CN112115925A - Face recognition method and device and computer readable storage medium - Google Patents

Abstract

The invention discloses a face recognition method, a device and a computer-readable storage medium. The face recognition method includes: obtaining interference information; modulating the interference information into a light intensity control signal, and sending the light intensity control signal to a an illuminating device, so that the illuminating device adjusts the light intensity according to the light intensity control signal; acquires a face image detected by the camera, the face image includes the light intensity information of the illuminating device; and performs face recognition according to the face image. The invention is beneficial to improve the security of the face recognition system.

Description

Face recognition method, device and computer readable storage medium

technical field

The present invention relates to the field of image recognition, and in particular, to a face recognition method, device and computer-readable storage medium.

Background technique

Interference with face recognition systems. The present attack uses photos, 3D face masks and other equipment to forge faces to deceive the face recognition system. It has simple operation, low cost, low technical threshold and good interference effect. However, there are currently many detection schemes for this interference method. At present, the threat of face recognition methods to face recognition systems in practical scenarios is low, and it is difficult to help face recognition systems to further break through the bottleneck of security.

SUMMARY OF THE INVENTION

By providing a face recognition method, device and computer-readable storage medium, the embodiments of the present invention aim to solve the problem that the present attack method is less threatening to the face recognition system in practical scenarios, and it is difficult to help face recognition The system further breaks through the bottleneck of security.

A first aspect of the embodiments of the present invention provides a face recognition method, and the face recognition method includes:

obtain interference information;

modulating the interference information into a light intensity control signal, and sending the light intensity control signal to the lighting device, so that the lighting device adjusts the light intensity according to the light intensity control signal;

acquiring a face image detected by a camera, where the face image includes light intensity information of the lighting device;

Face recognition is performed according to the face image.

In one embodiment, the step of obtaining the interference information includes:

determine the type of interference;

The interference information is acquired according to the interference type.

In an embodiment, the step of obtaining the interference information according to the interference type includes:

When the interference type is coarse light and dark stripes, long-run interference information is generated.

In an embodiment, the step of obtaining the interference information according to the interference type includes:

When the interference type is fine light and dark stripes, short-run interference information is generated.

In an embodiment, the step of modulating the interference information into a light intensity control signal includes:

According to the interference information, determine the curve change relationship between the light intensity and the time point in the interference information;

According to the curve change relationship, the light intensity control signal of high and low levels is generated.

In one embodiment, after the step of performing face recognition according to the face image, it further includes:

determining the first image gradient of the face image;

Comparing the first image gradient with the pre-stored second image gradient to obtain a comparison result;

According to the comparison result, the face recognition result is determined.

In one embodiment, the step of determining the face recognition result according to the comparison result includes:

When the similarity between the first image gradient and the second image gradient is greater than or equal to a preset value, it is determined that the face recognition is successful;

When the similarity between the first image gradient and the second image gradient is lower than the preset value, it is determined that face recognition fails.

In one embodiment, after the step of determining the face recognition result according to the comparison result, it further includes:

Output the face recognition result.

In order to achieve the above object, the present invention provides a face recognition device, the face recognition device includes: a memory, a processor and a computer program stored on the memory and running on the processor, the processor When the computer program is executed, each step of the above-mentioned face recognition method is realized.

In order to achieve the above object, the present invention provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, each of the above-mentioned face recognition methods is implemented. step.

The face recognition method, device and computer-readable storage medium provided by the present invention obtain interference information; modulate the interference information into a light intensity control signal, and send the light intensity control signal to the lighting device, so that all The lighting device adjusts the light intensity according to the light intensity control signal; acquires a face image detected by the camera, where the face image includes light intensity information of the lighting device; and performs face recognition according to the face image. Because the face recognition device implants interference information at the stage of collecting face images before performing face recognition, so as to identify the face information in the face images carrying the interference information, by overcoming the interference information, the human face can be improved. The security of face recognition system.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a schematic diagram of a hardware architecture of a face recognition device involved in an embodiment of the present invention;

FIG. 2 is a schematic flowchart of the first embodiment of the face recognition method of the present invention;

3 is a schematic flowchart of a second embodiment of the face recognition method of the present invention;

4 is a schematic flowchart of a third embodiment of the face recognition method of the present invention;

5 is a schematic flowchart of a fourth embodiment of the face recognition method of the present invention;

6 is a schematic flowchart of a fifth embodiment of the face recognition method of the present invention;

7 is a schematic flowchart of a sixth embodiment of the face recognition method of the present invention;

FIG. 8 is a schematic flow chart of refinement of step 70 of the seventh embodiment of the face recognition method of the present invention;

FIG. 9 is a schematic flowchart of an eighth embodiment of a face recognition method according to the present invention.

Detailed ways

For better understanding of the above technical solutions, exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

The main solution of the present invention is: the face recognition method, device and computer-readable storage medium provided by the present invention obtain interference information; modulate the interference information into a light intensity control signal, and convert the light intensity control signal send to the lighting device, so that the lighting device adjusts the light intensity according to the light intensity control signal; acquire the face image detected by the camera, the face image includes the light intensity information of the lighting device; face image for face recognition.

Because the face recognition device implants interference information at the stage of collecting face images before performing face recognition, so as to recognize the face information in the face images carrying the interference information, by overcoming the interference information, the human face can be improved. The bottleneck of face recognition security.

Referring to FIG. 1 , FIG. 1 is a schematic diagram of a hardware architecture of a face recognition apparatus according to an embodiment of the present invention.

The embodiments of the present invention relate to a controller, and the controller includes: a processor 101 , such as a CPU, a memory 102 , a communication bus 103 , a collection module 104 , and a lighting module 105 . Among them, the communication bus 103 is used to realize the connection and communication between these components.

The memory 102 may be high-speed RAM memory, or may be non-volatile memory, such as disk memory. As shown in FIG. 1, a memory as a computer storage medium may include a detection program; and the processor 101 may be used to call the detection program stored in the memory 102, and perform the following operations:

obtain interference information;

modulating the interference information into a light intensity control signal, and sending the light intensity control signal to the lighting device, so that the lighting device adjusts the light intensity according to the light intensity control signal;

acquiring a face image detected by a camera, where the face image includes light intensity information of the lighting device;

Face recognition is performed according to the face image.

In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102, and perform the following operations:

determine the type of interference;

The interference information is acquired according to the interference type.

In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102, and perform the following operations:

When the interference type is coarse light and dark stripes, long-run interference information is generated.

In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102, and perform the following operations:

When the interference type is fine light and dark stripes, short-run interference information is generated.

In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102, and perform the following operations:

According to the interference information, determine the curve change relationship between the light intensity and the time point in the interference information;

According to the curve change relationship, the light intensity control signal of high and low levels is generated.

In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102, and perform the following operations:

determining the first image gradient of the face image;

Comparing the first image gradient with the pre-stored second image gradient to obtain a comparison result;

According to the comparison result, the face recognition result is determined.

In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102, and perform the following operations:

When the similarity between the first image gradient and the second image gradient is greater than or equal to a preset value, it is determined that the face recognition is successful;

When the similarity between the first image gradient and the second image gradient is lower than the preset value, it is determined that face recognition fails.

In one embodiment, the processor 101 may be configured to call the detection program stored in the memory 102, and perform the following operations:

Output the face recognition result.

In the technical solution provided in this embodiment, the interference information is acquired; the interference information is modulated into a light intensity control signal, and the light intensity control signal is sent to the lighting device, so that the lighting device can follow the light The strong control signal adjusts the light intensity; acquires a face image detected by the camera, the face image includes the light intensity information of the lighting device; and performs face recognition according to the face image. Because the face recognition device implants interference information at the stage of collecting face images before performing face recognition, so as to recognize the face information in the face images carrying the interference information, by overcoming the interference information, the human face can be improved. The bottleneck of face recognition security.

In order to better understand the above technical solutions, the above technical solutions will be described in detail below with reference to the accompanying drawings and specific embodiments.

Referring to FIG. 2, FIG. 2 is the first embodiment of the face recognition method of the present invention, and the face recognition method includes the following steps:

Step S10, obtaining interference information.

Attacks against face recognition systems include presentation attacks and adversarial attacks. Presentation attack uses photos, 3D face masks and other equipment to forge faces to deceive the face recognition system. It has simple operation, low cost, low technical threshold and good attack effect. However, there are currently a variety of presentation attack detection methods for this attack method. Schemes have been proposed and perfected one after another, and simple presentation attacks have been difficult to evade detection technology. Adversarial attack is a new type of attack method. It uses the loopholes in artificial intelligence algorithms to carefully construct input samples. Even if the human eye can detect the abnormality, it can mislead the face recognition system and produce a good attack effect. For example: confrontational glasses, confrontational stickers, etc. Experiments have shown that after the user wears "adversarial glasses" or affixes "adversarial stickers", the face recognition system will incorrectly determine the user's identity.

In this embodiment, optionally, the face recognition device of the present invention includes, but is not limited to, an interference information input module, an interference information implantation and signal modulation module, a lighting driving module, a lighting fixture, a collection module, and a face recognition system, Among them, the interference information input module, the interference information implantation module and the signal adjustment module, the lighting drive module and the face recognition system are all located in the processor of the above-mentioned face recognition device, and the interference information input module and the interference information implantation and signal modulation The modules are connected, and the interference information implantation and signal modulation module is also connected with the lighting drive module and the lighting fixture, and modulates the transmission signal of the implanted interference information to the lighting fixture to send out high-speed bright and dark flickering light signals that are invisible to the human eye. The illumination light is modulated by the signal modulation module, and the attack gradient information is regularly implanted in the image acquisition stage of the face recognition system, so that the face recognition system cannot detect faces or even recognize different faces, thereby realizing denial of service attacks and Escape attack. The above-mentioned interference information may be, but not limited to, modulating the transmitted signal of implanted attack information onto a lighting fixture to emit high-speed bright and dark flickering light signals that are not detectable by human eyes, such as LED lighting fixtures.

Step S20, modulate the interference information into a light intensity control signal, and send the light intensity control signal to the lighting device, so that the lighting device adjusts the light intensity according to the light intensity control signal.

In this embodiment, the above-mentioned interference information can be input in the form of digital information through the interference information input module to attack the face recognition device, that is, the human recognition system.

Step S30, acquiring a face image detected by the camera, where the face image includes light intensity information of the lighting device.

In the technical solution of this embodiment, the camera is the acquisition module, and the camera is used to obtain the face image required by the face recognition system, and at the same time receives the high-speed light and dark flickering light signals sent by the LED lighting fixture, and the obtained high-speed The light and dark flickering light signals form light and dark stripes on the image. When the camera takes a picture of a human face, due to the rolling shutter effect, a frame of pictures obtained contains signals at different times. Therefore, in the face image obtained by the camera, the implanted interference information appears as light and dark stripes superimposed on the face image. Face images have been implanted with distracting information.

Step S40, performing face recognition according to the face image.

In this embodiment, the superimposed light and dark stripes will generate additional gradient information on the face image, which will interfere with the face detection unit and the feature extraction unit of the face recognition system, which may cause the face detection unit Invalid to achieve denial of service attack, or reduce the difference of face images to achieve escape attack, perform face recognition on the face images collected by the above cameras, optionally, the security of the face recognition system can be determined by the face recognition results sex.

In the technical solution of this embodiment, the interference information is obtained; the interference information is modulated into a light intensity control signal, and the light intensity control signal is sent to the lighting device, so that the lighting device can adjust the light intensity according to the light intensity. The control signal adjusts the light intensity; acquires a face image detected by the camera, the face image includes the light intensity information of the lighting device; and performs face recognition according to the face image. Because the face recognition device implants interference information at the stage of collecting face images before performing face recognition, so as to identify the face information in the face images carrying the interference information, by overcoming the interference information, the human face can be improved. The security of face recognition system.

Referring to FIG. 3, FIG. 3 is a second embodiment of the face recognition method of the present invention. Based on the first embodiment, the step S10 includes:

Step S11, determine the interference type.

In this embodiment, the types of interference include but are not limited to denial of service attacks and escape attacks. An escape attack refers to an attack in which an attacker constructs specific input samples to deceive the target system without changing the target machine learning system. For example, an attacker could modify non-critical characteristics of a malware sample so that it is deemed benign by an antivirus system, thereby bypassing detection. Samples specially constructed by attackers to carry out escape attacks are often referred to as "adversarial samples". As long as a machine learning model does not learn the discriminative rules perfectly, it is possible for an attacker to construct adversarial examples to fool the machine learning system. For example, researchers have been trying to imitate human visual functions on computers, but because the human visual mechanism is too complex, there are certain differences in the rules that the two systems rely on to discriminate objects. Adversarial images take advantage of these differences to make machine learning models come up with very different results from human vision. A well-known escape sample is the example of pandas and gibbons used by Ian Goodfellow at the 2015 ICLR conference. The target was a deep learning research system from Google. The system uses a network of convolutional neurons to accurately distinguish pictures such as pandas and gibbons. However, the attacker can add a small amount of interference to the panda picture, and the generated picture can still be clearly judged as a panda by a human, but the deep learning system will mistake it for a gibbon.

Step S12: Acquire the interference information according to the interference type.

In this embodiment, the attack information that needs to be implanted is calculated according to the face recognition system to be interfered and the type of interference to be implemented. The above-mentioned interference type and attack information are a binding relationship that is associated in advance. Quickly generate interference information.

In the technical solution of the present embodiment, by determining to associate the interference type with the interference information, the interference information can be quickly generated after the interference type is determined, which improves the execution efficiency of the face recognition method of the present embodiment.

Referring to FIG. 4, FIG. 4 is a third embodiment of the face recognition method of the present invention. Based on the second embodiment, the step S12 includes:

Step S121, when the interference type is coarse light and dark stripes, generate long-run interference information.

In the technical solution of this embodiment, if a denial of service attack is to be carried out, the attack information segment with more 0 bits in a long connection can be selected, that is, long-run interference information is used, and this type of interference information can make the camera implant during imaging. If the thicker stripe information is input, thick stripes appear in the imaged face image. Compared with the thin stripe information implanted in the short-run interference information, the recognition is more difficult. If the face recognition system can identify people with a long run Face image, it can be considered that the stability of the face recognition system is higher, and by implanting long-range interference information that is more suitable for denial of service attacks, it is beneficial to improve the success rate of denial of service attacks on the face recognition system.

Referring to FIG. 5, FIG. 5 is the fourth embodiment of the face recognition method of the present invention. Based on the second embodiment, the step S12 includes:

Step S122, when the interference type is fine light and dark stripes, generate short-run interference information.

In the technical solution of this embodiment, when the interference type is fine light and dark stripes, the attack information segment with fewer 0 bits is selected, and short-run interference information is used. This type of interference information can make the camera perform imaging when imaging. The thin stripe information is implanted to make the imaged face image appear thin stripes. Compared with the thick stripe information embedded in the long-run interference information, the recognition difficulty is weaker, which is in line with the conditions required for the implementation of escape attacks. It is beneficial to improve the success rate of evasion attacks on the face recognition system.

Referring to FIG. 6, FIG. 6 is a fifth embodiment of the face recognition method of the present invention. Based on any one of the first to fourth embodiments, the step S20 includes:

Step S21, according to the interference information, determine a curve change relationship between the light intensity and the time point in the interference information.

Step S22, generating the light intensity control signal of high and low levels according to the curve change relationship.

In this embodiment, the interference information implantation and signal modulation module in the face recognition device converts the calculated interference information into high and low level modulation signals, which can be described by the following formula:

l _dc ×s (t)=LED (t)

Among them, ldc in the above formula is the brightness value of the lighting light, that is, the above-mentioned light intensity, s (t) is the digital information to be implanted that changes with time t, and LED (t) is the composite signal of the two, which is to be loaded Modulation signal on the LED light, and changes with time t; s (t) is a binary digital signal, which takes the value of "0" or "1", therefore, the value of LED (t) is "0" or l _dc .

The lighting driving module in the face recognition device is used to drive the LED (t) of the synthetic modulation signal to drive the LED lighting fixture to emit light; the LED light-emitting chip of the LED lighting fixture is driven to emit light by the synthetic modulation signal, so as to realize the lighting function, and at the same time, the human eye cannot detect it. The received high-speed light and dark flickering signals covertly broadcast interference information; the LED light-emitting chip of the LED lighting fixture is a light-emitting device that supports high-speed modulation, and the LED light-emitting chip is under the control of the synthetic modulation signal LED (t) to emit fast light and dark flickering with time t The illumination light signal of the illuminating light signal, and the rapid light and dark changes of the illumination light signal are not detected by the naked eye, so that the interference information carried by the light is broadcast covertly while illuminating.

In the technical solution of the present embodiment, by transmitting the broadcast interference information in an explicit and covert manner, the face recognition system can be interfered without being noticed, the intensity of the interference is improved, and the face recognition system in this embodiment is further improved. security bottleneck.

Referring to FIG. 7, FIG. 7 is a sixth embodiment of the face recognition method of the present invention. Based on any one of the first to fifth embodiments, after step S40, the method further includes:

Step S50, determining the first image gradient of the face image.

Step S60, comparing the first image gradient with the pre-stored second image gradient to obtain a comparison result.

Step S70: Determine a face recognition result according to the comparison result.

The image gradient can be regarded as a two-dimensional discrete function, and the image gradient is actually the derivation of this two-dimensional discrete function:

G(x,y) = dx(i,j) + dy(i,j); dx(i,j) = I(i+1,j) - I(i,j)

dy(i,j) = I(i,j+1) - I(i,j)

Image gradients can also generally use median difference:

dx(i,j) = [I(i+1,j) - I(i-1,j)]/2

dy(i,j) = [I(i,j+1) - I(i,j-1)]/2

Among them, G(x, y) in the above formula is the image gradient, I is the value of the image pixel (eg: RGB value), and (i, j) is the coordinate of the pixel.

Image edges are generally achieved by performing gradient operations on the image. The above is a simple gradient definition, in fact, there are more and more complex gradient formulas.

In this embodiment, the first image gradient refers to the image gradient of the face image corresponding to the collected face information, and the second image gradient is the image gradient of the pre-stored sample face image carrying interference information.

In the technical solution of this embodiment, by processing the image gradient, it can be quickly determined whether the face information processed by the face recognition system is extracted from the face image with interference information, so as to avoid the appearance of the face image recognized by the face recognition system. It is concluded that the interference information is not carried, and the interference information is broken, and the accuracy of the face recognition in this embodiment is improved.

Referring to FIG. 8, FIG. 8 is a seventh embodiment of the face recognition method of the present invention. Based on the first to sixth embodiments, the step S70 includes:

Step S71, when the similarity between the first image gradient and the second image gradient is greater than or equal to a preset value, it is determined that the face recognition is successful.

Step S72, when the similarity between the first image gradient and the second image gradient is lower than the preset value, determine that the face recognition fails.

In the technical solution of this embodiment, through the gradient value information degree of the sample face image, it can be quickly determined whether the face information processed by the face recognition system is extracted from the face image with interference information, so as to avoid the appearance of the face recognition system. The recognized face image does not carry the interference information, and it can be concluded that the interference information is broken, and the accuracy of the face recognition in this embodiment is improved.

Referring to FIG. 9, FIG. 9 is an eighth embodiment of the face recognition method of the present invention. Based on the first to seventh embodiments, after step S40, the method further includes:

Step S80, outputting the face recognition result.

In the technical solution of this embodiment, the face recognition result includes but is not limited to generating prompt information of successful interference, failure of interference and safety factor to prompt the administrator of the facial recognition system, thereby enabling the administrator to understand the security of the facial recognition system sex.

In order to achieve the above purpose, the present invention provides a face recognition device, the face recognition device includes: a collection module, a lighting module, a memory, a processor and a computer stored on the memory and running on the processor A program, when the processor executes the computer program, implements each step of the above-mentioned face recognition method.

In order to achieve the above object, the present invention provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, each of the above-mentioned face recognition methods is implemented. step.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowcharts and/or block diagrams, and combinations of flows and/or blocks in the flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in one or more of the flowcharts and/or one or more blocks of the block diagrams.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions An apparatus implements the functions specified in a flow or flows of the flowcharts and/or a block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

It should be noted that, in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not preclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. do not denote any order. These words can be interpreted as names.

Although the preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include the preferred embodiment and all changes and modifications that fall within the scope of the present invention.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention. Thus, provided that these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims (10)

1. A face recognition method is characterized by comprising the following steps:

acquiring interference information;

modulating the interference information into a light intensity control signal, and sending the light intensity control signal to a lighting device so that the lighting device adjusts the light intensity according to the light intensity control signal;

acquiring a face image detected by a camera, wherein the face image comprises light intensity information of the lighting device;

and carrying out face recognition according to the face image.

2. The face recognition method of claim 1, wherein the step of obtaining the interference information comprises:

determining an interference type;

and acquiring the interference information according to the interference type.

3. The face recognition method of claim 2, wherein the step of obtaining the interference information according to the interference type comprises:

and when the interference type is a thick light and dark stripe, generating long-run interference information.

4. The face recognition method of claim 2, wherein the step of obtaining the interference information according to the interference type comprises:

and when the interference type is the thin bright and dark stripe, generating short-run interference information.

5. The face recognition method of any one of claims 1 to 4, wherein the step of modulating the interference information into a light intensity control signal comprises:

determining a curve change relation between light intensity and time points in the interference information according to the interference information;

and generating the light intensity control signals of high and low levels according to the curve change relationship.

6. The face recognition method of claim 5, wherein after the step of performing face recognition based on the face image, further comprising:

determining a first image gradient of the face image;

comparing the first image gradient with a prestored second image gradient to obtain a comparison result;

and determining a face recognition result according to the comparison result.

7. The face recognition method of claim 6, wherein the step of determining the face recognition result according to the comparison result comprises:

when the similarity between the first image gradient and the second image gradient is greater than or equal to a preset value, determining that the face recognition is successful;

and when the similarity of the first image gradient and the second image gradient is lower than the preset value, determining that the face recognition fails.

8. The face recognition method according to claim 6 or 7, wherein after the step of determining the face recognition result according to the comparison result, further comprising:

and outputting the face recognition result.

9. A face recognition method device is characterized in that the face recognition method device comprises the following steps: an acquisition module, a lighting module, a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the face recognition method according to any one of claims 1 to 8 when executing the computer program.

10. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, carries out the steps of the face recognition method according to any one of claims 1 to 8.

Images