Multi-modal biological recognition fusion system

Abstract

The invention discloses a multi-modal biological recognition fusion system, which comprises a multi-modal data acquisition engine, a dynamic cross validation engine and an identity label generation module, and the multi-modal data acquisition engine, the dynamic cross validation engine and the identity label generation module are connected with the dynamic cross validation engine and the identity label generation module. The feature level fusion module is used for realizing dynamic weight distribution and feature level fusion by integrating multi-dimensional biological features such as fingerprints, human faces, irises and voiceprints, and constructing a unique identity binding architecture in a high-security scene; according to the method, the technical bottlenecks of a traditional biological recognition system in the aspects of security boundary, environmental adaptability and anti-attack ability can be broken through by constructing a multi-modal feature dynamic fusion framework and creatively integrating the generative adversarial network, federated learning and edge computing optimization technologies.

Description

Technical Field

[0001] The present invention relates to the technical field of self-service terminals, and in particular to a multimodal biometric fusion system. Background Art

[0002] Traditional biometric systems rely on single-modal features, making them susceptible to counterfeiting and lacking cross-scenario generalization. Multimodal systems also suffer from siloed feature data and rigid dynamic verification strategies. Existing technologies cannot balance authentication accuracy and processing efficiency in high-security scenarios like cross-border payments, and lack effective defenses against deepfake attacks. Summary of the Invention

[0003] The purpose of the present invention is to provide a multimodal biometric fusion system to address the above-mentioned problems in the prior art, thereby solving all or one of the above-mentioned problems in the prior art.

[0004] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: The present invention provides a multimodal biometric fusion system, comprising: The multimodal data acquisition engine, dynamic cross-validation engine and identity generation module are used to achieve dynamic weight allocation and feature-level fusion by integrating multi-dimensional biometric features such as fingerprints, faces, irises and voiceprints, and build a unique identity binding architecture in high-security scenarios.

[0005] As an improved solution, a heterogeneous sensor collaborative working protocol is deployed in the multimodal data acquisition engine to support the synchronous triggering and noise suppression of fingerprint contact sensing, three-dimensional face point cloud acquisition and iris micron-level texture capture.

[0006] As an improved solution, the dynamic cross-validation engine is specifically used to adopt a feature space alignment algorithm based on a generative adversarial network to analyze the biometric correlation between different modalities in real time and dynamically adjust the confidence threshold of the verification strategy.

[0007] As an improved solution, the identity generation module is specifically used to construct a federated feature embedding vector, map multimodal features into irreversible distributed hash identifiers through homomorphic encryption technology, and support privacy protection for cross-platform identity authentication.

[0008] As an improved solution, the multimodal biometric fusion system is also provided with a modal redundancy decision tree engine, which is used to automatically activate multi-level alternative modal combination verification when forgery features are detected in any modality, thereby ensuring authentication reliability in abnormal scenarios.

[0009] As an improved solution, the multimodal biometric fusion system is also provided with a biometric liveness detection submodule, which is used to combine infrared spectrum analysis, micro-expression capture and voiceprint frequency detection technology to resist photo, mask and deep fake attacks.

[0010] As an improved solution, the multimodal biometric fusion system is also equipped with an edge computing optimization engine, which is used to achieve real-time feature comparison in offline environments through model lightweight distillation technology, and support continuous authentication capabilities in network-free scenarios such as cross-border payments.

[0011] As an improved solution, the multimodal biometric fusion system is also provided with a dynamic knowledge distillation framework for continuously optimizing the multimodal fusion weight parameters based on federated learning to adapt to the differences in biometric distribution of users in different regions.

[0012] As an improved solution, the multimodal biometric fusion system is also provided with an adversarial sample defense engine for generating modality-specific adversarial perturbations through transfer learning to enhance the system's robustness against camouflage attacks.

[0013] As an improved solution, the multimodal biometric fusion system is also equipped with a cross-scenario adaptive engine for dynamically switching authentication modes according to the business risk level. For example, for high-value transactions, dual-factor enhanced verification of iris and voiceprint is mandatory.

[0014] The beneficial effects of the technical solution of the present invention are: by constructing a dynamic fusion framework of multimodal features, the present invention innovatively integrates adversarial generative networks, federated learning and edge computing optimization technologies, and breaks through the technical bottlenecks of traditional biometric systems in terms of security boundaries, environmental adaptability and anti-attack capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 Schematic diagram of the architecture of the multimodal biometric fusion system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more precise definition of the protection scope of the present invention.

[0018] In the description of the present invention, it should be noted that the embodiments described in the present invention are only part of the embodiments of the present invention, rather than all of the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of the present invention.

[0019] The terms "first," "second," and the like in the specification and claims herein and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in orders other than those illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product, or device.

[0020] Embodiment, this embodiment provides a multimodal biometric fusion system, such as Figure 1 As shown, including: The multimodal data acquisition engine, dynamic cross-validation engine and identity generation module are used to achieve dynamic weight allocation and feature-level fusion by integrating multi-dimensional biometric features such as fingerprints, faces, irises and voiceprints, and build a unique identity binding architecture in high-security scenarios.

[0021] As an improved solution, a heterogeneous sensor collaborative working protocol is deployed in the multimodal data acquisition engine to support the synchronous triggering and noise suppression of fingerprint contact sensing, three-dimensional face point cloud acquisition and iris micron-level texture capture.

[0022] As an improved solution, the dynamic cross-validation engine is specifically used to adopt a feature space alignment algorithm based on a generative adversarial network to analyze the biometric correlation between different modalities in real time and dynamically adjust the confidence threshold of the verification strategy.

[0023] As an improved solution, the identity generation module is specifically used to construct a federated feature embedding vector, map multimodal features into irreversible distributed hash identifiers through homomorphic encryption technology, and support privacy protection for cross-platform identity authentication.

[0024] As an improved solution, the multimodal biometric fusion system is also provided with a modal redundancy decision tree engine, which is used to automatically activate multi-level alternative modal combination verification when forgery features are detected in any modality, thereby ensuring authentication reliability in abnormal scenarios.

[0025] As an improved solution, the multimodal biometric fusion system is also provided with a biometric liveness detection submodule, which is used to combine infrared spectrum analysis, micro-expression capture and voiceprint frequency detection technology to resist photo, mask and deep fake attacks.

[0026] As an improved solution, the multimodal biometric fusion system is also equipped with an edge computing optimization engine, which is used to achieve real-time feature comparison in offline environments through model lightweight distillation technology, and support continuous authentication capabilities in network-free scenarios such as cross-border payments.

[0027] As an improved solution, the multimodal biometric fusion system is also provided with a dynamic knowledge distillation framework for continuously optimizing the multimodal fusion weight parameters based on federated learning to adapt to the differences in biometric distribution of users in different regions.

[0028] As an improved solution, the multimodal biometric fusion system is also provided with an adversarial sample defense engine for generating modality-specific adversarial perturbations through transfer learning to enhance the system's robustness against camouflage attacks.

[0029] As an improved solution, the multimodal biometric fusion system is also equipped with a cross-scenario adaptive engine for dynamically switching authentication modes according to the business risk level. For example, for high-value transactions, dual-factor enhanced verification of iris and voiceprint is mandatory.

[0030] It should be noted that the above examples are only for explaining the present invention and are not intended to limit the scope of protection of the present invention.

[0031] It should also be understood that in the embodiments herein, the term "and / or" merely describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" could represent: A alone, A and B simultaneously, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0032] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0033] In the several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices, or units, or can be an electrical, mechanical, or other form of connection.

[0034] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments herein.

[0035] In addition, the functional units in the various embodiments herein may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0036] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this article is essentially or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this article. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0037] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multimodal biometric fusion system, characterized in that: include: The multimodal data acquisition engine, dynamic cross-validation engine and identity generation module are used to achieve dynamic weight allocation and feature-level fusion by integrating multi-dimensional biometric features such as fingerprints, faces, irises and voiceprints, and build a unique identity binding architecture in high-security scenarios.

2. The multimodal biometric fusion system according to claim 1, characterized in that: The multimodal data acquisition engine is deployed with a heterogeneous sensor collaborative work protocol to support the synchronous triggering and noise suppression of fingerprint contact sensing, three-dimensional face point cloud acquisition and iris micron-level texture capture.

3. The multimodal biometric fusion system according to claim 1, characterized in that: The dynamic cross-validation engine is specifically further used to adopt a feature space alignment algorithm based on a generative adversarial network to analyze the biometric correlation between different modalities in real time and dynamically adjust the confidence threshold of the verification strategy.

4. The multimodal biometric fusion system according to claim 1, characterized in that: The identity generation module is also specifically used to construct a federated feature embedding vector, map multimodal features into irreversible distributed hash identifiers through homomorphic encryption technology, and support privacy protection for cross-platform identity authentication.

5. The multimodal biometric fusion system according to claim 1, characterized in that: The multimodal biometric fusion system is also provided with a modal redundancy decision tree engine, which is used to automatically activate multi-level alternative modal combination verification when forgery features are detected in any modality, thereby ensuring the reliability of authentication in abnormal scenarios.

6. The multimodal biometric fusion system according to claim 1, characterized in that: The multimodal biometric fusion system is also provided with a biometric liveness detection submodule, which is used to combine infrared spectrum analysis, micro-expression capture and voiceprint frequency detection technology to resist photo, mask and deep fake attacks.

7. The multimodal biometric fusion system according to claim 1, characterized in that: The multimodal biometric fusion system is also equipped with an edge computing optimization engine, which is used to achieve real-time feature comparison in an offline environment through model lightweight distillation technology, and support continuous authentication capabilities in network-free scenarios such as cross-border payments.

8. The multimodal biometric fusion system according to claim 1, characterized in that: The multimodal biometric fusion system is also provided with a dynamic knowledge distillation framework for continuously optimizing the multimodal fusion weight parameters based on federated learning to adapt to the differences in biometric distribution of users in different regions.

9. The multimodal biometric fusion system according to claim 1, characterized in that: The multimodal biometric fusion system is also provided with an adversarial sample defense engine for generating modality-specific adversarial perturbations through transfer learning to enhance the system's robustness against camouflage attacks.

10. The multimodal biometric fusion system according to claim 1, characterized in that: The multimodal biometric fusion system is also equipped with a cross-scenario adaptive engine for dynamically switching authentication modes based on the business risk level. For example, high-value transactions can be forcibly enhanced with dual-factor authentication of iris and voiceprint.

Images