CN110337656A

CN110337656A - For the optical sensor of recognition of face, device, method and electronic equipment

Info

Publication number: CN110337656A
Application number: CN201980000833.9A
Authority: CN
Inventors: 吴勇辉; 潘雷雷
Original assignee: Shenzhen Huiding Technology Co Ltd
Current assignee: Shenzhen Goodix Technology Co Ltd
Priority date: 2019-05-27
Filing date: 2019-05-27
Publication date: 2019-10-15
Also published as: WO2020237483A1

Abstract

It is a kind of for the optical sensor of recognition of face, device, method and electronic equipment, it is able to ascend the safety of recognition of face, this is used for the optical sensor of recognition of face, it include: pixel array, the first pixel unit set in the pixel array is for receiving the reflected light signal reflected by least two optical signals that light source successively emits from face, and at least two facial images are obtained according to the reflected light signal, wherein, at least two optical signal corresponds to different wavelength bands, and at least two facial image is for determining the true and false of the face.

Description

For the optical sensor of recognition of face, device, method and electronic equipment

Technical field

This application involves technical field of face recognition, and pass more particularly, to a kind of optics for recognition of face Sensor, device, method and electronic equipment.

Background technique

Safe and convenient and fast user experience is brought to user using the electronic equipment of face recognition technology still to pass through The human face data of the forgeries such as user picture (for example, printing or electronics) or made 3D face mold is face A security risk in identification application.Therefore, how to identify true and false face, with promoted the safety of recognition of face be one urgently Problem to be solved.

Summary of the invention

The embodiment of the present application provides a kind of for the optical sensor of recognition of face, device, method and electronic equipment, energy Identify the true and false of face, enough so as to promote the safety of recognition of face.

In a first aspect, providing a kind of optical sensor for recognition of face, comprising:

Pixel array, the first pixel unit set in the pixel array are successively emitted at least for receiving by light source The reflected light signal that two kinds of optical signals are reflected from face, and at least two facial images are obtained according to the reflected light signal, In, at least two optical signal corresponds to different wavelength bands, and at least two facial image is for determining the face It is true and false.

In some possible implementations, at least two optical signal include the first optical signal, the second optical signal and Third optical signal, wherein first optical signal corresponds to first band range, and second optical signal corresponds to second band model It encloses, the third optical signal corresponds to third wavelength band, the first band range, the second band range and the third Wavelength band is different two-by-two；At least two facial image includes the first facial image, the second facial image and third face Image, respectively corresponds first optical signal, second optical signal and the third optical signal, first facial image, Second facial image and the third facial image are for determining the true and false of the face.

In some possible implementations, the first band range, the second band range and the third wave One of respectively following three kinds of wavelength bands of segment limit: the wavelength band including 560nm, the wavelength band including 980nm, Wavelength band including 940nm.

In some possible implementations, the pixel unit in the first pixel unit set is not provided with optical filter.

In some possible implementations, other in the pixel array in addition to the first pixel unit set Pixel unit is not provided with optical filter, or the optical filter of setting specific band range.

In some possible implementations, the optical filter of the specific band range be include 940nm wavelength band Optical filter.

In some possible implementations, the first pixel unit set includes the part picture in the pixel array Plain unit.

In some possible implementations, the quantity of the pixel unit in the first pixel unit set and the picture The ratio of the total quantity of pixel unit in pixel array is less than the first ratio.

In some possible implementations, pixel unit in the first pixel unit set is discrete be distributed in it is described In pixel array.

In some possible implementations, the quantity of continuous pixel unit is less than in the first pixel unit set Or it is equal to specific threshold.

In some possible implementations, the first pixel unit set includes whole pictures in the pixel array Plain unit.

In some possible implementations, other in the pixel array in addition to the first pixel unit set The facial image of pixel unit acquisition is used for recognition of face.

Second aspect provides a kind of device for recognition of face, comprising:

Such as the optical sensor of the recognition of face in first aspect to second aspect and its any possible implementation；

Light source, for successively emitting at least two optical signals, at least two optical signal corresponds to different wavelength bands；

Wherein, the first pixel unit set of the optical sensor be used to receive the light source successively emits it is described extremely The reflected light signal that few two kinds of optical signals are reflected from face, and at least two facial images are obtained according to the reflected light signal, At least two facial image is for determining the true and false of the face.

In some possible implementations, the light source is specifically used for:

Successively emit the first optical signal, the second optical signal and third optical signal to the face, wherein the first light letter Number corresponding first band range, second optical signal correspond to second band range, and the third optical signal corresponds to third wave band Range, the first band range, the second band range and the third wavelength band are different two-by-two.

In some possible implementations, the light source is a light source, the optical signal that the light source can emit Wavelength band includes the first band range, the second band range and third wavelength band.

In some possible implementations, the light source includes the first sub-light source, the second sub-light source and third sub-light source, It is respectively used to emit the first band range, the optical signal of the second band range and the third wavelength band.

In some possible implementations, described device further include:

Light source control module successively emits first optical signal to the face for controlling the light source, and described Two optical signals and the third optical signal.

In some possible implementations, the optical sensor is specifically used for:

First optical signal, the second optical signal and third optical signal are successively received by the first pixel unit set The reflected light signal reflected respectively from the face, and the first facial image is obtained according to the reflected light signal respectively, second Facial image and third facial image.

In some possible implementations, described device further include:

Processor, for according to first facial image, second facial image and the third facial image to be true Determine the true and false of the face.

In some possible implementations, the processor is also used to:

According to calibration parameter, to first facial image, second facial image and the third facial image into Row calibration；

According to first facial image after calibration, second facial image and the third facial image determine institute State the true and false of face.

In some possible implementations, the processor is also used to:

According to references object to the first band range, the light of the second band range and the third wavelength band Relationship between the response of spectrum determines the calibration parameter.In some possible implementations, the optical sensor is also used In:

Successively emit the first band range, the second band range and institute to the references object in the light source When stating the optical signal of third wavelength band, three width images of the references object are acquired respectively；

The processor is also used to:

According to the relationship of the pixel value of the three width image, determine the calibration parameter, the calibration parameter be used for so that The pixel value of the three width image is in same range.

In some possible implementations, the processor is also used to:

According to first facial image after calibration, second facial image and the third facial image are closed At obtaining colorized face images, wherein each pixel in the colorized face images includes the face to the first wave Three response pixel values of the spectrum of segment limit, the second band range and the third wavelength band；

The colorized face images are subjected to feature extraction, obtain the characteristic information of the colorized face images；

According to the characteristic information of the colorized face images, the true and false of the face is determined.

In some possible implementations, the processor is specifically used for:

According to sampled pixel values of the first pixel unit in the first pixel unit set in first facial image, Determine the corresponding first response pixel value of the first pixel in the colorized face images, wherein the first response pixel value Indicate response of the face to the spectrum of the first band range, first pixel corresponds to first pixel unit；

According to sampled pixel values of the first pixel unit in the first pixel unit set in second facial image, Determine the corresponding second response pixel value of first pixel, wherein the second response pixel value indicates the face to institute State the response of the spectrum of second band range；And

According to sampled pixel values of the first pixel unit in the first pixel unit set in the third facial image, Determine the corresponding third response pixel value of first pixel, wherein the third response pixel value indicates the face to institute State the response of the spectrum of third wavelength band.

In some possible implementations, the processor is specifically used for:

It is handled by characteristic information of the deep learning network to the colorized face images, determines the true of the face It is false.

In some possible implementations, the processor is also used to:

According to the face of other pixel units acquisition in the pixel array in addition to the first pixel unit set Image carries out recognition of face.

In some possible implementations, the processor is specifically used for:

By the face figure of other pixel units acquisition in the pixel array in addition to the first pixel unit set As being matched with the facial image template of registration, determine whether recognition of face succeeds.

In some possible implementations, the processor is also used to:

The case where in the facial image and the facial image template matching registered and the face is real human face Under, determine recognition of face success.

The third aspect provides a kind of method for recognition of face, which comprises

When light source successively emits at least two optical signals, successively connect by the first pixel unit set of optical sensor The reflected light signal that at least two optical signal is reflected from the face is received, and obtains at least two according to the reflected light signal A facial image, wherein at least two optical signal corresponds to different wavelength bands；

The true and false of the face is determined according at least two facial image.

In some possible implementations, the light source successively emits at least two optical signals to face, comprising:

The light source successively emits the first optical signal, the second optical signal and third optical signal to the face, wherein described First optical signal corresponds to first band range, and second optical signal corresponds to second band range, and the third optical signal is corresponding Third wavelength band.

In some possible implementations, the first band range, the second band range and the third wave Segment limit is respectively one of following three kinds of wavelength bands:

Wavelength band including 560nm, the wavelength band including 980nm, the wavelength band including 940nm.

In some possible implementations, the method also includes:

It controls the light source and successively emits first optical signal, second optical signal and the third to the face Optical signal.

It is described that institute is successively received by the first pixel unit set of optical sensor in some possible implementations The reflected light signal that at least two optical signals are reflected from the face is stated, and at least two people are obtained according to the reflected light signal Face image, comprising:

First optical signal, the second optical signal are successively received by the pixel unit in the first pixel unit set The reflected light signal reflected respectively from the face with third optical signal, and obtained respectively according to the reflected light signal the first Face image, the second facial image and third facial image.

In some possible implementations, the method also includes:

According to first facial image, second facial image and the third facial image determine the face It is true and false.

It is described according to first facial image, second facial image and institute in some possible implementations It states third facial image and determines the true and false of the face, comprising:

According to first facial image after calibration, second facial image and the third facial image are determined The face it is true and false.

In some possible implementations, the method also includes:

According to references object to the first band range, the light of the second band range and the third wavelength band Relationship between the response of spectrum determines the calibration parameter.

In some possible implementations, it is described according to references object to the first band range, second wave Relationship between segment limit and the response of the spectrum of the third wavelength band, determines the calibration parameter, comprising:

Successively emit the first band range, the second band range and institute to the references object in the light source When stating the optical signal of third wavelength band, the reference is acquired by the pixel unit in the first pixel unit set respectively Three width images of object；

In some possible implementations, first facial image according to after calibration, second face Image and the third facial image, determine the true and false of the face, comprising:

In some possible implementations, first facial image according to after calibration, second face Image and the third facial image are synthesized, and colorized face images are obtained, comprising:

In some possible implementations, the characteristic information according to the colorized face images determines the people Face it is true and false, comprising:

In some possible implementations, the method also includes:

In some possible implementations, it is described according in the pixel array remove the first pixel unit set with The facial image of outer other pixel units acquisition carries out recognition of face, comprising:

In some possible implementations, it is described by the pixel array in addition to the first pixel unit set Other pixel units acquisition facial image matched with the facial image template of registration, determine recognition of face whether at Function, comprising:

In the facial image and the facial image template matching registered and in the case that the face is real human face, really Determine recognition of face success.

Fourth aspect provides a kind of electronic equipment, including such as second aspect to second aspect and its any possible reality The device for recognition of face in existing mode.

5th aspect, provides a kind of computer-readable medium, for storing computer program, the computer program packet It includes for executing the instruction in the above-mentioned third aspect and its any possible implementation.

6th aspect, provides a kind of computer program product including instruction, when computer runs the computer journey When the described instruction of sequence product, the computer execute in the above-mentioned third aspect and its any possible implementation for people Face knows method for distinguishing.

Specifically, which can run on the electronic equipment of above-mentioned fourth aspect.

Based on the above-mentioned technical proposal, the optical signal that at least two wavelength bands are successively emitted by light source, is passed by optics Sensor, which carries out multi collect, can obtain at least two spectral responses of target to be identified, may further based on this at least two Spectral response carries out vivo identification, is conducive to the safety for promoting recognition of face.

Detailed description of the invention

Fig. 1 is the reflection spectrum curve of human skin.

Fig. 2 is the schematic diagram according to the optical sensor for recognition of face of the embodiment of the present application.

Fig. 3 is the schematic diagram according to the device for recognition of face of the embodiment of the present application.

Fig. 4 is the schematic flow chart according to the method for recognition of face of the embodiment of the present application.

Fig. 5 is the overall flow figure according to the method for recognition of face of the embodiment of the present application.

Fig. 6 is the schematic block diagram according to the electronic equipment of the embodiment of the present application.

Specific embodiment

Below in conjunction with attached drawing, technical solutions in the embodiments of the present application is described.

It should be understood that the embodiment of the present application can be applied to various face identification systems, the application scenarios common as one kind, Face identification system provided by the embodiments of the present application can be applied in the mobile terminals such as smart phone, tablet computer and door lock, door Access control system or other electronic equipments.

In traditional face identification system, active false proof is by the way of interaction, for example, being become using blink or expression Modes, this modes such as change usually require a few frame images of continuous acquisition, reduce recognition speed.

Usually, by the shadow of the factors such as the skin thickness of human skin tissue, hemoglobin concentration, melanin content It ringing, human skin tissue has certain particularity to the light reflecting properties of specific band range, as shown in Figure 1, human body Skin is in the wavelength band of 560nm or so, and the wavelength band of 980nm is with special spectral response, this special spectrum sound It should be not present on the spectral response curve of the artificial materials such as paper, mold.

Accordingly, this application provides a kind of methods of face active false proof, can acquire target to be identified to multiple specific The response of the spectrum of wavelength band is based further on the spectral response and carries out active false proof, is conducive to promote recognition speed, simultaneously The safety of recognition of face can also be promoted.

It it should be understood that the target to be identified in the embodiment of the present application can be face, or may be other portions of human body Position, such as finger, palm, the embodiment of the present application are not construed as limiting this.

Fig. 2 is a kind of schematic diagram of optical sensor 20 for recognition of face provided by the embodiments of the present application, The optical sensor 20 includes:

Pixel array 200, the first pixel unit set 21 in the pixel array are successively emitted for receiving by light source The reflected light signal that is reflected from face of at least two optical signals, and at least two face figures are obtained according to the reflected light signal Picture, wherein at least two optical signal corresponds to different wavelength bands, and at least two facial image is for described in determination Face it is true and false.

In the embodiment of the present application, it does not need to make pixel array special design, it only need to be based at least two different waves The optical signal of segment limit, response of the target to be identified to the spectrum of at least two wavelength bands can be obtained by carrying out multi collect, Vivo identification may further be carried out based on the response of at least two spectrum, be conducive to the safety for promoting recognition of face.

In the embodiment of the present application, the wavelength band of the light source can be specially designed, optional real as one Existing mode, can design the wavelength band of the light source according to the reflection spectrum curve of human skin, for example, designing the light The wavelength band of wavelength band or other visible-ranges or 980nm or so that the wavelength band in source is 560nm or so, or Person may be the wavelength band of recognition of face performance preferably infrared band range, such as 940nm or so, alternatively, can also be with According to the other biological feature of living body, suitable wavelength band is selected, as long as there can be apparent discrimination with prosthese.

It should be understood that in this embodiment, at least two facial image can be in the pixel array of optical sensor The acquisition of whole pixel units, or the partial pixel unit acquisition that is also possible in pixel array, that is to say, that can be with Vivo identification is done using entire pixel array, or only can also do vivo identification using partial pixel unit, latter is realized Mode advantageously reduces the power consumption of mould group, improves acquisition speed and recognition speed.

When doing vivo identification using the partial pixel unit of the pixel array, described first is removed in the pixel array The facial image of other pixel units acquisition except pixel unit set is used for recognition of face, for example, can will it is described other The facial image of pixel unit acquisition is matched with the facial image template of registration, it is determined whether successful match, i.e., described the The facial image of pixel unit acquisition in one pixel unit set can be used for active false proof, remove institute in the pixel array Stating other pixel units except the first pixel unit set can be used for recognition of face, to determine the facial image and note of acquisition Whether the facial image template of volume matches.

When doing vivo identification using the partial pixel unit of the pixel array, sensor drive module can close institute Other pixel units in pixel array in addition to the first pixel unit set are stated, so as to reduce the power consumption of mould group, Promote acquisition speed and recognition speed.

Optionally, described when the first pixel unit set includes the partial pixel unit in the pixel array The ratio of the total quantity of the quantity and pixel unit in the pixel array of pixel unit in first pixel unit set is small In the first ratio, such as 5%, to avoid recognition of face performance is influenced.

Optionally, pixel unit in the first pixel unit set is discrete to be distributed in the pixel array.It can Guarantee that vivo identification function does not influence recognition of face performance.

Optionally, in the embodiment of the present application, continuous pixel unit in the first pixel unit set can be set Quantity be less than or equal to specific threshold, for example, 6, pass through continuous pixel list in setting the first pixel unit set The number of member is less than certain threshold value, and can be avoided influences recognition of face performance.

As one embodiment, the pixel unit in the first pixel unit set can be not provided with optical filter, for example, Transparent processing, or setting transparent material are done, advantageously ensures that the first pixel unit set can collect the light source The optical signal of the wavelength band of transmitting.In other embodiments, the pixel unit in the first pixel unit set can also be with The optical filter of specific band is set, for example, for filtering out the stray light for influencing recognition of face and vivo identification.

Optionally, other pixel units in the pixel array in addition to the first pixel unit set are not provided with filtering Mating plate, or the optical filter of setting specific band range, for example, optical filter, such as 940nm of infrared band or so wavelength band Optical filter.

Optionally, in some embodiments, at least two optical signal includes the first optical signal, the second optical signal and the Two optical signals, wherein first optical signal corresponds to first band range, and second optical signal corresponds to second band range, The third optical signal corresponds to third wavelength band, the first band range, the second band range and the third wave Segment limit is different two-by-two, and the first pixel unit set 21 is specifically used for:

When the light source successively emits first optical signal, second optical signal and the third optical signal, according to Reflected light letter secondary to receive first optical signal, that second optical signal and the third optical signal are reflected from the face Number, and respectively corresponded according to the reflected light signal and obtain the first facial image, the second facial image and third facial image, In, first facial image, second facial image and third facial image for determining the true and false of face, i.e., these three Facial image may be used as vivo identification.

Optionally, in the application one embodiment, the first band range, the second band range and described Three wavelength bands are respectively one of following three kinds of wavelength bands:

Optionally, in other embodiments, above three wavelength band can be determined in visible light wave range, described first Wavelength band, the second band range and the third wavelength band can be respectively red spectral band, blue wave band and green light One kind of wave band.For example, it is 440nm~475nm that the wavelength band of blue light, which can be center wave band, upper cut-off wave band is about 550nm；It is 520nm~550nm that the wavelength band of green light, which can be center wave band, and upper cut-off wave band is about 620nm, lower cut-off wave Duan Yuewei 460nm；It is about 550nm that the wavelength band of feux rouges, which can be lower cut-off wave band,.

Therefore, in the embodiment of the present application, photoelectric sensor can carry out face based on the optical signal of three kinds of wavelength bands The acquisition of image, so that response of the face to the spectrum of three kinds of wavelength bands is obtained, it may further be based on three kinds of spectrum Response carries out vivo identification, is conducive to the safety for promoting recognition of face.

Fig. 3 is according to the schematic diagram of the device for recognition of face of the embodiment of the present application, as shown in figure 3, should Device 30 may include: light source 31, and for successively emitting at least two optical signals, at least two optical signal corresponds to different Wavelength band；

First pixel unit set of optical sensor 32, the optical sensor 32 is successively sent out for receiving the light source The reflected light signal that at least two optical signal penetrated is reflected from face, and at least two are obtained according to the reflected light signal Facial image, at least two facial image is for determining the true and false of the face.

It should be understood that the optical sensor 32 can correspond to the optical sensor 20 in embodiment illustrated in fig. 2, it is specific real The associated description of previous embodiment can be now referred to, which is not described herein again.

Optionally, in some embodiments, at least two optical signal may include the first optical signal, the second optical signal With third optical signal, first optical signal corresponds to first band range, and second optical signal corresponds to second band range, institute It states third optical signal and corresponds to third wavelength band.Wherein, the first band range, the second band range and the third Wavelength band realizes the associated description that can refer to previous embodiment, and which is not described herein again.

Optionally, in some embodiments, the light source 31 is a light source, the optical signal that the light source 31 can emit Wavelength band include the first band range, the second band range and the third wavelength band.It is three kinds i.e. above-mentioned Optical signal is emitted by same light source, for example, it can be made to emit the light of different-waveband range by controlling the frequency of light source Signal.

Optionally, in other embodiments, the light source 31 be include the first sub-light source, the second sub-light source and third sub-light The combination of light sources in source, wherein first sub-light source, second sub-light source and the third sub-light source are respectively used to transmitting institute First band range, the optical signal of the second band range and the third wavelength band are stated, i.e., above-mentioned three kinds of optical signals are Emitted by different light sources, each light source can be used for emitting the optical signal of a wavelength band.

Optionally, in the application one embodiment, described device 30 further include:

Light source control module successively emits first optical signal to the face for controlling the light source 31, described Second optical signal and the third optical signal.

For example, the light source control module can control the light source 31 and successively emit if the light source 31 is a light source The optical signal of different-waveband range, alternatively, the light source control module can control described if the light source includes multiple light sources Multiple light sources successively shine, to emit the optical signal of different-waveband range.

Optionally, light source 31 can be the built-in light source of described device 30, or be also possible to the external of described device 30 Light source, or the light source in the electronic equipment that described device 30 is installed can also be multiplexed to emit the light letter for vivo identification Number, in this case, described device 30 can not include the light source 31, the embodiment of the present application is not construed as limiting this.

Optionally, in one embodiment, the optical sensor 32 is specifically used for:

When the light source 31 successively emits the first optical signal, the second optical signal and third optical signal to the face, lead to It crosses the first pixel unit set and successively receives first optical signal, the second optical signal and third optical signal are respectively from described The reflected light signal of face reflection, and the first facial image is obtained according to the reflected light signal respectively, the second facial image and Third facial image.

Optionally, in some embodiments, described device 30 can also include:

Processor 33, for according to first facial image, second facial image and the third facial image Determine the true and false of the face.

It should be understood that if the first pixel unit set only includes the partial pixel unit of pixel array, it is described the first Face image, second facial image and the third facial image can be local facial image, if first picture Plain unit set includes whole pixel units of pixel array, first facial image, second facial image and described Third facial image can be complete facial image.

Wherein, first facial image is response of people's face to the spectrum of first band range, the second face figure As being response of the face to the spectrum of the second band range, the third facial image is the face to third wave band model The response of the spectrum enclosed.Since the face has special needs to three kinds of spectrum, based on the response of three kinds of spectrum, The true and false of face can effectively be distinguished.

It, can be according to a spectral response in the response of above-mentioned three kinds of spectrum, really as an optional implementation Determine the true and false of face, is adopted in this way, the optical signal that can also only use a wavelength band in man face image acquiring carries out face Collection, is based further on a spectral response and does vivo identification.

But artificial material (such as paper) may be with living person to the wave band model to the response of the spectrum of some wavelength band The response of the spectrum enclosed, which exists, to partly overlap, if the response of the spectrum based on the wavelength band carries out vivo identification, may lead Cause misrecognition.In the embodiment of the present application, target to be identified can be acquired by the first pixel unit set for multiple wave bands The response of the spectrum of range, the response of the spectrum of multiple wavelength band may include the target to be identified to first band range Spectrum response, the target to be identified is to the response of the spectrum of second band range and the target to be identified to third wave The response of the spectrum of segment limit, that is to say, that the corresponding spectrum of each pixel unit in the first pixel unit set is rung It should be able to include response of the face to the spectrum of three kinds of different-waveband ranges, in this way, even if some of artificial material and living person There is overlapping in the response of the spectrum of wavelength band, can also be distinguished by the response of the spectrum of other wavelength bands, thus It is able to ascend the accuracy of vivo identification.

In the embodiment of the present application, for the test object of a pure color, for example, white paper, for different wave bands For the spectrum of range, it is desirable to which the difference of the collected spectral response of pixel unit in the first pixel unit set is not Greatly, that is to say, that this first pixel unit set is same or similar for the response of the optical signal of three kinds of wavelength bands, still, In practical application, the size of the first pixel unit set three kinds of spectral responses collected may have certain difference, In this way, if some spectral response is excessive, may cause other spectral responses cannot be by effective district when three kinds of spectral responses of synthesis Point, in order to promote the discrimination of living body and prosthese, in the embodiment of the present application, the first pixel unit set can also be acquired Facial image is calibrated.

Optionally, in some embodiments, the processor 33 is also used to:

Using the references object as test object, the calibration parameter is determined, which can be pure color object, example Such as white paper, yellowish pink object etc., it is expected that the references object of the first pixel unit set acquisition is to the first wave The response of the spectrum of segment limit, the second band range and the third wavelength band is based on this purpose in same level, right The references object of the first pixel unit collective entity acquisition is to the first band range, the second band range Response with the spectrum of the third wavelength band is calibrated, and determines the calibration parameter.

Specifically, successively emit the first band range, the second band to the references object in the light source When the optical signal of range and the third wavelength band, the references object is acquired by the first pixel unit set respectively Three width images, be denoted as the first image, the second image and third image.Further, the processor 33 is according to three width The relationship of the pixel value of respective pixel unit in image determines that the calibration parameter, the calibration parameter are used for so that described The pixel value of three width images is in same range.

It is assumed that the pixel value of the first pixel unit P1 is 200 in the first image, the first pixel described in the second image The pixel value of unit P1 acquisition is 100, and the pixel value that the first pixel unit P1 is acquired in third image is 50, above three picture Plain value respectively indicates the response of three kinds of spectrum, proportionate relationship 4:2:1, in order to enable the first pixel unit P1 acquisition is described References object in same level, can calibrate the response of three kinds of spectrum to it, such as can be by this in the second image The pixel value of one pixel unit P1 acquisition multiplied by 2, pixel value that the first pixel unit P1 in third image is acquired multiplied by 4, In this way, in subsequent colorized face images of three pixel values synthesis including three kinds of spectral responses based on pixel unit acquisition When, it can preferably distinguish every kind of spectral response.

Optionally, in other embodiments, the calibration parameter is preset value, for example, can be according to three kinds of spectrum The empirical value of response determines, or can also be determined according to above-mentioned calibration steps, for example, determining calibration ginseng through the above steps After number, the calibration parameter can be prestored, the calibration of the facial image for subsequent acquisition, i.e., the calibration of subsequent facial image The calibration parameter is all used, the embodiment of the present application is not construed as limiting this.

It should be understood that in the embodiment of the present application, the response of three kinds of spectrum can refer to three kinds of spectral responses in same range Difference be less than specific threshold or three kinds of spectral responses pixel value it is suitable, in other words, be in same level.

Optionally, in the embodiment of the present application, the school of each pixel unit in the first pixel unit set can be determined Then quasi- parameter is calibrated according to pixel value of the calibration parameter of each pixel unit to subsequent acquisition, alternatively, can also incite somebody to action The calibration parameter of each pixel unit is averaged, and unified calibration parameter is obtained, according to the unified calibration parameter to first The pixel value of all pixels unit acquisition in pixel unit set is calibrated, and the embodiment of the present application is for the specifically side of calibration Formula is not construed as limiting.

Optionally, in some embodiments, the processor 33 is also used to:

For example, the processor 33 can be according to the first pixel unit in the first pixel unit set described the first Sampled pixel values in face image determine the corresponding first response pixel value of the first pixel in the colorized face images, In, the first response pixel value indicates response of the face to the spectrum of the first band range, first pixel Corresponding first pixel unit；

Specifically, the colorized face images may include three Color Channels, such as RGB, a kind of spectral response pair Answer a Color Channel, that is to say, that each pixel in colorized face images includes (i.e. described three responses of three pixel values Pixel value), respectively correspond three kinds of spectral responses.To determine three kinds of light of the first pixel unit P1 in the first pixel unit set It is illustrated for spectrum response, it can be by first facial image after calibration, second facial image and the third Corresponding three pixel values of first pixel unit P1 described in facial image, as respective pixel in the colorized face images The pixel value of three Color Channels.Each pixel unit in the first pixel unit set can be determined in a similar way Three kinds of spectrum response, to obtain this colorized face images.

Further, which can carry out vivo identification according to the colored human face, to identify the true and false of face, example Such as, the processor 33 can extract the characteristic information of the colored human face, for example, color character information, is specifically as follows coloration, Then saturation degree and purity (Hue, Saturation, Value, HSV) information input the characteristic information of the colour local facial Classify to deep learning network, determines the true and false of face.

Optionally, in the embodiment of the present application, which can be convolutional neural networks or other depth Learning network.By taking convolutional neural networks as an example, illustrate specific training process.

Firstly, building convolutional neural networks structure, such as two layers of convolutional neural networks can be used, or can also use Three Tiered Network Architecture or more structure etc..

Secondly, the initial training parameter and the condition of convergence of the convolutional neural networks is arranged.

What the initial training parameter can be randomly generated, or obtain based on experience value, or be also possible to according to big The parameter of the good convolutional neural networks model of the true and false human face data pre-training of amount.

Non-limiting as example, which may include at least one of the following:

1, the colorized face images of real human face are determined as that the probability from real human face is greater than the first probability, for example, 98%；

2, the colorized face images of dummy's face are judged as that the probability from dummy's face is greater than the second probability, such as 95%；

3, the colorized face images of real human face are determined as that the probability from dummy's face is less than third probability, for example, 2%；

4, it is judged as the probability from real human face less than the 4th probability, such as 3% colorized face images of dummy's face.

Then, the feature letter of the colorized face images of a large amount of real human face and dummy's face is inputted to the convolutional neural networks Breath, the convolutional neural networks can be handled based on characteristic information of the initial training parameter to above-mentioned colorized face images, really The fixed judgement to each colorized face images is as a result, further, according to the judgement as a result, the structure of adjustment convolutional neural networks And/or the training parameter of each layer, until determining that result meets the condition of convergence, so far, training is completed.It later, can be by subsequent need The characteristic information of the colorized face images for the face to be identified is input to the convolutional neural networks, which can make It is handled with characteristic information of the trained parameter to the colorized face images, determines whether the colorized face images come from very Real face.

Optionally, in some embodiments, the processor 33 is also used to:

According to the people of other pixel units acquisition in addition to the first pixel unit set in the pixel array Face image carries out recognition of face.

For example, the processor 33 can be in the mesh to be identified for the facial image and registration that other described pixel units acquire In the case where target facial image template matching, vivo identification further is carried out to the target to be identified, in the target to be identified Recognition of face success is determined in the case where for real human face, thereby executing the operation for triggering the recognition of face, for example, carrying out terminal The operation such as unlock or payment.

In other embodiments, which can also be in the case where target to be identified be real human face, further Judge in pixel array in addition to the first pixel unit set other pixel units acquisition facial image whether with The facial image template matching of the target to be identified of registration determines recognition of face success in the event of a match, further holds Row triggers the operation of the recognition of face, for example, carrying out the operation such as terminal unlocking or payment.

It should be understood that the device 30 for recognition of face according to the embodiment of the present application is readily applicable to other biological feature Identify scene, such as fingerprint recognition scene, for example, when acquiring fingerprint image, the finger based on the acquisition of partial pixel unit At least two spectral responses are based further at least two spectral response, determine the true and false of finger.

In the embodiment of the present application, the device 30 for recognition of face may include the processor 33, such as at this The micro-control unit (Micro Control Unit, MCU) that device 33 can be used in the device 30 of recognition of face for this is managed, or Person, in other embodiments, the device 30 for being used for recognition of face can not include the processor 33, in this case, the place Managing function performed by device 33 can be by the processor in electronic equipment that the device 30 for recognition of face is installed, example If master control (Host) module executes, the embodiment of the present application is not construed as limiting this.

Above in association with Fig. 2 to Fig. 3, the Installation practice of the application is described in detail, below in conjunction with Fig. 4, detailed description is originally The embodiment of the method for application, it should be appreciated that embodiment of the method is corresponded to each other with Installation practice, and similar description is referred to device Embodiment.

Fig. 4 is the schematic flow chart of the method 40 for recognition of face of another embodiment of the application, as shown in figure 4, This method 40 includes:

S41, when light source successively emits at least two optical signals, by the first pixel unit set of optical sensor according to The secondary reflected light signal for receiving at least two optical signal and being reflected from the face, and according to the reflected light signal obtain to Few two facial images, wherein at least two optical signal corresponds to different wavelength bands；

S42 determines the true and false of the face according at least two facial image.

It should be understood that this method 40 can be executed by the device for recognition of face, such as the device 30 in previous embodiment, Specifically, S41 can be executed by the optical sensor in the device 30, S42 can by the processor in the device 30, such as MCU is executed；Alternatively, the electronic equipment that this method 40 can also be installed by the device for recognition of face executes, for example, S42 can be executed by the processor in electronic equipment, such as Host module, and the embodiment of the present application is not construed as limiting this.

Optionally, in some embodiments, the light source successively emits at least two optical signals to face, comprising: described Light source successively emits the first optical signal, the second optical signal and third optical signal to the face, wherein first optical signal pair First band range is answered, second optical signal corresponds to second band range, and the third optical signal corresponds to third wavelength band.

Optionally, in some embodiments, the first band range, the second band range and the third wave band Range is respectively one of following three kinds of wavelength bands: the wavelength band including 560nm, the wavelength band including 980nm, packet Include the wavelength band of 940nm.

Optionally, in some embodiments, the light source is a light source, the wave for the optical signal that the light source can emit Segment limit includes the first band range, the second band range and third wavelength band.

Optionally, in some embodiments, the light source includes the first sub-light source, the second sub-light source and third sub-light source, It is respectively used to emit the first band range, the optical signal of the second band range and the third wavelength band.

Optionally, in some embodiments, the method 40 further include:

Optionally, in some embodiments, described that institute is successively received by the first pixel unit set of optical sensor The reflected light signal that at least two optical signals are reflected from the face is stated, and at least two people are obtained according to the reflected light signal Face image, comprising:

Optionally, in some embodiments, the method 40 further include:

Optionally, in some embodiments, described according to first facial image, second facial image and described Third facial image determines the true and false of the face, comprising:

Optionally, in some embodiments, the method 40 further include:

Optionally, in some embodiments, it is described according to references object to the first band range, the second band Relationship between the response of the spectrum of range and the third wavelength band, determines the calibration parameter, comprising:

Optionally, in some embodiments, first facial image according to after calibration, the second face figure Picture and the third facial image, determine the true and false of the face, comprising:

Optionally, in some embodiments, first facial image according to after calibration, the second face figure Picture and the third facial image are synthesized, and colorized face images are obtained, comprising:

Optionally, in some embodiments, the characteristic information according to the colorized face images, determines the face It is true and false, comprising: handled by characteristic information of the deep learning network to the colorized face images, determine the face It is true and false.

Optionally, in some embodiments, the method 40 further include:

Optionally, in some embodiments, it is described according in the pixel array remove the first pixel unit set with The facial image of outer other pixel units acquisition carries out recognition of face, comprising:

In the case where the facial image is matched with the facial image registered and the face is real human face, people is determined Face identifies successfully.

Hereinafter, illustrating the overall flow of the method for recognition of face according to the embodiment of the present application, such as Fig. 5 in conjunction with Fig. 5 Shown, this method may include following content:

S51 passes through the first pixel unit collection in light source the first optical signal of transmission, the second optical signal and third optical signal Conjunction acquires the first facial image, the second facial image and third facial image respectively；

In S52, to first facial image, second facial image and the third facial image carry out school It is quasi-；

Specific implementation refers to the related description of previous embodiment, and which is not described herein again.

In S53, according to first facial image after calibration, second facial image and the third face figure As being synthesized, colorized face images are obtained；

In S54, the color character information of the colorized face images, such as HSV information are extracted；

In S55, is classified according to the color character information of the colorized face images, determine the true and false of face.Tool Body, which can be input to deep learning network, to determine the true and false of face.

As shown in fig. 6, the electronic equipment 60 may include using the embodiment of the present application also provides a kind of electronic equipment 60 In the device 61 of recognition of face, which can be in aforementioned device embodiment for recognition of face Device 30, it can be used to execute the content in embodiment of the method described in Fig. 4 to Fig. 5, for sake of simplicity, no longer superfluous here It states.

It should be understood that the processor or processing unit of the embodiment of the present application can be a kind of IC chip, there is signal Processing capacity.During realization, each step of above method embodiment can be patrolled by the integrated of the hardware in processor The instruction for collecting circuit or software form is completed.Above-mentioned processor can be general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field Programmable Gate Array, FPGA) or other can Programmed logic device, discrete gate or transistor logic, discrete hardware components.It may be implemented or execute the application implementation Disclosed each method, step and logic diagram in example.General processor can be microprocessor or the processor can also be with It is any conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present application, can be embodied directly in hardware decoding Processor executes completion, or in decoding processor hardware and software module combination execute completion.Software module can position In random access memory, flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register In the storage medium of equal this fields maturation.The storage medium is located at memory, and processor reads the information in memory, in conjunction with it Hardware completes the step of above method.

It is appreciated that the recognition of face of the embodiment of the present application can also include memory, memory can be volatibility and deposit Reservoir or nonvolatile memory, or may include both volatile and non-volatile memories.Wherein, nonvolatile memory can Be read-only memory (Read-Only Memory, ROM), programmable read only memory (Programmable ROM, PROM), Erasable Programmable Read Only Memory EPROM (Erasable PROM, EPROM), electrically erasable programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.Volatile memory can be random access memory (Random Access Memory, RAM), it is used as External Cache.By exemplary but be not restricted explanation, many forms RAM is available, such as static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), Synchronous Dynamic Random Access Memory (Synchronous DRAM, SDRAM), Double Data Rate synchronous dynamic Random access memory (Double Data Rate SDRAM, DDR SDRAM), enhanced Synchronous Dynamic Random Access Memory (Enhanced SDRAM, ESDRAM), synchronized links dynamic random access memory (Synchlink DRAM, SLDRAM) and straight Meet rambus random access memory (Direct Rambus RAM, DR RAM).It should be noted that system described herein and side The memory of method is intended to include but is not limited to the memory of these and any other suitable type.

The embodiment of the present application also proposed a kind of computer readable storage medium, the computer-readable recording medium storage one A or multiple programs, the one or more program include instruction, and the instruction is when by the portable electronic including multiple application programs When equipment executes, method that the portable electronic device can be made to execute Fig. 4 to embodiment illustrated in fig. 5.

The embodiment of the present application also proposed a kind of computer program, which includes instruction, when the computer journey When sequence is computer-executed, the method that allows computer to execute Fig. 4 to embodiment illustrated in fig. 5.

The embodiment of the present application also provides a kind of chip, which includes input/output interface, at least one processor, extremely A few memory and bus, for storing instruction, at least one processor is for calling this extremely for at least one processor Instruction in a few memory, the method to execute Fig. 4 to embodiment illustrated in fig. 5.

Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed Scope of the present application.

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 arriving, disclosed systems, devices and methods can To realize by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit Division, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or group Part can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown Or the mutual coupling, direct-coupling or communication connection discussed can be through some 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, each functional unit in each embodiment of the application can integrate in 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 a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, institute Computer software product is stated to be stored in a storage medium, including some instructions are used so that computer equipment (can be with It is personal computer, server or the network equipment etc.) execute all or part of step of each embodiment the method for the application Suddenly.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), deposits at random The various media that can store program code such as access to memory (Random Access Memory, RAM), magnetic or disk.

The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain Lid is within the scope of protection of this application.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.

Claims

1. a kind of optical sensor for recognition of face characterized by comprising

Pixel array, the first pixel unit set in the pixel array is for receiving at least two successively emitted by light source The reflected light signal that optical signal is reflected from face, and at least two facial images are obtained according to the reflected light signal, wherein institute It states at least two optical signals and corresponds to different wavelength bands, at least two facial image is for determining the true of the face It is false.

2. optical sensor according to claim 1, which is characterized in that at least two optical signal is believed including the first light Number, the second optical signal and third optical signal, wherein first optical signal corresponds to first band range, second optical signal Corresponding second band range, the third optical signal correspond to third wavelength band, the first band range, the second band Range and the third wavelength band are different two-by-two；

At least two facial image include the first facial image, the second facial image and third facial image, described first Facial image, the second facial image and third facial image are respectively by first optical signal, second optical signal and described Third optical signal obtains after face reflection, first facial image, second facial image and the third party Face image is for determining the true and false of the face.

3. optical sensor according to claim 2, which is characterized in that the first band range, the second band Range and the third wavelength band are respectively one of following three kinds of wavelength bands:

4. optical sensor according to any one of claim 1 to 3, which is characterized in that the first pixel unit collection Pixel unit in conjunction is not provided with optical filter.

5. optical sensor according to any one of claim 1 to 4, which is characterized in that remove institute in the pixel array It states other pixel units except the first pixel unit set and is not provided with optical filter, or the optical filter of setting specific band range.

6. optical sensor according to claim 5, which is characterized in that the optical filter of the specific band range is to include The optical filter of 940nm wavelength band.

7. optical sensor according to any one of claim 1 to 6, which is characterized in that the first pixel unit collection It closes including the partial pixel unit in the pixel array.

8. optical sensor according to any one of claim 1 to 7, which is characterized in that the first pixel unit collection The ratio of the quantity of pixel unit in conjunction and the total quantity of the pixel unit in the pixel array is less than the first ratio.

9. optical sensor according to any one of claim 1 to 8, which is characterized in that the first pixel unit collection The quantity of continuous pixel unit is less than or equal to specific threshold in conjunction.

10. optical sensor according to any one of claim 1 to 9, which is characterized in that the first pixel unit collection Pixel unit in conjunction is discrete to be distributed in the pixel array.

11. optical sensor according to any one of claims 7 to 10, which is characterized in that removed in the pixel array The facial image of other pixel units acquisition except the first pixel unit set is used for recognition of face.

12. a kind of device for recognition of face characterized by comprising

Optical sensor as described in any one of claims 1 to 11；

Wherein, the first pixel unit set of the optical sensor is for receiving the light source successively emits described at least two The reflected light signal that kind optical signal is reflected from face, and at least two facial images are obtained according to the reflected light signal, it is described At least two facial images are for determining the true and false of the face.

13. device according to claim 12, which is characterized in that the light source is specifically used for:

Successively emit the first optical signal, the second optical signal and third optical signal to the face, wherein first optical signal pair First band range is answered, second optical signal corresponds to second band range, and the third optical signal corresponds to third wavelength band, The first band range, the second band range and the third wavelength band are different two-by-two.

14. device according to claim 13, which is characterized in that the light source is a light source, and the light source can be sent out The wavelength band for the optical signal penetrated includes the first band range, the second band range and third wavelength band.

15. device according to claim 13, which is characterized in that the light source includes the first sub-light source, the second sub-light source With third sub-light source, it is respectively used to emit the first band range, the second band range and the third wavelength band Optical signal.

16. device described in any one of 3 to 15 according to claim 1, which is characterized in that described device further include: light source control Molding block successively emits first optical signal to the face for controlling the light source, second optical signal and described Third optical signal.

17. device described in any one of 3 to 16 according to claim 1, which is characterized in that the optical sensing implement body is used In:

First optical signal, the second optical signal and third optical signal difference are successively received by the first pixel unit set The reflected light signal reflected from the face, and the first facial image, the second face are obtained according to the reflected light signal respectively Image and third facial image.

18. device according to claim 17, which is characterized in that described device further include:

Processor, for determining institute according to first facial image, second facial image and the third facial image State the true and false of face.

19. device according to claim 18, which is characterized in that the processor is also used to:

According to calibration parameter, to first facial image, second facial image and the third facial image carry out school It is quasi-；

According to first facial image after calibration, second facial image and the third facial image determine the people Face it is true and false.

20. device according to claim 19, which is characterized in that the processor is also used to:

According to references object to the first band range, the spectrum of the second band range and the third wavelength band Relationship between response determines the calibration parameter.

21. device according to claim 20, which is characterized in that the optical sensor is also used to: the light source to The references object successively emits the first band range, the light letter of the second band range and the third wavelength band Number when, acquire three width images of the references object respectively；

The processor is also used to:

According to the relationship of the pixel value of the three width image, determine that the calibration parameter, the calibration parameter are used for so that described The pixel value of three width images is in same range.

22. the device according to claim 20 or 21, which is characterized in that the processor is also used to:

According to first facial image after calibration, second facial image and the third facial image are synthesized, Obtain colorized face images, wherein each pixel in the colorized face images includes the face to the first band Three response pixel values of the spectrum of range, the second band range and the third wavelength band；

23. device according to claim 22, which is characterized in that the processor is specifically used for:

According to sampled pixel values of the first pixel unit in the first pixel unit set in first facial image, determine The corresponding first response pixel value of the first pixel in the colorized face images, wherein the first response pixel value indicates Response of the face to the spectrum of the first band range, first pixel correspond to first pixel unit；

According to sampled pixel values of the first pixel unit in the first pixel unit set in second facial image, determine The corresponding second response pixel value of first pixel, wherein the second response pixel value indicates the face to described the The response of the spectrum of two wavelength bands；And

According to sampled pixel values of the first pixel unit in the first pixel unit set in the third facial image, determine The corresponding third of first pixel responds pixel value, wherein the third response pixel value indicates the face to described the The response of the spectrum of three wavelength bands.

24. the device according to claim 22 or 23, which is characterized in that the processor is specifically used for: by depth It practises network to handle the characteristic information of the colorized face images, determines the true and false of the face.

25. device described in any one of 8 to 24 according to claim 1, which is characterized in that the processor is also used to:

By in the pixel array in addition to the first pixel unit set other pixel units acquisition facial image with The facial image template of registration is matched, and determines whether recognition of face succeeds.

26. device according to claim 25, which is characterized in that the processor is also used to:

27. a kind of method for recognition of face, which is characterized in that the described method includes:

When light source successively emits at least two optical signals, institute is successively received by the first pixel unit set of optical sensor The reflected light signal that at least two optical signals are reflected from the face is stated, and at least two people are obtained according to the reflected light signal Face image, wherein at least two optical signal corresponds to different wavelength bands；

28. according to the method for claim 27, which is characterized in that the light source successively emits at least two light letter to face Number, comprising:

The light source successively emits the first optical signal, the second optical signal and third optical signal to the face, wherein described first Optical signal corresponds to first band range, and second optical signal corresponds to second band range, and the third optical signal corresponds to third Wavelength band, the first band range, the second band range and the third wavelength band are different two-by-two.

29. according to the method for claim 28, which is characterized in that the first band range, the second band range It is respectively one of following three kinds of wavelength bands: the wavelength band including 560nm with the third wavelength band, including The wavelength band of 980nm, the wavelength band including 940nm.

30. the method according to claim 28 or 29, which is characterized in that the light source is a light source, the light source energy The wavelength band of the optical signal enough emitted includes the first band range, the second band range and third wavelength band.

31. the method according to any one of claim 28 to 30, which is characterized in that the light source includes the first sub-light Source, the second sub-light source and third sub-light source, are respectively used to emit the first band range, the second band range and described The optical signal of third wavelength band.

32. the method according to any one of claim 28 to 31, which is characterized in that the method also includes: control institute It states light source and successively emits first optical signal, second optical signal and the third optical signal to the face.

33. the method according to any one of claim 28 to 32, which is characterized in that described to pass through the of optical sensor One pixel unit set successively receives the reflected light signal that at least two optical signal is reflected from the face, and according to described Reflected light signal obtains at least two facial images, comprising:

First optical signal, the second optical signal and are successively received by the pixel unit in the first pixel unit set The reflected light signal that three optical signals are reflected from the face respectively, and the first face figure is obtained according to the reflected light signal respectively Picture, the second facial image and third facial image.

34. according to the method for claim 33, which is characterized in that the method also includes:

According to first facial image, second facial image and the third facial image determine the true of the face It is false.

35. according to the method for claim 34, which is characterized in that it is described according to first facial image, described second Facial image and the third facial image determine the true and false of the face, comprising:

According to first facial image after calibration, second facial image and the third facial image, determine described in Face it is true and false.

36. according to the method for claim 35, which is characterized in that the method also includes:

37. according to the method for claim 36, which is characterized in that it is described according to references object to the first band model It encloses, the relationship between the response of the spectrum of the second band range and the third wavelength band determines the calibration parameter, Include:

Successively emit the first band range, the second band range and described to the references object in the light source When the optical signal of three wavelength bands, the references object is acquired by the pixel unit in the first pixel unit set respectively Three width images；

38. the method according to claim 36 or 37, which is characterized in that the first face figure according to after calibration Picture, second facial image and the third facial image, determine the true and false of the face, comprising:

39. according to the method for claim 38, which is characterized in that first facial image according to after calibration, Second facial image and the third facial image are synthesized, and colorized face images are obtained, comprising:

40. the method according to claim 38 or 39, which is characterized in that the feature according to the colorized face images Information determines the true and false of the face, comprising:

It is handled by characteristic information of the deep learning network to the colorized face images, determines the true and false of the face.

41. the method according to any one of claim 38 to 40, which is characterized in that the method also includes:

42. according to the method for claim 41, which is characterized in that described to remove first pixel in the pixel array The facial image of other pixel units acquisition other than unit set is matched with the facial image template of registration, determines face Identify whether success, comprising:

43. a kind of electronic equipment characterized by comprising

The device for recognition of face as described in any one of claim 12 to 26.