CN109284597A - A kind of face unlocking method, device, electronic equipment and computer-readable medium - Google Patents
A kind of face unlocking method, device, electronic equipment and computer-readable medium Download PDFInfo
- Publication number
- CN109284597A CN109284597A CN201811400961.6A CN201811400961A CN109284597A CN 109284597 A CN109284597 A CN 109284597A CN 201811400961 A CN201811400961 A CN 201811400961A CN 109284597 A CN109284597 A CN 109284597A
- Authority
- CN
- China
- Prior art keywords
- image
- result
- face
- target image
- library
- 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
- G06V40/172—Classification, e.g. identification
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Abstract
The present invention provides a kind of face unlocking method, device, electronic equipment and computer-readable mediums, are related to the technical field of image procossing, this method comprises: obtaining the target image comprising face to be identified；If target image is RGB image, target image and the bottom RGB library image are compared by RGB identification model, obtain the first result；If target image is the IR image with speckle, target image and the bottom RGB library image are carried out by the first cross-module state identification model to obtain second as a result, the first result and the second result are used for determining whether face to be identified and default face are identical across modal idenlification；Determine whether to execute terminal device face unlock operation in conjunction with the In vivo detection result and objective result of face to be identified；Objective result includes: the first result or second as a result, the present invention alleviates existing face unlocking algorithm when being unlocked using the IR image with speckle, unlocks precision and the poor technical problem of accuracy.
Description
Technical field
The present invention relates to the technical fields of image procossing, more particularly, to a kind of face unlocking method, device, electronic equipment
And computer-readable medium.
Background technique
In existing face unlock scheme, while the face of RGB and infrared image being supported to unlock scheme.In light,
RGB picture is obtained using the preposition RGB camera (RGB Camera) of mobile device.In half-light or total darkness environment, utilization is red
Outer floodlight (IR Flood) cooperates preposition IR (Infrared Radiation) camera (IR Camera) to obtain IR picture,
And in this, as the input of face unlock.This hardware plan, which is gradually developed by hardware vendor, saves infrared floodlight, only stays
The hardware plan of the lower speckle projector (Projector).Hardware plan after differentiation, due to saving infrared floodlight, at
This is lower, simultaneously as supporting to project speckle on the image, therefore can obtain depth information abundant.
In the only hardware plan of the speckle projector, speckle projector quality, depth of exposure etc. cause picture quality compared with
Difference, and speckle information can seriously affect face key point information simultaneously, produce a very large impact to face algorithm.At this point, will
It will affect the precision and accuracy of face unlocking algorithm.
Summary of the invention
It can in view of this, the purpose of the present invention is to provide a kind of face unlocking method, device, electronic equipment and computers
Medium is read, to alleviate existing face unlocking algorithm when being unlocked using the IR image with speckle, unlock precision and accurate
Spend poor technical problem.
In a first aspect, the embodiment of the invention provides a kind of face unlocking methods, comprising: obtain comprising face to be identified
Target image；If the target image is RGB image, pass through RGB identification model for the target image and the bottom RGB library image
It is compared, obtains the first result；If the target image is the IR image with speckle, pass through the first cross-module state identification model
The target image and the bottom RGB library image are carried out to obtain second as a result, first result and described second across modal idenlification
As a result for determining whether face to be identified and default face are identical；In conjunction with the In vivo detection result and mesh of the face to be identified
Mark result determines whether to execute terminal device face unlock operation；The objective result includes: first result or institute
State the second result.
Further, determine whether in conjunction with the In vivo detection result and objective result of the face to be identified to terminal device
If executing face unlock operation includes: that the In vivo detection result passes through for In vivo detection, and first result is greater than first
Threshold value then executes face unlock operation to the terminal device；Alternatively, if the In vivo detection result passes through for In vivo detection,
And second result is greater than second threshold, then executes face unlock operation to the terminal device.
Further, the method also includes: if second result be more than or equal to second threshold, judge whether
In the presence of the bottom IR corresponding with target image library image；If it does not exist, and the target image meets the bottom IR library typing mark
Standard, then using the target image as the bottom IR library image.
Further, it is judged by the following manner whether the target image meets the bottom IR library typing standard, specifically includes:
Obtain the mass parameter of the target image；If the mass parameter of the target image meets preset quality parameter request, base
In vivo detection is carried out to the face to be identified in the target image；If In vivo detection result passes through, it is determined that the target
Image meets the bottom IR library typing standard.
Further, the method also includes: if second result be less than second threshold, and exist and the target pair
As the corresponding bottom IR library image, then the target image and the bottom IR library image are compared by the second cross-module state identification model
It is right, obtain third result；If the third result is more than or equal to third threshold value, face solution is executed to the terminal device
Lock operation.
Further, the method also includes: if second result be less than second threshold, and be not present and the target
The object corresponding bottom IR library image, it is determined that fail to the unlocking terminal equipment.
Further, the method also includes: obtain the original image of the photographic device shooting of the terminal device, and it is right
The original image carries out Face datection, obtains Face datection result；If determining the original based on the Face datection result
Face is not included in beginning image, it is determined that fail to the unlocking terminal equipment；If being determined based on the Face datection result
It include face in the original image, it is determined that get comprising the target image.
Further, the method also includes: detection of attribute is carried out to the face to be identified based on the target image,
Obtain detection of attribute result；If the detection of attribute result is that detection passes through, judge whether the target image is the band
The IR image of speckle；If the detection of attribute result is that detection does not pass through, it is determined that fail to the unlocking terminal equipment.
Further, judge that the target image whether be the IR image with speckle includes: to obtain default mark,
In, it is described it is default be identified as photographic device shoot generate after the target image for determine the target image whether be
The identification information of IR image with speckle；Determine whether the target image is the IR with speckle based on the default mark
Image.
Second aspect, the embodiment of the invention provides a kind of face trippers, comprising: acquiring unit, for obtaining packet
Target image containing face to be identified；Comparing unit passes through RGB identification model if being RGB image for the target image
The target image and the bottom RGB library image are compared, the first result is obtained；Cross-module state recognition unit, if being used for the mesh
Logo image is the IR image with speckle, then by the first cross-module state identification model by the target image and the bottom RGB library image into
Row obtains second as a result, first result and second result are used to determine face to be identified and preset across modal idenlification
Whether face is identical；Determination unit, in conjunction with the face to be identified In vivo detection result and objective result determine whether
Face unlock operation is executed to terminal device；The objective result includes: first result or second result.
The third aspect the embodiment of the invention provides a kind of electronic equipment, including memory, processor and is stored in described
On memory and the computer program that can run on the processor, the processor are realized when executing the computer program
Method described in any one of above-mentioned first aspect.
Fourth aspect, the embodiment of the invention provides a kind of meters of non-volatile program code that can be performed with processor
Calculation machine readable medium, said program code make the processor execute method described in any one of above-mentioned first aspect.
In embodiments of the present invention, the target image comprising face to be identified is obtained first；If target image is RGB figure
Target image and the bottom RGB library are then compared by RGB identification model, obtain the first result by picture；If target image is that band dissipates
Target image and the bottom RGB library image then obtain across modal idenlification by the IR image of spot by the first cross-module state identification model
Second result；Finally, the In vivo detection result and objective result according to face to be identified determine whether to terminal device executor
Face unlock operation.
As can be seen from the above description, it is unlocked for existing face unlocking algorithm using the IR image with speckle
When, precision and the poor technical problem of accuracy are unlocked, is RGB image and the IR image difference with speckle in the present embodiment
Provided with corresponding identification model, i.e., RGB image is identified by RGB identification model, passes through the first across modal idenlification mould
Type identifies the IR image with speckle, thus improve face unlock scheme to the processing capacity of the IR image with speckle,
Further improve face unlock precision and accuracy.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is the schematic diagram of a kind of electronic equipment according to an embodiment of the present invention；
Fig. 2 is a kind of flow chart of face unlocking method according to an embodiment of the present invention；
Fig. 3 is a kind of schematic diagram of IR image with speckle according to an embodiment of the present invention；
Fig. 4 is the flow chart of another face unlocking method according to an embodiment of the present invention；
Fig. 5 is a kind of schematic diagram of face tripper according to an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
Embodiment 1:
Firstly, describing the electronic equipment 100 for realizing the embodiment of the present invention referring to Fig.1, which can be used
In the face unlocking method of operation various embodiments of the present invention.
As shown in Figure 1, electronic equipment 100 includes one or more processors 102, one or more memories 104, input
Device 106, output device 108 and video camera 110, the connection machine that these components pass through bus system 112 and/or other forms
The interconnection of structure (not shown).It should be noted that the component and structure of electronic equipment 100 shown in FIG. 1 are only exemplary, rather than limit
Property, as needed, the electronic equipment also can have other assemblies and structure.
The processor 102 can use digital signal processor (DSP, Digital Signal Processing), show
Field programmable gate array (FPGA, Field-Programmable Gate Array), programmable logic array (PLA,
Programmable Logic Array) and ASIC (Application Specific Integrated Circuit) in
At least one example, in hardware realizes that the processor 102 can be central processing unit (CPU, Central Processing
Unit), graphics processor (GPU, Graphics Processing Unit) or have data-handling capacity and/or instruction hold
The processing unit of the other forms of row ability, and can control other components in the electronic equipment 100 to execute expectation
Function.
The memory 104 may include one or more computer program products, and the computer program product can be with
Including various forms of computer readable storage mediums, such as volatile memory and/or nonvolatile memory.It is described volatile
Property memory for example may include random access memory (RAM) and/or cache memory (cache) etc..It is described non-easy
The property lost memory for example may include read-only memory (ROM), hard disk, flash memory etc..On the computer readable storage medium
It can store one or more computer program instructions, processor 102 can run described program instruction, described below to realize
The embodiment of the present invention in the client functionality (realized by processor) and/or other desired functions.In the calculating
Various application programs and various data can also be stored in machine readable storage medium storing program for executing, such as the application program is used and/or produced
Raw various data etc..
The input unit 106 can be the device that user is used to input instruction, and may include keyboard, mouse, wheat
One or more of gram wind and touch screen etc..
The output device 108 can export various information (for example, image or sound) to external (for example, user), and
It and may include one or more of display, loudspeaker etc..
The video camera 110 is for carrying out Image Acquisition, wherein video camera target image collected passes through the face
Unlocking method obtained after being handled whether to terminal device execute face unlock operation as a result, for example, video camera can be with
The desired target image of user is shot, then, is obtained after which is handled by the face unlocking method
Whether to terminal device execute face unlock operation as a result, captured image can also be stored in the storage by video camera
For the use of other components in device 104.
Illustratively, the electronic equipment for realizing face unlocking method according to an embodiment of the present invention may be implemented as
The intelligent mobile terminals such as smart phone, tablet computer.
Embodiment 2:
According to embodiments of the present invention, a kind of embodiment of face unlocking method is provided, it should be noted that in attached drawing
The step of process illustrates can execute in a computer system such as a set of computer executable instructions, although also,
Logical order is shown in flow chart, but in some cases, it can be to be different from shown by sequence execution herein or retouch
The step of stating.
Fig. 2 is a kind of flow chart of face unlocking method according to an embodiment of the present invention, as shown in Fig. 2, this method includes
Following steps:
Step S202 obtains the target image comprising face to be identified.
Step S204 passes through RGB identification model for the target image and RGB if the target image is RGB image
Bottom library image is compared, and obtains the first result.
Step S206 passes through the first cross-module state identification model for institute if the target image is the IR image with speckle
It states target image and the bottom RGB library image carries out obtaining second as a result, first result and second result across modal idenlification
For determining whether face to be identified and default face are identical；As shown in Figure 3 is a kind of IR image with speckle.
Step S208 determines whether in conjunction with the In vivo detection result and objective result of the face to be identified to terminal device
Execute face unlock operation；The objective result includes: first result or second result.
As can be seen from the above description, it is unlocked for existing face unlocking algorithm using the IR image with speckle
When, precision and the poor technical problem of accuracy are unlocked, is RGB image and the IR image difference with speckle in the present embodiment
Provided with corresponding identification model, i.e., RGB image is identified by RGB identification model, passes through the first across modal idenlification mould
Type identifies the IR image with speckle, thus improve face unlock scheme to the processing capacity of the IR image with speckle,
Further improve face unlock precision and accuracy.
As can be seen from the above description, in the present embodiment, it is acquired first by the photographic device of terminal device for carrying out
The image of unlock.
Under the lights scene such as strong light, normal light, terminal device can shoot the RGB image of object to be identified, and use
The RGB image is unlocked.Under half-light, completely black scene, terminal device can shoot the IR figure with speckle of object to be identified
Then picture carries out face unlock using the IR picture with speckle.
It in the present embodiment, first can be with after getting target image (RGB image or IR image) with speckle
Whether judge in the target image comprising facial image.If not including facial image in the target image, face is directly returned
Unlock failure as a result, detailed process is described as follows:
Step S1011 obtains the camera shooting dress of the terminal device before obtaining the target image comprising face to be identified
The original image of shooting is set, and Face datection is carried out to the original image, obtains Face datection result；
Step S1012, if determining not including face in the original image based on the Face datection result, it is determined that
Fail to the unlocking terminal equipment；
Step S1013, if being determined in the original image based on the Face datection result comprising face, it is determined that obtain
It gets comprising the target image.
As can be seen from the above description, in the present embodiment, getting that terminal device takes for being unlocked
After original image, Face datection can be carried out to original image, whether to detect in original image comprising face.Optionally,
In the present embodiment, Face datection can be carried out to original image by Face datection model.
If the testing result of Face datection model is to include face in the original image, it is determined that get comprising wait know
The target image of others' face.Later, so that it may execute step described in above-mentioned steps S202 to step S208, that is, utilize target
Image executes unlock operation to terminal device.If the testing result of Face datection model is not include people in the original image
Face, it is determined that fail to unlocking terminal equipment.
By aforesaid operations, it can be avoided and the image execution above-mentioned steps S202 to step S208 for not including face is retouched
The step of stating can reject the image for not including face, to accomplish more accurately to carry out people before executing above-mentioned steps
Face unlock improves the efficiency of face unlock, further shortens the time of face unlock.
In the present embodiment, it determines in the target image based on the Face datection result comprising after face,
This method further includes following steps:
Step S11 carries out detection of attribute to the face to be identified based on the target image, obtains detection of attribute knot
Fruit；
Step S12 judges whether the target image is that the band dissipates if the detection of attribute result is that detection passes through
The IR image of spot；
Step S13, if the detection of attribute result is that detection does not pass through, it is determined that fail to the unlocking terminal equipment.
In the present embodiment, if being determined in original image based on Face datection model comprising face, it is determined that get
Target image comprising face to be identified.At this point it is possible to continue to carry out detection of attribute to the target image.
It is alternatively possible to carry out detection of attribute to the target image by detection of attribute model, detection of attribute result is obtained.
It should be noted that in the present embodiment, the underlying attribute parameter of detection of attribute includes: detection of closing one's eyes of opening eyes, occlusion detection, people
The detection of face position or face irradiating angle.
For example, if detecting in the target image, face to be identified is in closed-eye state, alternatively, detecting face to be identified
Left side face be blocked, at this point, determining that detection of attribute result does not pass through.If detection of attribute result is not pass through, really
It is fixed to fail to unlocking terminal equipment.If detection of attribute result is that detection passes through, judge whether target image is with speckle
IR image.
It should be noted that different property parameters can be arranged in detection of attribute model with the difference of practical application scene, this
It is not specifically limited in embodiment.
Optionally, judge whether the target image is that the IR image with speckle includes:
Firstly, obtaining default mark, wherein default be identified as after photographic device shoots the target image generates
For determine the target image whether be the IR image with speckle identification information；
Then, determine whether the target image is the IR image with speckle based on the default mark.
As can be seen from the above description, under the lights scene such as strong light, normal light, terminal device can shoot object to be identified
RGB image, and be unlocked using the RGB image.Under half-light, completely black scene, the image that terminal device takes is band
Then the IR image of speckle carries out face unlock using the IR picture with speckle.
In the picture pick-up device photographic subjects image of terminal device, which will be set automatically, wherein MG_
UNLOCK_IMG_NV21 indicates that the target image taken is not IR image, and MG_UNLOCK_IMG_IR_PATTERN indicates to clap
The target image taken the photograph is IR image.
For example, picture pick-up device is shot after obtaining target image, picture pick-up device under the lights scene such as strong light, normal light
By the default mark setting are as follows: MG_UNLOCK_IMG_NV21.Under half-light, completely black scene, picture pick-up device shoots to obtain target
After image, the default mark is arranged picture pick-up device are as follows: MG_UNLOCK_IMG_IR_PATTERN.
That is, it is MG_UNLOCK_IMG_ that the default mark, which can be arranged, in picture pick-up device automatically according to photographed scene
NV21 or MG_UNLOCK_IMG_IR_PATTERN.
Based on this, in the present embodiment, can judge whether the target image is the IR figure with speckle based on default mark
Picture.Under normal circumstances, after the photographic device of terminal device shoots to obtain target image, mode as described above is set
The default mark is set, and the default mark and target image are passed to together in the processor of terminal device and handled.At this point,
The processor of terminal device can judge whether the target image is the IR image with speckle according to the default mark.
If processor judges the default mark are as follows: MG_UNLOCK_IMG_IR_PATTERN then shows the target image
For the IR image to speckle.
As can be seen from the above description, target image includes two types, respectively RGB image and the IR image with speckle.
Above-mentioned two situations will be introduced respectively below.
Situation one, target image are RGB image
If target image is RGB image, target image and the bottom RGB library image are compared using RGB identification model,
Obtain the first result.Optionally, which can be a numerical value, for characterize target image and the bottom RGB library image it
Between similarity degree.Correspondingly, the corresponding threshold value of the RGB identification model, i.e. first threshold.
In the present embodiment, the bottom RGB library image can be the preparatory typing of user.For example, the terminal is arranged in user for the first time
When the unlock scheme of equipment, terminal device may remind the user that typing unlocks image accordingly.Terminal device is being got accordingly
Unlock image after, which can be detected, for example, carry out detection of attribute, comprising: open eyes close one's eyes detection,
Occlusion detection, the detection of face location or face irradiating angle.In another example whether can detecte in the image comprising face etc.
Deng.If to the unlock image detection by (that is, the unlock image meets the bottom RGB library typing standard), by the unlock image
As the bottom RGB library image.
Optionally, user can be opened with typing one or multiple bottom RGB library images, the present embodiment are not specifically limited.
After obtaining the bottom RGB library image in the manner described above, so that it may compare target image and the bottom RGB library image
It is right, obtain the first result, wherein the first result is wrapped in face included in target image and the bottom RGB library image for characterizing
Containing the similarity between face.
It should be noted that in the present embodiment, passing through if carrying out detection of attribute to target image, being also based on the mesh
Logo image carries out In vivo detection to face to be identified, obtains In vivo detection result.It is alternatively possible to pass through In vivo detection model pair
Target image is handled, to obtain In vivo detection result.
If the In vivo detection result passes through for In vivo detection, and first result is greater than first threshold, then to described
Terminal device executes face unlock operation.
Optionally, first threshold can be set according to practical application scene, and the present embodiment is not specifically limited.Example
Such as, it is 80% that first threshold, which can choose, it is also an option that being 75% etc..
That is, in the present embodiment, if being obtained after carrying out In vivo detection to face to be identified based on target image
It is that In vivo detection passes through as a result, and the first result for being obtained using RGB identification model be greater than first threshold (for example, 80%), then
It determines and face unlock operation is executed to terminal device.
Situation two, target image are the IR image with speckle
If target image is the IR image with speckle, utilize the first cross-module state identification model by target image and the bottom RGB
Library image is compared, and obtains the second result.Optionally, which can be a numerical value, for characterizing target image
Similarity degree between the image of the bottom RGB library.Correspondingly, the corresponding threshold value of the first cross-module state identification model, i.e. the second threshold
Value.
It should be noted that in the present embodiment, passing through if carrying out detection of attribute to target image, being also based on the mesh
Logo image carries out In vivo detection to face to be identified, obtains In vivo detection result.It is alternatively possible to pass through In vivo detection model pair
Target image is handled, to obtain In vivo detection result.
If the In vivo detection result passes through for In vivo detection, and second result is greater than second threshold, then to described
Terminal device executes face unlock operation.
Optionally, second threshold can be set according to practical application scene, and the present embodiment is not specifically limited.Example
Such as, it is 80% that second threshold, which can choose, it is also an option that being 75% etc..
That is, in the present embodiment, if being obtained after carrying out In vivo detection to face to be identified based on target image
It is that In vivo detection passes through as a result, and the second result for being obtained using the first cross-module state identification model be greater than second threshold (for example,
80%) it, is then determined based on the second result and face unlock operation is executed to terminal device.
In the present embodiment, this method further includes following steps:
Step S21 is judged whether there is and the target figure if second result is more than or equal to second threshold
As the corresponding bottom IR library image；
Step S22, if it does not exist, and the target image meets the bottom IR library typing standard, then makees the target image
For the bottom IR library image.
If the IR figure with speckle compares (that is, the second result is more than or equal to second threshold) by RGB-IR, judge
With the presence or absence of the bottom IR corresponding with target image library.If judging whether the IR image with speckle meets without the bottom IR library
The bottom IR library typing standard.If satisfied, then using target image as the bottom IR library.
As can be seen from the above description, in the present embodiment, if the target image that photographic device takes is with speckle
IR image, and the IR image with speckle meets the bottom IR library typing standard, and the user's also bottom non-typing IR library figure on the terminal device
Picture, then at this point it is possible to the IR image with speckle that photographic device is taken is as the bottom IR library image.
By aforesaid operations, does not need user and be manually entered the bottom IR library image, the bottom IR library image can be automatically stored, be used in combination
In subsequent face alignment, it is not necessarily to user's active typing.
Optionally, in the present embodiment, it can be judged by the following manner whether the target image meets the record of the bottom IR library
Enter standard, specifically include:
Obtain the mass parameter of the target image；
If the mass parameter of the target image meets preset quality parameter request, based on the target image to described
Face to be identified carries out In vivo detection；
If In vivo detection result passes through, it is determined that the target image meets the bottom IR library typing standard.
Specifically, in the present embodiment, firstly, obtaining the mass parameter of target image, wherein mass parameter can be more
Kind parameter, for example, the parameter of the fog-level (or readability) for characterizing target image, for characterizing in target image
The parameter of the location information of face to be identified, wherein the location information be face to be identified to the left, to the right, upwardly or downwardly
The angle of deflection.
If judging that target image meets preset quality parameter request based on mass parameter, treated based on target image
It identifies that face carries out In vivo detection, obtains In vivo detection result.If In vivo detection result is to pass through, it is determined that target image meets
The bottom IR library typing standard, and using the target image as the bottom IR library image.
In the present embodiment, this method further includes following steps:
If second result is less than second threshold, and there is the bottom IR corresponding with the target object in step S31
The target image and the bottom IR library image are then compared by the second cross-module state identification model, obtain third result by library；
If second result is less than second threshold, and the bottom IR corresponding with the target object is not present in step S32
Library, it is determined that fail to the unlocking terminal equipment.
Step S33 executes face solution to the terminal device if the third result is more than or equal to third threshold value
Lock operation；
Specifically, in the present embodiment, if after the first cross-module state identification model identifies the IR image with speckle,
Identification by (i.e. the second result is less than second threshold), does not then judge whether there is the target object corresponding bottom IR library image,
Wherein, the face that face is target object is preset.If there is the corresponding bottom IR library image, then pass through the second across modal idenlification mould
IR image with speckle is carried out image with the bottom IR library and is compared by type, obtains third result.If there is no corresponding IR
Bottom library image, it is determined that fail to unlocking terminal equipment.
Optionally, which can be a numerical value, for characterizing the phase between target image and the bottom IR library image
Like degree.Correspondingly, the corresponding threshold value of the two cross-modules state identification model, i.e. third threshold value.If third result is greater than or waits
In third threshold value, then face unlock operation is executed to terminal device.
It should be noted that above-mentioned first threshold, second threshold and third threshold value can be identical, it can be with difference, this
Embodiment is not specifically limited, and can select first threshold, the specific value of second threshold and third threshold value according to actual needs.
But by foregoing description, in the present embodiment, specific technical solution is mainly described as follows:
Typing RGB image guarantees bottom library quality, obtains best face alignment effect as bottom library under normal light scene.
Under the lights scene such as strong light, normal light, unlocked using target image row, it, will after judging target image RGB image
Target image is sent into RGB identification model and is identified, using RGB-RGB threshold value (first threshold), judges face to be identified and pre-
If whether face is the same person.
Under half-light, completely black scene, face unlock is done using the IR image with speckle, judges target image for speckle
After IR image, the IR image with speckle is sent into cross-module state identification model and is judged using RGB-IR threshold value (second threshold) wait know
Whether others' face and default face are the same persons.
For the IR image with speckle by unlock, after Quality estimation, the IR image by this with speckle is deposited automatically
The second bottom library for the bottom IR library image, when being compared as subsequent IR picture；If being sent into the band of algorithm under half-light, completely black scene
The IR image of speckle is compared with the bottom RGB library image not to succeed, then continues to be compared with the bottom IR library image, use IR-IR threshold
It is worth (third threshold value), judges whether face to be identified and default face are the same persons.
It as can be seen from the above description, should if the target image that photographic device takes is the IR image with speckle
When IR image with speckle is compared with the bottom RGB library image, comparing successful probability will be reduced.If user's preparatory typing
The bottom IR library image.By the way that the IR image with speckle to be compared with the bottom IR library image, the success rate of comparison can be improved,
To improve the unlock efficiency of terminal device, user experience is improved.Because when the target image that photographic device takes is that band dissipates
When the IR image of spot, show that scene locating for user can not probably take clearly RGB image, if being not provided with the bottom IR
Library image, this will lead to terminal device can not successful execution unlock operation, reduce the unlock efficiency of terminal device.
Benefit of the invention is that the advantage that existing RGB face algorithm has accumulated can be multiplexed, under light scene completely
The ability for reaching pure RGB algorithm, under half-light or completely black scene, the present invention is provided simultaneously with RGB-IR, IR-IR cross-module state face again
Unlock ability.
Fig. 4 is a kind of flow chart of face unlocking method according to an embodiment of the present invention, as shown in figure 4, this method includes
Following steps:
Step S401 obtains the original image of the photographic device shooting of terminal device；
Step S402 carries out Face datection to original image, obtains Face datection result；
Whether step S403 is judged in original image based on Face datection result comprising face；If so, thening follow the steps
S404；It is no to then follow the steps S417；
Step S404 carries out detection of attribute to face to be identified based on target image, obtains detection of attribute result；
Step S405 judges whether that detection passes through based on detection of attribute result；If so, thening follow the steps S406 and step
S414, it is no to then follow the steps S417；
Step S406 judges whether target image is the IR image with speckle；If so, thening follow the steps S408, otherwise hold
Row step S407；
Target image and the bottom RGB library image are compared by RGB identification model by step S407, obtain first as a result,
And after obtaining the first result, step S415 is executed；
Step S408 is carried out target image and the bottom RGB library image across modal idenlification by the first cross-module state identification model,
Obtain second as a result, and after obtaining the second result, execute step S409；
Step S409, judges whether the second result is greater than second threshold；If so, thening follow the steps S410, step is otherwise executed
Rapid S412；
Step S410 judges whether there is the bottom IR corresponding with target image library image；If so, thening follow the steps
S411；Otherwise, step S415 is executed；
Step S411 using target image as the bottom IR library image, and is held if target image meets the bottom IR library typing standard
Row step S415；
Step S412 judges whether there is the bottom IR corresponding with target image library image；If so, thening follow the steps
S413；It is no to then follow the steps S415；
Target image and the bottom IR library image are compared by the second cross-module state identification model by step S413, obtain
Three results；And execute step S415；
Step S414 carries out In vivo detection to face to be identified based on target image, obtains In vivo detection result；
Step S415 determines whether to execute terminal device face unlock behaviour based on In vivo detection result and objective result
Make, wherein objective result includes: the first result, the second result and third result；If so, thening follow the steps S416, otherwise execute
Step S417；
Step S416, to unlocking terminal equipment success；
Step S417 fails to unlocking terminal equipment.
As can be seen from the above description, in the present embodiment, getting that terminal device takes for being unlocked
After original image, Face datection can be carried out to original image, whether to detect in original image comprising face.Optionally,
In the present embodiment, Face datection can be carried out to original image by Face datection model.
Embodiment 3:
The embodiment of the invention also provides a kind of face tripper, which is mainly used for executing the present invention
Face unlocking method provided by embodiment above content below makees specifically face tripper provided in an embodiment of the present invention
It introduces.
Fig. 5 is a kind of schematic diagram of face tripper according to an embodiment of the present invention, as shown in figure 5, the face unlocks
Device mainly includes acquiring unit 10, comparing unit 20, cross-module state recognition unit 30 and determination unit 40, in which:
Acquiring unit 10, for obtaining the target image comprising face to be identified；
Comparing unit 20 passes through RGB identification model for the target figure if being RGB image for the target image
Picture and the bottom RGB library image are compared, and obtain the first result；
Cross-module state recognition unit 30 passes through the first cross-module state if being the IR image with speckle for the target image
Identification model carries out the target image and the bottom RGB library image across modal idenlification, obtain second as a result, first result and
Second result is for determining whether face to be identified and default face are identical；
Determination unit 40, in conjunction with the face to be identified In vivo detection result and objective result determine whether to end
End equipment executes face unlock operation；The objective result includes: first result or second result.
As can be seen from the above description, it is unlocked for existing face unlocking algorithm using the IR image with speckle
When, precision and the poor technical problem of accuracy are unlocked, is RGB image and the IR image difference with speckle in the present embodiment
Provided with corresponding identification model, i.e., RGB image is identified by RGB identification model, passes through the first across modal idenlification mould
Type identifies the IR image with speckle, thus improve face unlock scheme to the processing capacity of the IR image with speckle,
Further improve face unlock precision and accuracy.
Optionally it is determined that unit is used for: if the In vivo detection result passes through for In vivo detection, and first result is big
In first threshold, then face unlock operation is executed to the terminal device；Alternatively, if the In vivo detection result is In vivo detection
Pass through, and second result is greater than second threshold, then face unlock operation is executed to the terminal device.
Optionally, described device is also used to: if second result is more than or equal to second threshold, judging whether to deposit
In the bottom IR corresponding with target image library image；If it does not exist, and the target image meets the bottom IR library typing standard,
Then using the target image as the bottom IR library image.
Optionally, described device is judged by the following manner whether the target image meets the bottom IR library typing standard, tool
Body includes: the mass parameter for obtaining the target image；It is wanted if the mass parameter of the target image meets preset quality parameter
It asks, then In vivo detection is carried out to the face to be identified based on the target image；If In vivo detection result passes through, it is determined that institute
It states target image and meets the bottom IR library typing standard.
Optionally, described device is also used to: if second result is less than second threshold, and being existed and the target object
The corresponding bottom IR library image is then compared the target image and the bottom IR library image by the second cross-module state identification model
It is right, obtain third result；If the third result is more than or equal to third threshold value, face solution is executed to the terminal device
Lock operation.
Optionally, described device is also used to: if second result is less than second threshold, and being not present and the target pair
As the corresponding bottom IR library image, it is determined that fail to the unlocking terminal equipment.
Optionally, described device is also used to: obtaining the original image of the photographic device shooting of the terminal device, and to institute
It states original image and carries out Face datection, obtain Face datection result；If being determined based on the Face datection result described original
Face is not included in image, it is determined that fail to the unlocking terminal equipment；If determining institute based on the Face datection result
It states in original image comprising face, it is determined that get comprising the target image.
Optionally, described device is also used to: being carried out detection of attribute to the face to be identified based on the target image, is obtained
To detection of attribute result；If the detection of attribute result is that detection passes through, judge whether the target image is that the band dissipates
The IR image of spot；If the detection of attribute result is that detection does not pass through, it is determined that fail to the unlocking terminal equipment.
Optionally, described device is also used to: obtaining default mark；Determine that the target image is based on the default mark
No is the IR image with speckle.
The technical effect and preceding method embodiment phase of device provided by the embodiment of the present invention, realization principle and generation
Together, to briefly describe, Installation practice part does not refer to place, can refer to corresponding contents in preceding method embodiment.
In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, of the invention
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the present invention
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can be with
Store the medium of program code.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (12)
1. a kind of face unlocking method characterized by comprising
Obtain the target image comprising face to be identified；
If the target image is RGB image, the target image and the bottom RGB library image are carried out by RGB identification model
It compares, obtains the first result；
If the target image is the IR image with speckle, by the first cross-module state identification model by the target image and
The bottom RGB library image carries out obtaining second as a result, first result and second result are used to determine wait know across modal idenlification
Whether others' face and default face are identical；
Determine whether to execute terminal device face unlock in conjunction with the In vivo detection result and objective result of the face to be identified
Operation；The objective result includes: first result or second result.
2. the method according to claim 1, wherein in conjunction with the In vivo detection result and mesh of the face to be identified
Mark result determines whether that face unlock operation is executed to terminal device includes:
If the In vivo detection result passes through for In vivo detection, and first result is greater than first threshold, then to the terminal
Equipment executes face unlock operation；Or
If the In vivo detection result passes through for In vivo detection, and second result is greater than second threshold, then to the terminal
Equipment executes face unlock operation.
3. the method according to claim 1, wherein the method also includes:
If second result is more than or equal to second threshold, IR corresponding with the target image is judged whether there is
Bottom library image；
If it does not exist, and the target image meets the bottom IR library typing standard, then using the target image as the bottom IR library
Image.
4. according to the method described in claim 3, it is characterized in that, being judged by the following manner whether the target image meets
The bottom IR library typing standard, specifically includes:
Obtain the mass parameter of the target image；
If the mass parameter of the target image meets preset quality parameter request, based on the target image to described wait know
Others carries out In vivo detection by face；
If In vivo detection result passes through, it is determined that the target image meets the bottom IR library typing standard.
5. the method according to claim 1, wherein the method also includes:
If second result is less than second threshold, and there is the bottom IR corresponding with target object library image, then pass through
The target image and the bottom IR library image are compared second cross-module state identification model, obtain third result；
If the third result is more than or equal to third threshold value, face unlock operation is executed to the terminal device.
6. according to the method described in claim 5, it is characterized in that, the method also includes:
If second result is less than second threshold, and the bottom IR corresponding with target object library image is not present, then really
It is fixed to fail to the unlocking terminal equipment.
7. the method according to claim 1, wherein the method also includes:
The original image of the photographic device shooting of the terminal device is obtained, and Face datection is carried out to the original image, is obtained
To Face datection result；
If determining not including face in the original image based on the Face datection result, it is determined that the terminal device
Unlock failure；
If being determined in the original image based on the Face datection result comprising face, it is determined that get comprising the mesh
Logo image.
8. the method according to the description of claim 7 is characterized in that the method also includes:
Detection of attribute is carried out to the face to be identified based on the target image, obtains detection of attribute result；
If the detection of attribute result is that detection passes through, judge whether the target image is the IR image with speckle；
If the detection of attribute result is that detection does not pass through, it is determined that fail to the unlocking terminal equipment.
9. according to the method described in claim 8, it is characterized in that, judging whether the target image is the IR with speckle
Image includes:
Acquisition, which is preset, to be identified, wherein the default photographic device that is identified as shoots being used for really for target image generation later
The fixed target image whether be the IR image with speckle identification information；
Determine whether the target image is the IR image with speckle based on the default mark.
10. a kind of face tripper characterized by comprising
Acquiring unit, for obtaining the target image comprising face to be identified；
Comparing unit passes through RGB identification model for the target image and RGB if being RGB image for the target image
Bottom library image is compared, and obtains the first result；
Cross-module state recognition unit passes through the first across modal idenlification mould if being the IR image with speckle for the target image
Type carries out the target image and the bottom RGB library image across modal idenlification, obtains second as a result, first result and described the
Two results are for determining whether face to be identified and default face are identical；
Determination unit, in conjunction with the face to be identified In vivo detection result and objective result determine whether to terminal device
Execute face unlock operation；The objective result includes: first result or second result.
11. a kind of electronic equipment, including memory, processor and it is stored on the memory and can transports on the processor
Capable computer program, which is characterized in that the processor realizes the claims 1 to 9 when executing the computer program
Any one of described in method.
12. a kind of computer-readable medium for the non-volatile program code that can be performed with processor, which is characterized in that described
Program code makes the processor execute method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811400961.6A CN109284597A (en) | 2018-11-22 | 2018-11-22 | A kind of face unlocking method, device, electronic equipment and computer-readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811400961.6A CN109284597A (en) | 2018-11-22 | 2018-11-22 | A kind of face unlocking method, device, electronic equipment and computer-readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109284597A true CN109284597A (en) | 2019-01-29 |
Family
ID=65173134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811400961.6A Pending CN109284597A (en) | 2018-11-22 | 2018-11-22 | A kind of face unlocking method, device, electronic equipment and computer-readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284597A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110462693A (en) * | 2019-06-28 | 2019-11-15 | 深圳市汇顶科技股份有限公司 | Door lock and recognition methods |
| CN112861764A (en) * | 2021-02-25 | 2021-05-28 | 广州图语信息科技有限公司 | Face recognition living body judgment method |
| CN112861583A (en) * | 2019-11-27 | 2021-05-28 | 深圳市万普拉斯科技有限公司 | Face verification method, electronic device and readable storage medium |
| CN113516089A (en) * | 2021-07-27 | 2021-10-19 | 中国平安人寿保险股份有限公司 | Face image recognition method, device and equipment and readable storage medium |
| CN113536953A (en) * | 2021-06-22 | 2021-10-22 | 浙江吉利控股集团有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN113673286A (en) * | 2020-05-15 | 2021-11-19 | 深圳市光鉴科技有限公司 | Depth reconstruction method, system, device and medium based on target area |
| WO2022032549A1 (en) * | 2020-08-11 | 2022-02-17 | 中国科学院自动化研究所 | Anti-counterfeiting facial detection method, system and apparatus based on cross-modality conversion assistance |
| CN113536953B (en) * | 2021-06-22 | 2024-04-19 | 浙江吉利控股集团有限公司 | Face recognition method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964056A (en) * | 2010-10-26 | 2011-02-02 | 徐勇 | Bimodal face authentication method with living body detection function and system |
| CN103400108A (en) * | 2013-07-10 | 2013-11-20 | 北京小米科技有限责任公司 | Face identification method and device as well as mobile terminal |
| CN106909905A (en) * | 2017-03-02 | 2017-06-30 | 中科视拓（北京）科技有限公司 | A kind of multi-modal face identification method based on deep learning |
| CN107105217A (en) * | 2017-04-17 | 2017-08-29 | 深圳奥比中光科技有限公司 | Multi-mode depth calculation processor and 3D rendering equipment |
| CN107169483A (en) * | 2017-07-12 | 2017-09-15 | 深圳奥比中光科技有限公司 | Tasks carrying based on recognition of face |
| CN108197585A (en) * | 2017-12-13 | 2018-06-22 | 北京深醒科技有限公司 | Recognition algorithms and device |
| CN108804895A (en) * | 2018-04-28 | 2018-11-13 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN108805024A (en) * | 2018-04-28 | 2018-11-13 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
-
2018
- 2018-11-22 CN CN201811400961.6A patent/CN109284597A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964056A (en) * | 2010-10-26 | 2011-02-02 | 徐勇 | Bimodal face authentication method with living body detection function and system |
| CN103400108A (en) * | 2013-07-10 | 2013-11-20 | 北京小米科技有限责任公司 | Face identification method and device as well as mobile terminal |
| CN106909905A (en) * | 2017-03-02 | 2017-06-30 | 中科视拓（北京）科技有限公司 | A kind of multi-modal face identification method based on deep learning |
| CN107105217A (en) * | 2017-04-17 | 2017-08-29 | 深圳奥比中光科技有限公司 | Multi-mode depth calculation processor and 3D rendering equipment |
| CN107169483A (en) * | 2017-07-12 | 2017-09-15 | 深圳奥比中光科技有限公司 | Tasks carrying based on recognition of face |
| CN108197585A (en) * | 2017-12-13 | 2018-06-22 | 北京深醒科技有限公司 | Recognition algorithms and device |
| CN108804895A (en) * | 2018-04-28 | 2018-11-13 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
| CN108805024A (en) * | 2018-04-28 | 2018-11-13 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable storage medium and electronic equipment |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110462693A (en) * | 2019-06-28 | 2019-11-15 | 深圳市汇顶科技股份有限公司 | Door lock and recognition methods |
| CN110462693B (en) * | 2019-06-28 | 2022-04-22 | 深圳市汇顶科技股份有限公司 | Door lock and identification method |
| CN112861583A (en) * | 2019-11-27 | 2021-05-28 | 深圳市万普拉斯科技有限公司 | Face verification method, electronic device and readable storage medium |
| CN113673286A (en) * | 2020-05-15 | 2021-11-19 | 深圳市光鉴科技有限公司 | Depth reconstruction method, system, device and medium based on target area |
| CN113673286B (en) * | 2020-05-15 | 2024-04-16 | 深圳市光鉴科技有限公司 | Depth reconstruction method, system, equipment and medium based on target area |
| WO2022032549A1 (en) * | 2020-08-11 | 2022-02-17 | 中国科学院自动化研究所 | Anti-counterfeiting facial detection method, system and apparatus based on cross-modality conversion assistance |
| CN112861764A (en) * | 2021-02-25 | 2021-05-28 | 广州图语信息科技有限公司 | Face recognition living body judgment method |
| CN112861764B (en) * | 2021-02-25 | 2023-12-08 | 广州图语信息科技有限公司 | Face recognition living body judging method |
| CN113536953A (en) * | 2021-06-22 | 2021-10-22 | 浙江吉利控股集团有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN113536953B (en) * | 2021-06-22 | 2024-04-19 | 浙江吉利控股集团有限公司 | Face recognition method and device, electronic equipment and storage medium |
| CN113516089A (en) * | 2021-07-27 | 2021-10-19 | 中国平安人寿保险股份有限公司 | Face image recognition method, device and equipment and readable storage medium |
| CN113516089B (en) * | 2021-07-27 | 2024-04-12 | 中国平安人寿保险股份有限公司 | Face image recognition method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284597A (en) | A kind of face unlocking method, device, electronic equipment and computer-readable medium | |
| JP7004017B2 (en) | Object tracking system, object tracking method, program | |
| US10824849B2 (en) | Method, apparatus, and system for resource transfer | |
| US11210541B2 (en) | Liveness detection method, apparatus and computer-readable storage medium | |
| WO2019128508A1 (en) | Method and apparatus for processing image, storage medium, and electronic device | |
| US8836777B2 (en) | Automatic detection of vertical gaze using an embedded imaging device | |
| CN103428428B (en) | Image capturing device and image catching method | |
| WO2016127437A1 (en) | Live body face verification method and system, and computer program product | |
| CN110135246A (en) | A kind of recognition methods and equipment of human action | |
| CN109684951A (en) | Face identification method, bottom library input method, device and electronic equipment | |
| CN108805047A (en) | A kind of biopsy method, device, electronic equipment and computer-readable medium | |
| CN102096805B (en) | Apparatus and method for registering plurality of facial images for face recognition | |
| WO2021228134A1 (en) | Identification method and device | |
| WO2021114814A1 (en) | Human body attribute recognition method and apparatus, electronic device and storage medium | |
| WO2007105768A1 (en) | Face-image registration device, face-image registration method, face-image registration program, and recording medium | |
| CN107395957B (en) | Photographing method and device, storage medium and electronic equipment | |
| EP3518522B1 (en) | Image capturing method and device | |
| CN111414858B (en) | Face recognition method, target image determining device and electronic system | |
| CN107424266A (en) | The method and apparatus of recognition of face unblock | |
| CN106603968A (en) | Information processing apparatus and information processing method | |
| CN109618149A (en) | Test method, device and the smart machine of equipment image quality | |
| JP2015106197A (en) | Image processing device and image processing method | |
| CN109214324A (en) | Most face image output method and output system based on polyphaser array | |
| CN106980527A (en) | Start method, device and the intelligent terminal of fingerprint recognition | |
| CN108596122A (en) | A kind of auth method, device, authentication machine and computer-readable 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: 20190129 |