An identity authentication method, device, apparatus and computer readable storage medium

Abstract

The application discloses an identity verification method, device and equipment and a computer readable storage medium. The method comprises the following steps: in a multi-person environment, collecting multi-user images; extracting user features of each user in the multi-user images; identifying user features matched with preset target features in the user features of each user, and determining a user corresponding to the user features matched with the target features as a target user; collecting biological feature information of the target user; and if the biological feature information of the target user is matched with preset standard biological feature information, performing an unlocking operation. The application identifies a target user in a multi-person environment, collects only biological feature information of the target user in the multi-person environment, and discriminates whether an identity verification operation can be performed according to the biological feature information. Through the application, the adverse effects of environmental factors on an identity verification process can be reduced, the identity verification time is shortened, the identity verification success rate is improved, and the user experience effect is improved.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to an authentication method, apparatus, device, and computer-readable storage medium. Background Technology

[0002] With the continuous development of terminal technology, smart terminals have become widespread and indispensable tools in people's daily lives. Users need to authenticate themselves before using a smart terminal to confirm their legitimacy. Among existing authentication methods, facial recognition is one option; however, in multi-person environments, facial recognition is significantly less effective.

[0003] For example, when a user uses facial recognition for authentication in a multi-person environment, multiple faces will appear on the terminal screen. The facial detection tool then needs to scan and detect these multiple faces to identify the legitimate user. Because multiple faces need to be detected separately, this increases authentication time and reduces the success rate, negatively impacting the user experience. Summary of the Invention

[0004] The main objective of this invention is to provide an authentication method, apparatus, device, and computer-readable storage medium to solve the problem of low success rate when using facial recognition for authentication in multi-person environments.

[0005] To address the aforementioned technical problems, the present invention provides the following technical solution:

[0006] This invention provides an authentication method, comprising: in a multi-user environment, acquiring multi-user images; extracting user features of each user from the multi-user images; identifying user features that match preset target features among the user features of each user, and determining the user corresponding to the user feature identified that matches the target feature as the target user; acquiring the biometric information of the target user; and performing an unlocking operation if the biometric information of the target user matches preset standard biometric information.

[0007] The user features include user action features; the target features include target action features.

[0008] Before acquiring multi-user images, the process further includes: acquiring an environmental image; detecting whether the environmental image contains multiple face images; and determining that the current environment is a multi-user environment if the environmental image contains multiple face images.

[0009] The biometric information includes at least one of the following: facial feature information, iris feature information, and voice feature information.

[0010] The present invention also provides an authentication device, comprising: a collection module for collecting images of multiple users in a multi-user environment; an extraction module for extracting user features of each user from the multi-user images; an identification module for identifying user features that match preset target features among the user features of each user, and determining the user corresponding to the user feature that matches the target feature as the target user; the collection module is further configured to collect biometric information of the target user; and a verification module for performing an unlocking operation when the biometric information of the target user matches preset standard biometric information.

[0011] The user features include user action features; the target features include target action features.

[0012] The device further includes a detection module; the detection module is used to: acquire an environmental image; detect whether the environmental image includes multiple face images; if the environmental image includes multiple face images, then determine that the current environment is a multi-person environment.

[0013] The biometric information includes at least one of the following: facial feature information, iris feature information, and voice feature information.

[0014] The present invention also provides an authentication device, which includes a processor and a memory; the processor is used to execute an authentication program stored in the memory to implement the above-described authentication method.

[0015] The present invention also provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the above-described authentication method.

[0016] The beneficial effects of this invention are as follows:

[0017] This invention identifies target users with specific characteristics in a multi-user environment and collects only the target user's biometric information for user authentication. This invention reduces the adverse effects of environmental factors on the authentication process, shortens authentication time, increases the success rate, and enhances the user experience. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0019] Figure 1 This is a flowchart of an authentication method according to an embodiment of the present invention;

[0020] Figure 2 This is a detailed flowchart of an authentication method according to an embodiment of the present invention;

[0021] Figure 3 This is a structural diagram of an authentication device according to an embodiment of the present invention;

[0022] Figure 4 This is a structural diagram of an authentication device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] According to embodiments of the present invention, an authentication method is provided. For example... Figure 1 The diagram shown is a flowchart of an authentication method according to an embodiment of the present invention.

[0025] Step S110: In a multi-user environment, acquire images from multiple users.

[0026] Multi-user images refer to photos or videos taken in an environment with multiple people.

[0027] After collecting images of multi-person environments, these images can be used to analyze users' physical characteristics.

[0028] After acquiring multiple frames of video images in a multi-user environment, a multi-user video can be created. This multi-user video can then be used to analyze the actions of each user in the multi-user environment.

[0029] In this embodiment, before acquiring multi-user images, an environmental image is acquired; it is detected whether the environmental image includes multiple face images; if the environmental image includes multiple face images, the current environment is determined to be a multi-user environment.

[0030] Step S120: Extract the user features of each user in the multi-user image.

[0031] User characteristics are used to reflect the features of the target user.

[0032] User characteristics, including but not limited to: user action characteristics.

[0033] For example, user action characteristics include opening the mouth, nodding, shaking the head, smiling, etc.

[0034] Of course, user characteristics can also include physical appearance. For example, long hair, short hair, etc.

[0035] If the multi-user image is a picture of a multi-person environment, the user appearance features of each user appearing in the picture can be extracted. If the multi-user image is a video image of a multi-person environment, the user action features of each user appearing in the video image can be extracted.

[0036] Step S130: Among the user characteristics of each user, identify the user characteristics that match the preset target characteristics, and determine the user corresponding to the user characteristics that match the target characteristics as the target user.

[0037] By detecting the user characteristics of each user in a multi-user environment, target users with preset target characteristics can be identified in the multi-user environment.

[0038] Target users refer to suspected legitimate users of the terminal device. Legitimate users are those who are the legitimate users or owners of the terminal device.

[0039] Target features are used to reflect the characteristics of target users, enabling quick identification of target users in a multi-user environment. Target features are pre-entered and stored by legitimate users.

[0040] Target features include, but are not limited to, target action features. For example, target action features include actions such as opening the mouth, nodding, shaking the head, and smiling. That is, in a multi-person environment, the system identifies target users with preset target action features. Furthermore, preset action recognition technology can be used to identify user action features that match the preset target action features from among the various user action features.

[0041] Of course, target features can also be physical characteristics. For example: long hair, short hair, etc.

[0042] In this embodiment, if the similarity between a user feature and a preset target feature is greater than a preset similarity threshold, then the user feature is determined to match the preset target feature. Furthermore, a preset image recognition technique can be used to identify user shape features that match the preset target shape features among the various user shape features.

[0043] Step S140: Collect the biometric information of the target user.

[0044] Biometric information includes at least one of the following: facial features, iris features, and voice features.

[0045] Step S150: If the biometric information of the target user matches the preset standard biometric information, then the unlocking operation is performed.

[0046] Standard biometric information is the pre-stored biometric information of legitimate users.

[0047] If the biometric information matches preset standard biometric information, the target user is determined to be a legitimate user, and the unlocking operation is performed; otherwise, the target user is determined to be an illegitimate user, and the unlocking operation is prohibited. Of course, after determining that the target user is an illegitimate user, the process of this embodiment can be terminated directly, or multiple user images can be re-captured to re-determine the target user.

[0048] Specifically, after the unlock verification event is triggered, if the current environment is determined to be a multi-user environment, the user characteristics of each user are detected. After collecting the biometric information of the target user, if the target user is determined to be a legitimate user, the unlock operation is performed; if the target user is determined to be an illegitimate user, the unlock operation is prohibited. Further, the unlock verification event is triggered after a preset button is clicked. This preset button can be a physical button or a virtual button. For example, the preset button is the power button of the terminal. After the power button is clicked, it begins to detect whether the current environment is a multi-user environment. If so, it begins to collect multi-user images and extract the user characteristics of each user; if not, it directly collects the biometric information of users in the current environment.

[0049] In this embodiment, in a multi-user environment, a target user with specific characteristics is identified. Furthermore, only the target user's biometric information is collected, and user authentication is performed based on this biometric information. This embodiment reduces the adverse impact of environmental factors on the authentication process, shortens authentication time, increases the success rate of authentication, and enhances the user experience.

[0050] This embodiment can be applied not only to smart terminals but also to devices requiring authentication. For example, the authentication method of this embodiment can be applied to smart home devices such as door locks and safes.

[0051] The following is a more specific embodiment to illustrate the authentication method of the present invention.

[0052] like Figure 2 The diagram shown is a detailed flowchart of an authentication method according to an embodiment of the present invention.

[0053] Step S210: After the unlock verification event is triggered, the camera is invoked to capture environmental images.

[0054] Step S220: Detect whether the environmental image includes multiple face images; if yes, proceed to step S230; if no, proceed to step S240.

[0055] Using facial recognition technology, the number of faces in an environmental image is identified to determine whether the environmental image contains multiple facial images.

[0056] Step S230: If the environmental image includes multiple face images, then the current environment is determined to be a multi-person environment, and step S250 is executed.

[0057] Step S240: If the environment image does not include multiple face images, then it is determined that the current environment is not a multi-person environment, and step S260 is executed.

[0058] Step S250: Collect images of a multi-user environment (multi-user images), and identify target users with preset target features in the collected images.

[0059] Legitimate users can preset target action characteristics in the system's authentication function settings.

[0060] For example, actions such as opening one's mouth, shaking one's head, nodding, and smiling. In this way, during the recognition process, the camera can identify whether a user is making such actions within its field of view, thus locking onto the target user.

[0061] Step S260: Collect the biometric information of the target user.

[0062] If the current environment is a multi-user environment, then the target users are users with specific user characteristics.

[0063] If the current environment is not a multi-person environment, then the user in the camera's field of view will be identified as the target user.

[0064] Step S270: Determine whether the biometric information of the target user matches the standard biometric information; if yes, proceed to step S280; if no, proceed to step S290.

[0065] Step S280: If the biometric information matches the preset standard biometric information, then perform the unlocking operation.

[0066] Step S290: If the biometric information does not match the preset standard biometric information, the unlocking operation is prohibited.

[0067] In this embodiment, to avoid the need to detect multiple faces appearing in the camera's field of view separately in a multi-person environment, this embodiment identifies the target user appearing in the camera's field of view. In this way, after identifying the target user with the target characteristics, it is no longer necessary to spend time identifying other people present, thus improving the identification speed. It is also unnecessary to spend time collecting the biometric information of other people present; only the biometric information of the target user needs to be collected, reducing the amount of biometric information collected and the computational workload of biometric information matching. This embodiment only matches the biometric information of the target user, which can effectively improve the unlocking success rate and shorten the unlocking time.

[0068] The following provides an authentication device. For example... Figure 3 The diagram shown is a structural diagram of an authentication device according to an embodiment of the present invention.

[0069] The identity verification device includes: a data acquisition module 310, an extraction module 320, an identification module 330, and a verification module 340.

[0070] The acquisition module 310 is used to acquire images from multiple users in a multi-user environment.

[0071] Extraction module 320 is used to extract user features of each user in the multi-user image.

[0072] The identification module 330 is used to identify user features that match preset target features among the user features of each user, and to determine the user corresponding to the identified user feature that matches the target feature as the target user.

[0073] The acquisition module 310 is also used to acquire the biometric information of the target user.

[0074] The verification module 340 is used to perform an unlocking operation if the biometric information of the target user matches the preset standard biometric information, and otherwise prohibit the unlocking operation.

[0075] The user features include user action features; the target features include target action features.

[0076] The device further includes a detection module (not shown in the figure); the detection module is used to acquire an environmental image before detecting the user characteristics of each user; detect whether the environmental image includes multiple face images; if the environmental image includes multiple face images, then determine that the current environment is a multi-person environment.

[0077] The biometric information includes at least one of the following: facial feature information, iris feature information, and voice feature information.

[0078] The function of the device described in this embodiment has been described in the above method embodiments. Therefore, for any parts not detailed in the description of this embodiment, please refer to the relevant descriptions in the foregoing embodiments, which will not be repeated here.

[0079] The following provides an authentication device. For example... Figure 4 The diagram shown is a structural diagram of an authentication device according to an embodiment of the present invention.

[0080] In this embodiment, the authentication device includes, but is not limited to, a processor 410 and a memory 420.

[0081] The processor 410 is used to execute the authentication program stored in the memory 420 to implement the above-described authentication method. Specifically, the processor 410 is used to execute the authentication program stored in the memory 420 to implement the following steps: in a multi-user environment, acquiring multi-user images; extracting user features of each user from the multi-user images; identifying user features that match preset target features among the user features of each user, and determining the user corresponding to the user feature that matches the target feature as the target user; acquiring the biometric information of the target user; if the biometric information of the target user matches preset standard biometric information, then performing an unlocking operation.

[0082] The user features include user action features; the target features include target action features.

[0083] Before acquiring multi-user images, the process further includes: acquiring an environmental image; detecting whether the environmental image contains multiple face images; and determining that the current environment is a multi-user environment if the environmental image contains multiple face images.

[0084] The biometric information includes at least one of the following: facial feature information, iris feature information, and voice feature information.

[0085] This invention also provides a computer-readable storage medium. This computer-readable storage medium stores one or more programs. The computer-readable storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; the memory may also include combinations of the above types of memory.

[0086] The above-described authentication method is implemented when one or more programs in a computer-readable storage medium can be executed by one or more processors.

[0087] Specifically, the processor is used to execute an authentication program stored in the memory to perform the following steps: in a multi-user environment, acquiring multi-user images; extracting user features of each user from the multi-user images; identifying user features that match preset target features among the user features of each user, and determining the user corresponding to the user feature that matches the target feature as the target user; acquiring the biometric information of the target user; if the biometric information of the target user matches preset standard biometric information, then performing an unlocking operation.

[0088] The user features include user action features; the target features include target action features.

[0089] Before detecting the user characteristics of each user, the method further includes: acquiring an environmental image; detecting whether the environmental image includes multiple face images; if the environmental image includes multiple face images, then determining that the current environment is a multi-person environment.

[0090] The biometric information includes at least one of the following: facial feature information, iris feature information, and voice feature information.

[0091] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. An identity verification method, characterized by, The method comprises the following steps: In a multi-person environment, a multi-user image is collected; User features of each user in the multi-user image are extracted; In the user features of each user, a user feature matching a preset target feature is identified, and a user corresponding to the user feature matching the target feature is determined as a target user; Biometric information of the target user is collected; If the biometric information of the target user matches preset standard biometric information, an unlocking operation is performed; The user features comprise user action features or user shape features; The target user refers to a suspected legal user of a terminal device, and the legal user refers to a legal user or owner of the terminal device; The target feature refers to a feature input and stored in advance by the legal user, and comprises a target action feature or a target shape feature.

2. The method of claim 1, wherein, Before the multi-user image is collected, the method further comprises the following steps: An environment image is collected; Whether the environment image comprises multiple face images is detected; If the environment image comprises multiple face images, it is determined that the current environment is a multi-person environment.

3. The method according to any one of claims 1 to 2, characterized in that, The biometric information comprises at least one of the following: face feature information, iris feature information and voice feature information.

4. An identity verification apparatus characterized by comprising: The method comprises the following steps: A collection module is configured to collect a multi-user image in a multi-person environment; An extraction module is configured to extract user features of each user in the multi-user image; An identification module is configured to identify, in the user features of each user, a user feature matching a preset target feature, and determine a user corresponding to the user feature matching the target feature as a target user; The collection module is further configured to collect biometric information of the target user; A verification module is configured to perform an unlocking operation if the biometric information of the target user matches preset standard biometric information; The user features comprise user action features or user shape features; The target user refers to a suspected legal user of a terminal device, and the legal user refers to a legal user or owner of the terminal device; The target feature refers to a feature input and stored in advance by the legal user, and comprises a target action feature or a target shape feature.

5. The apparatus of claim 4, wherein, The device further comprises a detection module configured to: Collect an environment image; Detect whether the environment image comprises multiple face images; If the environment image comprises multiple face images, it is determined that the current environment is a multi-person environment.

6. The apparatus of any one of claims 4-5, wherein, The biometric information comprises at least one of the following: face feature information, iris feature information and voice feature information.

7. An identity verification device, characterized by The identity verification device comprises a processor and a memory; the processor is configured to execute an identity verification program stored in the memory to implement the identity verification method in any one of claims 1-3.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs executable by one or more processors to implement the identity verification method in any one of claims 1-3.

Images