is validated user.
3. it is according to claim 1 based on face cut zone matching auth method, it is characterised in that the base
In the advance pore rank Scale invariant features transform algorithm realized, multiple pore characteristic points in each area grayscale image are determined
Skin pore feature, including：
For each area grayscale image, convolution is carried out using multiple different size of Gaussian kernels and the area grayscale image, it is raw
Into image of the multiple with different resolution；
The pixel value of the image with same resolution ratio is carried out into calculus of differences；
Local most dark point is defined as candidate feature point during the image after calculus of differences will be carried out；
Using preferable pore model it is determined that candidate feature point in select pore characteristic point；
The Feature Descriptor of each pore characteristic point is generated, the skin hair of each pore characteristic point of the area grayscale image is obtained
Hole characteristic.
4. it is according to claim 1 based on face cut zone matching auth method, it is characterised in that it is described right
The test image of each cut zone is pre-processed, and obtains the area grayscale image of the corresponding optimization of each cut zone, bag
Include：
The test image to each cut zone carries out gray processing treatment respectively, obtains the corresponding gray-scale map of each cut zone
Picture；
One cut zone of selection, the pixel value of the gray level image according to the cut zone calculates the gray-scale map of the cut zone
The average of picture；
Noise processed is removed to the corresponding gray level image of each cut zone respectively using the average, each segmentation is obtained
The area grayscale image of the corresponding optimization in region.
5. the auth method based on the matching of face cut zone according to any one of Claims 1-4, its feature exists
In when it is determined that the user is not validated user, also including：
The step of test image of the multiple cut zone for repeating the face for obtaining the user, until number of repetition
When reaching preset times threshold value, determine that the user is disabled user.
6. it is a kind of based on face cut zone matching authentication means, it is characterised in that including：
Area image obtains module, for when the authentication triggering command of user is received, obtaining the face of the user
Multiple cut zone test image；
Pretreatment module, pre-processes for the test image to each cut zone, obtains each cut zone corresponding
The area grayscale image of optimization, the pretreatment is processed and removal noise processed comprising gray processing；
Characteristic determination module, for based on the advance pore rank Scale invariant features transform algorithm realized, determining each region
The skin pore feature of multiple pore characteristic points in gray level image；
Characteristic matching module, for respectively by the skin pore feature of each pore characteristic point in each area grayscale image with it is pre-
The fixed reference feature of the pore characteristic point of corresponding cut zone is matched in the feature database for first obtaining；
Legitimacy determining module, for according to matching result, determining whether the user is validated user.
7. it is according to claim 6 based on face cut zone matching authentication means, it is characterised in that the conjunction
Method determining module, specifically for：
The ratio of the pore characteristic point total quantity included with the feature database in the quantity of the pore characteristic point of matching is more than default
During threshold value, determine that the user is validated user.
8. it is according to claim 6 based on face cut zone matching authentication means, it is characterised in that the spy
Determining module is levied, specifically for：
For each area grayscale image, convolution is carried out using multiple different size of Gaussian kernels and the area grayscale image, it is raw
Into image of the multiple with different resolution；
The pixel value of the image with same resolution ratio is carried out into calculus of differences；
Local most dark point is defined as candidate feature point during the image after calculus of differences will be carried out；
Using preferable pore model it is determined that candidate feature point in select pore characteristic point；
The Feature Descriptor of each pore characteristic point is generated, the skin hair of each pore characteristic point of the area grayscale image is obtained
Hole characteristic.
9. it is according to claim 6 based on face cut zone matching authentication means, it is characterised in that it is described pre-
Processing module, specifically for：
The test image to each cut zone carries out gray processing treatment respectively, obtains the corresponding gray-scale map of each cut zone
Picture；
One cut zone of selection, the pixel value of the gray level image according to the cut zone calculates the gray-scale map of the cut zone
The average of picture；
Noise processed is removed to the corresponding gray level image of each cut zone respectively using the average, each segmentation is obtained
The area grayscale image of the corresponding optimization in region.
10. according to any one of claim 6 to 9 based on face cut zone matching authentication means, its feature
It is, also including illegalities determining module, to be used for：
When it is determined that the user is not validated user, multiple cut zone of the face for obtaining the user are repeated
Test image the step of, until when number of repetition reaches preset times threshold value, determine that the user is disabled user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611168833.4A CN106778613A (en) | 2016-12-16 | 2016-12-16 | A kind of auth method and device based on the matching of face cut zone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611168833.4A CN106778613A (en) | 2016-12-16 | 2016-12-16 | A kind of auth method and device based on the matching of face cut zone |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106778613A true CN106778613A (en) | 2017-05-31 |
Family
ID=58892245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611168833.4A Pending CN106778613A (en) | 2016-12-16 | 2016-12-16 | A kind of auth method and device based on the matching of face cut zone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778613A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169960A (en) * | 2017-05-15 | 2017-09-15 | 精诚工坊电子集成技术（北京）有限公司 | A kind of skin surface pore size detection method based on color of image space |
| CN107239583A (en) * | 2017-08-02 | 2017-10-10 | 广东工业大学 | A kind of face retrieval method and device based on L1 norm neutral nets |
| CN107391996A (en) * | 2017-08-02 | 2017-11-24 | 广东工业大学 | A kind of auth method and device based on L1 norm neutral nets |
| CN107403166A (en) * | 2017-08-02 | 2017-11-28 | 广东工业大学 | A kind of method and apparatus for extracting facial image pore feature |
| CN107527046A (en) * | 2017-09-21 | 2017-12-29 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN107729904A (en) * | 2017-10-09 | 2018-02-23 | 广东工业大学 | A kind of face pore matching process based on the limitation of 3 D deformation face |
| CN107895108A (en) * | 2017-10-27 | 2018-04-10 | 维沃移动通信有限公司 | A kind of operation management method and mobile terminal |
| CN109068089A (en) * | 2018-09-30 | 2018-12-21 | 视联动力信息技术股份有限公司 | A kind of conferencing data generation method and device |
| CN110210342A (en) * | 2019-05-20 | 2019-09-06 | 深圳供电局有限公司 | A kind of Humanface image matching method and its system, readable storage medium storing program for executing |
| CN110889102A (en) * | 2019-11-27 | 2020-03-17 | Tcl移动通信科技（宁波）有限公司 | Image unlocking method and device, computer readable storage medium and terminal |
| CN115862121A (en) * | 2023-02-23 | 2023-03-28 | 中国人民解放军海军潜艇学院 | Face rapid matching method based on multimedia resource library |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503194A (en) * | 2002-11-26 | 2004-06-09 | 中国科学院计算技术研究所 | Status identification method by using body information matched human face information |
| CN103839039A (en) * | 2012-11-26 | 2014-06-04 | 上海市浦东新区知识产权保护协会 | Intelligent authentication device of pore features |
| CN104766062A (en) * | 2015-04-07 | 2015-07-08 | 广西大学 | Face recognition system and register and recognition method based on lightweight class intelligent terminal |
-
2016
- 2016-12-16 CN CN201611168833.4A patent/CN106778613A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1503194A (en) * | 2002-11-26 | 2004-06-09 | 中国科学院计算技术研究所 | Status identification method by using body information matched human face information |
| CN103839039A (en) * | 2012-11-26 | 2014-06-04 | 上海市浦东新区知识产权保护协会 | Intelligent authentication device of pore features |
| CN104766062A (en) * | 2015-04-07 | 2015-07-08 | 广西大学 | Face recognition system and register and recognition method based on lightweight class intelligent terminal |
Non-Patent Citations (1)
| Title |
|---|
| DONG LI等: "《High-Resolution Face Verification Using Pore-Scale Facial Features》", 《IEEE TRANSACTIONS ON IMAGE PROCESSING》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169960A (en) * | 2017-05-15 | 2017-09-15 | 精诚工坊电子集成技术（北京）有限公司 | A kind of skin surface pore size detection method based on color of image space |
| CN107239583A (en) * | 2017-08-02 | 2017-10-10 | 广东工业大学 | A kind of face retrieval method and device based on L1 norm neutral nets |
| CN107391996A (en) * | 2017-08-02 | 2017-11-24 | 广东工业大学 | A kind of auth method and device based on L1 norm neutral nets |
| CN107403166A (en) * | 2017-08-02 | 2017-11-28 | 广东工业大学 | A kind of method and apparatus for extracting facial image pore feature |
| CN107527046A (en) * | 2017-09-21 | 2017-12-29 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN107729904A (en) * | 2017-10-09 | 2018-02-23 | 广东工业大学 | A kind of face pore matching process based on the limitation of 3 D deformation face |
| CN107895108A (en) * | 2017-10-27 | 2018-04-10 | 维沃移动通信有限公司 | A kind of operation management method and mobile terminal |
| CN107895108B (en) * | 2017-10-27 | 2021-02-26 | 维沃移动通信有限公司 | Operation management method and mobile terminal |
| CN109068089A (en) * | 2018-09-30 | 2018-12-21 | 视联动力信息技术股份有限公司 | A kind of conferencing data generation method and device |
| CN110210342A (en) * | 2019-05-20 | 2019-09-06 | 深圳供电局有限公司 | A kind of Humanface image matching method and its system, readable storage medium storing program for executing |
| CN110889102A (en) * | 2019-11-27 | 2020-03-17 | Tcl移动通信科技（宁波）有限公司 | Image unlocking method and device, computer readable storage medium and terminal |
| CN110889102B (en) * | 2019-11-27 | 2023-06-20 | Tcl移动通信科技（宁波）有限公司 | Image unlocking method and device, computer readable storage medium and terminal |
| CN115862121A (en) * | 2023-02-23 | 2023-03-28 | 中国人民解放军海军潜艇学院 | Face rapid matching method based on multimedia resource library |
| CN115862121B (en) * | 2023-02-23 | 2023-05-09 | 中国人民解放军海军潜艇学院 | Face quick matching method based on multimedia resource library |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778613A (en) | A kind of auth method and device based on the matching of face cut zone | |
| CN105450411B (en) | The method, apparatus and system of authentication are carried out using card feature | |
| US10108858B2 (en) | Texture features for biometric authentication | |
| US20180034852A1 (en) | Anti-spoofing system and methods useful in conjunction therewith | |
| US11244152B1 (en) | Systems and methods for passive-subject liveness verification in digital media | |
| Ortega-Delcampo et al. | Border control morphing attack detection with a convolutional neural network de-morphing approach | |
| US10403076B2 (en) | Method for securing and verifying a document | |
| KR20180022019A (en) | Method and apparatus for liveness test | |
| CN106557726A (en) | A kind of band is mourned in silence the system for face identity authentication and its method of formula In vivo detection | |
| CN110084013A (en) | Biometric templates safety and key generate | |
| US11373449B1 (en) | Systems and methods for passive-subject liveness verification in digital media | |
| CN109670436A (en) | Vehicle operator's auth method, device and electronic equipment | |
| CN109829370A (en) | Face identification method and Related product | |
| CN107977559A (en) | A kind of identity identifying method, device, equipment and computer-readable recording medium | |
| CN106650657A (en) | Authentication method and device based on full face binary matching | |
| CN106599841A (en) | Full face matching-based identity verifying method and device | |
| CN111339897A (en) | Living body identification method, living body identification device, computer equipment and storage medium | |
| Lin et al. | Convolutional neural networks for face anti-spoofing and liveness detection | |
| US11068693B1 (en) | Liveness detection in fingerprint-based biometric systems | |
| CN109639664A (en) | Login validation method, apparatus and system | |
| Bashier et al. | Graphical password: Pass-images Edge detection | |
| Alharbi et al. | Spoofing Face Detection Using Novel Edge-Net Autoencoder for Security. | |
| Wang et al. | Low-effort user authentication for kiosk systems based on smartphone user’s gripping hand geometry | |
| Arathy et al. | Analysis of Spoofing Detection using Video Subsection Processing | |
| CN114840830A (en) | Identity authentication method, identity authentication device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |