Face authentication method and device and electronic equipment

Abstract

The invention provides a face authentication method. The face authentication method comprises the following steps: judging whether a preset starting condition for starting a face shielding authentication mode is met at present or not; and when it is determined that the preset starting condition is met currently, determining a target face shielding type to which a to-be-authenticated face image belongs, and authenticating the to-be-authenticated face image based on a shielding authentication mode corresponding to the target face shielding type. The invention further provides a facial authentication device and electronic equipment.

Description

Technical Field

[0001] The present disclosure relates to the field of authentication technology, and more particularly, to a facial authentication method, device, and electronic device. Background Art

[0002] With the increasing popularity of smart devices and networks, facial authentication is widely used in various businesses. For example, facial authentication can be used to unlock smart devices and confirm user identity when making payments using payment apps.

[0003] However, current facial authentication methods can only authenticate complete facial images, and are often difficult to authenticate for facial images with occlusions. For example, for facial images of users wearing sunglasses or masks, it is often necessary to manually change the authentication method, resulting in a low level of convenience in facial authentication. Summary of the Invention

[0004] In view of this, the present disclosure provides a facial authentication method, apparatus, and electronic device.

[0005] One aspect of the present disclosure provides a facial authentication method, comprising:

[0006] Determine whether the preset start conditions for starting the face cover authentication mode are currently met;

[0007] When it is determined that the preset starting condition is currently met, the target facial occlusion type to which the facial image to be authenticated belongs is determined, and authentication is performed on the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type.

[0008] Optionally, the preset start-up condition includes at least one of the following: the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started; the security authentication request for requesting permission to start the facial occlusion authentication mode is authenticated within the preset time period; the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started, and the duration for which the facial occlusion authentication mode is not started is less than a preset time threshold.

[0009] Optionally, the face occlusion authentication mode is used to perform occlusion authentication on a facial image belonging to the target face occlusion type.

[0010] Optionally, the above method further includes: when it is determined that the preset starting condition is currently met, determining that occlusion authentication is not allowed for facial images belonging to other facial occlusion types except the target facial occlusion type.

[0011] Optionally, the above method further includes: when it is determined that the preset start condition is not currently met, displaying preset inquiry information; the preset inquiry information is used to indicate: whether to initiate a security authentication request for requesting permission to start the face occlusion authentication mode.

[0012] Optionally, the above method further includes: performing full face authentication on the facial image to be authenticated based on a full face authentication method; if the full face authentication fails, determining a target facial occlusion type to which the facial image to be authenticated belongs.

[0013] Optionally, the target facial occlusion type is used to characterize a target occlusion area in a facial image; and the authentication of the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type includes: authenticating image content outside the target occlusion area in the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type.

[0014] Another aspect of the present disclosure provides a facial authentication device, comprising:

[0015] A determination unit, configured to determine whether a preset start condition for starting a face cover authentication mode is currently satisfied;

[0016] The occlusion unit is used to determine the target facial occlusion type to which the facial image to be authenticated belongs when it is determined that the preset starting condition is currently met, and to authenticate the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type.

[0017] Optionally, the preset start-up condition includes at least one of the following: the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started; the security authentication request for requesting permission to start the facial occlusion authentication mode is authenticated within the preset time period; the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started, and the duration for which the facial occlusion authentication mode is not started is less than a preset time threshold.

[0018] Optionally, the face occlusion authentication mode is used to perform occlusion authentication on a facial image belonging to the target face occlusion type.

[0019] Optionally, the occlusion unit is further configured to: when it is determined that the preset start condition is currently satisfied, determine that occlusion authentication is not allowed for facial images belonging to other facial occlusion types except the target facial occlusion type.

[0020] Optionally, the judgment unit is further used to: when it is determined that the preset startup condition is not currently met, display preset inquiry information; the preset inquiry information is used to indicate: whether to initiate a security authentication request for requesting permission to start the face occlusion authentication mode.

[0021] Optionally, the above-mentioned device also includes a full-face unit, which is used to: perform full-face authentication on the facial image to be authenticated based on the full-face authentication method; if the full-face authentication fails, determine the target facial occlusion type to which the facial image to be authenticated belongs.

[0022] Optionally, the target facial occlusion type is used to characterize a target occlusion area in a facial image; and the occlusion unit is used to: perform authentication on image content outside the target occlusion area in the facial image to be authenticated based on an occlusion authentication method corresponding to the target facial occlusion type.

[0023] Another aspect of the present disclosure provides an electronic device, comprising one or more processors and one or more memories, wherein the memories are used to store executable instructions, and when the executable instructions are executed by the processors, implement the above method.

[0024] Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method described above when executed.

[0025] Another aspect of the present disclosure provides a computer program product, comprising a computer program, wherein the computer program comprises computer-executable instructions, and the instructions are used to implement the method described above when executed.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0028] Figure 1 The following schematically illustrates an application scenario of a facial authentication method and apparatus according to an embodiment of the present disclosure;

[0029] Figure 2 A flowchart of a facial authentication method according to an embodiment of the present disclosure is schematically shown;

[0030] Figure 3 The following schematically shows a flow chart of another facial authentication method according to an embodiment of the present disclosure;

[0031] Figure 4 The following schematically shows a structural diagram of a facial authentication device according to an embodiment of the present disclosure;

[0032] Figure 5 The block diagram schematically shows an electronic device suitable for implementing a facial authentication method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0034] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved all comply with the provisions of relevant laws and regulations, adopt necessary confidentiality measures, and do not violate public order and good morals. In the technical solutions disclosed herein, the acquisition, collection, storage, use, processing, transmission, provision, disclosure, and application of data all comply with the provisions of relevant laws and regulations, adopt necessary confidentiality measures, and do not violate public order and good morals.

[0035] In scenarios where personal information is used for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure all provide users with corresponding operation portals for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge, and skills, and have reached a certain level of professionalism.

[0036] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0037] When expressions such as "at least one of A, B, or C," are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (e.g., "a system having at least one of A, B, or C" should include, but is not limited to, systems having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, and C, etc.). The terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the quantity of the technical features being referred to. Therefore, features specified as "first" or "second" may explicitly or implicitly include one or more of the aforementioned features.

[0038] With the increasing popularity of smart devices and networks, facial authentication is widely used in various businesses. For example, facial authentication can be used to unlock smart devices and confirm user identity when making payments using payment apps.

[0039] However, current facial authentication methods can only authenticate complete facial images, and are often difficult to authenticate for facial images with occlusions. For example, for facial images of users wearing sunglasses or masks, it is often necessary to manually change the authentication method, resulting in a low level of convenience in facial authentication.

[0040] The disclosed embodiment provides a facial authentication method, in which it is possible to automatically determine whether authentication can be performed on an obstructed facial image, thereby reducing the need for users to manually change authentication methods and improving the convenience of facial authentication.

[0041] Specifically, this method provides an occluded face authentication mode. This occluded face authentication mode can be used to authenticate facial images with occlusions. The specific authentication method is not limited. It can be used to authenticate only the image content outside the occluded area of ​​the facial image, or it can be used to authenticate with a reduced weight for the occluded area of ​​the facial image, or with a higher weight for the non-occluded area of ​​the facial image.

[0042] Accordingly, it can be determined whether the preset activation conditions for activating the face occlusion authentication mode are currently met. If the preset activation conditions are currently met, the face occlusion authentication mode can be activated to perform occlusion authentication on the obscured facial image. Specifically, if it is determined that the preset activation conditions are currently met, occlusion authentication can be performed on the facial image to be authenticated.

[0043] The present disclosure does not limit the specific preset activation conditions. Specifically, the user may pre-set the permission to activate the face occlusion authentication mode, or the user may pass biometric authentication, such as fingerprint authentication or pupil authentication.

[0044] In this method, a facial image to be authenticated can be first determined. If it is determined that the preset activation conditions for activating the facial occlusion authentication mode are currently met and that the facial image to be authenticated is obscured, authentication can be performed on the facial image to be authenticated based on the obscuration authentication method in the facial occlusion authentication mode. Specifically, the corresponding obscuration authentication method can be determined based on the type or location of obscuration in the facial image to be authenticated, or alternatively, the corresponding obscuration authentication method can be determined based on the type or location of obscuration in the facial occlusion authentication mode. The order of determining the preset activation conditions and determining whether the facial image to be authenticated is obscured is not restricted; the determinations can be performed in parallel or sequentially.

[0045] The above method can automatically determine whether the obscured face authentication mode can be started and whether authentication can be performed for obscured facial images by presetting the startup conditions, thereby reducing the need for users to manually change the authentication method and improving the convenience of facial authentication.

[0046] Figure 1 The following schematically illustrates an application scenario of a facial authentication method and device according to an embodiment of the present disclosure.

[0047] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, or the third terminal device 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables, etc.

[0048] The user may use the first terminal device 101, the second terminal device 102, or the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, or the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0049] The first terminal device 101, the second terminal device 102, or the third terminal device 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0050] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the first terminal device 101, the second terminal device 102, or the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal device.

[0051] Among them, the user can interact with the first terminal device 101, the second terminal device 102, or the third terminal device 103 to perform facial authentication locally on the terminal device, and the terminal device can execute a facial authentication method provided by an embodiment of the present disclosure. The user can also interact with the server 105 through the first terminal device 101, the second terminal device 102, or the third terminal device 103, and perform actual facial authentication through the server 105. The specific facial matching authentication can be performed by the server 105, and the determination of whether to activate the obstructed facial authentication mode can be performed by the terminal device or the server 105.

[0052] It should be noted that the facial authentication method provided in the embodiments of the present disclosure can generally be performed by the first terminal device 101, the second terminal device 102, the third terminal device 103, or the server 105. Accordingly, the facial authentication apparatus provided in the embodiments of the present disclosure can generally be set in the first terminal device 101, the second terminal device 102, the third terminal device 103, or the server 105. The facial authentication method provided in the embodiments of the present disclosure can also be performed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105. Accordingly, the facial authentication apparatus provided in the embodiments of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or the server 105.

[0053] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0054] The following is a detailed description of a facial authentication method provided in an embodiment of the present disclosure.

[0055] Figure 2 The flowchart of a facial authentication method according to an embodiment of the present disclosure is schematically shown.

[0056] The present method does not limit the specific execution subject. Optionally, the execution subject can be any electronic device or any software application, such as a computer, laptop, tablet computer, mobile phone or other mobile device, or a system application, payment application or communication software that requires facial recognition.

[0057] like Figure 2 As shown, the method flow may include the following steps.

[0058] S201: Determine whether a preset activation condition for activating a face cover authentication mode is currently met.

[0059] S202: When it is determined that the preset starting condition is currently met, determine the target facial occlusion type to which the facial image to be authenticated belongs, and authenticate the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type.

[0060] The above method can automatically determine whether the obscured face authentication mode can be started by presetting the startup conditions, which can reduce the situation where users have to manually change the authentication method and improve the convenience of facial authentication.

[0061] Alternatively, if it is determined that the preset activation conditions are not currently met, the face occlusion authentication mode may not be activated, or authentication may be rejected for the obscured face image. For example, a message such as "face authentication failed" or "face occlusion authentication rejected" may be displayed to the user.

[0062] It should be noted that the disclosed embodiments do not limit the specific form of the facial occlusion authentication mode; any mode capable of authenticating an obscured facial image is sufficient. S201 may specifically determine whether preset activation conditions for facial occlusion authentication are currently met. For an explanation of the specific facial occlusion authentication mode, please refer to other embodiments.

[0063] The embodiments of the present disclosure do not limit the facial image to be authenticated, and the facial image to be authenticated can be any facial image. For the convenience of description, any facial image that requires facial authentication is referred to as a facial image to be authenticated. The embodiments of the present disclosure do not limit the source of the facial image to be authenticated. For example, it can be a facial image captured in real time by a camera unit, or it can be a facial image obtained from an external device for authentication. In a specific example, when a user interacts with a terminal device, the terminal device can capture the user's facial image in real time through a camera unit as the facial image to be authenticated for facial authentication. Alternatively, the server can obtain the user's facial image sent by the terminal device and perform facial authentication.

[0064] The embodiments disclosed herein do not limit the specific form and content of the facial occlusion type. Optionally, the facial occlusion type can be divided into occlusion and non-occlusion; it can also be classified according to the facial area that is blocked, for example, eye occlusion, mouth occlusion, nose occlusion, lower face occlusion, etc.; it can also be classified according to the obstruction or the reason for the obstruction, for example, mask occlusion, backlight occlusion, makeup occlusion, sunglasses occlusion, hat brim occlusion, etc. Different facial occlusion types can also be combined. For example, mask occlusion usually includes mouth occlusion and nose occlusion. For specific explanations, please refer to other embodiments.

[0065] The embodiments disclosed herein do not limit the specific operation of the occlusion authentication method. Optionally, facial authentication usually involves matching a standard facial image with the facial image to be authenticated, and determining whether the degree of matching is greater than a preset matching degree threshold. The occlusion authentication method may specifically involve matching the non-occluded area in the standard facial image with the non-occluded area in the facial image to be authenticated; or it may involve combining the standard facial image with the occluded object according to the type of occluded object, and then matching the combined image with the facial image to be authenticated; or it may involve directly authenticating the facial image to be authenticated based on a pre-trained occlusion image recognition model, and the training samples of the occlusion image recognition model during the training process may include facial images with occlusions, so that identification and authentication can be performed on facial images with occlusions. For specific explanations, please refer to other embodiments.

[0066] The present disclosure does not limit subsequent operations when the preset start condition is not currently met. Optionally, when it is determined that the preset start condition is not currently met, the facial occlusion authentication may be rejected or the facial authentication may be determined to have failed.

[0067] The disclosed embodiments do not limit the steps after the facial occlusion authentication of the facial image to be authenticated passes or fails. Optionally, when the facial image to be authenticated passes the authentication based on the occlusion authentication method, corresponding operations can be performed, such as unlocking the device, unlocking the application, initiating a payment request, etc.; when the facial image to be authenticated fails or fails the authentication based on the occlusion authentication method, corresponding operations can be refused to be performed, such as refusing to unlock the device, refusing to initiate a payment request, etc., and the result of the authentication failure can be fed back to the user so that the user can perform further operations. Corresponding security measures can also be implemented, such as not performing facial occlusion authentication or not performing authentication after multiple authentication failures.

[0068] The above method flow is explained in detail below.

[0069] 1. S201: Determine whether a preset activation condition for activating a face cover authentication mode is currently met.

[0070] 1. Timing of execution.

[0071] The embodiment of the present disclosure does not limit the specific execution time or specific triggering situation of executing S201, and does not limit the specific execution time or specific triggering situation of determining whether the face occlusion authentication mode can be started.

[0072] Optionally, S201 can be executed periodically or continuously, and it can be periodically or continuously determined whether the preset starting conditions for starting the facial occlusion authentication mode are currently met. The preset starting conditions can be determined by real-time monitoring or periodic monitoring. S201 can also be triggered to be executed under a preset trigger condition to trigger the determination of whether the preset starting conditions for starting the facial occlusion authentication mode are currently met.

[0073] The embodiments of the present disclosure are not limited to specific preset triggering conditions. Optionally, the preset triggering condition may specifically be a situation where full face authentication fails, a situation where the image currently being authenticated is identified as obscured, or a situation where the image to be authenticated is determined to be obscured. Of course, other preset triggering conditions are also possible, such as a user requesting to initiate facial occlusion authentication mode. The above situations are merely exemplary.

[0074] In an optional embodiment, if full-face authentication fails for the facial image to be authenticated, a determination may be made as to whether preset activation conditions for initiating a facial obstruction authentication mode are currently met. Specifically, full-face authentication may be performed on the entire face. Full-face authentication typically authenticates the entire face (including facial features such as facial features and shape). For obstructed facial images, full-face authentication often struggles to accurately identify them, resulting in a high probability of authentication failure. Therefore, a determination may be made as to whether the facial obstruction authentication mode can be activated, thereby performing the facial obstruction authentication process and improving the convenience of facial authentication.

[0075] In another optional embodiment, upon determining that the facial image to be authenticated contains occlusion, a determination may be made as to whether the preset activation conditions for initiating the facial occlusion authentication mode are currently met. This embodiment does not limit the specific method for determining whether the facial image to be authenticated contains occlusion; identification may be performed using a pre-trained model. Furthermore, upon determining that the facial image to be authenticated contains occlusion, a direct determination of the corresponding facial occlusion type may be made. Thus, upon determining that the facial image to be authenticated contains a target facial occlusion type, a determination may be made as to whether the preset activation conditions for initiating the facial occlusion authentication mode are currently met.

[0076] In another optional embodiment, the above-mentioned preset triggering conditions can also be combined, and the embodiment of the present disclosure does not limit the specific combination method. Specifically, it can be: when the full-face authentication of the facial image to be authenticated fails and it is determined that there is occlusion in the facial image to be authenticated, it is determined whether the preset startup conditions for starting the facial occlusion authentication mode are currently met. Among them, the steps of performing full-face authentication on the face to be authenticated and judging whether there is occlusion in the facial image to be authenticated do not limit the order of execution of the steps. Specifically, they can be executed in parallel or in sequence, or when the full-face authentication of the facial image to be authenticated fails, it can trigger the judgment of whether there is occlusion in the facial image to be authenticated. Among them, judging whether there is occlusion in the facial image to be authenticated can specifically be determining the target facial occlusion type to which the facial image to be authenticated belongs.

[0077] Based on the above preset triggering conditions, it is possible to conveniently determine the timing of determining whether to perform facial occlusion authentication, thereby improving the convenience of facial occlusion authentication.

[0078] 2. Full face authentication and determining whether there is any occlusion in the facial image to be authenticated.

[0079] The embodiments of the present disclosure do not limit the execution timing and step sequence of full face authentication.

[0080] Optionally, full face authentication may be performed when the user requests facial authentication; or full face authentication may be performed on the facial image to be authenticated when it is determined that the preset startup condition is not currently met.

[0081] Optionally, corresponding to the explanation of the preset trigger conditions above, if the preset trigger conditions include full face authentication failure, full face authentication can be performed on the facial image to be authenticated before S201. Furthermore, if authentication fails based on the occlusion authentication method for the facial image to be authenticated in S202, full face authentication can be performed. Specifically, full face authentication can be performed after S202.

[0082] In addition, optionally, full face recognition can also be performed in parallel with S201 and S202 in the process of this method, and the execution order between full face recognition and the process of this method is not limited.

[0083] The embodiments of this disclosure do not limit the specific method of full-face authentication. Optionally, full-face authentication can be performed on the complete face in the facial image to be authenticated. Specifically, the complete face in the facial image to be authenticated can be directly matched with a standard facial image pre-stored by the user, or a pre-trained facial recognition model for full-face authentication can be directly used to perform full-face authentication on the facial image to be authenticated.

[0084] The embodiments of the present disclosure do not limit the timing and sequence of steps for determining whether there is occlusion in the facial image to be authenticated.

[0085] Optionally, when the user requests facial authentication, it can be determined whether there is any occlusion in the facial image to be authenticated; or when full-face authentication fails, it can be determined whether there is any occlusion in the facial image to be authenticated.

[0086] Optionally, corresponding to the explanation of the preset trigger conditions described above, if the preset trigger conditions include determining whether there is occlusion in the facial image to be authenticated, then whether there is occlusion in the facial image to be authenticated can be determined before S201. Optionally, the preset start conditions can also include determining whether there is occlusion in the facial image to be authenticated, so that during the execution of S201, whether there is occlusion in the facial image to be authenticated can be determined. Optionally, during the execution of S202, if it is determined that the preset start conditions are currently met, it can be determined whether there is occlusion in the facial image to be authenticated, thereby determining the target facial occlusion type of the facial image to be authenticated for subsequent facial occlusion authentication.

[0087] The disclosed embodiments do not limit the specific method for determining whether occlusion exists in the facial image to be authenticated. Alternatively, identification can be performed based on a pre-trained model for identifying whether occlusion exists, or based on the statistical distribution of pixel values ​​in the image. For example, for an image occluded by a mask, a large proportion of similar pixel values ​​are usually present in the mask content, and the presence of occlusion can be determined by analyzing the pixel value distribution.

[0088] Optionally, determining whether there is occlusion in the facial image to be authenticated may specifically include determining the facial occlusion type of the facial image to be authenticated. The disclosed embodiments do not limit the method for determining the facial occlusion type; specifically, identification may be performed based on a pre-trained model for identifying the facial occlusion type of an image. Facial occlusion types can be categorized as either occlusion or non-occlusion. The occlusion type can also be further subdivided into more occlusion types, as described in other embodiments.

[0089] In addition, it is also possible to directly determine the facial occlusion type of the facial image to be authenticated without determining whether there is occlusion in the facial image to be authenticated. Corresponding explanations can be found in other embodiments.

[0090] In an optional embodiment, full face authentication may be performed on the facial image to be authenticated based on a full face authentication method; if the full face authentication fails, the target facial occlusion type of the facial image to be authenticated is determined.

[0091] This embodiment can improve the flexibility and comprehensiveness of facial authentication by providing a full-face authentication method based on facial occlusion authentication. This embodiment does not limit the specific timing and order of executing the above steps. For details, please refer to the explanations of other embodiments. Optionally, the above steps can be executed before S202 to perform full-face authentication and determine the target facial occlusion type; or before S201. In this way, according to the corresponding preset trigger conditions, S201 can be executed if full-face authentication fails, or S201 can be executed if the target facial occlusion type is determined to at least indicate occlusion.

[0092] Optionally, if the determined target face occlusion type is unobstructed, since full face authentication has already failed, subsequent steps may be skipped and the authentication process may be directly deemed to have failed. This embodiment can adapt to situations where the face image to be authenticated is obstructed, automatically triggering the face occlusion authentication process, thereby improving the efficiency, flexibility, and convenience of facial authentication.

[0093] 3. Face occlusion authentication mode.

[0094] The disclosed embodiments do not limit the facial occlusion authentication mode, and may specifically be used to indicate that authentication is allowed for facial images with occlusion.

[0095] Optionally, the face occlusion authentication mode may specifically allow authentication for facial images of all face occlusion types, or may allow authentication for facial images of multiple face occlusion types, or may allow authentication for facial images of a single face occlusion type.

[0096] In a specific example, the facial occlusion authentication mode may specifically allow authentication for facial images of the eye occlusion type, while not allowing authentication for facial images of other facial occlusion types, thereby improving the security of facial authentication.

[0097] Therefore, optionally, the face occlusion authentication mode can be used to perform occlusion authentication on facial images belonging to the target face occlusion type. This embodiment can improve the granularity and security of face occlusion authentication by allowing occlusion authentication on facial images belonging to the target face occlusion type.

[0098] Accordingly, since the face occlusion authentication mode allows occlusion authentication for facial images belonging to the target face occlusion type, subsequent step S202 can perform occlusion authentication for the facial image to be authenticated belonging to the target face occlusion type. Optionally, prior to step S201, the target face occlusion type of the facial image to be authenticated can be identified and determined, thereby further determining the face occlusion authentication mode corresponding to the target face occlusion type. By executing S201 to determine whether the face occlusion authentication mode is activated, it is determined whether occlusion authentication is allowed for the facial image belonging to the target face occlusion type.

[0099] In a specific example, different facial occlusion types may correspond to different facial occlusion authentication modes. For example, a facial occlusion authentication mode may be set corresponding to a makeup occlusion type, a facial occlusion authentication mode corresponding to an eye occlusion type, a facial occlusion authentication mode corresponding to a mouth occlusion type, and so on. When it is determined that the facial image to be authenticated is makeup occlusion, S201 may be executed to determine whether a preset activation condition for activating the facial occlusion authentication mode corresponding to the makeup occlusion type is currently met. Specifically, the preset activation condition of "allowing facial images with makeup occlusion type to be authenticated for occlusion authentication" may be determined.

[0100] In addition, optionally, if the facial occlusion authentication mode corresponding to any facial occlusion type is activated, the activated facial occlusion authentication modes corresponding to other facial occlusion types can be directly closed; or, the activated facial occlusion authentication modes corresponding to different facial occlusion types can coexist.

[0101] Therefore, optionally, if it is determined that the preset activation condition is currently met, it is determined that facial images belonging to other facial occlusion types other than the target facial occlusion type are not allowed to be occluded for authentication. This embodiment can improve the security of facial authentication by only allowing facial images with one facial occlusion type to be authenticated at a time.

[0102] In another optional embodiment, the facial occlusion authentication mode may specifically allow authentication for facial images of all facial occlusion types, and then it may be directly determined whether the preset activation condition is currently satisfied. Accordingly, the target facial occlusion type of the facial image to be authenticated may be identified and determined in S201, S202, or before S202.

[0103] For example, if it is determined that a preset activation condition is currently satisfied, the target facial occlusion type of the facial image to be authenticated may be identified and determined. Alternatively, the preset activation condition may include determining whether there is occlusion in the facial image to be authenticated, thereby enabling the target facial occlusion type of the facial image to be authenticated to be identified and determined in S201.

[0104] 4. Preset start conditions.

[0105] The embodiments of the present disclosure do not limit specific preset starting conditions.

[0106] Optionally, the judgment can be made based on user settings. The user can pre-set whether to enable facial occlusion authentication mode and whether to allow occlusion authentication for obscured facial images. The user can also set the validity period for enabling facial occlusion authentication mode. Alternatively, the judgment can be made based on the user's real-time authentication status. This can be done by determining the user's identity after passing authentication based on other authentication methods (non-facial authentication), thereby determining whether to enable facial occlusion authentication mode and whether to allow occlusion authentication for obscured facial images. Different preset activation conditions can be combined, and the presently disclosed embodiments are not limited to specific combinations.

[0107] Therefore, optionally, the preset start-up condition may include at least one of the following: (1) the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started; (2) the security authentication request for requesting permission to start the facial occlusion authentication mode is authenticated within the preset time period; (3) the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started, and the duration for which the facial occlusion authentication mode is not started is less than the preset time threshold.

[0108] This embodiment can improve the security of face occlusion authentication by setting a preset activation condition. Specifically, the security of activating face occlusion authentication can be improved by setting a validity period for activating the face occlusion authentication mode or security authentication.

[0109] The disclosed embodiments do not limit the specific method for setting the effective time period for enabling facial occlusion authentication mode. Alternatively, the effective time period for enabling facial occlusion authentication mode can be pre-set by the user, or automatically determined after the user allows the mode to be enabled.

[0110] The disclosed embodiments do not limit the triggering circumstances and form of the security authentication request for requesting permission to initiate the face-covered authentication mode. Alternatively, the security authentication request may be initiated when a user performs facial authentication, or when full-face authentication fails. In response to the security authentication request, security authentication may be performed to determine whether the security authentication succeeded.

[0111] Optionally, if it is determined that the preset startup conditions are not currently met, a preset query message may be displayed; the preset query message is used to indicate whether a security authentication request for requesting permission to start the facial occlusion authentication mode is initiated. This embodiment can facilitate users to initiate security authentication requests by interacting with the user, thereby improving the convenience of facial authentication. This embodiment does not limit the specific form of the preset query message, which may specifically be a pop-up window. It is understandable that, in response to the displayed preset query message, the user can choose to initiate or not initiate the above-mentioned security authentication request. In the case where the user initiates a security authentication request, S201 may be continued to be executed, and based on the result of the security authentication, it may be determined whether facial occlusion authentication is allowed for the facial image with occlusion. This embodiment can improve the security of facial occlusion authentication through security authentication.

[0112] The embodiments of the present disclosure do not limit the specific method of security authentication. Optionally, security authentication can be user biometric authentication, such as fingerprint authentication, voiceprint authentication, pupil authentication, etc., or password authentication, etc. If the security authentication passes, it can be determined that the facial occlusion authentication mode is allowed to be activated. Specifically, a preset time period can be set, for example, the authentication is passed within 1 minute of initiating the security authentication request. Of course, the preset time period can also be not set. Specifically, for a security authentication request for requesting permission to activate the facial occlusion authentication mode, if it is determined that the security authentication passes, it can be determined that the facial occlusion authentication mode is allowed to be activated.

[0113] Optionally, when the above security authentication is passed, it can be determined that the facial occlusion authentication mode is allowed to be activated, and a valid time period for allowing the facial occlusion authentication mode to be activated can also be determined, so as to facilitate the subsequent determination of the preset activation conditions.

[0114] Furthermore, optionally, restrictions may be added to the validity period for enabling facial obscuration authentication mode, such as the duration of inactivity. If the duration of inactivity is greater than or equal to a preset threshold, it may be considered that the user has not performed facial obscuration authentication for an extended period of time. Consequently, the facial obscuration authentication model may be automatically disabled, preventing activation of facial obscuration authentication mode. This improves the security of facial obscuration authentication and reduces the risk of security degradation caused by users forgetting to disable facial obscuration authentication mode.

[0115] In a specific example, a user-initiated request to allow the activation of the facial obstruction authentication mode can be subject to security authentication. This security authentication can be used to confirm the user's identity. Specifically, password authentication or user biometric authentication can be used. The password in the password authentication can be used only to allow the activation of the facial obstruction authentication mode, distinguishing it from other passwords to improve security. If the user passes the security authentication, it can be determined that the activation of the facial obstruction authentication mode is allowed. Specifically, the activation of the facial obstruction authentication mode can be allowed within a certain validity period, for example, within 4 hours after passing the security authentication. Accordingly, if the user does not perform facial obstruction authentication for 2 consecutive hours within the validity period, the activation of the facial obstruction authentication mode can be directly prohibited, thereby improving the security of facial obstruction authentication.

[0116] It is understood that different facial occlusion authentication modes corresponding to different facial occlusion types may further correspond to the same or different preset activation conditions. In one specific example, the current moment may be within the valid time period for activating the facial occlusion authentication mode corresponding to the "eye occlusion type," but not within the valid time period for activating the facial occlusion authentication mode corresponding to the "mouth occlusion type." Therefore, the facial occlusion authentication mode corresponding to the "eye occlusion type" may be activated, while the facial occlusion authentication mode corresponding to the "mouth occlusion type" may not be activated.

[0117] 2. S202: When it is determined that the preset starting condition is currently met, determine the target facial occlusion type to which the facial image to be authenticated belongs, and authenticate the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type.

[0118] The disclosed embodiments do not limit the source of the facial image to be authenticated. Alternatively, it can be any facial image required for facial authentication that is locally acquired by the execution entity, any facial image required for facial authentication that is acquired from an external device, or any facial image required for facial authentication that is captured in real time by the execution entity. For detailed explanations, please refer to the explanations of other embodiments.

[0119] The present disclosure does not limit the specific method for determining the target facial occlusion type of the facial image to be authenticated. Alternatively, the target facial occlusion type of the facial image to be authenticated may be determined by real-time identification or by obtaining a pre-identified target facial occlusion type of the facial image to be authenticated.

[0120] Optionally, the operation of specifically identifying the target facial occlusion type of the facial image to be authenticated may be performed before S202, so that the target facial occlusion type in the pre-identification result can be directly obtained. Alternatively, the target facial occlusion type of the facial image to be authenticated may be identified in real time in S202.

[0121] The disclosed embodiments do not limit the specific method for identifying the facial occlusion type of the facial image to be authenticated. Alternatively, a pre-trained facial occlusion type classification model can be used to identify the facial image to be authenticated. The facial occlusion type classification model can be used to predict the corresponding facial occlusion type for the input facial image. For explanations of facial occlusion types, see other embodiments, for example, mouth occlusion, eye occlusion, makeup occlusion, mask occlusion, etc.

[0122] The embodiments of the present disclosure do not limit the specific occlusion authentication method. Alternatively, occlusion authentication can be performed based on a model for identifying occluded facial images, or by selecting unobstructed areas of the image for authentication, or by extracting facial feature points for matching based on different content or different parts of the facial image, or by directly performing a similarity match between the facial image to be authenticated and a pre-stored standard facial image, etc.

[0123] Optionally, different facial occlusion types may correspond to different occlusion authentication methods. For example, makeup occlusion may correspond to a model recognition occlusion authentication method, and mouth occlusion may correspond to a method of selecting a non-occluded area for authentication.

[0124] Optionally, the target facial occlusion type can be used to characterize a target occlusion region in a facial image. Based on the occlusion authentication method corresponding to the target facial occlusion type, authentication is performed on the facial image to be authenticated. Specifically, authentication can be performed based on the occlusion authentication method corresponding to the target facial occlusion type, targeting image content outside the target occlusion region in the facial image to be authenticated. This embodiment improves the efficiency and accuracy of facial occlusion authentication by authenticating image content outside the target occlusion region.

[0125] This embodiment does not limit the specific authentication method for the image content of the non-target occluded area. Optionally, authentication can be performed by extracting facial feature points for matching, or directly matching the image content of the non-target occluded area in a pre-stored standard facial image, or using a machine learning model for identifying and authenticating facial image content in the non-target occluded area, etc.

[0126] For ease of understanding, the present disclosure also provides an application example.

[0127] Facial recognition technology can use the camera system to capture and identify the user's facial features to quickly unlock the device or achieve other authentication functions.

[0128] However, facial recognition may have some problems in certain scenarios, such as (1) extreme lighting conditions: in a completely dark environment, facial recognition may be affected, such as difficulty in eye recognition. (2) mouth occlusion: such as wearing a mask, facial recognition may not be able to accurately capture enough facial features, resulting in unlocking failure. (3) eye occlusion: such as wearing sunglasses.

[0129] In this application embodiment, there is no need to manually set a static facial occlusion authentication mode, such as "eyes open and closed mode" or "mask mode", and the facial occlusion authentication mode is automatically switched to.

[0130] Specifically, when a face unlock request with eyes covered is identified, a password input interface may pop up. After the password authentication is passed, the user may be allowed to enter the face occlusion authentication mode corresponding to eye occlusion (referred to as eye occlusion authentication mode for the sake of convenience). For example, unlocking with eyes covered, such as wearing sunglasses, may be allowed within the next 12 hours. After the time expires, the device will return to normal mode. In addition, if the face unlock method or eye occlusion authentication mode is not used to unlock the device for 4 consecutive hours, the device may return to normal mode.

[0131] Similarly, when a facial unlock request with the mouth covered is identified, a password input interface may pop up. After the password authentication is passed, the user is allowed to perform the facial occlusion authentication mode corresponding to the mouth cover (referred to as the mouth occlusion authentication mode for the convenience of description). For example, unlocking with the mouth covered, such as wearing a mask, may be allowed within the next 12 hours, and the device will return to normal mode after the time expires. Furthermore, if the face unlock method or the mouth occlusion authentication mode is not used to unlock the device for 4 consecutive hours, the device may return to normal mode.

[0132] In addition, users can select dynamic or static options for "eyes open and closed mode", and users can also select dynamic or static options for "mask mode".

[0133] This application embodiment also provides a specific operation process. Figure 3 The flowchart schematically shows another facial authentication method according to an embodiment of the present disclosure.

[0134] The full face authentication can be performed on the input facial image to be authenticated. If the full face authentication succeeds, the device can be unlocked successfully. If the full face authentication fails, the facial occlusion type of the facial image to be authenticated can be further identified.

[0135] If the facial image to be authenticated is unobstructed, the authentication may be considered to have failed because the full face authentication has failed.

[0136] If the facial image to be authenticated is occluded, it can be further determined whether a facial occlusion authentication mode corresponding to the identified facial occlusion type is currently enabled. The facial occlusion type here specifically includes, for example, mouth occlusion.

[0137] If the facial occlusion authentication mode corresponding to the identified facial occlusion type has been enabled, occlusion authentication may be performed, and success or failure of the authentication may be determined based on the result of the occlusion authentication.

[0138] If the facial occlusion authentication mode corresponding to the identified facial occlusion type is not enabled, the user may be asked whether to enable the facial occlusion authentication mode corresponding to the identified facial occlusion type.

[0139] If the user operation indicates that the facial occlusion authentication mode corresponding to the identified facial occlusion type does not need to be enabled, it may be determined that the authentication has failed.

[0140] If the user operation indicates that the facial occlusion authentication mode corresponding to the identified facial occlusion type needs to be turned on, further security authentication or identity authentication can be performed, specifically in the form of password authentication, to obtain the authentication password entered by the user.

[0141] If the authentication password is correct, the facial occlusion authentication mode corresponding to the identified facial occlusion type can be enabled. Based on the password being correct, the authentication can be directly determined to be successful, thereby unlocking the device and enabling the facial occlusion authentication mode corresponding to the identified facial occlusion type for the next authentication, while disabling facial occlusion authentication modes corresponding to other facial occlusion types. In other embodiments, based on the password being correct, facial occlusion authentication can be performed based on the enabled facial occlusion authentication mode, and the authentication success or failure can be determined based on the result of the facial occlusion authentication.

[0142] If the authentication password is incorrect, it can be determined that the authentication has failed.

[0143] The above-mentioned face occlusion authentication mode can be used for the authentication function of unlocking a device, specifically for unlocking a mobile device such as a mobile phone. The user's facial image can be captured by the device's built-in camera for unlocking authentication.

[0144] The above-mentioned application embodiment can provide a dynamic setting for automatically identifying whether to switch to the facial occlusion authentication mode, thereby improving the convenience of facial authentication and the security of facial authentication, and reducing the potential safety hazards caused by turning on partial occlusion recognition due to the needs of individual occasions but not returning to the normal mode in time.

[0145] Corresponding to the above method embodiment, the present disclosure also provides a corresponding device embodiment. The explanation of this device embodiment can refer to other embodiments.

[0146] like Figure 4 As shown, Figure 4 The figure schematically shows a structural diagram of a facial authentication device according to an embodiment of the present disclosure.

[0147] The facial authentication device 400 may include a judgment unit 401 and a shielding unit 402 .

[0148] The judgment unit 401 is used to judge whether the preset starting condition for starting the face cover authentication mode is currently met. In an optional embodiment, the judgment unit 401 can be used to execute S201 described above, which will not be repeated here.

[0149] Occlusion unit 402 is configured to, upon determining that a preset activation condition is currently satisfied, determine a target facial occlusion type for the facial image to be authenticated and, based on the occlusion authentication method corresponding to the target facial occlusion type, authenticate the facial image to be authenticated. In an optional embodiment, occlusion unit 402 may be configured to execute step S202 described above, which will not be further described here.

[0150] Optionally, the preset start-up conditions include at least one of the following: the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started; the security authentication request for requesting permission to start the facial occlusion authentication mode is authenticated within the preset time period; the current moment is within the valid time period for allowing the facial occlusion authentication mode to be started, and the duration during which the facial occlusion authentication mode is not started is less than a preset time threshold.

[0151] Optionally, a face occlusion authentication mode is used to perform occlusion authentication on a facial image belonging to a target face occlusion type.

[0152] Optionally, the occlusion unit 402 is further configured to: when it is determined that a preset starting condition is currently satisfied, determine that occlusion authentication is not allowed for facial images belonging to other facial occlusion types except the target facial occlusion type.

[0153] Optionally, the judgment unit 401 is further configured to: display preset inquiry information when it is determined that the preset startup condition is not currently met; the preset inquiry information is used to indicate: whether to initiate a security authentication request for requesting permission to start the face occlusion authentication mode.

[0154] Optionally, the above-mentioned device also includes a full-face unit, which is used to: perform full-face authentication on the facial image to be authenticated based on the full-face authentication method; if the full-face authentication fails, determine the target facial occlusion type to which the facial image to be authenticated belongs.

[0155] Optionally, the target facial occlusion type is used to characterize the target occlusion area in the facial image; the occlusion unit 402 is used to: based on the occlusion authentication method corresponding to the target facial occlusion type, authenticate the image content outside the target occlusion area in the facial image to be authenticated.

[0156] According to embodiments of the present application, any multiple modules in the judgment unit 401 and the shielding unit 402 can be combined into a single module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present application, at least one of the judgment unit 401 and the shielding unit 402 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or can be implemented in any one of the three implementation methods of software, hardware, and firmware, or any appropriate combination of any of these. Alternatively, at least one of the judgment unit 401 and the shielding unit 402 can be at least partially implemented as a computer program module that, when executed, can perform the corresponding functions.

[0157] Figure 5 The block diagram schematically shows an electronic device suitable for implementing a facial authentication method according to an embodiment of the present disclosure.

[0158] like Figure 5 As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage unit 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0159] Various programs and data required for the operation of the electronic device 900 are stored in the RAM 903. The processor 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. The processor 901 executes the various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 902 and / or the RAM 903. It should be noted that the programs may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also execute the various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0160] According to an embodiment of the present disclosure, electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to bus 904. Electronic device 900 may also include one or more of the following components connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 908 including a hard disk; and a communication section 909 including a network interface card such as a LAN card or modem. Communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. Removable media 911, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 910 as needed, so that computer programs read from the removable media can be installed into storage section 908 as needed.

[0161] The present disclosure also provides an electronic device, comprising: one or more processors configured to execute any method embodiment in the embodiments of the present disclosure.

[0162] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0163] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to cause the computer system to implement the method of the embodiments of the present disclosure.

[0164] Those skilled in the art will appreciate that various combinations and / or combinations of features described in the various embodiments and / or claims of this disclosure may be made, even if such combinations or combinations are not explicitly described in this disclosure. In particular, various combinations and / or combinations of features described in the various embodiments and / or claims of this disclosure may be made, without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0165] The embodiments of the present disclosure are described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be used in combination to advantage. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A facial authentication method, comprising: Determine whether the preset start conditions for starting the face cover authentication mode are currently met; When it is determined that the preset starting condition is currently met, the target facial occlusion type to which the facial image to be authenticated belongs is determined, and authentication is performed on the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type.

2. The method according to claim 1, wherein the preset starting condition comprises at least one of the following: The current moment is within the valid time period for enabling the facial obstruction authentication mode; Passing the security authentication request for requesting permission to start the face-obstruction authentication mode within a preset time period; The current moment is within the valid time period for allowing the facial obstruction authentication mode to be activated, and the duration during which the facial obstruction authentication mode is not activated is less than a preset duration threshold.

3. The method according to claim 1 or 2, wherein the face occlusion authentication mode is used to perform occlusion authentication on a facial image belonging to the target face occlusion type.

4. The method according to claim 3, further comprising: In a case where it is determined that the preset starting condition is currently satisfied, it is determined that occlusion authentication is not allowed for facial images belonging to other facial occlusion types except the target facial occlusion type.

5. The method according to claim 1, further comprising: If it is determined that the preset start condition is not currently met, displaying the preset inquiry information; The preset query information is used to indicate whether to initiate a security authentication request for requesting permission to start the face-covering authentication mode.

6. The method according to claim 1, further comprising: Based on the full face authentication method, performing full face authentication on the facial image to be authenticated; In the event that full face authentication fails, the target face occlusion type to which the facial image to be authenticated belongs is determined.

7. The method according to claim 1, wherein the target facial occlusion type is used to characterize a target occlusion area in a facial image; The occlusion authentication method corresponding to the target facial occlusion type is used to authenticate the facial image to be authenticated, including: Based on the occlusion authentication method corresponding to the target facial occlusion type, authentication is performed on image content outside the target occlusion area in the facial image to be authenticated.

8. A facial authentication device, comprising: A determination unit, configured to determine whether a preset start condition for starting a face cover authentication mode is currently satisfied; The occlusion unit is used to determine the target facial occlusion type to which the facial image to be authenticated belongs when it is determined that the preset starting condition is currently met, and to authenticate the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type.

9. An electronic device comprising: One or more processors configured to perform: Determine whether the preset start conditions for starting the face cover authentication mode are currently met; When it is determined that the preset starting condition is currently met, the target facial occlusion type to which the facial image to be authenticated belongs is determined, and authentication is performed on the facial image to be authenticated based on the occlusion authentication method corresponding to the target facial occlusion type. 10 . A computer-readable storage medium storing computer-executable instructions, wherein the instructions are used to implement the method according to claim 1 when executed.

Images