1. A hybrid biometric authentication system (100), the system (100) comprising: a user device (102) configured to receive authentication input from a user, the user device comprising a display interface, input interface, and housing structure configured to support biometric authentication operations; a communication network (104) operatively connected to the user device (102) and configured to transmit authentication data, control signals, and authentication results between the user device and an external access-control system; a fingerprint sensor (106) integrated within the user device (102), the fingerprint sensor (106) being configured to capture fingerprint ridge patterns and minutiae features from a user finger and generate fingerprint data signals representative of the captured fingerprint; a flickering display screen (108) configured to generate a periodic visual stimulus at a predefined flickering frequency range to induce a steady-state visual evoked potential (SSVEP) neural response from the user during an authentication session; an electroencephalogram (EEG) headset (110) comprising a plurality of electrodes positioned at occipital regions of a user and configured to acquire brainwave signals generated in response to the periodic visual stimulus, the EEG headset further comprising signal acquisition circuitry for transmitting EEG signals; a processing unit (112) operatively connected to the fingerprint sensor (106), the flickering display screen (108), and the EEG headset (110), the processing unit (112) comprises at least one processors and memory storing executable instructions, wherein the processing unit (112) further comprising: a fingerprint feature extraction module (114) configured to receive fingerprint data from the fingerprint sensor (106) and generate fingerprint feature parameters including ridge structure and minutiae information; a fingerprint matching module (116) configured to compare the generated fingerprint feature parameters with stored fingerprint templates and output a fingerprint authentication confidence score; an EEG signal acquisition interface module (118) configured to receive raw EEG signals acquired from the EEG headset (110); an EEG signal pre-processing module (120) configured to perform filtering, artefact removal, and noise reduction on the received EEG signals to generate pre-processed EEG signals; an SSVEP detection module (122) configured to identify stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis; a brainwave feature extraction module (124) configured to generate brainwave feature parameters corresponding to detected SSVEP responses; an EEG classification module (126) configured to classify the brainwave feature parameters and generate an EEG authentication confidence score; a fusion decision module (128) configured to combine the fingerprint authentication confidence score and the EEG authentication confidence score according to a predefined fusion rule to generate a final authentication score; an authentication controller (130) operatively connected to the processing unit (112), the authentication controller (130) being configured to compare the final authentication score with a predefined threshold value and output an authentication decision signal for granting and denying access to a protected system.

2. The system (100) as claimed in claim 1, wherein the visual stimulus generation module (108) is configured to generate a periodic flickering visual stimulus within a frequency range of 8 Hz to 20 Hz to evoke steady-state visual evoked potential (SSVEP) responses from a user.

3. The system (100) as claimed in claim 1, wherein the EEG headset (110) comprises a plurality of electrodes positioned at occipital brain regions including O1, Oz, and O2 electrode locations for acquisition of SSVEP signals.

4. The system (100) as claimed in claim 1, wherein the EEG signal pre-processing module (120) performs band-pass filtering within a frequency range of 5 Hz to 50 Hz and noise reduction to remove motion artefacts and environmental interference.

5. The system (100) as claimed in claim 1, wherein the SSVEP detection module (122) performs frequency-domain analysis using at least one of Fast Fourier Transform (FFT) and Canonical Correlation Analysis (CCA) to detect dominant stimulus-correlated frequencies.

6. The system (100) as claimed in claim 1, wherein the EEG classification module (126) comprises a trained machine-learning classifier selected from a group consisting of at least one Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) models.

7. The system (100) as claimed in claim 1, wherein the fusion decision module (128) generates the final authentication score using a weighted fusion rule defined as Sfinal = w1S1 + w2S2 where S1 represents the fingerprint authentication confidence score and S2 represents the EEG authentication confidence score.

8. The system (100) as claimed in claim 1, wherein the authentication controller module (114) grants access only when the final authentication score exceeds a predefined threshold, thereby enabling dual-factor liveness-verified authentication.

9. The system (100) as claimed in claim 1, wherein the fingerprint authentication process is executed prior to EEG-based authentication such that SSVEP verification is performed as a secondary cognitive liveness verification stage.

10. A method (200) for making hybrid biometric authentication system (100), the method (200) comprising: receiving (202), by a fingerprint sensor (106), fingerprint data of a user; extracting (204), by a fingerprint feature extraction module (114) executed by a processing unit (112), fingerprint feature parameters including ridge structure and minutiae information; comparing (206), by a fingerprint matching module (116), the extracted fingerprint feature parameters with stored fingerprint templates to generate a fingerprint authentication confidence score; generating (208), by a visual stimulus generation module (108), a flickering visual stimulus configured to evoke SSVEP responses from the user; acquiring (210), by an EEG headset (110), raw EEG signals corresponding to user attention toward the flickering visual stimulus; receiving (212), by an EEG signal acquisition interface module (118), the raw EEG signals; pre-processing (214), by an EEG signal pre-processing module (120), the raw EEG signals including filtering and noise reduction to generate pre-processed EEG signals; detecting (216), by an SSVEP detection module (122), stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis; extracting (218), by a brainwave feature extraction module (124), brainwave feature parameters corresponding to the detected SSVEP frequency components; classifying (220), by an EEG classification module (126), the extracted brainwave feature parameters to generate an EEG authentication confidence score; combining (222), by a fusion decision module (128), the fingerprint authentication confidence score and the EEG authentication confidence score to generate a final authentication score; granting and denying (224), by an authentication controller module (114), access to a protected system based on comparison of the final authentication score with a predefined authentication threshold.

Description:FIELD OF DISCLOSURE
[0001] The present disclosure generally relates to biometric authentication systems, more specifically, relates to hybrid biometric authentication system based on hybrid SSVEP-based brainwave and fingerprint biometric authentication system.
BACKGROUND OF THE DISCLOSURE
[0002] Biometric authentication systems are widely used in access control, digital security, financial transactions, and personal electronic devices to verify user identity based on physiological or behavioural characteristics. Commonly used biometric modalities include fingerprint recognition, facial recognition, iris scanning, and voice identification.
[0003] Among these, fingerprint-based authentication systems are extensively deployed due to their low cost, ease of integration, and fast verification performance. However, conventional fingerprint authentication systems rely solely on physical biometric characteristics, making them vulnerable to spoofing attacks, replica fingerprints, and unauthorized duplication techniques.
[0004] Existing single-modality biometric systems also suffer from limitations associated with lack of liveness detection, wherein a biometric sample may be accepted without confirming the real-time presence or conscious participation of the user. Such limitations increase the risk of unauthorized access, particularly in high-security applications including defense, banking, healthcare, and critical infrastructure systems.
[0005] Additionally, once a biometric template such as a fingerprint is compromised, it cannot be replaced or reissued like traditional passwords, thereby raising long-term privacy and security concerns. Environmental factors, sensor noise, and minor physiological variations may further lead to false acceptance or false rejection during authentication processes.
[0006] Brain–computer interface (BCI) technologies based on electroencephalogram (EEG) signals have recently emerged as alternative biometric approaches due to their inherent resistance to spoofing and ability to represent neural activity generated by a live user. In particular, Steady-State Visual Evoked Potential (SSVEP) responses produced when a user focuses attention on a flickering visual stimulus provide measurable and distinctive neural signatures.
[0007] Although prior systems have proposed EEG-based authentication or SSVEP-based attention verification, such approaches are generally implemented as standalone modalities and often lack integration with conventional biometric systems. Similarly, existing multimodal authentication techniques typically combine EEG signals with other modalities without providing a structured workflow that utilizes fingerprint authentication followed by cognitive liveness verification.
[0008] Further, known authentication systems do not adequately address the need for a unified hybrid architecture capable of combining fingerprint-based physical identity verification with SSVEP-based neural response authentication using an efficient fusion decision mechanism to improve reliability and security.
[0009] Therefore, there exists a need for an improved biometric authentication system that integrates fingerprint recognition with SSVEP-based brainwave verification to provide enhanced spoof resistance, real-time liveness detection, improved authentication accuracy, and secure dual-factor identity verification.
[0010] Thus, in light of the above-stated discussion, there exists a need for a hybrid SSVEP-based brainwave and fingerprint biometric authentication system.
SUMMARY OF THE DISCLOSURE
[0011] The following is a summary description of illustrative embodiments of the invention. It is provided as a preface to assist those skilled in the art to more rapidly assimilate the detailed design discussion which ensues and is not intended in any way to limit the scope of the claims which are appended hereto in order to particularly point out the invention.
[0012] According to illustrative embodiments, the present disclosure focuses on a hybrid SSVEP-based brainwave and fingerprint biometric authentication system which overcomes the above-mentioned disadvantages or provide the users with a useful or commercial choice.
[0013] An objective of the present disclosure is to provide a biometric authentication system capable of performing fingerprint-based identity verification followed by brainwave-based liveness verification using steady-state visual evoked potential (SSVEP) responses
[0014] Another objective of the present disclosure is to provide a system comprising a fingerprint sensor configured to acquire fingerprint data and generate fingerprint feature parameters including ridge and minutiae information for authentication processing.
[0015] Another objective of the present disclosure is to provide a visual stimulus generation module configured to present a flickering visual stimulus to a user for eliciting SSVEP responses detectable through EEG signals.
[0016] Another objective of the present disclosure is to provide an EEG headset configured to acquire brainwave signals corresponding to user attention directed toward the visual stimulus.
[0017] Another objective of the present disclosure is to provide a processing unit configured to execute signal pre-processing, SSVEP detection, brainwave feature extraction, classification, and fusion decision operations.
[0018] Another objective of the present disclosure is to provide an EEG signal pre-processing module configured to perform filtering and noise reduction for improving signal quality prior to feature analysis.
[0019] Another objective of the present disclosure is to provide an SSVEP detection module configured to detect stimulus-correlated frequency components from EEG signals using frequency-domain analysis.
[0020] Another objective of the present disclosure is to provide a brainwave feature extraction and EEG classification framework configured to generate an EEG authentication confidence score corresponding to a user’s neural response.
[0021] Another objective of the present disclosure is to provide a fusion decision module configured to combine fingerprint authentication confidence scores and EEG authentication confidence scores to generate a final authentication score.
[0022] Another objective of the present disclosure is to provide an authentication controller module configured to grant or deny access based on comparison of the final authentication score with a predefined threshold.\
[0023] Another objective of the present disclosure is, a hybrid biometric authentication system is provided comprising a user device, a fingerprint sensor, a visual stimulus generation module, an EEG headset, a processing unit including multiple functional modules for fingerprint and EEG signal analysis, a fusion decision module, and an authentication controller configured to perform dual-stage authentication.
[0024] Another objective of the present disclosure is the system performs fingerprint authentication as a primary verification stage and executes SSVEP-based brainwave authentication as a secondary cognitive verification stage to ensure user liveness and enhance spoof resistance.
[0025] Another objective of the present disclosure is, the fusion decision module applies a weighted score fusion rule to combine fingerprint and EEG authentication confidence scores for improved authentication accuracy.
[0026] Another objective of the present disclosure, is a method for hybrid biometric authentication is provided comprising acquiring fingerprint data, extracting fingerprint features, acquiring EEG signals corresponding to a flickering visual stimulus, pre-processing and analysing EEG signals to detect SSVEP responses, generating authentication confidence scores, performing fusion processing, and granting access based on a final authentication score.
[0027] An objective of the present disclosure is to provide a hybrid biometric authentication system capable of combining physical biometric verification with neural-response-based authentication to enhance overall system security.
[0028] Another objective of the present disclosure is to provide an authentication mechanism that performs fingerprint-based identity verification together with SSVEP-based brainwave authentication to ensure dual-factor validation.
[0029] Another objective of the present disclosure is to provide a biometric authentication system capable of real-time liveness detection by verifying neural responses generated from a visually induced stimulus.
[0030] Another objective of the present disclosure is to reduce vulnerability to spoofing attacks by requiring both fingerprint matching and cognitive response verification during a single authentication session.
[0031] Another objective of the present disclosure is to improve authentication accuracy by combining independent biometric confidence scores through a fusion decision mechanism.
[0032] Another objective of the present disclosure is to provide an efficient authentication workflow capable of completing biometric verification within a short operational time window while maintaining high reliability.
[0033] Another objective of the present disclosure is to provide a system architecture that supports integration of wearable EEG acquisition hardware with conventional fingerprint sensing devices within a unified authentication platform.
[0034] Another objective of the present disclosure is to provide adaptive decision-making capability through fusion-based evaluation, thereby reducing false acceptance and false rejection rates compared with single-modality systems.
[0035] Another objective of the present disclosure is to enable secure communication of authentication results between the user device and external access-control systems using a communication network interface.
[0036] Another objective of the present disclosure is to provide a scalable and implementable authentication solution suitable for secure access control, smart devices, enterprise systems, and high-security environments requiring enhanced identity verification.
[0037] Yet another objective of the present disclosure is to bridge the gap between conventional biometric authentication and brain–computer interface technologies by integrating physical identity verification with neural signal-based authentication in a single operational framework.
[0038] In light of the above, in one aspect of the present disclosure, a hybrid biometric authentication system is disclosed herein. The system comprises a user device configured to receive authentication input from a user, the user device comprising a display interface, input interface, and housing structure configured to support biometric authentication operations. The system includes a communication network operatively connected to the user device and configured to transmit authentication data, control signals, and authentication results between the user device and an external access-control system. The system also includes a fingerprint sensor integrated within the user device, the fingerprint sensor being configured to capture fingerprint ridge patterns and minutiae features from a user finger and generate fingerprint data signals representative of the captured fingerprint. The system also includes a flickering display screen configured to generate a periodic visual stimulus at a predefined flickering frequency range to induce a steady-state visual evoked potential (SSVEP) neural response from the user during an authentication session. The system also includes an electroencephalogram (EEG) headset comprising a plurality of electrodes positioned at occipital regions of a user and configured to acquire brainwave signals generated in response to the periodic visual stimulus, the EEG headset further comprising signal acquisition circuitry for transmitting EEG signals. The system also includes a processing unit operatively connected to the fingerprint sensor, the flickering display screen, and the EEG headset, the processing unit comprising one or more processors and memory storing executable instructions, wherein the processing unit comprising a fingerprint feature extraction module configured to receive fingerprint data from the fingerprint sensor and generate fingerprint feature parameters including ridge structure and minutiae information, a fingerprint matching module configured to compare the generated fingerprint feature parameters with stored fingerprint templates and output a fingerprint authentication confidence score, an EEG signal acquisition interface module configured to receive raw EEG signals acquired from the EEG headset, an EEG signal pre-processing module configured to perform filtering, artefact removal, and noise reduction on the received EEG signals to generate pre-processed EEG signals, an SSVEP detection module configured to identify stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis, a brainwave feature extraction module configured to generate brainwave feature parameters corresponding to detected SSVEP responses, an EEG classification module configured to classify the brainwave feature parameters and generate an EEG authentication confidence score. The system also included a fusion decision module configured to combine the fingerprint authentication confidence score and the EEG authentication confidence score according to a predefined fusion rule to generate a final authentication score.
[0039] In one embodiment, the visual stimulus generation module is configured to generate a periodic flickering visual stimulus within a frequency range of 8 Hz to 20 Hz to evoke steady-state visual evoked potential (SSVEP) responses from a user.
[0040] In one embodiment, the wherein the EEG headset comprises a plurality of electrodes positioned at occipital brain regions including O1, Oz, and O2 electrode locations for acquisition of SSVEP signals.
[0041] In one embodiment, the EEG signal pre-processing module performs band-pass filtering within a frequency range of 5 Hz to 50 Hz and noise reduction to remove motion artefacts and environmental interference.
[0042] In one embodiment, the SSVEP detection module performs frequency-domain analysis using at least one of Fast Fourier Transform (FFT) and Canonical Correlation Analysis (CCA) to detect dominant stimulus-correlated frequencies.
[0043] In one embodiment, the EEG classification module comprises a trained machine-learning classifier selected from a group consisting of Support Vector Machine (SVM), Convolutional Neural Network (CNN), or Long Short-Term Memory (LSTM) models.
[0044] In one embodiment, the fusion decision module generates the final authentication score using a weighted fusion rule defined as Sfinal = w1S1 + w2S2 where S1 represents the fingerprint authentication confidence score and S2 represents the EEG authentication confidence score.
[0045] In one embodiment, the authentication controller module grants access only when the final authentication score exceeds a predefined threshold, thereby enabling dual-factor liveness-verified authentication.
[0046] In one embodiment, the fingerprint authentication process is executed prior to EEG-based authentication such that SSVEP verification is performed as a secondary cognitive liveness verification stage.
[0047] In light of the above, in one aspect of the present disclosure, a hybrid biometric authentication system is disclosed herein. The method includes receiving, by a fingerprint sensor, fingerprint data of a user. The method also include extracting, by a fingerprint feature extraction module executed by a processing unit, fingerprint feature parameters including ridge structure and minutiae information. The method also includes comparing, by a fingerprint matching module, the extracted fingerprint feature parameters with stored fingerprint templates to generate a fingerprint authentication confidence score. The method also include generating, by a visual stimulus generation module, a flickering visual stimulus configured to evoke SSVEP responses from the user. The method also include acquiring, by an EEG headset, raw EEG signals corresponding to user attention toward the flickering visual stimulus. The method also includes receiving, by an EEG signal acquisition interface module, the raw EEG signals. The method also includes pre-processing, by an EEG signal pre-processing module, the raw EEG signals including filtering and noise reduction to generate pre-processed EEG signals. The method also includes detecting, by an SSVEP detection module, stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis. The method also includes extracting, by a brainwave feature extraction module, brainwave feature parameters corresponding to the detected SSVEP frequency components. The method also includes classifying, by an EEG classification module, the extracted brainwave feature parameters to generate an EEG authentication confidence score. The method also includes combining, by a fusion decision module, the fingerprint authentication confidence score and the EEG authentication confidence score to generate a final authentication score. The method also includes granting or denying, by an authentication controller module, access to a protected system based on comparison of the final authentication score with a predefined authentication threshold.
[0048] These and other advantages will be apparent from the present application of the embodiments described herein.
[0049] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
[0050] These elements, together with the other aspects of the present disclosure and various features are pointed out with particularity in the claims annexed hereto and form a part of the present disclosure. For a better understanding of the present disclosure, its operating advantages, and the specified object attained by its uses, reference should be made to the accompanying drawings and descriptive matter in which there are illustrated exemplary embodiments of the present disclosure.
BRIEF DESCRIPTION OF THE DRAWINGS
[0051] To describe the technical solutions in the embodiments of the present disclosure or in the prior art more clearly, the following briefly describes the accompanying drawings required for describing the embodiments or the prior art. Apparently, the accompanying drawings in the following description merely show some embodiments of the present disclosure, and a person of ordinary skill in the art can derive other implementations from these accompanying drawings without creative efforts. All of the embodiments or the implementations shall fall within the protection scope of the present disclosure.
[0052] The advantages and features of the present disclosure will become better understood with reference to the following detailed description taken in conjunction with the accompanying drawing, in which:
[0053] FIG. 1 illustrates a block diagram of a hybrid biometric authentication system, in accordance with an embodiment of the present disclosure;
[0054] FIG. 2 illustrates a flow chart of a method, outlining the sequential step for hybrid biometric authentication system in accordance with an embodiment of the present disclosure;
[0055] Like reference, numerals refer to like parts throughout the description of several views of the drawing.
[0056] The hybrid SSVEP-based brainwave and fingerprint biometric authentication system is illustrated in the accompanying drawings, which like reference letters indicate corresponding parts in the various figures. It should be noted that the accompanying figure is intended to present illustrations of exemplary embodiments of the present disclosure. This figure is not intended to limit the scope of the present disclosure. It should also be noted that the accompanying figure is not necessarily drawn to scale.
DETAILED DESCRIPTION OF THE DISCLOSURE
[0057] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure.
[0058] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be apparent to one skilled in the art that embodiments of the present disclosure may be practiced without some of these specific details.
[0059] Various terms as used herein are shown below. To the extent a term is used, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.
[0060] The terms “a” and “an” herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced items.
[0061] The terms “having”, “comprising”, “including”, and variations thereof signify the presence of a component.
[0062] Referring now to FIG. 1 to FIG. 2 to describe various exemplary embodiments of the present disclosure. FIG. 1 illustrates a block diagram of a hybrid biometric authentication system, in accordance with an embodiment of the present disclosure.
[0063] The system 100 may include a user device 102. The system 100 may also include a communication network 104. The system 100 may also include a fingerprint sensor 106. The system 100 may also include a flickering display screen 108. The system 100 may also include an electroencephalogram EEG headset 110. The system 100 may also include a processing unit 112 which further comprises a fingerprint feature extraction module 114, a fingerprint matching module 116, an EEG signal acquisition interface module 118, an EEG signal pre-processing module 120, an SSVEP detection module 122, a brainwave feature extraction module 124, an EEG classification module 126, a fusion decision module 128. The system 100 may also include an authentication controller 130.
[0064] In one embodiment of the present invention, the fingerprint authentication process is executed prior to EEG-based authentication such that SSVEP verification is performed as a secondary cognitive liveness verification stage.
[0065] The user device 102 configured to receive authentication input from a user, the user device comprising a display interface, input interface, and housing structure configured to support biometric authentication operations. The user device 102 acts as the primary physical platform through which authentication interaction occurs. The device may be implemented as a handheld terminal, workstation interface, access-control panel, and portable computing device. The housing structure provides mechanical support for integrated biometric hardware while maintaining ergonomic alignment for simultaneous fingerprint placement and visual attention. The device coordinates user interaction flow by initiating authentication sessions, presenting visual cues, and transmitting system responses. In practical implementations, the user device maintains synchronization between visual stimulus generation and biometric acquisition timing to ensure consistent authentication conditions.
[0066] The communication network 104 operatively connected to the user device 102 and configured to transmit authentication data, control signals, and authentication results between the user device and an external access-control system. The communication network 104 provides bidirectional data exchange between the user device and external infrastructure such as authentication servers, access-control gateways, and secure databases. The network may comprise wired and wireless communication protocols including local area networks, encrypted wireless channels, and secure cloud-based connections. Beyond simple data transmission, the communication network enables remote verification, template storage access, and centralized authentication logging. The network architecture allows authentication decisions to be propagated in real time to external systems such as doors, computing environments, and secured applications.
[0067] The fingerprint sensor 106 integrated within the user device 102, the fingerprint sensor 106 being configured to capture fingerprint ridge patterns and minutiae features from a user finger and generate fingerprint data signals representative of the captured fingerprint. The fingerprint sensor 106 operates as a biometric acquisition interface designed to capture high-resolution surface characteristics of a user’s finger. The sensor converts physical ridge patterns into electrical and digital signal representations through optical, capacitive, and ultrasonic sensing mechanisms. During operation, the sensor performs contact detection and initiates acquisition only upon stable finger placement, thereby reducing noise and partial image capture. The generated signal data is formatted into standardized biometric input suitable for downstream processing, enabling consistent extraction of identity-defining features.
[0068] The flickering display screen 108 configured to generate a periodic visual stimulus at a predefined flickering frequency range to induce a steady-state visual evoked potential (SSVEP) neural response from the user during an authentication session. The flickering display screen 108 serves as a visual stimulus generator intended to evoke neural responses associated with steady-state visual evoked potentials. The screen may employ LED-based illumination, LCD refresh modulation, and software-controlled brightness oscillation to produce periodic flickering patterns. The display maintains controlled stimulus timing and luminance stability to ensure repeatable neural responses across authentication sessions. The flickering sequence may be visually embedded within graphical interfaces to maintain user comfort while ensuring accurate neural stimulation.
[0069] In one embodiment of the present invention, the visual stimulus generation module 108 is configured to generate a periodic flickering visual stimulus within a frequency range of 8 Hz to 20 Hz to evoke steady-state visual evoked potential (SSVEP) responses from a user.
[0070] The electroencephalogram (EEG) headset 110 comprising a plurality of electrodes positioned at occipital regions of a user and configured to acquire brainwave signals generated in response to the periodic visual stimulus, the EEG headset further comprising signal acquisition circuitry for transmitting EEG signals. The EEG headset 110 provides neural signal acquisition by establishing electrical contact with scalp regions associated with visual cortex activity. The headset includes electrode assemblies, signal amplification circuitry, and analog-to-digital conversion components designed to capture low-amplitude brainwave signals. Integrated shielding and grounding structures minimize interference from environmental electrical noise. The headset architecture allows rapid placement and stable signal acquisition during short authentication windows while maintaining user comfort for repeated usage.
[0071] In one embodiment of the present invention, the EEG headset 110 comprises a plurality of electrodes positioned at occipital brain regions including O1, Oz, and O2 electrode locations for acquisition of SSVEP signals.
[0072] The processing unit 112 operatively connected to the fingerprint sensor 106, the flickering display screen 108, and the EEG headset 110, the processing unit 112 comprises at least one processors and memory storing executable instructions. The processing unit 112 functions as the central computational core responsible for coordinating biometric signal processing, synchronization, and decision generation. The processing unit executes stored instruction sets enabling sequential and parallel handling of fingerprint and EEG data streams. Internal memory resources maintain temporary signal buffers, template data, and intermediate processing results. The processing unit further manages timing coordination between stimulus generation and EEG acquisition to ensure correct alignment between visual stimulation and neural response analysis.
[0073] The fingerprint feature extraction module 114 configured to receive fingerprint data from the fingerprint sensor 106 and generate fingerprint feature parameters including ridge structure and minutiae information. The fingerprint feature extraction module 114 transforms raw fingerprint signal data into structured feature representations suitable for identity comparison. The module performs image enhancement, ridge orientation analysis, and minutiae localization to isolate discriminative fingerprint characteristics. Feature normalization techniques are applied to ensure robustness against rotation, pressure variation, and minor sensor inconsistencies. The resulting feature parameters provide compact identity descriptors for efficient matching operations.
[0074] In one embodiment of the present invention, the authentication controller module 114 grants access only when the final authentication score exceeds a predefined threshold, thereby enabling dual-factor liveness-verified authentication.
[0075] The fingerprint matching module 116 configured to compare the generated fingerprint feature parameters with stored fingerprint templates and output a fingerprint authentication confidence score. The fingerprint matching module 116 evaluates similarity between extracted fingerprint features and reference templates stored within secure memory. The module performs alignment correction and similarity scoring to compensate for translational and rotational differences between samples. Matching logic may utilize correlation-based, distance-based, and pattern-alignment approaches to generate confidence metrics representing identity likelihood. The module outputs standardized confidence values enabling integration with multimodal fusion processing.
[0076] The EEG signal acquisition interface module 118 configured to receive raw EEG signals acquired from the EEG headset 110. The EEG signal acquisition interface module 118 acts as a bridge between the EEG headset and internal processing stages. The module receives digitized neural signals, verifies signal integrity, and organizes incoming data into time-synchronized buffers. Signal framing mechanisms ensure consistent sampling intervals and maintain alignment with visual stimulus timing. The interface also performs preliminary validation to detect signal loss and electrode detachment conditions.
[0077] The EEG signal pre-processing module 120 configured to perform filtering, artefact removal, and noise reduction on the received EEG signals to generate pre-processed EEG signals. The EEG signal pre-processing module 120 improves signal quality by reducing artefacts generated from eye movement, muscle activity, and environmental interference. The module applies filtering operations and baseline correction techniques to isolate relevant neural frequency bands. Adaptive noise suppression algorithms may be employed to maintain signal clarity across varying operating conditions. The output produced by this stage provides stable neural data suitable for frequency analysis.
[0078] In one embodiment of the present invention, the EEG signal pre-processing module 120 performs band-pass filtering within a frequency range of 5 Hz to 50 Hz and noise reduction to remove motion artefacts and environmental interference.
[0079] The SSVEP detection module 122 configured to identify stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis. The SSVEP detection module 122 analyses the pre-processed EEG data to identify neural oscillations corresponding to the visual stimulus frequency. The module performs spectral analysis to detect frequency peaks that indicate user attention toward the flickering stimulus. Detection logic evaluates signal consistency over time windows to avoid false detections caused by transient noise. This stage establishes the presence of intentional cognitive engagement required for liveness verification.
[0080] In one embodiment of the present invention, the SSVEP detection module 122 performs frequency-domain analysis using at least one of Fast Fourier Transform (FFT) and Canonical Correlation Analysis (CCA) to detect dominant stimulus-correlated frequencies.
[0081] The brainwave feature extraction module 124 configured to generate brainwave feature parameters corresponding to detected SSVEP responses. The brainwave feature extraction module 124 converts detected neural frequency information into structured feature vectors representing user-specific response patterns. Parameters such as spectral amplitude distribution, phase stability, and response strength may be computed to characterize neural signatures. Feature normalization and scaling operations ensure compatibility with classification models while preserving discriminatory information.
[0082] The EEG classification module 126 configured to classify the brainwave feature parameters and generate an EEG authentication confidence score. The EEG classification module 126 interprets extracted brainwave features to determine whether the observed neural response corresponds to a previously enrolled user pattern. The module may employ at least one statistical models and trained machine-learning classifiers to evaluate similarity and produce probabilistic confidence outputs. Classification processing converts complex neural data into a simplified authentication confidence score suitable for multimodal fusion.
[0083] In one embodiment of the present invention, the EEG classification module 126 comprises a trained machine-learning classifier selected from a group consisting of Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) models.
[0084] The fusion decision module 128 configured to combine the fingerprint authentication confidence score and the EEG authentication confidence score according to a predefined fusion rule to generate a final authentication score. The fusion decision module 128 integrates outputs from both biometric modalities to produce a unified authentication metric. The module applies predefined fusion logic that balances physical biometric certainty with neural verification confidence. Adaptive weighting strategies may be employed to account for signal quality variations between modalities. The fusion process improves reliability by reducing dependence on a single biometric source and mitigating false acceptance scenarios.
[0085] In one embodiment of the present invention, the fusion decision module 128 generates the final authentication score using a weighted fusion rule defined as Sfinal = w1S1 + w2S2 where S1 represents the fingerprint authentication confidence score and S2 represents the EEG authentication confidence score.
[0086] The authentication controller 130 operatively connected to the processing unit 112, the authentication controller 130 being configured to compare the final authentication score with a predefined threshold value and output an authentication decision signal for granting and denying access to a protected system. The authentication controller 130 performs final decision execution based on outputs received from the fusion decision module. The controller enforces predefined security policies and threshold criteria to determine access authorization. Upon successful authentication, the controller generates control signals for external systems such as access doors, computing sessions, and secure databases. In unsuccessful cases, the controller may trigger rejection signals, logging mechanisms, and additional verification requests. The controller thereby acts as the final enforcement layer connecting biometric intelligence with real-world security actions.
[0087] FIG. 2 illustrates a flow chart of a method 200, outlining the sequential step for hybrid biometric authentication system 100 in accordance with an embodiment of the present disclosure.
[0088] At step 202, receiving, by a fingerprint sensor 106, fingerprint data of a user.
[0089] At step 204, extracting, by a fingerprint feature extraction module 114 executed by a processing unit 112, fingerprint feature parameters including ridge structure and minutiae information.
[0090] At step 206, comparing, by a fingerprint matching module 116, the extracted fingerprint feature parameters with stored fingerprint templates to generate a fingerprint authentication confidence score.
[0091] At step 208, generating, by a visual stimulus generation module 108, a flickering visual stimulus configured to evoke SSVEP responses from the user.
[0092] At step 210, acquiring, by an EEG headset 110, raw EEG signals corresponding to user attention toward the flickering visual stimulus.
[0093] At step 212, receiving, by an EEG signal acquisition interface module 118, the raw EEG signals.
[0094] At step 214, pre-processing, by an EEG signal pre-processing module 120, the raw EEG signals including filtering and noise reduction to generate pre-processed EEG signals.
[0095] At step 216, detecting, by an SSVEP detection module 122, stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis.
[0096] At step 218, extracting, by a brainwave feature extraction module 124, brainwave feature parameters corresponding to the detected SSVEP frequency components.
[0097] At step 220, classifying, by an EEG classification module 126, the extracted brainwave feature parameters to generate an EEG authentication confidence score.
[0098] At step 222, combining, by a fusion decision module 128, the fingerprint authentication confidence score and the EEG authentication confidence score to generate a final authentication score.
[0099] At step 224, granting and denying, by an authentication controller module 114, access to a protected system based on comparison of the final authentication score with a predefined authentication threshold.
[0100] In the best mode of operation, the hybrid biometric authentication system 100 remains in a standby state awaiting initiation of an authentication session by a user. Upon initiation, the user device 102 activates the biometric authentication workflow and coordinates operation of the fingerprint sensor 106, flickering display screen 108, and electroencephalogram (EEG) headset 110 under control of the processing unit 112. During authentication, the user places a finger on the fingerprint sensor 106, which captures fingerprint ridge structures and minutiae characteristics and transmits corresponding fingerprint data to the processing unit 112. The fingerprint feature extraction module 114 processes the captured data to generate structured fingerprint feature parameters representing the biometric identity of the user. The generated features are then forwarded to the fingerprint matching module 116, which compares the extracted features with enrolled fingerprint templates stored within system memory and generates a fingerprint authentication confidence score representing the degree of match. Following fingerprint acquisition, and concurrently depending on system configuration, the flickering display screen 108 presents a periodic visual stimulus at a predefined frequency. The user is instructed to visually focus on the stimulus, thereby inducing a steady-state visual evoked potential (SSVEP) response within the visual cortex. The EEG headset 110, positioned over occipital regions of the user’s scalp, acquires neural signals generated in response to the visual stimulus and transmits the signals to the processing unit 112 through the EEG signal acquisition interface module 118. The EEG signal pre-processing module 120 performs signal conditioning operations including filtering, artefact suppression, and noise reduction to isolate relevant neural components from raw EEG data. The pre-processed signals are analysed by the SSVEP detection module 122, which identifies frequency components correlated with the flickering stimulus. Upon successful detection, the brainwave feature extraction module 124 generates feature parameters representing neural response characteristics. These features are processed by the EEG classification module 126, which evaluates correspondence between the acquired brainwave pattern and previously registered neural signatures to generate an EEG authentication confidence score. The fusion decision module 128 receives both the fingerprint authentication confidence score and the EEG authentication confidence score and combines them according to a predefined fusion rule to generate a final authentication score. The fusion process ensures that both physical identity verification and cognitive liveness verification are considered jointly, thereby improving security robustness against spoofing attempts. The authentication controller 130 compares the final authentication score against a predefined authentication threshold. When the score exceeds the threshold, the authentication controller generates an authorization signal that is transmitted via the communication network 104 to an external access-control system, thereby granting access to a protected resource and environment. If the final score does not meet the threshold requirement, the authentication controller outputs a denial signal and optionally initiates re-authentication and security logging procedures. Throughout operation, the processing unit 112 maintains synchronization between visual stimulus timing and EEG acquisition windows to ensure accurate SSVEP detection. In the preferred operational configuration, the system completes authentication within a short interaction period while ensuring reliable liveness verification and dual-biometric confirmation. Upon completion of the authentication session, the system returns to standby mode awaiting the next authentication request.
[0101] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it will be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0102] A person of ordinary skill in the art may be aware that, in combination with the examples described in the embodiments disclosed in this specification, units and algorithm steps may be implemented by electronic hardware, computer software, or a combination thereof.
[0103] The foregoing descriptions of specific embodiments of the present disclosure have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present disclosure to the precise forms disclosed, and many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described to best explain the principles of the present disclosure and its practical application, and to thereby enable others skilled in the art to best utilize the present disclosure and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient, but such omissions and substitutions are intended to cover the application or implementation without departing from the scope of the present disclosure.
[0104] Disjunctive language such as the phrase “at least one of X, Y, Z,” unless specifically stated otherwise, is otherwise understood with the context as used in general to present that an item, term, etc., may be either X, Y, or Z, or any combination thereof (e.g., X, Y, and/or Z). Thus, such disjunctive language is not generally intended to, and should not, imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z to each be present.
[0105] In a case that no conflict occurs, the embodiments in the present disclosure and the features in the embodiments may be mutually combined. The foregoing descriptions are merely specific implementations of the present disclosure, but are not intended to limit the protection scope of the present disclosure. Any variation or replacement readily figured out by a person skilled in the art within the technical scope disclosed in the present disclosure shall fall within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
, Claims:I/We Claim:
1. A hybrid biometric authentication system (100), the system (100) comprising:
a user device (102) configured to receive authentication input from a user, the user device comprising a display interface, input interface, and housing structure configured to support biometric authentication operations;
a communication network (104) operatively connected to the user device (102) and configured to transmit authentication data, control signals, and authentication results between the user device and an external access-control system;
a fingerprint sensor (106) integrated within the user device (102), the fingerprint sensor (106) being configured to capture fingerprint ridge patterns and minutiae features from a user finger and generate fingerprint data signals representative of the captured fingerprint;
a flickering display screen (108) configured to generate a periodic visual stimulus at a predefined flickering frequency range to induce a steady-state visual evoked potential (SSVEP) neural response from the user during an authentication session;
an electroencephalogram (EEG) headset (110) comprising a plurality of electrodes positioned at occipital regions of a user and configured to acquire brainwave signals generated in response to the periodic visual stimulus, the EEG headset further comprising signal acquisition circuitry for transmitting EEG signals;
a processing unit (112) operatively connected to the fingerprint sensor (106), the flickering display screen (108), and the EEG headset (110), the processing unit (112) comprises at least one processors and memory storing executable instructions, wherein the processing unit (112) further comprising:
a fingerprint feature extraction module (114) configured to receive fingerprint data from the fingerprint sensor (106) and generate fingerprint feature parameters including ridge structure and minutiae information;
a fingerprint matching module (116) configured to compare the generated fingerprint feature parameters with stored fingerprint templates and output a fingerprint authentication confidence score;
an EEG signal acquisition interface module (118) configured to receive raw EEG signals acquired from the EEG headset (110);
an EEG signal pre-processing module (120) configured to perform filtering, artefact removal, and noise reduction on the received EEG signals to generate pre-processed EEG signals;
an SSVEP detection module (122) configured to identify stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis;
a brainwave feature extraction module (124) configured to generate brainwave feature parameters corresponding to detected SSVEP responses;
an EEG classification module (126) configured to classify the brainwave feature parameters and generate an EEG authentication confidence score;
a fusion decision module (128) configured to combine the fingerprint authentication confidence score and the EEG authentication confidence score according to a predefined fusion rule to generate a final authentication score;
an authentication controller (130) operatively connected to the processing unit (112), the authentication controller (130) being configured to compare the final authentication score with a predefined threshold value and output an authentication decision signal for granting and denying access to a protected system.
2. The system (100) as claimed in claim 1, wherein the visual stimulus generation module (108) is configured to generate a periodic flickering visual stimulus within a frequency range of 8 Hz to 20 Hz to evoke steady-state visual evoked potential (SSVEP) responses from a user.
3. The system (100) as claimed in claim 1, wherein the EEG headset (110) comprises a plurality of electrodes positioned at occipital brain regions including O1, Oz, and O2 electrode locations for acquisition of SSVEP signals.
4. The system (100) as claimed in claim 1, wherein the EEG signal pre-processing module (120) performs band-pass filtering within a frequency range of 5 Hz to 50 Hz and noise reduction to remove motion artefacts and environmental interference.
5. The system (100) as claimed in claim 1, wherein the SSVEP detection module (122) performs frequency-domain analysis using at least one of Fast Fourier Transform (FFT) and Canonical Correlation Analysis (CCA) to detect dominant stimulus-correlated frequencies.
6. The system (100) as claimed in claim 1, wherein the EEG classification module (126) comprises a trained machine-learning classifier selected from a group consisting of at least one Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) models.
7. The system (100) as claimed in claim 1, wherein the fusion decision module (128) generates the final authentication score using a weighted fusion rule defined as Sfinal = w1S1 + w2S2 where S1 represents the fingerprint authentication confidence score and S2 represents the EEG authentication confidence score.
8. The system (100) as claimed in claim 1, wherein the authentication controller module (114) grants access only when the final authentication score exceeds a predefined threshold, thereby enabling dual-factor liveness-verified authentication.
9. The system (100) as claimed in claim 1, wherein the fingerprint authentication process is executed prior to EEG-based authentication such that SSVEP verification is performed as a secondary cognitive liveness verification stage.
10. A method (200) for making hybrid biometric authentication system (100), the method (200) comprising:
receiving (202), by a fingerprint sensor (106), fingerprint data of a user;
extracting (204), by a fingerprint feature extraction module (114) executed by a processing unit (112), fingerprint feature parameters including ridge structure and minutiae information;
comparing (206), by a fingerprint matching module (116), the extracted fingerprint feature parameters with stored fingerprint templates to generate a fingerprint authentication confidence score;
generating (208), by a visual stimulus generation module (108), a flickering visual stimulus configured to evoke SSVEP responses from the user;
acquiring (210), by an EEG headset (110), raw EEG signals corresponding to user attention toward the flickering visual stimulus;
receiving (212), by an EEG signal acquisition interface module (118), the raw EEG signals;
pre-processing (214), by an EEG signal pre-processing module (120), the raw EEG signals including filtering and noise reduction to generate pre-processed EEG signals;
detecting (216), by an SSVEP detection module (122), stimulus-correlated frequency components from the pre-processed EEG signals using frequency-domain analysis;
extracting (218), by a brainwave feature extraction module (124), brainwave feature parameters corresponding to the detected SSVEP frequency components;
classifying (220), by an EEG classification module (126), the extracted brainwave feature parameters to generate an EEG authentication confidence score;
combining (222), by a fusion decision module (128), the fingerprint authentication confidence score and the EEG authentication confidence score to generate a final authentication score;
granting and denying (224), by an authentication controller module (114), access to a protected system based on comparison of the final authentication score with a predefined authentication threshold.