WO2022105650A1

WO2022105650A1 - Update method for face image, storage medium, electronic device, and vehicle

Info

Publication number: WO2022105650A1
Application number: PCT/CN2021/129692
Authority: WO
Inventors: 代芳; 杨冬生; 刘柯; 王欢
Original assignee: 比亚迪股份有限公司
Priority date: 2020-11-23
Filing date: 2021-11-10
Publication date: 2022-05-27
Also published as: CN114529961A

Abstract

An update method for a face image, a storage medium, an electronic device, and a vehicle, relating to the technical field of image recognition. The update method for a face image comprises: acquiring a face image to be recognized; evaluating said face image to obtain a first quality score, and extracting features of said face image to obtain a first image feature; obtaining a pre-stored image feature of a pre-stored standard face image; and determining, according to the first quality score, the first image feature and the pre-stored image feature, whether to update the pre-stored image feature to the first image feature.

Description

Face image update method, storage medium, electronic device, and vehicle

CROSS-REFERENCE TO RELATED APPLICATIONS

The present disclosure claims the priority of the Chinese Patent Application No. 202011320274.0, filed on November 23, 2020, and entitled "Method for Updating Face Image, Storage Medium, Electronic Device, and Vehicle", the entire contents of which are incorporated by reference in in this disclosure.

technical field

The present disclosure relates to the technical field of image recognition, and in particular, to a face image updating method, a storage medium, an electronic device, and a vehicle.

Background technique

At present, face recognition technology is more and more widely used in the automotive field, such as face unlocking system outside the car, driver fatigue detection in the car, driver identification, etc. In the application of face recognition technology, it is necessary to ensure the security of face recognition and the ease of use of the face recognition system. Since the vehicle-mounted face unlocking system has a long service cycle, it is necessary to update the standard face features to avoid the occurrence of people in different time periods of the same individual due to the variability of the face and the influence of factors such as light, age, fat and thinness. When the face images cannot be matched.

In order to solve the above problem, a technology of updating standard face features according to the interval time between two face unlocks is proposed in the related art. However, this technology needs to be related to time, and is not suitable for situations where the user has not unlocked for a long time and the face is deformed greatly, such as short-term weight gain or weight loss. At the same time, there is no unified standard for the preset unlocking time between two intervals, which is not friendly to the usability of the system.

SUMMARY OF THE INVENTION

The present disclosure aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the present disclosure proposes a face image update method, storage medium, electronic device, and vehicle, so as to realize real-time update of a standard face image, thereby reducing the influence of face variability on the face recognition system, and improving human performance. Accuracy and ease of use of face recognition.

In a first aspect, the present disclosure provides a method for updating a face image, the method comprising the following steps: collecting a face image to be recognized; evaluating the quality of the face image to be recognized to obtain a first quality score, and extracting The feature of the face image to be recognized is to obtain the first image feature; the pre-stored image feature of the pre-stored standard face image is obtained; according to the first quality score, the first image feature and the pre-stored image feature, determine whether to The pre-stored image feature is updated to the first image feature.

In the face image updating method according to the embodiment of the present disclosure, when the to-be-recognized face image is collected, the quality evaluation of the to-be-recognized face image is performed to obtain a first quality score, and feature extraction is performed on the to-be-recognized face image to obtain the first quality score. image features; and then determine whether to update the pre-stored image features to the first image features according to the first quality score, the first image features, and the pre-stored image features. In this way, the standard face image can be updated in real time, thereby reducing the influence of face variability on the face recognition system, and improving the accuracy and ease of use of face recognition.

In a second aspect, the present disclosure provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the above-mentioned method for updating a face image.

The computer-readable storage medium of the embodiment of the present disclosure, when the computer program stored on the computer program corresponding to the above-mentioned method for updating a face image is executed, can realize real-time updating of a standard face image, thereby reducing the performance of the face recognition system. Affected by the variability of faces, the accuracy and ease of use of face recognition are improved.

In a third aspect, the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory. When the computer program is executed by the processor, the above-mentioned method for updating a face image is implemented. .

The electronic device according to the embodiment of the present disclosure can realize the real-time update of the standard face image by implementing the above-mentioned method for updating the face image, thereby reducing the influence of the face variability on the face recognition system and improving the accuracy of face recognition. flexibility and ease of use.

In a fourth aspect, the present disclosure provides a vehicle including the above electronic device.

The vehicle of the embodiment of the present disclosure can realize real-time update of the standard face image through the above-mentioned electronic device, thereby reducing the influence of face variability on the face recognition system, and improving the accuracy and ease of use of face recognition.

Additional aspects and advantages of the present disclosure will be set forth, in part, from the following description, and in part will be apparent from the following description, or may be learned by practice of the present disclosure.

Description of drawings

1 is a flowchart of a method for updating a face image according to a first embodiment of the present disclosure;

2 is a flowchart of a method for updating a face image according to a second embodiment of the present disclosure;

3 is a flowchart of a method for updating a face image according to a specific embodiment of the present disclosure;

FIG. 4 is a structural block diagram of a vehicle according to an embodiment of the present disclosure.

Detailed ways

Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to explain the present disclosure and should not be construed as a limitation of the present disclosure.

The method for updating a face image, an electronic device, and a vehicle according to embodiments of the present disclosure will be described below with reference to FIGS. 1-4 .

FIG. 1 is a flowchart of a method for recognizing a face image according to an embodiment of the present disclosure.

As shown in Figure 1, the face image recognition method includes the following steps:

S11, collect a face image to be recognized.

As an example, as shown in FIG. 3 , a face video stream to be recognized may be collected by a collection device (such as a camera on a vehicle terminal), and then an image of a face to be recognized may be obtained according to the face video stream to be recognized. The above-mentioned face image may be any one of a 2D image, a depth image and a 3D face image.

Specifically, obtaining the face image to be identified according to the face video stream to be identified may include: obtaining an image containing a face according to the face video stream to be identified, and then performing face region extraction and key point positioning on the image, such as , an image containing a human face can be input into a preset face detection network, so as to obtain the face area and key point location, and then obtain key point information according to the key point location. Wherein, the image in the above-mentioned face region can be used as the face image to be recognized, and the above-mentioned key points can be 5 points or 68 points.

S12 , evaluating the quality of the face image to be recognized to obtain a first quality score, and extracting features of the face image to be recognized to obtain first image features.

Specifically, quality evaluation is performed on the extracted face region to obtain a first quality score. For example, face alignment can be performed according to the above-mentioned key point information, and then the quality of the face region can be evaluated to obtain the first quality score.

After the first quality score is obtained, it can be determined whether the first quality score is within the first preset quality range; if the first quality score is within the first preset quality range, the above-mentioned face image to be recognized is performed. Feature extraction, the step of obtaining the first image feature.

As an example, as shown in FIG. 3 , it can be determined whether the first quality score is within the first preset quality range by comparing the relationship between the first quality score and the first quality threshold. If the above-mentioned first quality score represents the quality of the face image, the higher the first quality score, the better the quality of the face image. At this time, to achieve that the first quality score is within the first preset quality range, the first quality score needs to be greater than the first quality threshold. If the above-mentioned first quality score represents the quality loss of the face image, the higher the first quality score is, the worse the quality of the face image is. At this time, in order to realize that the first quality score is within the first preset quality range, the first quality score needs to be smaller than the first quality threshold.

The first quality threshold may be set by the user, for example, a percentage r1 of the first quality threshold and the possible maximum value of the first quality score may be set, where r1 is a certain value from 0 to 100%.

Optionally, if the above-mentioned first quality score is not within the first preset quality range, the above-mentioned step of acquiring the face image to be recognized is performed again.

In this way, it can be detected whether the quality of the face image to be recognized is qualified. Specifically, if the first quality score is within the first preset quality range, it means that the quality of the face image to be recognized corresponding to the first quality score is qualified, and the subsequent update steps can be continued; If the quality score is not within the first preset quality range, it means that the quality of the face image to be recognized corresponding to the first quality score is unqualified, the image cannot realize face unlocking, and is not suitable for updating standard images.

In a feasible implementation manner, if the quality of the above-mentioned face image to be recognized is qualified, feature extraction is performed on the face image to be recognized to obtain the first image feature.

Specifically, feature extraction is performed on the face image to be recognized to obtain a feature matrix, and the feature matrix is used as the first image feature.

Optionally, the face image to be recognized can also be extracted to obtain features capable of face recognition, for example, the HOG (Histogram of Oriented Gradient, histogram of directional gradient) feature, Haar feature ( At least one of a Haar feature), a color feature, and the like, which can then be used as the first image feature.

It should be noted that, after obtaining the first image feature according to the above-mentioned face image to be recognized, the living body feature of the above-mentioned face image to be recognized can also be obtained. The living body feature is a feature describing whether the face included in the face image to be recognized is a living body face, and the living body feature may include local texture features, light reflection features, biological motion features, etc. in the face image.

S13: Acquire pre-stored image features of the pre-stored standard face image.

Specifically, pre-stored image features can be stored in a template library for face recognition. The acquisition process of the pre-stored image features may be as follows: feature extraction is performed on the pre-stored standard face image to obtain a feature matrix, and then the feature matrix may be used as a pre-stored image feature. The pre-stored image feature may be obtained after obtaining the pre-stored standard face image and pre-stored in the face recognition system, thereby improving the update processing efficiency; it may also be that when the first image feature is obtained, The face image is obtained by feature extraction.

It should be noted that the template library can be a database in a vehicle face recognition system, and the database can also include a pre-stored standard face image used for face recognition and unlocking, the pre-stored standard face image and its pre-stored image features There is a correspondence between them. The above-mentioned pre-stored standard face images are pre-stored standard face images, the number of which may be one or more. Taking two as an example, the first standard face image and the second standard face image may be included. When the user registers with the face recognition system, the face image used in the user registration can be obtained as the initial first standard face image and the initial second standard face image. Of course, the initial second standard may not be set. face image.

S14, according to the first quality score, the first image feature, and the pre-stored image feature, determine whether to update the pre-stored image feature to the first image feature.

Specifically, the living body characteristics of the face image to be recognized corresponding to the first quality score can be judged first, and after judging by living body characteristics (for example, judging that a living body face is recognized), according to the first quality score, the first image characteristics and the Pre-stored image features to determine whether to update the pre-stored image features to the first image features.

In this way, the collected image is subjected to live detection, so that the standard face image can be updated in real time according to the live face image, and the security of the face recognition system is improved.

In an embodiment of the present disclosure, as shown in FIG. 2 , the above-mentioned determining whether to update the pre-stored image feature to the first image feature according to the first quality score, the first image feature, and the pre-stored image feature may include:

S21: Calculate the similarity between the first image feature and the pre-stored image feature corresponding to the first standard face image to obtain the first similarity.

S22: Determine whether the first similarity is greater than a first preset similarity threshold.

It should be noted that, in the embodiment of the present disclosure, the initial first standard face image is the face image obtained when the user registers, but the non-initial first standard face image is updated by the face image to be recognized owned. Because the face image to be recognized and the initial first standard face image may be acquired by the same acquisition device, or may be acquired by different acquisition devices. Therefore, in order to more accurately judge the first similarity, it is necessary to select an appropriate first preset similarity threshold. Specifically, it can be judged whether the collection devices of the face image to be recognized and the first standard face image are the same (for example, whether the type of the collection equipment is the same, or the same collection equipment); the first preset is determined according to the judgment result. Similarity threshold, wherein the first preset similarity threshold for which the determination result is the same determination is greater than the preset similarity threshold for which the determination result is different determination.

It should be understood that in the same-model comparison, that is, the two face images used for comparison are from the same type of acquisition device, at this time, fewer factors need to be considered and the error is smaller, so the corresponding first The preset similarity threshold is relatively large; heterogeneous comparison, that is, the two face images used for comparison are from different types of collection devices. For example, the face image to be recognized is collected by the above collection settings, and the first standard face image The image is collected by the face registration device. At this time, more factors need to be considered in the comparison of the similarity, and the error is larger, so the corresponding first preset similarity threshold is relatively small.

S23, if the first similarity is greater than the first preset similarity threshold, perform face unlocking, and determine whether the first quality score is within the second preset quality range, wherein the image corresponding to the second preset quality range The quality is better than the image quality corresponding to the first preset quality range.

Specifically, if the first similarity is greater than the first preset similarity threshold, it means that the current face image to be recognized satisfies the unlocking conditions of the face recognition system, and face unlocking can be performed, and then the first quality score can be judged again , to determine whether the current face image to be recognized is suitable for updating the pre-stored standard face image.

Optionally, if the first similarity is less than or equal to the first preset similarity threshold, the similarity between the first image feature and the pre-stored image feature corresponding to the second standard face image is calculated to obtain the second similarity; Determine whether the second similarity is greater than the second preset similarity threshold; if the second similarity is greater than the second preset similarity threshold, perform face unlocking. If the second similarity is less than or equal to the second preset similarity threshold, first prompt information is sent (eg, a preset prompt picture, text information, etc. is displayed on the display screen of the vehicle terminal) to prompt the face unlock failure.

The second preset quality range may be determined according to the quality of the first standard face image and the quality of the second standard face image. For example, taking the positive correlation between image quality and the first quality score as an example, the second preset quality range may be a range greater than a second quality threshold, and the second quality threshold may be the average of the scores of two standard face images, and the second quality The threshold should be greater than or equal to the above-mentioned first quality threshold.

In this way, face recognition unlocking can be implemented according to at least two standard images, thereby improving the accuracy and probability of face recognition unlocking and improving user experience.

It should be noted that the update method of the embodiment of the present disclosure may be performed in the process of unlocking through a face image, that is to say, the vehicle-mounted face recognition system may perform the unlocking interaction of the present disclosure while performing the conventional face recognition unlocking interaction. Update method. The manner of determining the second preset similarity threshold is similar to that of determining the first preset similarity threshold, and can be obtained by judging whether the face image to be recognized and the second standard face image are the same collection device.

S24, if the first quality score is within the second preset quality range, update the pre-stored image feature corresponding to the first standard face image to the first image feature.

S25, if the first quality score is not within the second preset quality range, update the pre-stored image feature corresponding to the second standard face image to the first image feature.

It should be noted that when the standard face image is updated according to the face image to be recognized, the above-mentioned key point information and image features of the face image also need to be updated into the template library.

As an example, as shown in FIG. 3 , it can be determined whether the first quality score is within the second preset quality range by comparing the relationship between the first quality score and the second quality threshold. The above-mentioned second quality threshold may be an average value of the first standard face image and the second standard face image. If the first quality score is greater than the second quality threshold, the first quality score is within the second preset quality range, and the pre-stored image feature corresponding to the first standard face image is updated to the first image feature; if the first quality score If it is less than or equal to the second quality threshold, the first quality score is not within the second preset quality range, and the pre-stored image feature corresponding to the second standard face image is updated to the first image feature.

In some embodiments, the quality of the first standard face image obtained by a certain update may be high, resulting in that only the second standard face image is updated after successful face unlocking for several consecutive times, and the face image to be recognized cannot be The situation of face unlocking through the first standard image. Therefore, it is also possible to obtain the consecutive times of using the second standard face image to unlock the face; if the consecutive times reach the first preset times, update the pre-stored image feature corresponding to the current first standard face image to the current first image feature . Thus, the real-time performance of the standard face images in the template library can be guaranteed.

It should be noted that, after the face is successfully unlocked, it is determined whether the consecutive number of times reaches the first preset number of times, and if so, the standard face image in the template library is updated directly without comparing the first quality score and the first quality score. The relationship between the two preset quality ranges.

As an example, when updating the standard face images in the template library, if there is an update, a prompt message can be sent through the vehicle terminal to prompt the user that the template library is updated; if there is no update, no prompt can be given. Of course, you can also not prompt when there is an update, and prompt when there is no update; no prompt when there is an update or not, at this time, the update process runs in the background without interaction with the user; you can also prompt when there is an update or not.

To sum up, the method for updating a face image according to the embodiment of the present disclosure can realize real-time updating of a standard face image, thereby reducing the influence of the face recognition system on the variability of faces, and improving the accuracy and ease of use of face recognition. sex. Moreover, before face recognition, live detection is also performed, which improves the security of the face recognition system. Face recognition is performed according to at least two standard images, thereby further improving the accuracy of face recognition.

The present disclosure also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the above-mentioned method for updating a face image.

The present disclosure also proposes an electronic device.

In the present disclosure, an electronic device includes a memory, a processor, and a computer program stored on the memory. When the computer program is executed by the processor, the above-mentioned method for updating a face image is implemented.

The electronic device according to the embodiment of the present disclosure can realize the real-time update of the standard face image by implementing the above-mentioned method for updating the face image, thereby reducing the influence of the face variability on the face recognition system and improving the accuracy of face recognition. flexibility and ease of use. Moreover, before face recognition, live detection is also performed, which improves the security of the face recognition system. Face recognition is performed according to at least two standard images, thereby further improving the accuracy of face recognition.

As shown in FIG. 4 , the vehicle 1000 includes the aforementioned electronic device 100 .

The vehicle of the embodiment of the present disclosure can realize real-time update of the standard face image through the above-mentioned electronic device, thereby reducing the influence of face variability on the face recognition system, and improving the accuracy and ease of use of face recognition. Moreover, before face recognition, live detection is also performed, which improves the security of the face recognition system. Face recognition is performed according to at least two standard images, thereby further improving the accuracy of face recognition.

It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, for example, may be considered to be an ordered listing of executable instructions for implementing the logical functions, and may be embodied in any computer readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in combination with these Used in order to execute a system, apparatus or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in conjunction with an instruction execution system, apparatus, or apparatus. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections with one or more wiring (electronic devices), portable computer disk cartridges (magnetic devices), random access memory (RAM), Read Only Memory (ROM), Erasable Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program may be printed, as the paper or other medium may be optically scanned, for example, followed by editing, interpretation, or other suitable medium as necessary process to obtain the program electronically and then store it in computer memory.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or a combination of the following techniques known in the art: Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structures, materials, or features are included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

In the description of the present disclosure, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", " Rear, Left, Right, Vertical, Horizontal, Top, Bottom, Inner, Outer, Clockwise, Counterclockwise, Axial, The orientations or positional relationships indicated by "radial direction", "circumferential direction", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present disclosure and simplifying the description, rather than indicating or implying the indicated devices or elements It must have, be constructed, and operate in a particular orientation, and therefore should not be construed as a limitation of the present disclosure.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless expressly and specifically defined otherwise.

In the present disclosure, unless otherwise expressly specified and limited, the terms "installed", "connected", "connected", "fixed" and other terms should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection , or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between the two elements, unless otherwise specified limit. For those of ordinary skill in the art, the specific meanings of the above terms in the present disclosure can be understood according to specific situations.

In the present disclosure, unless expressly stated and defined otherwise, a first feature "on" or "under" a second feature may be in direct contact with the first and second features, or indirectly through an intermediary between the first and second features touch. Also, the first feature being "above", "over" and "above" the second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is level higher than the second feature. The first feature being "below", "below" and "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature has a lower level than the second feature.

Although the embodiments of the present disclosure have been shown and described above, it should be understood that the above-described embodiments are exemplary and should not be construed as limitations of the present disclosure, and those of ordinary skill in the art may interpret the above-described embodiments within the scope of the present disclosure. Embodiments are subject to variations, modifications, substitutions and variations.

Claims

A method for updating a face image, comprising the following steps:

Collect face images to be recognized;

Evaluating the quality of the face image to be identified to obtain a first quality score, and extracting features of the face image to be identified to obtain first image features;

Obtain the pre-stored image features of the pre-stored standard face image;

According to the first quality score, the first image feature and the pre-stored image feature, it is determined whether to update the pre-stored image feature to the first image feature.
The method for updating a face image according to claim 1, wherein before extracting the feature of the face image to be recognized to obtain the first image feature, the updating method further comprises:

determining whether the first quality score is within a first preset quality range;

If the first quality score is within the first preset quality range, the step of extracting the feature of the face image to be recognized to obtain the first image feature is performed.
The method for updating a face image according to claim 2, wherein the pre-stored standard face image comprises a first standard face image and a second standard face image, wherein the The score, the first image feature, and the pre-stored image feature, to determine whether to update the pre-stored image feature to the first image feature, including:

Calculate the similarity between the first image feature and the pre-stored image feature corresponding to the first standard face image to obtain the first similarity;

determining whether the first similarity is greater than a first preset similarity threshold;

If the first similarity is greater than the first preset similarity threshold, perform face unlocking, and determine whether the first quality score is within a second preset quality range, where the second preset It is assumed that the image quality corresponding to the quality range is better than the image quality corresponding to the first preset quality range;

If the first quality score is within the second preset quality range, updating the pre-stored image feature corresponding to the first standard face image to the first image feature;

If the first quality score is not within the second preset quality range, updating the pre-stored image feature corresponding to the second standard face image to the first image feature.
The method for updating a face image according to claim 3, characterized in that, according to the first quality score, the first image feature and the pre-stored image feature, determining whether to update the pre-stored image feature The first image feature further includes:

If the first similarity is less than or equal to the first preset similarity threshold, calculate the similarity between the first image feature and the pre-stored image feature corresponding to the second standard face image to obtain the first Second similarity;

determining whether the second similarity is greater than a second preset similarity threshold;

If the second similarity is greater than the second preset similarity threshold, face unlocking is performed.
The updating method of human face image as claimed in claim 4, is characterized in that, described updating method further comprises:

If the second similarity is less than or equal to the second preset similarity threshold, first prompt information is sent to prompt a face unlock failure.
The updating method of human face image as claimed in claim 4, is characterized in that, described updating method further comprises:

Obtain the consecutive times of face unlocking using the second standard face image;

If the consecutive number of times reaches the first preset number of times, the pre-stored image feature corresponding to the current first standard face image is updated to the current first image feature.
The method for updating a face image according to any one of claims 3-6, wherein the method for updating further comprises:

The second preset quality range is determined according to the quality of the first standard face image and the quality of the second standard face image.
The method for updating a face image according to any one of claims 3-7, wherein the method for updating further comprises:

Determine whether the acquisition device of the face image to be recognized and the first standard face image is the same;

The first preset similarity threshold is determined according to the judgment result,

Wherein, the first preset similarity threshold determined with the same judgment results is greater than the preset similarity threshold determined with different judgment results.
A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the method for updating a face image according to any one of claims 1-8 is implemented.
An electronic device, comprising a memory, a processor and a computer program stored on the memory, characterized in that, when the computer program is executed by the processor, the implementation of any one of claims 1-8 method for updating face images.
A vehicle, characterized by comprising the electronic device as claimed in claim 10 .