CN107358079A - Real-time face identifies login validation method and system - Google Patents
Real-time face identifies login validation method and system Download PDFInfo
- Publication number
- CN107358079A CN107358079A CN201710456698.1A CN201710456698A CN107358079A CN 107358079 A CN107358079 A CN 107358079A CN 201710456698 A CN201710456698 A CN 201710456698A CN 107358079 A CN107358079 A CN 107358079A
- Authority
- CN
- China
- Prior art keywords
- face
- picture
- user
- current request
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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
Abstract
The present invention relates to recognition of face logon domain, and in particular to and real-time face identifies login validation method and system, including：When user asks to log in, user in real photo；Recognition of face is carried out to the user picture got, obtains corresponding face picture；When confirmation user is non-first logs into, the conventional face's picture stored is copied from local face database, similarity comparison checking is carried out after current request is logged in respectively the face's picture used and replicate each obtained conventional face's picture processing as one dimensional histograms：If current request logs in the face's picture used and verified by similarity comparison, user is allowed to log in；If current request logs in the face's picture used and do not verified by similarity comparison, refusal user logs in.The present invention can improve the hit rate of recognition of face.
Description
Technical field
The present invention relates to recognition of face logon domain, and in particular to real-time face identifies login validation method and system.
Background technology
One to step on face recognition software be one kind popular in prior art, there is provided free SDK
Bag, service end storage user portrait, user is supported to draw a portrait retrieval and face character analysis etc. with logging in safety-related service.With
Family needs one user's portrait of storage when first logging into, and one steps on after service end receives and can generate unique ID, user for the portrait
Still new user's portrait is uploaded when logging on later, one, which steps on service end, is retrieved according to this portrait and returned unique
ID, the ID that client obtains first time is compared with this ID obtained, and if the same certification is by can normally step on
Record.
Face recognition software is stepped on using one and does recognition of face login, and only one user's portrait of storage, is examined with new portrait
Hit rate is relatively low when rope contrasts；Other one to step on recognition of face be a process logged in online, that is, need to network when logging in and to
One, which steps on service end, is repeatedly asked, and this can cause log in the case where network speed is bad.
The content of the invention
The technical problem to be solved in the present invention is, overcomes the shortcomings of existing technology, there is provided real-time face identification logs in
Verification method and system, it can improve the hit rate of recognition of face.
To reach above-mentioned technical purpose, on the one hand, real-time face provided by the invention identifies login validation method, including：
When user asks to log in, user in real photo；
Recognition of face is carried out to the user picture got, obtains corresponding face picture；
When confirmation user is non-first logs into, the conventional face's picture stored is copied from local face database,
Current request is logged in the face's picture used respectively with replicating each obtained conventional face's picture processing as one-dimensional Nogata
Similarity comparison checking is carried out after figure：
If current request logs in the face's picture used and verified by similarity comparison, user is allowed to log in；
If current request logs in the face's picture used and do not verified by similarity comparison, refusal user logs in.
On the other hand, real-time face identification login authentication system provided by the invention, including local face database, are also wrapped
Include：
Acquiring unit, for user ask log in when, user in real photo；
Face identification unit, for carrying out recognition of face to the user picture got, obtain corresponding face picture；
It is non-to first log into unit, for confirm user for it is non-first log into when, copied from local face database
Conventional face's picture of storage, current request is logged in the face's picture used respectively with replicating each obtained conventional face
Picture processing is progress similarity comparison checking after one dimensional histograms：If face's picture that current request login uses passes through similar
Contrast verification is spent, then allows user to log in；If current request logs in the face's picture used and not verified by similarity comparison,
Refuse user to log in.
In the present invention, whether the user picture for first determining whether user's login is that the effect of face's picture is in order to avoid non-face
Portion picture flow into after flow in, therefore, judge whether user picture is efficiency that face's picture just improves recognition of face；
Second, the present invention uses when contrasting face's picture and conventional face's picture and carries out picture processing for one dimensional histograms form
Contrast, speed and accuracy rate during the contrast so further improved.3rd, it is local human face data for store photo
Storehouse, face's picture of a user is only stored with corresponding local face database.So user logs in recognition of face
When, and do not need internet, so that it may call each functional unit in the system to pass through recognition of face.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the method flow block diagram of the embodiment of the present invention；
Fig. 2 is the structural representation of system of the embodiment of the present invention；
Fig. 3 is the method and step flow chart of the embodiment of the present invention；
Fig. 4 is the structural representation of face identification unit in embodiment in the present invention；
Fig. 5 is the non-structural representation for first logging into unit in embodiment in the present invention；
Fig. 6 is the structural representation of the first updating block in embodiment in the present invention；
Fig. 7 is the structural representation of update module in embodiment in the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
Method of the present invention can apply to cellphone subscriber and log in mobile phone, log in function of keeping secret.
As shown in figures 1 and 3, real-time face identification login validation method, comprises the following steps：
101st, when user asks to log in, user in real photo.
102nd, recognition of face is carried out to the user picture got, obtains corresponding face picture；
Using the faceDetector methods of the CIDetector classes in image procossing framework CoreImage to user picture
Recognition of face is carried out, in faceDetector methods, using current user picture for input, face data array is exports；
If face data array is not sky, judgement detects face, intercepts face's scope in current user picture
Picture, and remove noise image and obtain corresponding face picture；
If face data array is sky, judgement is not detected by face, returns to user in real photo；
The face data array includes：Face's range data, the central point of face's critical organ and face's critical organ
Status data.
Image procossing framework CoreImage is an image procossing framework in OS system X and iOS system, is based on
OpenGL top layers create, and bottom then handles image with tinter, image is handled based on hardware-accelerated using GPU, there is provided
Abundant and powerful image procossing interface.
104th, judge whether user is to first log into；
When the storage content of local face database is sky, then it is to first log into confirm user；
If confirming, the face's picture for first logging into use to first log into, is passed through OpenCV (Open Source by user
Computer Vision Library, computer vision of increasing income storehouse) processing is histogram, and stores and arrive local face database
In.
When the storage content of local face database is not sky, then it is non-first log into confirm user.
103rd, when confirmation user is non-first logs into, the conventional face figure stored is copied from local face database
Piece, current request is logged in the face's picture used respectively with replicating each obtained conventional face's picture processing to be one-dimensional straight
Similarity comparison checking is carried out after square figure：
If the 1031, current request logs in the face's picture used and verified by similarity comparison, user is allowed to log in；
If the 1032, current request logs in the face's picture used and do not verified by similarity comparison, refusal user logs in；
Then, optionally, user in real photo can be returned.
The process of similarity comparison checking is as follows：
Confirm that current request logs in the face's picture used and replicates the big of obtained conventional face's picture with each respectively
It is small consistent；And
If conventional face's picture size that face's picture that current request logs in use obtains with the duplication currently contrasted is not
Unanimously, then by the ROI (Region of interest, area-of-interest) of the longer picture of the length of side partly using OpenCV's
CvSetImageROI is cut, and without changing COI (Channels of interest, passage interested) part, is made current
It is consistent that request logs in conventional face's picture size that the face's picture used obtains with the duplication currently contrasted.
It can so keep the color of photo unaffected.Because in recognition of face login process, the face of acquisition schemes
Piece and the photo size stored in the corresponding customer data base being locally stored are inconsistent, so easily cause to survey in contrast afterwards
Fail during examination, therefore ensure that two photos of contrast are in the same size, contrast test percent of pass can be improved.
Current request is logged in by the face's picture used by OpenCV respectively and each is replicated obtained conventional face
Picture processing is one dimensional histograms；The process that photo disposal is one dimensional histograms is by the OpenCV：
Photo is subjected to color space change using OpenCV；
Using OpenCV by photo from rgb color patten transformation to hsv color model；
Then calculate corresponding histogram and normalize, obtain the one dimensional histograms of photo.
Calculate the one-dimensional Nogata for face's picture that current request login uses respectively by OpenCV cvCompareHist
Similarity between figure and each one dimensional histograms for replicating obtained conventional face's picture；All similarities all pass through a bar formula
Distance algorithm is calculated；Similarity is the fractional value of one 0 to 1, and it is more similar to be worth smaller representative；
All similarities being calculated are averaged to obtain average similarity；
By average similarity compared with similarity threshold set in advance；
If average similarity is less than similarity threshold, judge that current request logs in the face's picture used and passes through similarity
Contrast verification；
If average similarity is more than or equal to similarity threshold, judge that current request logs in the face's picture used and do not passed through
Similarity comparison is verified.
105th, local face database is updated；
Current request log in use face's picture verified by similarity comparison after, judge be in local face database
The no conventional face's picture that storage duration be present and exceed setting duration threshold value；
If in the presence of, by the current request verified by similarity comparison log in use face's picture by OpenCV at
Manage as histogram, and store and arrive local face database；And storage duration is most long in the local face database of deletion one
Conventional face's picture or storage duration exceed a conventional face picture of setting duration threshold value.
Specific update mode is as follows：
Record when being verified by similarity comparison the proving time for face's picture that current request login uses and it is all with
Stored toward face's picture to the storage time of local face database；
Current request is logged in proving time and the storage time life of every conventional face picture of the face's picture used
Answer time difference (storing duration) in pairs；
It is more than or equal to duration threshold value set in advance whenever inquiring a time difference, then starts to local human face data
Storehouse is updated operation；
By this current request verified by similarity comparison log in face's picture for using with OpenCV processing for
Nogata piece；
The histogram that the current request that this is verified by similarity comparison is logged in the face's picture used is stored to this
Ground face database；
Then the conventional face's picture for deleting a storage duration most long (it is most remote to store duration) is corresponded to.
If all time differences are both less than time threshold set in advance, the customer data base for judging to be locally stored is not required to
Update operation.
The mode of renewal is not limited to above-mentioned update mode, can also include：Current request logs in the face's picture used and led to
After crossing similarity comparison checking, the current request verified by similarity comparison is logged in the face's picture used and passes through OpenCV
Handle as histogram, and store into local face database；
Local face database is regularly updated, only retains conventional face's picture of the newest setting quantity of storage time.
As shown in Fig. 2, Fig. 4 to Fig. 7, real-time face of the present invention identifies login authentication system, including local face
Database 21, in addition to：
Acquiring unit 22, for user ask log in when, user in real photo；
Face identification unit 23, for carrying out recognition of face to the user picture got, obtain corresponding face picture；
Judging unit 24 first, for judging whether the storage content of local face database is empty, if it is empty, is then confirmed
User is first logs into, and otherwise, confirms that user first logs into be non-；
Unit 25 is first logged into, if for confirming that to first log into, the face's picture for first logging into use is led to by user
It is histogram to cross Computer Vision function library OpenCV processing, and is stored into local face database；
It is non-to first log into unit 26, for confirm user for it is non-first log into when, copied from local face database
The conventional face's picture stored, current request is logged in the face's picture used respectively with replicating each obtained conventional face
Portion's picture processing is progress similarity comparison checking after one dimensional histograms：If current request, which logs in the face's picture used, passes through phase
Like degree contrast verification, then user is allowed to log in；If current request logs in the face's picture used and not verified by similarity comparison,
Then refuse user to log in.
The face identification unit 23 includes：
Data computation module 231, for utilizing the CIDetector classes in CoreImage image procossing frameworks
FaceDetector methods carry out recognition of face to user picture, and faceDetector methods are using current user picture to be defeated
Enter, face data array is output；
First face's determination module 232, if being not sky for face data array, judgement detects face, and interception is worked as
Face's scope picture in preceding user picture, and remove noise image and obtain corresponding face picture；
Second face's determination module 233, if being sky for face data array, judgement is not detected by face, returns real
When obtain user picture；
The face data array includes：Face's range data, the central point of face's critical organ and face's critical organ
Status data.
The non-unit 26 that first logs into includes：
Module 261 is cut, replicates what is obtained with each for confirming that current request logs in the face's picture used respectively
Face's picture was in the same size in the past；And if current request logs in what the face's picture used obtained with the duplication currently contrasted
Conventional face picture size is inconsistent, then by the ROI (Region of interest, area-of-interest) of the longer picture of the length of side
Part is cut using OpenCV cvSetImageROI, without change COI (Channels of interest, it is interested
Passage) part, make conventional face's picture size that current request logs in the face's picture used and the duplication currently contrasted obtains
Unanimously.
OpenCV cvSetImageROI is cut to the ROI section of photo, the COI parts without changing photo, this
Sample can keep the color of photo unaffected.Due in recognition of face login process, face's picture of acquisition and it is corresponding this
The photo size stored in the customer data base of ground storage is inconsistent, so easily causes during contrast test afterwards
Failure, therefore ensure that two photos of contrast are in the same size, contrast test percent of pass can be improved.
One-dimensional processing module 262, for current request to be logged in into the face's picture and each used by OpenCV respectively
It is one dimensional histograms to open conventional face's picture processing that duplication obtains；Mistakes of the OpenCV by photo disposal for one dimensional histograms
Cheng Wei：
Photo is subjected to color space change using OpenCV；
Using OpenCV by photo from rgb color patten transformation to hsv color model；
Then calculate corresponding histogram and normalize, obtain the one dimensional histograms of photo.
Similar computing module 263, for calculate respectively current request log in use face's picture one dimensional histograms with
Similarity between each one dimensional histograms for replicating obtained conventional face's picture；All similarities all pass through a bar formula distance
Algorithm is calculated；Similarity is the fractional value of one 0 to 1, and it is more similar to be worth smaller representative.
Average computation block 264, for averaging to obtain average similarity by all similarities being calculated；
Similar comparison module 265, for by average similarity compared with similarity threshold set in advance；It is if average
Similarity is less than similarity threshold, then judges that current request logs in the face's picture used and verified by similarity comparison；It is if flat
Equal similarity is more than or equal to similarity threshold, then judges that current request logs in the face's picture used and do not tested by similarity comparison
Card.
The system also includes：First updating block 27 or the second updating block 28；
Second updating block 28, after the face's picture used for current request login is verified by similarity comparison, sentence
Exceed conventional face's picture of setting duration threshold value in disconnected local face database with the presence or absence of storage duration；If in the presence of, by
The current request verified by similarity comparison logs in the face's picture used and handled by OpenCV as histogram, and stores and arrive
Local face database；And delete and most long conventional face's picture of duration or storage are stored in local face database
Duration exceedes a conventional face picture of setting duration threshold value.
Specifically include：
Time module 281 is recorded, current request logs in the face's figure used when being verified for recording by similarity comparison
The proving time of piece and all face's pictures in the past are stored to the storage time of local face database；
Difference block 282, for current request to be logged in proving time and the every conventional face of the face's picture used
The corresponding time difference (storing duration) of storage time generation of picture；
Update module 283, for being more than or equal to duration threshold value set in advance whenever inquiring a time difference, then open
Beginning is updated operation to local face database；Specifically include：
Photo disposal submodule 2831, the current request for this to be verified by similarity comparison log in the face used
Portion's picture is Nogata piece with OpenCV processing；
Sub-module stored 2832, the current request for this to be verified by similarity comparison log in the face used and schemed
The histogram of piece is stored to local face database；
Submodule 2833 is deleted, a most long conventional face's picture of storage duration is deleted for corresponding.
If all time differences are both less than time threshold set in advance, the customer data base for judging to be locally stored is not required to
Update operation.
First updating block 27, log in the face's picture used for current request and verified by similarity comparison
Afterwards, the current request verified by similarity comparison is logged in the face's picture used to handle as histogram by OpenCV, and
Store in local face database；Local face database is regularly updated, only retains the newest setting quantity of storage time
Conventional face picture.
In method of the present invention, employ first CoreImage judge user's login user picture whether
For face's picture, so as not to non-face's picture flow into after flow in, which improves the efficiency of recognition of face, so as to improve
The hit rate of contrast test；Second, this method is employed OpenCV and is stored face's picture using the form of histogram, is improved
Speed when identification calculates, further improves hit rate；3rd, this method employ OpenCV contrast face's picture and in the past
During face's picture, use and contrasted face's picture processing for one dimensional histograms form, the contrast so further improved
When speed and accuracy rate；And two pictures are just cut to picture of the same size before contrast with OpenCV, can be with
Improve the hit rate of contrast test.On the other hand, system of the present invention, the face that user the is locally stored figure carried is possessed
The face database of piece, face's picture of a user is only stored with each face database.So user knows in face
When not logging in, and internet is not needed, so that it may call each functional unit in the system to pass through recognition of face.
The present invention can be used for the mobile phone application for being related to individual privacy, the APP of such as note class or class of keeping accounts.Start first
First brush face is needed during APP and stores face's picture of user, identification checking can be just done when restarting APP next time.User starts
APP, APP can open front camera, obtain camera data in real time and start to identify face, face is intercepted after face is identified
Portion's picture is compared with the conventional face's picture having in APP databases, and if the verification passes, as same person then can be with
Normal to log in, otherwise refusal is logged in and verified again.
It should be understood that the particular order or level of the step of during disclosed are the examples of illustrative methods.Based on setting
Count preference, it should be appreciated that during the step of particular order or level can be in the feelings for the protection domain for not departing from the disclosure
Rearranged under condition.Appended claim to a method gives the key element of various steps with exemplary order, and not
It is to be limited to described particular order or level.
In above-mentioned detailed description, various features combine in single embodiment together, to simplify the disclosure.No
This open method should be construed to reflect such intention, i.e. the embodiment of theme claimed needs to compare
The more features of feature clearly stated in each claim.On the contrary, as appended claims is reflected
Like that, the present invention is in the state fewer than whole features of disclosed single embodiment.Therefore, appended claims
It is hereby expressly incorporated into detailed description, wherein each claim is alone as the single preferred embodiment of the present invention.
To enable any technical staff in the art to realize or using the present invention, disclosed embodiment being entered above
Description is gone.To those skilled in the art；The various modification modes of these embodiments will be apparent from, and this
The General Principle of text definition can also be applied to other embodiments on the basis of the spirit and scope of the disclosure is not departed from.
Therefore, the disclosure is not limited to embodiments set forth herein, but most wide with principle disclosed in the present application and novel features
Scope is consistent.
Described above includes the citing of one or more embodiments.Certainly, in order to above-described embodiment is described and description portion
The all possible combination of part or method is impossible, but it will be appreciated by one of ordinary skill in the art that each implementation
Example can do further combinations and permutations.Therefore, embodiment described herein is intended to fall into appended claims
Protection domain in all such changes, modifications and variations.In addition, with regard to the term used in specification or claims
"comprising", the mode that covers of the word are similar to term " comprising ", just as " including " solved in the claims as link word
As releasing.In addition, the use of any one term "or" in the specification of claims is to represent " non-exclusionism
Or ".
Those skilled in the art will also be appreciated that the various illustrative components, blocks that the embodiment of the present invention is listed
(illustrative logical block), unit, and step can pass through the knot of electronic hardware, computer software, or both
Conjunction is realized.To clearly show that the replaceability of hardware and software (interchangeability), above-mentioned various explanations
Property part (illustrative components), unit and step universally describe their function.Such work(
Can be that specific application and the design requirement of whole system are depended on to realize by hardware or software.Those skilled in the art
Various methods can be used to realize described function, but this realization is understood not to for every kind of specific application
Beyond the scope of protection of the embodiment of the present invention.
Various illustrative logical blocks described in the embodiment of the present invention, or unit can by general processor,
Digital signal processor, application specific integrated circuit (ASIC), field programmable gate array or other programmable logic devices, discrete gate
Or the design of transistor logic, discrete hardware components, or any of the above described combination is come the function described by realizing or operate.General place
It can be microprocessor to manage device, and alternatively, the general processor can also be any traditional processor, controller, microcontroller
Device or state machine.Processor can also be realized by the combination of computing device, such as digital signal processor and microprocessor,
Multi-microprocessor, one or more microprocessors combine a Digital Signal Processor Core, or any other like configuration
To realize.
The step of method or algorithm described in the embodiment of the present invention can be directly embedded into hardware, computing device it is soft
Part module or the combination of both.Software module can be stored in RAM memory, flash memory, ROM memory, EPROM storages
Other any form of storaging mediums in device, eeprom memory, register, hard disk, moveable magnetic disc, CD-ROM or this area
In.Exemplarily, storaging medium can be connected with processor, to allow processor to read information from storaging medium, and
Write information can be deposited to storaging medium.Alternatively, storaging medium can also be integrated into processor.Processor and storaging medium can
To be arranged in ASIC, ASIC can be arranged in user terminal.Alternatively, processor and storaging medium can also be arranged at use
In different parts in the terminal of family.
In one or more exemplary designs, above-mentioned function described by the embodiment of the present invention can be in hardware, soft
Part, firmware or any combination of this three are realized.If realized in software, these functions can store and computer-readable
On medium, or with one or more instruction or code form be transmitted on the medium of computer-readable.Computer readable medium includes electricity
Brain storaging medium and it is easy to so that allowing computer program to be transferred to other local telecommunication medias from a place.Storaging medium can be with
It is that any general or special computer can be with the useable medium of access.For example, such computer readable media can include but
It is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or other
What can be used for carrying or store with instruct or data structure and it is other can be by general or special computer or general or specially treated
The medium of the program code of device reading form.In addition, any connection can be properly termed computer readable medium, example
Such as, if software is to pass through a coaxial cable, fiber optic cables, double from a web-site, server or other remote resources
Twisted wire, Digital Subscriber Line (DSL) or with defined in being also contained in of the wireless way for transmitting such as infrared, wireless and microwave
In computer readable medium.Described disk (disk) and disk (disc) include Zip disk, radium-shine disk, CD, DVD, floppy disk
And Blu-ray Disc, disk is generally with magnetic duplication data, and disk generally carries out optical reproduction data with laser.Combinations of the above
It can also be included in computer readable medium.
Above-described embodiment, the purpose of the present invention, technical scheme and beneficial effect are carried out further
Describe in detail, should be understood that the embodiment that the foregoing is only the present invention, be not intended to limit the present invention
Protection domain, within the spirit and principles of the invention, any modification, equivalent substitution and improvements done etc., all should include
Within protection scope of the present invention.
Claims (12)
1. a kind of real-time face identifies login validation method, it is characterised in that including：
When user asks to log in, user in real photo；
Recognition of face is carried out to the user picture got, obtains corresponding face picture；
When confirmation user is non-first logs into, the conventional face's picture stored is copied from local face database, respectively
After current request is logged in the face's picture used and replicates each obtained conventional face picture processing as one dimensional histograms
Carry out similarity comparison checking：
If current request logs in the face's picture used and verified by similarity comparison, user is allowed to log in；
If current request logs in the face's picture used and do not verified by similarity comparison, refusal user logs in.
2. real-time face according to claim 1 identifies login validation method, it is characterised in that judge user whether headed by
The method of secondary login, is specifically included：
Whether the storage content for judging local face database is empty, if it is empty, then confirms user to first log into, otherwise, really
Recognize user to first log into be non-；And
Methods described also includes：
If confirming, the face's picture for first logging into use to first log into, is passed through the computer vision storehouse OpenCV that increases income by user
Handle as histogram, and store into local face database.
3. real-time face according to claim 2 identifies login validation method, it is characterised in that the described pair of use got
Family photo carries out recognition of face, obtains corresponding face picture, specifically includes：
Using image procossing framework, using current user picture as input, face data array is output；
If face data array is not sky, judgement detects face, intercepts face's scope picture in current user picture,
And remove noise image and obtain corresponding face picture；
If face data array is sky, judgement is not detected by face, returns to user in real photo；
The face data array includes：The shape of face's range data, the central point of face's critical organ and face's critical organ
State data.
4. real-time face according to claim 3 identifies login validation method, it is characterised in that
It is described respectively by current request log in each conventional face's picture processing that face's picture for using obtains with duplication for
Similarity comparison checking is carried out after one dimensional histograms, is specifically included：
Current request is logged in by the face's picture used by OpenCV respectively and each is replicated obtained conventional face's picture
Handle as one dimensional histograms；
Current request is calculated respectively logs in the conventional face that the one dimensional histograms of the face's picture used obtain with each duplication
Similarity between the one dimensional histograms of picture；
All similarities being calculated are averaged to obtain average similarity；
By average similarity compared with similarity threshold set in advance；
If average similarity is less than similarity threshold, judge that current request logs in the face's picture used and passes through similarity comparison
Checking；
If average similarity is more than or equal to similarity threshold, judge that current request logs in the face's picture used not by similar
Spend contrast verification.
5. real-time face according to claim 4 identifies login validation method, it is characterised in that described to pass through respectively
Current request is logged in the face's picture used and each conventional face's picture processing for replicating to obtain to be one-dimensional straight by OpenCV
Before square figure, methods described also includes：
Confirm that current request logs in the face's picture used and each size one for replicating obtained conventional face's picture respectively
Cause；And
If it is inconsistent that current request logs in conventional face's picture size that the face's picture used obtains with the duplication currently contrasted,
Then the region of interest ROI part of the longer picture of the length of side is cut using OpenCV, without changing channel C OI interested
Part, current request is set to log in conventional face's picture size that the face's picture used obtains with the duplication currently contrasted consistent.
6. real-time face according to any one of claim 1 to 5 identifies login validation method, it is characterised in that described
Method also includes：
It is current by being verified by similarity comparison after face's picture that current request login uses is verified by similarity comparison
Request logs in the face's picture used and handled by OpenCV as histogram, and stores into local face database；
Local face database is regularly updated, only retains conventional face's picture of the newest setting quantity of storage time；
Or
After face's picture that current request login uses is verified by similarity comparison, judge whether deposited in local face database
Exceed conventional face's picture of setting duration threshold value in storage duration；
If in the presence of, by the current request verified by similarity comparison log in face's picture for using by OpenCV processing for
Histogram, and store and arrive local face database；And storage duration is most long in the local face database of deletion one was in the past
Face's picture or storage duration exceed a conventional face picture of setting duration threshold value.
7. a kind of real-time face identifies login authentication system, it is characterised in that including local face database, in addition to：
Acquiring unit, for user ask log in when, user in real photo；
Face identification unit, for carrying out recognition of face to the user picture got, obtain corresponding face picture；
It is non-to first log into unit, for confirm user for it is non-first log into when, copy and stored from local face database
Conventional face's picture, current request is logged in the face's picture used respectively with replicating obtained each conventional face picture
Handle to carry out similarity comparison checking after one dimensional histograms：If current request, which logs in the face's picture used, passes through similarity pair
Than checking, then user is allowed to log in；If current request logs in the face's picture used and do not verified by similarity comparison, refuse
User logs in.
8. real-time face according to claim 7 identifies login authentication system, it is characterised in that the system also includes：
Judging unit first, for judging whether the storage content of local face database is empty, if it is empty, then confirms that user is
First log into, otherwise, confirm that user first logs into be non-；
Unit is first logged into, if for confirming that user to first log into, will first log into face's picture of use by increasing income
OpenCV processing in computer vision storehouse is histogram, and is stored into local face database.
9. real-time face according to claim 8 identifies login authentication system, it is characterised in that the face identification unit
Including：
Data computation module, for utilizing image procossing framework, using current user picture as input, face data array is defeated
Go out；
First face's determination module, if being not sky for face data array, judgement detects face, intercepts current user
Face's scope picture in photo, and remove noise image and obtain corresponding face picture；
Second face's determination module, if being sky for face data array, judgement is not detected by face, returns to obtain in real time and uses
Family photo；
The face data array includes：The shape of face's range data, the central point of face's critical organ and face's critical organ
State data.
10. real-time face according to claim 9 identifies login authentication system, it is characterised in that
The non-unit that first logs into includes：
One-dimensional processing module, for being replicated respectively by the OpenCV face's pictures for using current request login and each
The conventional face's picture processing arrived is one dimensional histograms；
Similar computing module, for calculating respectively, current request logs in the one dimensional histograms of the face's picture used and each is answered
Similarity between the one dimensional histograms for the conventional face's picture being made；
Average computation block, for averaging to obtain average similarity by all similarities being calculated；
Similar comparison module, for by average similarity compared with similarity threshold set in advance；If average similarity
Less than similarity threshold, then judge that current request logs in the face's picture used and verified by similarity comparison；It is if average similar
Degree is more than or equal to similarity threshold, then judges that current request logs in the face's picture used and do not verified by similarity comparison.
11. real-time face according to claim 10 identifies login authentication system, it is characterised in that described non-to first log into
Unit also includes：Module is cut, for current request to be logged in into what is used by OpenCV respectively in the one-dimensional processing module
Before face's picture and each conventional face's picture processing for replicating to obtain are one dimensional histograms, confirm that current request is stepped on respectively
Record the face's picture used and replicate the in the same size of obtained conventional face's picture with each；And
If it is inconsistent that current request logs in conventional face's picture size that the face's picture used obtains with the duplication currently contrasted,
Then the region of interest ROI part of the longer picture of the length of side is cut using OpenCV, without changing channel C OI interested
Part, current request is set to log in conventional face's picture size that the face's picture used obtains with the duplication currently contrasted consistent.
12. the real-time face identification login authentication system according to any one of claim 7 to 11, it is characterised in that institute
Stating system also includes：
First updating block, after the face's picture used for current request login is verified by similarity comparison, phase will be passed through
The face's picture used is logged in by OpenCV processing as histogram like the current request of degree contrast verification, and is stored and arrived native
In face database；Local face database is regularly updated, only retains conventional face's picture of the newest setting quantity of storage time；
Or
Second updating block, after the face's picture used for current request login is verified by similarity comparison, judge local
Exceed conventional face's picture of setting duration threshold value in face database with the presence or absence of storage duration；If in the presence of phase will be passed through
The face's picture used is logged in by OpenCV processing as histogram like the current request of degree contrast verification, and is stored and arrived native
Face database；And delete to store most long conventional face's picture of duration in local face database or store duration and surpass
Cross a conventional face picture of setting duration threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710456698.1A CN107358079A (en) | 2017-06-16 | 2017-06-16 | Real-time face identifies login validation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710456698.1A CN107358079A (en) | 2017-06-16 | 2017-06-16 | Real-time face identifies login validation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107358079A true CN107358079A (en) | 2017-11-17 |
Family
ID=60272787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710456698.1A Pending CN107358079A (en) | 2017-06-16 | 2017-06-16 | Real-time face identifies login validation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107358079A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145704A (en) * | 2018-06-14 | 2019-01-04 | 西安电子科技大学 | A kind of human face portrait recognition methods based on face character |
| CN109344588A (en) * | 2018-09-03 | 2019-02-15 | 平安科技（深圳）有限公司 | Safety certifying method and terminal device |
| CN109413495A (en) * | 2018-09-06 | 2019-03-01 | 广州虎牙信息科技有限公司 | A kind of login method, device, system, electronic equipment and storage medium |
| CN109815664A (en) * | 2018-12-21 | 2019-05-28 | 深圳科安达电子科技股份有限公司 | A method of the login railway dedicated system based on recognition of face |
| CN109818924A (en) * | 2018-12-21 | 2019-05-28 | 深圳科安达电子科技股份有限公司 | A kind of device of the login railway dedicated system based on recognition of face |
| CN110851457A (en) * | 2019-10-21 | 2020-02-28 | 广东优世联合控股集团股份有限公司 | Method for searching login information |
| CN113170045A (en) * | 2018-12-07 | 2021-07-23 | 索尼半导体解决方案公司 | Solid-state imaging device, solid-state imaging method, and electronic apparatus |
| CN113469012A (en) * | 2021-06-28 | 2021-10-01 | 广州云从鼎望科技有限公司 | Method, system, medium, and apparatus for user face-brushing verification |
| CN113469012B (en) * | 2021-06-28 | 2024-05-03 | 广州云从鼎望科技有限公司 | User face brushing verification method, system, medium and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116749A (en) * | 2013-03-12 | 2013-05-22 | 上海洪剑智能科技有限公司 | Near-infrared face identification method based on self-built image library |
| CN105335726A (en) * | 2015-11-06 | 2016-02-17 | 广州视源电子科技股份有限公司 | Face recognition confidence acquisition method and system |
| CN105844202A (en) * | 2015-01-12 | 2016-08-10 | 芋头科技（杭州）有限公司 | Image recognition system and method |
| CN105869235A (en) * | 2015-01-20 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Safe gate inhibition method and system thereof |
| CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
| CN106411856A (en) * | 2016-09-06 | 2017-02-15 | 北京交通大学 | Authentication method and apparatus based on face recognition of mobile terminal |
| CN106778764A (en) * | 2016-11-18 | 2017-05-31 | 安阳师范学院 | A kind of auxiliary first osteocomma conjugation methods based on color of image feature extraction |
-
2017
- 2017-06-16 CN CN201710456698.1A patent/CN107358079A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116749A (en) * | 2013-03-12 | 2013-05-22 | 上海洪剑智能科技有限公司 | Near-infrared face identification method based on self-built image library |
| CN105844202A (en) * | 2015-01-12 | 2016-08-10 | 芋头科技（杭州）有限公司 | Image recognition system and method |
| CN105869235A (en) * | 2015-01-20 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Safe gate inhibition method and system thereof |
| CN105335726A (en) * | 2015-11-06 | 2016-02-17 | 广州视源电子科技股份有限公司 | Face recognition confidence acquisition method and system |
| CN105938552A (en) * | 2016-06-29 | 2016-09-14 | 北京旷视科技有限公司 | Face recognition method capable of realizing base image automatic update and face recognition device |
| CN106411856A (en) * | 2016-09-06 | 2017-02-15 | 北京交通大学 | Authentication method and apparatus based on face recognition of mobile terminal |
| CN106778764A (en) * | 2016-11-18 | 2017-05-31 | 安阳师范学院 | A kind of auxiliary first osteocomma conjugation methods based on color of image feature extraction |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145704A (en) * | 2018-06-14 | 2019-01-04 | 西安电子科技大学 | A kind of human face portrait recognition methods based on face character |
| CN109344588A (en) * | 2018-09-03 | 2019-02-15 | 平安科技（深圳）有限公司 | Safety certifying method and terminal device |
| CN109413495A (en) * | 2018-09-06 | 2019-03-01 | 广州虎牙信息科技有限公司 | A kind of login method, device, system, electronic equipment and storage medium |
| CN113170045A (en) * | 2018-12-07 | 2021-07-23 | 索尼半导体解决方案公司 | Solid-state imaging device, solid-state imaging method, and electronic apparatus |
| CN113170045B (en) * | 2018-12-07 | 2023-11-21 | 索尼半导体解决方案公司 | Solid-state imaging device, solid-state imaging method, and electronic apparatus |
| CN109815664A (en) * | 2018-12-21 | 2019-05-28 | 深圳科安达电子科技股份有限公司 | A method of the login railway dedicated system based on recognition of face |
| CN109818924A (en) * | 2018-12-21 | 2019-05-28 | 深圳科安达电子科技股份有限公司 | A kind of device of the login railway dedicated system based on recognition of face |
| CN110851457A (en) * | 2019-10-21 | 2020-02-28 | 广东优世联合控股集团股份有限公司 | Method for searching login information |
| CN113469012A (en) * | 2021-06-28 | 2021-10-01 | 广州云从鼎望科技有限公司 | Method, system, medium, and apparatus for user face-brushing verification |
| CN113469012B (en) * | 2021-06-28 | 2024-05-03 | 广州云从鼎望科技有限公司 | User face brushing verification method, system, medium and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358079A (en) | Real-time face identifies login validation method and system | |
| CN105144156B (en) | Metadata is associated with the image in personal images set | |
| CN105024986B (en) | The methods, devices and systems that account number logs in | |
| US9378408B2 (en) | Assisted photo-tagging with facial recognition models | |
| CN105138985A (en) | Real-name authentication method based on WeChat public number and system | |
| US10803013B2 (en) | Efficient similarity detection | |
| CN104021467A (en) | Method and device for protecting payment security of mobile terminal and mobile terminal | |
| CN105554137B (en) | A kind of standby system and method | |
| CN106407078A (en) | An information interaction-based client performance monitoring device and method | |
| CN107203574A (en) | Data management and the polymerization of data analysis | |
| US11755708B2 (en) | Methods and systems for facilitating secure authentication of user based on known data | |
| CN110532529A (en) | A kind of recognition methods of file type and device | |
| CN106611313A (en) | A payment method, a terminal and a payment server | |
| US20150020167A1 (en) | System and method for managing files | |
| CN114925388A (en) | Method and device for deleting multiple copies of private information, electronic equipment and storage medium | |
| CN111260833A (en) | Binding and management method and device for access control card | |
| CN105718820A (en) | Anti-fake electronic seal system | |
| CN106330661A (en) | Data centralized processing method | |
| CN106331872A (en) | Message screening method and device in live broadcast interaction process | |
| CN107911443A (en) | A kind of session information processing method, device, server and readable storage medium storing program for executing | |
| CN110135190B (en) | Data management method, server and computer storage medium | |
| CN108198305A (en) | Airport quick security check method, readable storage medium storing program for executing and quick security check platform | |
| CN111666552A (en) | Personal information management system | |
| CN109634845A (en) | A kind of method and device generating context record text | |
| CN109656945A (en) | A kind of information processing method |
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: 20171117 |