A non-contact multi-dimensional biometric identification method, system, device, and medium

Abstract

The application provides a non-contact multi-dimensional biometric identification method, system, device and medium, the method comprising: pre-acquiring a multi-dimensional biometric identification mode; determining whether a preset custom decision exists, and if so, performing biometric identification according to the custom decision; determining whether a risk exists; if so, determining whether precision decreases or fails in each biometric identification mode in turn until at least two identification modes with no precision decrease or failure are obtained for identification; and if not, determining whether precision decreases or fails in each biometric identification mode in turn until any identification mode with no precision decrease or failure is obtained for identification. The application solves the security problem existing in single-dimensional biometric identification application and improves the usability of multi-dimensional biometric identification.

Description

Technical Field

[0001] This invention relates to the field of biometrics, and in particular to a non-contact multidimensional biometrics method, system, device and medium. Background Technology

[0002] Traditional identification methods rely on identifiable items and knowledge. However, because they primarily depend on external objects, if these items or knowledge are stolen or forgotten, the identity can easily be impersonated or replaced. Biometric technology offers greater security, confidentiality, and convenience than traditional methods. Biometric identification technology boasts advantages such as being less prone to forgetting, having strong anti-counterfeiting capabilities, being difficult to forge or steal, being portable, and usable anytime, anywhere.

[0003] Current biometric technologies utilize single-dimensional biometric identification, such as face recognition, iris recognition, and voiceprint recognition. The problems with these current applications are: first, the security risks of theft and impersonation due to single-dimensional biometric applications; second, the risk of cross-infection due to contact-based biometrics; third, the high cost and inability to achieve adaptive scheduling for custom combinations of multi-dimensional biometric factors; and finally, the high degree of coupling between basic biometric services such as face, iris, and voiceprint recognition, preventing flexible selection. Summary of the Invention

[0004] The purpose of this invention is to provide a non-contact multidimensional biometric method to solve the security problems existing in single-dimensional biometric applications and improve the ease of use of multidimensional biometrics.

[0005] To achieve the above objectives, in a first aspect, embodiments of the present invention provide a non-contact multidimensional biometric identification method, the method comprising:

[0006] The multidimensional biometric identification methods are pre-acquired, and the multidimensional biometric identification methods include at least face recognition, voiceprint recognition, and iris recognition;

[0007] In response to a biometric request, determine whether there is a preset custom decision. If there is, perform biometric recognition based on the custom decision. The custom decision is to perform biometric recognition in one or more dimensions from all the multidimensional biometric recognition methods set by the user.

[0008] Determine whether there is a risk, which is caused by the usage environment and changes in user behavior;

[0009] If there is a risk, then check in turn whether there is a decrease in accuracy or failure in each biometric method until at least two identification methods with no decrease in accuracy or failure are obtained for identification.

[0010] If there is no risk, then each biometric method is sequentially checked for accuracy degradation or failure until an identification method with no degradation or failure is found for identification.

[0011] Furthermore, if a risk exists, the accuracy of each biometric method is sequentially assessed for degradation or failure until at least two identification methods with undiminished accuracy or no failure are obtained for identification, including:

[0012] If no biometric method experiences a decrease in accuracy or failure, then all biometric methods will be used for biometric identification.

[0013] If at least one biometric method experiences a decrease in accuracy or fails, then the biometric method that does not experience a decrease in accuracy or fail shall be used for biometric identification.

[0014] Furthermore, the risks include: device changes caused by switching between different devices, spatial changes caused by changes in geographical location, time changes caused by changes in specific time periods, and behavioral changes caused by multiple retries and repeated verifications.

[0015] Furthermore, the determination of whether each biometric method has experienced a decrease in accuracy or failure includes:

[0016] Determine whether factors such as face angle, background, light intensity, and face occlusion cause a decrease or failure in face recognition accuracy.

[0017] Determine whether environmental noise, the listener's emotions, or the listener's physical condition cause a decrease or failure in voiceprint recognition accuracy;

[0018] Determine whether the decrease or failure of iris recognition accuracy is caused by recognition distance or iris occlusion.

[0019] Secondly, embodiments of the present invention provide a non-contact multidimensional biometric identification system, the system comprising:

[0020] The registration and activation module is used to pre-acquire multi-dimensional biometric identification methods, including face recognition, voiceprint recognition, and iris recognition.

[0021] A custom recognition module is used to respond to a biometric request and determine whether there is a preset custom decision. If there is, biometric recognition is performed according to the custom decision. The custom decision is to perform biometric recognition in one or more dimensions from all the multidimensional biometric methods set by the user.

[0022] An adaptive identification module is used to determine whether there is a risk, which is caused by the usage time and space environment and changes in user behavior;

[0023] If there is a risk, then check in turn whether there is a decrease in accuracy or failure in each biometric method until at least two identification methods with no decrease in accuracy or failure are obtained for identification.

[0024] If there is no risk, then each biometric method is sequentially checked for accuracy degradation or failure until an identification method with no degradation or failure is found for identification.

[0025] Furthermore, the adaptive recognition module is also used for:

[0026] If no biometric method experiences a decrease in accuracy or failure, then all biometric methods will be used for biometric identification.

[0027] If at least one biometric method experiences a decrease in accuracy or fails, then the biometric method that does not experience a decrease in accuracy or fail shall be used for biometric identification.

[0028] Furthermore, the risks include: device changes caused by switching between different devices, spatial changes caused by changes in geographical location, time changes caused by changes in specific time periods, and behavioral changes caused by multiple retries and repeated verifications.

[0029] Furthermore, the determination of whether each biometric method has experienced a decrease in accuracy or failure includes:

[0030] Determine whether factors such as face angle, background, light intensity, and face occlusion cause a decrease or failure in face recognition accuracy.

[0031] Determine whether environmental noise, the listener's emotions, or the listener's physical condition cause a decrease or failure in voiceprint recognition accuracy;

[0032] Determine whether the decrease or failure of iris recognition accuracy is caused by recognition distance or iris occlusion.

[0033] Thirdly, embodiments of the present invention also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0034] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method.

[0035] This invention provides a non-contact multidimensional biometric identification method, system, device, and medium. It involves: pre-acquiring multidimensional biometric identification methods; determining whether a preset custom decision exists; if so, performing biometric identification based on the custom decision; determining whether there is a risk; if so, sequentially determining whether each biometric identification method experiences accuracy degradation or failure until at least two identification methods with no accuracy degradation or failure are obtained for identification; if not, sequentially determining whether each biometric identification method experiences accuracy degradation or failure until any identification method with no accuracy degradation or failure is obtained for identification. This invention solves the security problems existing in single-dimensional biometric identification applications and improves the usability of multidimensional biometric identification. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating a non-contact multidimensional biometric identification method according to an embodiment of the present invention;

[0037] Figure 2 This is a system block diagram of a non-contact multidimensional biometric identification system according to an embodiment of the present invention;

[0038] Figure 3 This is an overall architecture diagram of a non-contact multidimensional biometric system according to an embodiment of the present invention;

[0039] Figure 4 This is an internal structural diagram of the computer device in an embodiment of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and beneficial effects of this application clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Obviously, the embodiments described below are only part of the embodiments of the present invention and are used to illustrate the present invention, but are not intended to limit the scope of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0041] In one embodiment, such as Figure 1 As shown, the present invention provides a non-contact multidimensional biometric identification method, the method comprising:

[0042] S11. Pre-acquire multi-dimensional biometric identification methods, wherein the multi-dimensional biometric identification methods include at least face recognition, voiceprint recognition, and iris recognition;

[0043] In this embodiment, multi-dimensional biometric identification methods are not limited to facial recognition, voiceprint recognition, and iris recognition. More contactless biometric identification methods, such as palm vein recognition and gait recognition, can also be set according to actual needs. During multi-dimensional biometric authentication, official verification through a legal identity document authentication service is required to ensure authorized operation and guarantee the authority of the multi-dimensional biometric factors.

[0044] Before the identification process begins, users must register and activate their accounts. First, their identity is verified using their mobile phone number, name, and ID card number. If verification is successful, users can choose to collect biometric information such as iris scans and voiceprints. If successful, the relevant information will be stored in the database. If collection fails, the user will be prompted to adjust their settings and resample. For example, if iris scan collection fails, the user may be prompted to remove sunglasses, etc. Successfully collected data will be associated with the user's information for comparison during identification.

[0045] S12. In response to the biometric request, determine whether there is a preset custom decision. If there is, perform biometric recognition according to the custom decision. The custom decision is to perform biometric recognition in one or more dimensions among all the multidimensional biometric recognition methods set by the user.

[0046] In this embodiment, the user-defined custom decision can be a single-dimensional biometric, such as facial recognition, or a multi-dimensional biometric, such as voiceprint and iris recognition, or a combination of facial, voiceprint, and iris recognition. Users can also specify the random use of a single-dimensional biometric. Furthermore, users can adjust the specific parameters of each biometric. When a preset custom decision exists, there is no need for subsequent risk assessment. This embodiment's custom recognition method can more effectively address diverse biometric needs based on user requirements.

[0047] S13. Determine whether there is a risk, the risk being caused by the usage environment and abnormal user behavior.

[0048] In this embodiment, due to the existence of risks, multiple biometric identification methods should be adopted to make biometric identification more accurate. Furthermore, if all biometric identification methods experience a decrease in accuracy or failure, a prompt message should be sent to the user to allow for corresponding adjustments to the biometric identification methods, thereby improving the usability of biometric identification.

[0049] If a risk exists, then each biometric method will be sequentially assessed for accuracy degradation or failure until at least two identification methods with consistent accuracy or no failure are obtained for identification, including:

[0050] If no biometric method experiences a decrease in accuracy or failure, then all biometric methods will be used for biometric identification.

[0051] If at least one biometric method experiences a decrease in accuracy or fails, then the biometric method that does not experience a decrease in accuracy or fail shall be used for biometric identification.

[0052] If there is no risk, then each biometric method is sequentially checked for accuracy degradation or failure until an identification method with no degradation or failure is found for identification.

[0053] In this embodiment, there is no particular restriction on the order of the various biometric methods. For example, if the predetermined order is face recognition, voiceprint recognition, and iris recognition, and it is determined that face recognition does not experience a decrease in accuracy or failure, then only face recognition is used, without the need to use other subsequent biometric methods. That is, it is a one-dimensional biometric identification method. This embodiment can improve the efficiency of biometric identification when there is no change in the risk factor.

[0054] In this embodiment, after determining if a risk exists, it can be further determined whether there is a change in the risk coefficient. If the change indicates that there is no risk, then each biometric identification method is sequentially checked for accuracy degradation or failure until an identification method with no accuracy degradation or failure is obtained for identification. There are many situations that can cause changes in the risk coefficient. In this embodiment, changes in the risk coefficient include: device changes caused by switching between different devices, spatial changes caused by changes in geographical location, time changes caused by changes in a specific time period, and behavioral changes caused by multiple retries and repeated verifications.

[0055] The determination of whether the biometric identification method has experienced a decrease in accuracy or failure includes:

[0056] Determine whether factors such as face angle, background, light intensity, and face occlusion cause a decrease or failure in face recognition accuracy.

[0057] Determine whether environmental noise, the listener's emotions, or the listener's physical condition cause a decrease or failure in voiceprint recognition accuracy;

[0058] Determine whether the decrease or failure of iris recognition accuracy is caused by recognition distance or iris occlusion.

[0059] In this embodiment, since the user's device, geographical location, and usage time are usually fixed, the above situations typically indicate a certain security risk in biometric identification. Device switching can be determined by its IMEI code, and changes in geographical location can be judged by IP address or satellite positioning. For multiple attempts and repeated verifications, a certain time interval can be set; for example, if verification is repeated more than 3 times within 10 minutes, it is considered multiple retries and repeated verifications. Regarding facial recognition, prompts can be provided to allow the user to adjust their facial angle or remove masks or hats to improve facial recognition accuracy. Image equalization processing can also improve situations where sunlight is too strong or the contrast between the recognition background and the user is low. Regarding voiceprint recognition, a noise compensation model can be established to reduce the impact of ambient noise. Regarding iris recognition, when the user wears colored contact lenses, tinted glasses, or sunglasses, iris recognition accuracy may decrease or fail. In this case, deep learning techniques can be used for image processing to remove the iris obstruction and restore the iris image as much as possible for recognition.

[0060] This invention provides a non-contact multi-dimensional biometric identification method, which effectively improves the application security level and avoids security risks through the comprehensive application of multi-dimensional biometric identification; the non-contact method can reduce the risk of cross-infection; the multi-dimensional biometric identification scheduling mechanism based on adaptive and custom strategies can be applied more conveniently, and multiple identification methods can realize flexible decoupled middleware services.

[0061] Based on the aforementioned non-contact multidimensional biometric identification method, this invention also provides a non-contact multidimensional biometric identification system, such as... Figure 2 As shown, the system includes:

[0062] Registration and activation module 1 is used to pre-acquire multi-dimensional biometric identification methods, including face recognition, voiceprint recognition, and iris recognition;

[0063] Custom recognition module 2 is used to respond to a biometric recognition request and determine whether there is a preset custom decision. If there is, biometric recognition is performed according to the custom decision. The custom decision is to perform biometric recognition in one or more dimensions among all the multidimensional biometric recognition methods set by the user.

[0064] Adaptive recognition module 3 is used to determine whether there is a risk, which is caused by the usage time and space environment and changes in user behavior;

[0065] If there is a risk, then check in turn whether there is a decrease in accuracy or failure in each biometric method until at least two identification methods with no decrease in accuracy or failure are obtained for identification.

[0066] If there is no risk, then each biometric method is sequentially checked for accuracy degradation or failure until an identification method with no degradation or failure is found for identification.

[0067] like Figure 3 As shown, the system is divided into an application layer, service layer, infrastructure layer and storage layer in terms of overall architecture.

[0068] The application layer, as the module for the practical application of multidimensional biometrics, is divided into multidimensional biometric devices and supporting multidimensional biometric management applications. Multidimensional biometric devices include, but are not limited to, all-in-one machines, portable handheld devices, and vehicle-mounted devices, which can perform face, voiceprint, and iris recognition. Multidimensional biometric management applications can perform digital identity association, multidimensional biometric registration and activation, and multidimensional biometric authorization management.

[0069] The service layer is the core module of multidimensional biometrics. Among them, the front-end services include legal identity authentication services and digital identity authentication services; the registration and verification services are for registering and verifying faces, irises, and voiceprints; the management services are responsible for device access and device management; the scheduling services include adaptive decision-making services and custom orchestration services; and the adaptation services include iris, face, and voiceprint recognition services. It can realize the front-end verification, registration and activation, verification of multidimensional identity recognition factors, and management of access applications and devices for multidimensional biometrics.

[0070] The base layer includes the iris engine, portrait engine, and voiceprint engine, which are the basic algorithm modules for implementing multi-dimensional biometric identification. The biometric engines it contains are pluggable, replaceable, and loosely coupled, and can be freely combined and flexibly applied to various application scenarios.

[0071] The storage layer includes an iris database, a facial image database, a voiceprint database, and a business database. It is responsible for storing data such as facial features, iris features, voiceprint features, and business information, providing data persistence services for business applications, and providing business support for the operation of other modules.

[0072] In addition, the present invention can also be used as a plug-in module, including front-end SDK plug-in, server-side SDK plug-in, etc., to be integrated into various terminal devices that carry actual business scenarios, such as App applications, web H5 applications, mini-program applications, all-in-one machine applications, and vehicle applications. It can also be adaptively adjusted according to the differences in the capabilities of different types and manufacturers of biometric recognition engines.

[0073] For specific limitations regarding a contactless multidimensional biometric system, please refer to the limitations of a contactless multidimensional biometric method described above, which will not be repeated here. Each module in the above system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0074] Figure 4 An internal structural diagram of a computer device is shown in one embodiment. This computer device may specifically be a terminal or a server. Figure 4 As shown, the computer device includes a processor, memory, network interface, display, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0075] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computing devices may include more or fewer components than shown in the diagram, or combine certain components, or have the same component arrangement.

[0076] In summary, this invention provides a non-contact multidimensional biometric identification method, system, device, and medium. It involves: pre-acquiring multidimensional biometric identification methods; determining whether a preset custom decision exists; if so, performing biometric identification based on the custom decision; determining whether there is a risk; if so, sequentially determining whether each biometric identification method experiences accuracy degradation or failure until at least two identification methods with no accuracy degradation or failure are obtained for identification; if not, sequentially determining whether each biometric identification method experiences accuracy degradation or failure until any identification method with no accuracy degradation or failure is obtained for identification. This invention solves the security problems existing in single-dimensional biometric identification applications and improves the usability of multidimensional biometric identification.

[0077] The various embodiments in this specification are described in a progressive manner. For directly identical or similar parts of the embodiments, refer to each other. Each embodiment focuses on its differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0078] The embodiments described above are merely preferred embodiments of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various improvements and substitutions without departing from the technical principles of this invention, and these improvements and substitutions should also be considered within the scope of protection of this application. Therefore, the scope of protection of this patent application should be determined by the scope of the claims.

Claims

1. A non-contact multidimensional biometric identification method, characterized in that, The method includes: The multidimensional biometric identification methods are pre-acquired, and the multidimensional biometric identification methods include at least face recognition, voiceprint recognition, and iris recognition; In response to a biometric request, determine whether there is a preset custom decision. If there is, perform biometric recognition based on the custom decision. The custom decision is to perform biometric recognition in one or more dimensions from all the multidimensional biometric recognition methods set by the user. To determine whether there is a risk, the risk is caused by changes in the usage environment and user behavior. The risks include: device changes caused by switching between different devices, spatial changes caused by changes in geographical location, time changes caused by changes in time period, and behavioral changes caused by multiple retries and repeated verifications. If there is a risk, then check in turn whether there is a decrease in accuracy or failure in each biometric method until at least two identification methods with no decrease in accuracy or failure are obtained for identification. If there is no risk, then check in turn whether each biometric method has decreased accuracy or failed, until a method with no decrease in accuracy or failure is found for identification. If a risk exists, the accuracy of each biometric method will be sequentially assessed for degradation or failure until at least two biometric methods with no degradation or failure are obtained for identification, including: If no biometric method experiences a decrease in accuracy or failure, then all biometric methods will be used for biometric identification. If at least one biometric method experiences a decrease in accuracy or fails, then the biometric method that does not experience a decrease in accuracy or fail shall be used for biometric identification. The determination of whether each biometric method has decreased accuracy or failed includes: Determine whether factors such as face angle, background, light intensity, and face occlusion cause a decrease or failure in face recognition accuracy. Determine whether environmental noise, the listener's emotions, or the listener's physical condition cause a decrease or failure in voiceprint recognition accuracy; Determine whether the decrease or failure of iris recognition accuracy is caused by recognition distance or iris occlusion.

2. A non-contact multidimensional biometric system, characterized in that, The system includes: The registration and activation module is used to pre-acquire multi-dimensional biometric identification methods, including face recognition, voiceprint recognition, and iris recognition. A custom recognition module is used to respond to a biometric request and determine whether there is a preset custom decision. If there is, biometric recognition is performed according to the custom decision. The custom decision is to perform biometric recognition in one or more dimensions from all the multidimensional biometric methods set by the user. An adaptive identification module is used to determine whether there is a risk. The risk is caused by changes in the usage environment and user behavior. The risks include: device changes caused by switching between different devices, spatial changes caused by changes in geographical location, time changes caused by changes in time period, and behavioral changes caused by multiple retries and repeated verifications. If there is a risk, then check in turn whether there is a decrease in accuracy or failure in each biometric method until at least two identification methods with no decrease in accuracy or failure are obtained for identification. If there is no risk, then check in turn whether each biometric method has decreased accuracy or failed, until a method with no decrease in accuracy or failure is found for identification. The adaptive recognition module is also used for: If no biometric method experiences a decrease in accuracy or failure, then all biometric methods will be used for biometric identification. If at least one biometric method experiences a decrease in accuracy or fails, then the biometric method that does not experience a decrease in accuracy or fail shall be used for biometric identification. The determination of whether each biometric method has decreased accuracy or failed includes: Determine whether factors such as face angle, background, light intensity, and face occlusion cause a decrease or failure in face recognition accuracy. Determine whether environmental noise, the listener's emotions, or the listener's physical condition cause a decrease or failure in voiceprint recognition accuracy; Determine whether the decrease or failure of iris recognition accuracy is caused by recognition distance or iris occlusion.

3. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method of claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method of claim 1.

Images