CN109034004A - A kind of identity verification method and device based on recognition of face - Google Patents
A kind of identity verification method and device based on recognition of face Download PDFInfo
- Publication number
- CN109034004A CN109034004A CN201810732920.0A CN201810732920A CN109034004A CN 109034004 A CN109034004 A CN 109034004A CN 201810732920 A CN201810732920 A CN 201810732920A CN 109034004 A CN109034004 A CN 109034004A
- Authority
- CN
- China
- Prior art keywords
- image
- threshold value
- checked
- identity
- comparison threshold
- 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
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
Abstract
The present invention provides a kind of identity verification method and device based on recognition of face, comprising: obtains the visible images and gray level image of target to be checked；Using current daylighting situation as foundation, the first comparison threshold value corresponding with current daylighting situation and the second comparison threshold value are obtained in the database；Judge whether the first coincidence factor between the first pre-stored image stored in visible images and database is greater than the first comparison threshold value；If the first coincidence factor is greater than the first comparison threshold value, judge whether the second coincidence factor between the second pre-stored image stored in gray level image and database is greater than the second comparison threshold value；If the second coincidence factor is greater than the second comparison threshold value, it is determined that the identity of target to be checked is legal.As it can be seen that implementing above-mentioned method can be improved the precision of recognition of face.
Description
Technical field
The present invention relates to field of image recognition, in particular to a kind of identity checking method based on recognition of face and
Device.
Background technique
With the continuous development of science and technology, biometrics identification technology also continuous progress therewith, among these, face
Identification technology develops especially rapid.Face recognition technology is substantially a kind of based on the progress identification of face characteristic information
A kind of biological identification technology, therefore in terms of identification and verifying, face recognition technology has advantageous advantage.
However, it has been found in practice that although face recognition technology development very rapidly, still exist because time of occurrence is still short
Many problems need to solve, wherein the problem of accuracy is then one of the greatest problem that face recognition technology is faced.
Summary of the invention
In view of the above problems, the present invention provides a kind of identity verification method and device based on recognition of face, Neng Gouti
The precision of high recognition of face.
To achieve the goals above, the present invention adopts the following technical scheme that: (modifying referring to claim)
In a first aspect, the present invention provides a kind of identity checking method based on recognition of face, the identity checking method
The following steps are included:
Obtain the visible images and gray level image of target to be checked；
Using current daylighting situation as foundation, the first comparison threshold value corresponding with the current daylighting situation and second are obtained
Comparison threshold value；
Judge whether the first coincidence factor between the visible images and pre-stored first pre-stored image is greater than
One comparison threshold value；
If first coincidence factor is greater than the first comparison threshold value, judge that the gray level image is pre- with pre-stored second
Deposit whether the second coincidence factor between image is greater than second comparison threshold value；
If second coincidence factor is greater than second comparison threshold value, it is determined that the identity of the target to be checked is legal.
As an alternative embodiment, judge second coincidence factor be greater than second comparison threshold value it
Afterwards, the method also includes:
Using ultraviolet light as foundation, judge whether the target to be checked is living body；
If living body, then the legal step of the identity of the determination target to be checked is executed.
As an alternative embodiment, it is described using ultraviolet light as foundation, judge whether the target to be checked is living body
The step of, comprising:
Obtain first the second ultraviolet image of ultraviolet image 548C；
Judge whether first ultraviolet image and second ultraviolet image meet preset living body graphics standard；
If meeting, determine that the target to be checked is living body, and the identity for executing the determination target to be checked is legal
The step of；
If not meeting, export for prompting the illegal warning information of identity.
As an alternative embodiment, judging that first ultraviolet image and second ultraviolet image meet
After preset living body graphics standard, the method also includes:
Using first ultraviolet image and second ultraviolet image as foundation, stereoscopic face image is generated；
Judge whether the third coincidence factor of the stereoscopic face image and default stereoscopic face image is greater than preset coincidence
Rate threshold value；
If more than then executing the legal step of the identity of the determination target to be checked.
As an alternative embodiment, the visible images and gray level image for obtaining target to be checked the step of
Later, the method also includes:
Whether judge the first area accounting of facial image that the visible images include in the visible images
Greater than default first area ratio；
If the first area accounting is greater than default first area ratio, the face figure that the gray level image includes is judged
As whether the second area accounting in the gray level image is greater than default second area ratio；
If the second area accounting is greater than default second area ratio, execute it is described with current daylighting situation be according to
According to the step of obtaining the first comparison threshold value corresponding with the current daylighting situation and the second comparison threshold value.
As an alternative embodiment, judge the second area accounting be greater than default second area ratio it
Afterwards, the method also includes:
Judge whether the first area accounting and the accounting difference of the second area accounting are less than preset difference value；
If the accounting difference is less than preset difference value, described using current daylighting situation as foundation, middle acquisition and institute are executed
The step of stating corresponding first comparison threshold value of current daylighting situation and the second comparison threshold value.
Second aspect, the identity based on recognition of face that the present invention provides a kind of veritify device, and the identity veritifies device
Including photographic device and the computing device being connected with the photographic device, and the computing device includes database, wherein
The photographic device is for obtaining current daylighting situation, the visible images of target to be checked and the target to be checked
Gray level image；
The computing device is used for using the current daylighting situation as foundation, is obtained in the database and described current
Corresponding first comparison threshold value of daylighting situation and the second comparison threshold value, and judging the visible images and the data
The first coincidence factor between the first pre-stored image stored in library is greater than the first comparison threshold value and the gray level image and the number
When being greater than second comparison threshold value according to the second coincidence factor between the second pre-stored image pre-stored in library, determine it is described to
The identity for examining target is legal.
As an alternative embodiment, the photographic device is binocular camera and including optical-filter switcher,
In,
The optical-filter switcher is used to switch the type that the photographic device receives light, so that the photographic device obtains
Take ultraviolet image.
The third aspect, the present invention provides a kind of computer equipment, including memory and processor, the memory is used
In storage computer program, the processor runs the computer program so that the computer equipment executes first aspect public affairs
The identity checking method based on recognition of face opened.
Fourth aspect, the present invention provides a kind of computer readable storage mediums, are stored in above-mentioned computer equipment
The used computer program.
The identity checking method based on recognition of face provided according to the present invention, can obtain the visible light figure of target to be checked
Picture and gray level image, and according to current daylighting situation, the reduced parameter for meeting current daylighting situation is transferred in the database,
When so that visible images and gray level image are compared with the default portrait stored in database, using reduced parameter as foundation,
Judge whether the image of target to be detected matches with default portrait, to judge whether target to be checked is legal object.
As it can be seen that implement this embodiment, can by it is multiple it is multispectral multi-level inspection is carried out to target to be checked, and use
Gray level image can improve resolving ability in the case where insufficient light, therefore, implement this embodiment, can effectively mention
The precision of high recognition of face.
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
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of the scope of the invention.
Fig. 1 is the flow diagram for the identity checking method based on recognition of face that the embodiment of the present invention one provides；
Fig. 2 is the flow diagram of the identity checking method provided by Embodiment 2 of the present invention based on recognition of face；
Fig. 3 is the structural schematic diagram that the identity based on recognition of face that the embodiment of the present invention three provides veritifies device；
Fig. 4 is a kind of structural schematic diagram for binocular camera that the embodiment of the present invention three provides.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
For the problems of the prior art, the present invention provides a kind of identity checking method based on recognition of face, the body
Part method of calibration can obtain the visible images and gray level image of current daylighting situation and target to be checked, and according to current
Daylighting situation, the reduced parameter for meeting current daylighting situation is transferred in the database, so that visible images and gray level image
With reduced parameter be according to being compared with the default portrait stored in database, thus judge target to be detected image whether
Match with default portrait, and then and judges whether target to be checked is legal object.As it can be seen that implementing this embodiment, energy
It is enough to realize the multispectral inspection of colored gray scale, to guarantee the resolving ability under any light conditions, and then effectively improve people
The precision of face identification.
Wherein, above-mentioned technical method can also be realized using relevant software or hardware, in this present embodiment
No longer add to repeat.For the identity verification method and device based on recognition of face, it is described below by embodiment.
Embodiment 1
Referring to Fig. 1, Fig. 1 is a kind of process signal of identity checking method based on recognition of face provided in this embodiment
Figure.
As shown in Figure 1, identity checking method of this kind based on recognition of face the following steps are included:
S101, the visible images and gray level image for obtaining target to be checked.
In the present embodiment, the executing subject of the step can veritify device or other tools for the identity based on recognition of face
There is the electronic equipment of more mesh cameras.
In the present embodiment, more mesh cameras refer to that imaging sensor quantity is not less than 2 cameras, wherein work as acquisition
Spectrum picture quantity is greater than imaging sensor quantity, then optical-filter switcher (IRCUT) has can be set in imaging sensor.Citing
For, if two imaging sensors will acquire four width images, each imaging sensor will be provided with optical filter switching
Device, so that imaging sensor can carry out the switching between two optical filters by optical-filter switcher, to complete four width figures
The acquisition of picture.Wherein spectrum picture quantity refers to the number of species under different wavelengths of light, and the shooting number of non-image sensor
Amount.
In the present embodiment, more mesh cameras are preferably binocular camera.
In the present embodiment, target to be checked is visiting subscriber or user to be checked etc., therefore visible target to be checked is usually
People.On the other hand, target to be checked is also possible to other objects, only this method meeting when checking that target to be checked is other objects
It sounds an alarm.
In the present embodiment, it is seen that light is the appreciable part of human eye in electromagnetic spectrum, it is seen that spectrum does not have accurate model
It encloses；The wavelength of the appreciable electromagnetic wave of the eyes of common people is between 400~760nm, but there are also some to perceive
Electromagnetic wave of the wavelength about between 380~780nm.Wherein in the present embodiment, it is seen that the wave-length coverage of light takes 380~780nm.
As it can be seen that visible images are the multispectral images that multi-wavelength is in that the band of 380~780nm is composed.
In the present embodiment, multispectral image refers to the image comprising many bands, and (redgreenblue is color for only 3 bands sometimes
Chromatic graph picture is exactly an example), but can actually be more, even up to a hundred bands are also that can form piece image.So
And each band is a width gray level image among these, it can represent generate the band sensor scene brightness, and this
Scape brightness is obtained according to the susceptibility of the sensor of the band.
In the present embodiment, gray level image refers to the image of each only one sample color of pixel.This kind of image usually may be used
To show most dark black to the gray scale between most bright white, this is allowed for theoretically, any face in this sampling
Color can be different the depth, it might even be possible to be different brightness.Wherein, gray level image is different from black white image, in computer
Black white image only has two kinds of colors of black and white in image domains, and there are many more the colors of grade between black and white for gray level image
Depth.
In the present embodiment, gray level image, which can be, to be acquired by Single wavelength imaging sensor.
S102, using current daylighting situation as foundation, obtain corresponding with current daylighting situation the first comparison threshold value and the
Two comparison threshold values.
As an alternative embodiment, being obtained corresponding with current daylighting situation using current daylighting situation as foundation
The first comparison threshold value and the second comparison threshold value, comprising:
Using current daylighting situation as foundation, the first comparison threshold value corresponding with current daylighting situation is obtained in the database
With the second comparison threshold value.
Implement this embodiment, the position of data storage can be limited, stored, facilitated with unified database
The calling of data, to improve the efficiency of step completion and the efficiency of identity veritification.
Light in the present embodiment, when current daylighting situation is above-mentioned more mesh camera acquisition visible images and gray level image
According to situation；Wherein, which can be acquired by more mesh cameras, obtain by other instruments
It arrives, to not being limited in any way in this present embodiment.
In the present embodiment, database is pre-set, wherein database includes different daylighting situations corresponding first
Comparison threshold value and the second comparison threshold value, meanwhile, the first pre-stored image and the second pre-stored image is also stored in database.
In the present embodiment, the first pre-stored image and the second pre-stored image should be one group of pre-stored image, this group of pre-stored image
The target being mapped to is the same person.Meanwhile first pre-stored image be visible light type image, the second pre-stored image be gray scale
The image of type.
In the present embodiment, the first comparison threshold value is used in current daylighting, judges whether visible images are effective
Threshold value；Similarly, the second comparison threshold value is used in current daylighting, judges the whether effective threshold value of gray level image.
For example, when daylighting is in bad order, the first comparison threshold value can reduction appropriate, and the second comparison threshold value
It can be adjusted as the case may be, wherein the adjustment requirement of the second comparison threshold value is higher than the first comparison threshold value.Most cases
Under, the first comparison threshold value is adjusted according to daylighting situation, and the second comparison threshold value is without adjustment.
S103, judge whether the first coincidence factor between visible images and pre-stored first pre-stored image is greater than
One comparison threshold value, if more than S104 is thened follow the steps；If being not more than, terminate this process.
In the present embodiment, the first pre-stored image can be the image being stored in advance in the database.
In the present embodiment, the first coincidence factor refer in visible images in the portrait of target to be checked and the first pre-stored image to
Examine the ratio being overlapped between the portrait of target, wherein whether first coincidence factor is competent person for characterizing for inspection personnel.
As an alternative embodiment, the first pre-stored image stored in judging visible images and database it
Between the first coincidence factor whether be greater than before the first comparison threshold value, this method further include:
The portrait size in visible images and the first pre-stored image is adjusted, so that visible images and the first pre-stored image
In portrait size it is essentially identical.
Implement this embodiment, visible images and the first pre-stored image can be made to be compared under conditions of waiting big
It is right, to improve the efficiency and accuracy of comparison.
S104, judge whether the second coincidence factor between gray level image and pre-stored second pre-stored image is greater than second
Comparison threshold value, if more than S105 is thened follow the steps；If being not more than, terminate this process.
In the present embodiment, the second pre-stored image can be the image being stored in advance in the database.
In the present embodiment, the second coincidence factor refers in visible images in the portrait and the second pre-stored image of target to be checked
The ratio being overlapped between the portrait of target to be checked, wherein whether second coincidence factor is competent person for characterizing for inspection personnel.
In the present embodiment, image when gray level image under single wavelength, have it is apparent comparative, therefore, can be bright
It spends in insufficient situation and keeps contrast effect.
In the present embodiment, the second pre-stored image, which can be, to be stored directly in database, is also possible to pre- according to first
Deposit what image was converted to, to not being limited in any way in this present embodiment.
S105, determine that the identity of target to be checked is legal.
In the present embodiment, determine that target to be checked is legal it may be considered that being to authenticate successfully.
As shown in Figure 1, the identity checking method based on recognition of face provided according to the present invention, it can be according to target to be checked
Visible images and gray level image and current daylighting situation automatically judge, acquire corresponding contrast threshold
Value can also carry out multiple alignment according to above-mentioned comparison threshold value, thus realization pair after getting corresponding comparison threshold value
The identification for the target to be checked for including in visible images and gray level image, and then judge whether target to be checked is legitimate targets.It can
See, implement this embodiment, effective recognition of face can be carried out in different daylightings, and by multiple multispectral
Comparison, the accuracy of recognition of face can be effectively improved, it is also possible to effectively improve the universal range of recognition of face
And use scope.
Embodiment 2
Referring to Fig. 2, Fig. 2 is a kind of process signal of identity checking method based on recognition of face provided in this embodiment
Figure.As shown in Fig. 2, should identity checking method based on recognition of face the following steps are included:
S201, the visible images and gray level image for obtaining target to be checked.
S202, judge whether the first area accounting of facial image that visible images include in visible images is greater than
Default first area ratio, if so, thening follow the steps S203；If it is not, thening follow the steps 213.
For example, by the first imaging sensor of above-mentioned binocular camera and switching optical filter, visible light is acquired
Image, and judge whether comprising face in image, and judge whether the accounting of face and image is greater than 45% (default first area
Ratio).
Implement this embodiment, the too small situation of portrait can be effectively avoided and occur, it is remote so as to avoid
Shooting or interference shooting equally likely possibility, avoid Identification of Images from mistake occur.
S203, to judge whether the second area accounting of facial image that gray level image includes in gray level image is greater than default
Second area ratio, if so, thening follow the steps S204；If it is not, thening follow the steps S213.
In the present embodiment, with step S202, implement this embodiment it is possible to prevente effectively from the situation for avoiding portrait too small
Occur, so as to avoid wide-long shot or interference shooting equally likely possibility, Identification of Images is avoided mistake occur.
S204, judge whether the first area accounting and the accounting difference of second area accounting are less than preset difference value, if so,
Execute step S205；If it is not, thening follow the steps S213.
Implement this embodiment, it is possible to determine that whether is the face size in the face and gray level image in visible images
It is similar, it alarms if dissimilar, if similar, assert that visible images and gray level image are available.
S205, using current daylighting situation as foundation, in the database obtain it is corresponding with current daylighting situation first pair
Than threshold value and the second comparison threshold value.
Corresponding first comparison threshold value and the second contrast threshold in the case of various daylightings are stored in the present embodiment, in database
Value, is already mentioned above as the purposes of the first comparison threshold value and the second comparison threshold value, then no longer adds to repeat herein.
S206, judge whether the first coincidence factor between visible images and pre-stored first pre-stored image is greater than
One comparison threshold value, if more than S207 is thened follow the steps；If being not more than, S213 is thened follow the steps.
In the present embodiment, the first pre-stored image for prestoring storage is stored in database, wherein database can be
Store the virtual bench of mass data, or the entity apparatus for storing mass data, it is any to not making in this present embodiment
It limits.
Implement this embodiment, it can be determined that whether the face in visible images is the face stored in database.
S207, judge whether the second coincidence factor between gray level image and pre-stored second pre-stored image is greater than second
Comparison threshold value, if more than S208~S209 is thened follow the steps；If being not more than, S213 is thened follow the steps.
Implement this embodiment, can by comparison of light and shade and gray scale situation come the face of further target to be checked whether
It is the Gray Face stored in database.
In the present embodiment, pre-stored second pre-stored image is stored in database, as database, above
It has been described, will not be described in great detail herein.
S208, the first ultraviolet image and the second ultraviolet image are obtained.
In the present embodiment, binocular camera obtains ultraviolet image by optical-filter switcher and built-in imaging sensor.
Wherein, optical filter can be 395nm-UV optical filter.
S209, judge whether the first ultraviolet image and the second ultraviolet image meet preset living body graphics standard, if meeting,
Then follow the steps S210~S211；If not meeting, S213 is thened follow the steps.
For example, by imaging sensor and switching optical filter, 395nm image (the first ultraviolet image and second are acquired
Ultraviolet image), and judge the skins such as the face for including in above-mentioned 395nm image and skin speckle, texture, pore in the face
Skin characteristic, and judge whether above-mentioned skin properties meet the standard of living body true man.
Implement this embodiment, preliminary living body can be carried out and determined, to improve the order of accuarcy of recognition of face.
S210, determine that target to be checked is living body, and using the first ultraviolet image and the second ultraviolet image as foundation, generate three-dimensional
Facial image.
Implement this embodiment, one can be constructed based on the 3D face under UV spectrum.
S211, judge whether the third coincidence factor of stereoscopic face image and default stereoscopic face image is greater than default coincidence factor
Threshold value, if more than S212 is thened follow the steps；If being not more than, S213 is thened follow the steps.
It in the present embodiment, is compared by 3D facial image, further increases the In vivo detection accuracy rate of target to be checked, thus
Improve the order of accuarcy of recognition of face.
S212, determine that the identity of target to be checked is legal.
S213, output are for prompting the illegal warning information of identity.
In the present embodiment, warning information can may be video information for voice messaging, to not making in this present embodiment
Any restriction.
For example, switching optical filter of this method built in by binocular camera and binocular camera acquires visible light
The gray level image of image and 850nm, and judge in visible images whether to include face, it whether include face in gray level image,
Whether the accounting of face and default facial image in visible images is greater than the face in 45% and gray level image and presets
Whether the accounting of facial image is greater than 45%.When including face in visible images, gray level image includes face, and visible light figure
The accounting of face and default facial image as in is greater than 45%, and the accounting of face and default facial image in gray level image is big
When 45%, judge the pixel difference of the facial image in the face and gray level image in visible images whether less than 20%, i.e.,
Guarantee that the facial image size of two kinds of images is almost of the same size.After this, two figures for including by binocular sensor
As sensor and switching optical filter (395nm-UV light), two width 395nm images are acquired, and judge whether wrap in above-mentioned two images
Containing face, and obtain skin speckle in two width 395nm images, texture, the skin properties such as pore meet whether living body true man
Standard, and in the case where meeting living body true man's standard, one is constructed based on the 3D face under UV spectrum, with the 3D face
To be examined to complete the identity based on recognition of face according to stereoscopic face image inspection is carried out.Meanwhile by above step
Living body faces identification can be completed, and visible images, gray level image, two width 395nm images and 3D can also be collected
Face.
As shown in Fig. 2, the identity checking method based on recognition of face provided according to the present invention, it can be according to target to be checked
Visible images and gray level image and current daylighting situation automatically judge, acquire corresponding contrast threshold
Value can also carry out multiple alignment according to above-mentioned comparison threshold value, thus realization pair after getting corresponding comparison threshold value
The identification for the target to be checked for including in visible images and gray level image, and then judge whether target to be checked is legitimate targets.It can
See, implement this embodiment, effective recognition of face can be carried out in different daylightings, and by multiple multispectral
Comparison, the accuracy of recognition of face can be effectively improved, it is also possible to effectively improve the universal range of recognition of face
And use scope.
Embodiment 3
Referring to Fig. 3, Fig. 3 is the structure that a kind of identity based on recognition of face provided in an embodiment of the present invention veritifies device
Schematic diagram.
As shown in figure 3, should based on recognition of face identity veritify device, including photographic device 301 and with photographic device 301
The computing device 302 being connected, and computing device 302 includes database, wherein and photographic device 301 is currently adopted for obtaining
The gray level image of light situation, the visible images of target to be checked and target to be checked.
In the present embodiment, photographic device 301 can be binocular camera, and it includes two images which, which is a kind of,
The camera of sensor.
As shown in figure 4, photographic device 301 can be a kind of binocular camera, and the structure of the binocular camera can be as
Shown in Fig. 4, it is seen then that the binocular camera includes two imaging sensors, including left sensor and right sensor, wherein
Left sensor and right sensor can include that ultraviolet light (395nm) switches optical filter.
In the present embodiment, connection relationship between computing device 302 and photographic device 301 can be with communication connection, can also be with
Connect line, to not being limited in any way in this present embodiment.
It include database in computing device 302 in the present embodiment, which is also used as a memory module and carries out
Work.Wherein, the first pre-stored image, the second pre-stored image, the first comparison threshold value and the second comparison are stored in the database
Threshold value.
In the present embodiment, the available current daylighting situation of photographic device 301, specifically, photographic device 301 can pass through
Built-in camera lens or other devices carry out the acquisition of current daylighting situation.
In the present embodiment, photographic device 301 is used to obtain the visible of target to be checked by two built-in imaging sensors
The gray level image of light image and target to be checked.
Computing device 302 is used for using current daylighting situation as foundation, is obtained in the database opposite with current daylighting situation
The first comparison threshold value and the second comparison threshold value answered, and first stored in judging visible images and database prestores figure
The first coincidence factor as between is greater than between the second pre-stored image stored in the first comparison threshold value and gray level image and database
The second coincidence factor be greater than the second comparison threshold value when, determine that the identity of target to be checked is legal.
As an alternative embodiment, photographic device 301 can also include optical-filter switcher, wherein
Optical-filter switcher be used for switch photographic device 301 receive light type so that photographic device 301 obtain it is ultraviolet
Image.
Implement this embodiment, should veritify device based on the identity of recognition of face can carry out living body by ultraviolet image
Detection, to further improve the accuracy of recognition of face.
In addition, the computer equipment may include smart phone, put down the present invention also provides another computer equipment
Plate computer, vehicle-mounted computer, intelligent wearable device etc..The computer equipment includes memory and processor, and memory can be used for depositing
Store up computer program, processor by running above-mentioned computer program, thus make computer equipment execute the above method or on
State the function of each unit in device.
Memory may include storing program area and storage data area, wherein storing program area can storage program area, at least
Application program needed for one function (such as sound-playing function, image player function etc.) etc.；Storage data area can store root
Created data (such as audio data, phone directory etc.) etc. are used according to computer equipment.In addition, memory may include height
Fast random access memory, can also include nonvolatile memory, a for example, at least disk memory, flush memory device,
Or other volatile solid-state parts.
The present embodiment additionally provides a kind of computer storage medium, for storing calculating used in above-mentioned computer equipment
Machine program.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and structure in attached drawing
Figure shows the system frame in the cards of the device of multiple embodiments according to the present invention, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of above-mentioned module, section or code includes one or more for implementing the specified logical function
Executable instruction.It should also be noted that function marked in the box can also be to be different from the implementation as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that in structure chart and/or flow chart
The combination of each box and the box in structure chart and/or flow chart, can function or movement as defined in executing it is dedicated
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
In addition, each functional module or unit in each embodiment of the present invention can integrate one independence of formation together
Part, be also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
If described function is realized and when sold or used as an independent product in the form of software function module, can
To be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially or
Say that the part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, it should
Computer software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
Smart phone, personal computer, server or network equipment etc.) execute the complete of method described by each embodiment of the present invention
Portion or part steps.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 store journey
The medium of sequence code.
Content described above, only a specific embodiment of the invention, but protection scope of the present invention is not limited to
In this, anyone skilled in the art in the technical scope disclosed by the present invention, can readily occur in variation or replace
It changes, should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
Subject to.
Claims (10)
1. a kind of identity checking method based on recognition of face, which is characterized in that the identity checking method the following steps are included:
Obtain the visible images and gray level image of target to be checked；
Using current daylighting situation as foundation, obtains the first comparison threshold value corresponding with the current daylighting situation and second and compare
Threshold value；
Judge whether the first coincidence factor between the visible images and pre-stored first pre-stored image is greater than first pair
Compare threshold value；
If first coincidence factor is greater than the first comparison threshold value, judge that the gray level image and pre-stored second prestores figure
Whether the second coincidence factor as between is greater than second comparison threshold value；
If second coincidence factor is greater than second comparison threshold value, it is determined that the identity of the target to be checked is legal.
2. identity checking method according to claim 1, which is characterized in that
After judging that second coincidence factor is greater than second comparison threshold value, the method also includes:
Using ultraviolet light as foundation, judge whether the target to be checked is living body；
If living body, then the legal step of the identity of the determination target to be checked is executed.
3. identity checking method according to claim 2, which is characterized in that it is described using ultraviolet light as foundation, described in judgement
The step of whether target to be checked is living body, comprising:
Obtain the first ultraviolet image and the second ultraviolet image；
Judge whether first ultraviolet image and second ultraviolet image meet preset living body graphics standard；
If meeting, determine that the target to be checked is living body, and the step that the identity for executing the determination target to be checked is legal
Suddenly；
If not meeting, export for prompting the illegal warning information of identity.
4. identity checking method according to claim 3, which is characterized in that judging first ultraviolet image and institute
It states after the second ultraviolet image meets preset living body graphics standard, the method also includes:
Using first ultraviolet image and second ultraviolet image as foundation, stereoscopic face image is generated；
Judge whether the third coincidence factor of the stereoscopic face image and default stereoscopic face image is greater than preset coincidence factor threshold
Value；
If more than then executing the legal step of the identity of the determination target to be checked.
5. identity checking method according to claim 1, which is characterized in that in the visible light figure for obtaining target to be checked
After the step of picture and gray level image, the method also includes:
Judge whether the first area accounting of facial image that the visible images include in the visible images is greater than
Default first area ratio；
If the first area accounting is greater than default first area ratio, the facial image for judging that the gray level image includes exists
Whether the second area accounting in the gray level image is greater than default second area ratio；
If the second area accounting is greater than default second area ratio, execution is described using current daylighting situation as foundation, obtains
The step of taking the first comparison threshold value corresponding with the current daylighting situation and the second comparison threshold value.
6. identity checking method according to claim 5, which is characterized in that judging that the second area accounting is greater than
After default second area ratio, the method also includes:
Judge whether the first area accounting and the accounting difference of the second area accounting are less than preset difference value；
If the accounting difference is less than preset difference value, execution is described using current daylighting situation as foundation, and middle acquisition is worked as with described
The step of corresponding first comparison threshold value of preceding daylighting situation and the second comparison threshold value.
7. a kind of identity based on recognition of face veritifies device, which is characterized in that it includes photographic device that the identity, which veritifies device,
The computing device being connected with the photographic device, and the computing device includes database, wherein
The photographic device is used to obtain the gray scale of current daylighting situation, the visible images of target to be checked and the target to be checked
Image；
The computing device is used to obtain and the current daylighting in the database using the current daylighting situation as foundation
Corresponding first comparison threshold value of situation and the second comparison threshold value, and in judging the visible images and the database
The first coincidence factor between first pre-stored image of storage is greater than the first comparison threshold value and the gray level image and the database
In the second coincidence factor between pre-stored second pre-stored image when being greater than second comparison threshold value, determine the mesh to be checked
Target identity is legal.
8. identity according to claim 7 veritifies device, which is characterized in that the photographic device is binocular camera and packet
Include optical-filter switcher, wherein
The optical-filter switcher is used to switch the type that the photographic device receives light, so that the photographic device obtains purple
Outer image.
9. a kind of computer equipment, which is characterized in that including memory and processor, the memory is for storing computer
Program, the processor runs the computer program so that the computer equipment executes according to claim 1 to any in 6
The identity checking method based on recognition of face described in.
10. a kind of computer readable storage medium, which is characterized in that it is stored in computer equipment as claimed in claim 9
Used computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732920.0A CN109034004A (en) | 2018-07-05 | 2018-07-05 | A kind of identity verification method and device based on recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732920.0A CN109034004A (en) | 2018-07-05 | 2018-07-05 | A kind of identity verification method and device based on recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109034004A true CN109034004A (en) | 2018-12-18 |
Family
ID=64640486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810732920.0A Pending CN109034004A (en) | 2018-07-05 | 2018-07-05 | A kind of identity verification method and device based on recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109034004A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222663A (en) * | 2019-06-13 | 2019-09-10 | 红鼎互联(广州)信息科技有限公司 | A kind of identity verification method and device based on recognition of face |
| CN110298243A (en) * | 2019-05-22 | 2019-10-01 | 深圳壹账通智能科技有限公司 | Testimony verification method, apparatus, computer equipment and computer readable storage medium |
| CN110532957A (en) * | 2019-08-30 | 2019-12-03 | 北京市商汤科技开发有限公司 | Face identification method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639891A (en) * | 2008-07-28 | 2010-02-03 | 汉王科技股份有限公司 | Double-camera face identification device and method |
| KR20130054767A (en) * | 2011-11-17 | 2013-05-27 | 주식회사 에스원 | Multiple biometrics apparatus and method thereof |
| CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
| CN105530422A (en) * | 2014-09-30 | 2016-04-27 | 联想(北京)有限公司 | Electronic equipment, control method thereof, and control device |
| CN105718863A (en) * | 2016-01-15 | 2016-06-29 | 北京海鑫科金高科技股份有限公司 | Living-person face detection method, device and system |
| CN106778636A (en) * | 2016-12-22 | 2017-05-31 | 东软集团股份有限公司 | Auth method and device |
| CN107909063A (en) * | 2017-12-22 | 2018-04-13 | 天津科技大学 | Bio-identification video playback attack detection method based on grey scale change |
| CN108009531A (en) * | 2017-12-28 | 2018-05-08 | 北京工业大学 | A kind of face identification method of more tactful antifraud |
-
2018
- 2018-07-05 CN CN201810732920.0A patent/CN109034004A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101639891A (en) * | 2008-07-28 | 2010-02-03 | 汉王科技股份有限公司 | Double-camera face identification device and method |
| KR20130054767A (en) * | 2011-11-17 | 2013-05-27 | 주식회사 에스원 | Multiple biometrics apparatus and method thereof |
| CN103136533A (en) * | 2011-11-28 | 2013-06-05 | 汉王科技股份有限公司 | Face recognition method and device based on dynamic threshold value |
| CN105530422A (en) * | 2014-09-30 | 2016-04-27 | 联想(北京)有限公司 | Electronic equipment, control method thereof, and control device |
| CN105718863A (en) * | 2016-01-15 | 2016-06-29 | 北京海鑫科金高科技股份有限公司 | Living-person face detection method, device and system |
| CN106778636A (en) * | 2016-12-22 | 2017-05-31 | 东软集团股份有限公司 | Auth method and device |
| CN107909063A (en) * | 2017-12-22 | 2018-04-13 | 天津科技大学 | Bio-identification video playback attack detection method based on grey scale change |
| CN108009531A (en) * | 2017-12-28 | 2018-05-08 | 北京工业大学 | A kind of face identification method of more tactful antifraud |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298243A (en) * | 2019-05-22 | 2019-10-01 | 深圳壹账通智能科技有限公司 | Testimony verification method, apparatus, computer equipment and computer readable storage medium |
| CN110222663A (en) * | 2019-06-13 | 2019-09-10 | 红鼎互联(广州)信息科技有限公司 | A kind of identity verification method and device based on recognition of face |
| CN110532957A (en) * | 2019-08-30 | 2019-12-03 | 北京市商汤科技开发有限公司 | Face identification method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103024165B (en) | Method and device for automatically setting shooting mode | |
| CN103383723B (en) | Method and system for spoof detection for biometric authentication | |
| CN105933589B (en) | A kind of image processing method and terminal | |
| CN110569808A (en) | Living body detection method and device and computer equipment | |
| CN112288663A (en) | Infrared and visible light image fusion method and system | |
| CN112487922B (en) | Multi-mode human face living body detection method and system | |
| CN109376592A (en) | Biopsy method, device and computer readable storage medium | |
| CN109034004A (en) | A kind of identity verification method and device based on recognition of face | |
| CN110162462A (en) | Test method, system and the computer equipment of face identification system based on scene | |
| CN108629293B (en) | Self-adaptive near-infrared iris image acquisition method with feedback mechanism | |
| CN110532746B (en) | Face checking method, device, server and readable storage medium | |
| EP3493538B1 (en) | Color calibration device, color calibration system, color calibration hologram, color calibration method, and program | |
| CN112487921A (en) | Face image preprocessing method and system for living body detection | |
| CN111582238A (en) | Living body detection method and device applied to face shielding scene | |
| CN107690804A (en) | A kind of image processing method and user terminal | |
| CN111598065A (en) | Depth image acquisition method, living body identification method, apparatus, circuit, and medium | |
| CN103888663A (en) | Image processing apparatus, image pickup apparatus and image processing method | |
| CN110276831A (en) | Constructing method and device, equipment, the computer readable storage medium of threedimensional model | |
| CN113411507B (en) | Skin measurement image acquisition method, device, equipment and storage medium | |
| CN106920266B (en) | The Background Generation Method and device of identifying code | |
| CN116055895B (en) | Image processing method and device, chip system and storage medium | |
| WO2018150554A1 (en) | Pulse wave measuring device, mobile terminal device, and pulse wave measuring method | |
| CN112926367A (en) | Living body detection equipment and method | |
| CN109145855A (en) | A kind of method for detecting human face and device | |
| CN108875472A (en) | Image collecting device and face auth method based on the image collecting device |
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: 20181218 |