Mobile terminal intelligent identity recognition method and system based on biological multiple modes
Through biomultimodal recognition technology, combined with fingerprint, facial and iris characteristics, a comprehensive evaluation and weighted quality scoring strategy is adopted to solve the problems of insufficient biometric singularity and authentication flexibility in the existing technology, and achieve higher identity authentication Security and accuracy provide users with a more stable and convenient identity verification experience.
Patent Information
- Application Number
- CN202410870988.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-01
- Publication Date
- 2024-11-05
AI Technical Summary
When faced with multiple biometrics, existing biometric technologies have the limitations of a single feature and the inaccurate evaluation of feature quality, resulting in insufficient flexibility and insufficient security of identity authentication.
Using biomultimodal recognition technology, extract user information through sensors, design a mobile terminal system architecture, combine multiple biometric features (fingerprints, faces, iris) for identity verification, and adopt comprehensive evaluation and weighted quality scoring strategies to dynamically select the best features Carry out authentication and improve system stability through pre-processing and exception handling modules.
Effectively improve the security and accuracy of identity authentication, reduce the risks brought by a single feature, improve the flexibility and adaptability of the system, ensure the accuracy of user identity and the stability of the system, and provide users with a more secure Digital experience.
Smart Images

Figure CN118898059A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of biometric identification technology, and in particular to a mobile terminal intelligent identity recognition method and system based on biometric multimodality. Background Art
[0002] In today's society, with the continuous advancement of digitalization and intelligence, people's demand for security and convenience is increasing, and with it comes higher requirements for identity authentication technology, especially in the field of mobile terminals. Traditional identity authentication methods such as passwords and PIN codes are at risk of being guessed and stolen. Therefore, society has begun to turn to safer and more convenient biometric technology, which reflects the current society's pursuit of intelligence, high efficiency and security, and emphasizes the importance of personal information protection and data security.
[0003] Existing biometric recognition technology has the limitation of a single feature when facing multiple biometric features, as well as problems such as inaccurate feature quality assessment and insufficient flexibility in identity authentication. The present invention introduces biometric multimodal recognition, uses a combination of different biometric features for identity authentication, and solves the problems of insufficient biometric singleness and authentication flexibility in the prior art by comprehensively evaluating feature quality and selecting priorities, thereby improving the security and accuracy of mobile terminal identity recognition. Summary of the invention
[0004] In view of the problems existing in the existing mobile terminal intelligent identity recognition method and system based on biometric multimodality, the present invention is proposed.
[0005] Therefore, the purpose of the present invention is to provide a mobile terminal intelligent identity recognition method and system based on biometric multimodality, and to solve the problems of insufficient singleness of biometric features and insufficient authentication flexibility in the prior art by using the biometric multimodal recognition technology of the present invention.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In the first aspect, an embodiment of the present invention provides a method for intelligent identity recognition of a mobile terminal based on biometric multimodality, which includes: using sensors to extract user information, using biometric technology to design a mobile terminal system architecture, and selecting biometric features based on the system architecture; fusing the extracted user information and biometric features, and introducing a comprehensive authentication algorithm to verify the biometric features; establishing an abnormal recognition processing module to complete the monitoring fusion process, formulating a security measure emergency response strategy to maintain the mobile terminal system architecture, and deploying the maintained system to the actual environment for intelligent identity recognition.
[0008] As a preferred solution of the mobile terminal intelligent identity recognition method based on biometric multimodality of the present invention, wherein: the mobile terminal system architecture includes an application layer, a business logic layer, a biometric recognition engine layer and a data storage layer, and the application layer includes establishing a user-friendly interface to allow user information to select biometric features through the user-friendly interface;
[0009] The business logic layer includes identity authentication based on the selected biometric features based on the feature selection algorithm;
[0010] The biometric engine layer includes pre-processing the results after identity authentication using a feature extraction algorithm;
[0011] The data storage layer includes storing the preprocessed information through a storage layer structure.
[0012] As a preferred solution of the mobile terminal intelligent identity recognition method based on biometric multimodality of the present invention, wherein: the identity authentication includes evaluating the biometric features according to the historical records and the feature collection quality, and the evaluation includes a feature quality evaluation stage, a feature selection decision stage, a feature selection decision explanation stage and an identity authentication stage;
[0013] The feature quality assessment stage includes the user fingerprint quality score Q fingerprint、 User face quality score Q facial and user iris quality score Q iris ;
[0014] The feature selection decision stage includes the user fingerprint feature weight W fingerprint、 User facial feature weight W facial and user iris feature weight W iris ;
[0015] The feature selection decision explanation stage includes calculating the weighted quality score of the biometric feature according to the feature quality assessment stage and the feature selection decision stage, and calculating the weighted quality score of the biometric feature, and the specific steps are as follows:
[0016] The specific calculation formula for calculating the fingerprint quality of the weighted quality score is:
[0017]
[0018] The specific calculation formula for calculating the weighted quality score of the face quality is:
[0019]
[0020] The specific calculation formula for calculating the weighted quality score of the iris quality is:
[0021]
[0022] Among them, Q fj represents the weight of the i-th biometric feature, W fi represents the quality score of the i-th biometric feature;
[0023] The specific calculation formula for calculating the weighted quality score of the biometric feature is:
[0024]
[0025] Among them, S f represents the weighted quality score of the biometric feature, Represents feature quality considerations.
[0026] As a preferred solution of the mobile terminal intelligent identity recognition method based on biometric multimodality of the present invention, wherein: the identity authentication stage includes the system giving priority to selecting features with better quality for authentication according to different selection situations between users;
[0027] When the user selects fingerprint feature for authentication, if S fingerprint ≤S f When the face quality S facial ≤Iris quality S iris When , the system gives priority to iris quality S iris Conduct certification;
[0028] If S fingerprint >S f When the fingerprint feature is used for authentication, the system will give priority to fingerprint features;
[0029] When the user selects facial features for authentication, if S facial ≤S f When the fingerprint quality S fingerprint ≤Iris quality S iris When , the system gives priority to iris quality S iris Authentication is performed, otherwise, the system gives priority to fingerprint quality S fingerprint Conduct certification;
[0030] If S facial >S f When , the system gives priority to facial features for authentication;
[0031] When the user selects iris quality for authentication, if S iris ≤S f When the fingerprint quality S fingerprint≤Facial quality S facial When , the system gives priority to facial quality S facial Authentication is performed, otherwise, the system gives priority to fingerprint quality S fingerprint Conduct certification;
[0032] If S iris >S f , the system gives priority to iris quality for authentication.
[0033] As a preferred solution of the mobile terminal intelligent identity recognition method based on biometric multimodality of the present invention, the preprocessing includes mapping the identity authentication result into a high-dimensional feature space, and performing standardization processing on the biometric recognition feature. The standardization processing includes calculating the original value of the fingerprint feature, the original value of the facial feature, and the original value of the iris feature. The specific steps are as follows:
[0034] The specific formula for calculating the original value of the fingerprint feature is:
[0035]
[0036] Among them, Z fingerprint Represents the original value of fingerprint feature, μ fingerprint represents the mean value of fingerprint features, σ fingerprint Indicates the standard deviation of fingerprint features;
[0037] The specific calculation formula of the original value of the facial feature is:
[0038]
[0039] Among them, Z facial Represents the original value of facial features, μ facial represents the mean of facial features, σ facial represents the standard deviation of facial features;
[0040] The calculation formula of the original value of the iris feature is:
[0041]
[0042] Among them, Z iris Represents the original value of iris features, μ iris represents the mean of iris features, σ iris Represents the standard deviation of iris features.
[0043] As a preferred solution of the mobile terminal intelligent identity recognition method based on biometric multimodality of the present invention, wherein: the extraction of user information includes using a sensor to extract the bifurcation points of the pre-processed information, and calculating the similarity scores between the bifurcation points. The specific calculation formula is:
[0044]
[0045] Where n represents the number of fingerprint feature points, P(x i ,y i ) represents the coordinates of the i-th feature point in the user information, Q(x i ,y i ) represents the coordinates of the i-th feature point in the data storage layer, ω i Represents the weight of the i-th feature point;
[0046] The fusion includes combining the original values or features extracted from different biometric fingerprints, faces and irises, and the specific steps are as follows:
[0047] The raw values of the features extracted from the fingerprint sensor are combined with the mean and standard deviation to obtain a comprehensive representation of the fingerprint features;
[0048] Combining the raw values of features extracted from the facial sensor with the mean and standard deviation to obtain a comprehensive representation of the facial features;
[0049] The raw values of the features extracted from the iris sensor are combined with the mean and standard deviation to obtain a comprehensive representation of the iris features.
[0050] As a preferred solution of the mobile terminal intelligent identity recognition method based on biometric multimodality of the present invention, wherein: the verification of the biometric feature includes adding the weighted sum to the similarity score Compare and determine the authentication result. If the weighted sum is greater than the similarity score, If the authentication succeeds, then the authentication fails.
[0051] The maintenance of the mobile terminal system architecture includes extracting the authentication failure frequency and automatically processing the abnormal situation;
[0052] The automated processing includes establishing an abnormal identification processing module to audit the system, and the audit inspection includes deploying the results of the audit inspection to the actual environment for intelligent identity recognition.
[0053] In a second aspect, an embodiment of the present invention provides a mobile terminal intelligent identity recognition system based on biometric multimodality, which includes: a design module that uses a sensor to extract user information, uses biometric technology to design a mobile terminal system architecture, and selects biometric features based on the system architecture;
[0054] The verification module combines the extracted user information with the biometric features and introduces a comprehensive authentication algorithm to verify the biometric features;
[0055] The identification module deploys the maintained system into the actual environment for intelligent identity recognition.
[0056] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, any step of the above-mentioned mobile terminal intelligent identity recognition method based on biometric multimodality is implemented.
[0057] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned mobile terminal intelligent identity recognition method based on biometric multimodality is implemented.
[0058] The beneficial effects of the present invention are as follows: the present invention effectively improves the security and accuracy of identity authentication by applying biometric multimodal recognition to intelligent identity recognition of mobile terminals. By integrating multiple biometric features, such as fingerprints, faces, and irises, the system can more comprehensively verify the identity of users and reduce the authentication risks brought by a single feature. At the same time, the strategy of comprehensive evaluation and dynamic selection of the best features is adopted to make the system more flexible and adaptable, and can dynamically adjust the authentication scheme according to actual conditions to ensure the accuracy of user identities. In addition, the system also improves the stability and reliability of the system through preprocessing and exception handling modules, thereby ensuring the security and convenience of intelligent identity recognition of mobile terminals and providing users with a more secure digital experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:
[0060] Figure 1 A flowchart of a method and system for intelligent identity recognition of a mobile terminal based on biometric multimodality is provided in accordance with an embodiment of the present invention.
[0061] Figure 2 An identification and verification flow chart of a mobile terminal intelligent identity recognition method and system based on biometric multimodality provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0062] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0063] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0064] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0065] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.
[0066] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0067] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0068] Example 1
[0069] Reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a mobile terminal intelligent identity recognition method based on biometric multimodality, comprising:
[0070] S1: Use sensors to extract user information, use biometric technology to design the mobile terminal system architecture, and select biometric features based on the system architecture.
[0071] The mobile terminal system architecture includes an application layer, a business logic layer, a biometric engine layer, and a data storage layer. The application layer includes establishing a user-friendly interface, allowing user information to select biometric features through the user-friendly interface;
[0072] The business logic layer includes identity authentication based on the selected biometric features based on the feature selection algorithm;
[0073] The biometric engine layer includes preprocessing the authentication results using feature extraction algorithms;
[0074] The data storage layer includes storing the pre-processed information through a storage layer structure.
[0075] S1.1: Identity authentication includes an assessment of biometric features based on historical records and feature collection quality, including a feature quality assessment phase, a feature selection decision phase, a feature selection decision explanation phase, and an identity authentication phase;
[0076] The feature quality assessment stage includes the user fingerprint quality score Q fingerprint , user facial quality score Q facial and user iris quality score Q iris ;
[0077] The feature selection decision stage includes the user fingerprint feature weight W fingerprint , user facial feature weight W facial and user iris feature weight W iris ;
[0078] The feature selection decision explanation stage includes calculating the weighted quality score of the biometric feature according to the feature quality assessment stage and the feature selection decision stage, and calculating the weighted quality score of the biometric feature. The specific steps are as follows:
[0079] The specific calculation formula for fingerprint quality to calculate the weighted quality score is:
[0080]
[0081] The specific formula for calculating the weighted quality score of the face is:
[0082]
[0083] The specific calculation formula for iris quality to calculate the weighted quality score is:
[0084]
[0085] Among them, Q fj represents the weight of the i-th biometric feature, W fi represents the quality score of the i-th biometric feature;
[0086] The specific calculation formula for calculating the weighted quality score of the biometric feature is:
[0087]
[0088] Among them, S f represents the weighted quality score of the biometric feature, Represents feature quality considerations.
[0089] The system uses sensors to collect user biometric information and designs the system architecture of the mobile terminal through biometric technology, including the application layer, business logic layer, biometric engine layer and data storage layer. Users can select biometric features in the application layer interface. During the authentication stage, the system evaluates the feature quality and calculates the weighted quality score. For example, the fingerprint quality score is 85, the facial quality score is 90, and the iris quality score is 95. Based on the weighted quality score, the system determines the authentication result.
[0090] S1.2: The identity authentication stage includes that according to the different selection situations between users, the system gives priority to selecting features with better quality for authentication;
[0091] When the user selects fingerprint feature for authentication, if S fingerprint ≤S f When the face quality S facial ≤Iris quality S iris When , the system gives priority to iris quality S iris Conduct certification;
[0092] If S fingerprint >S f When the fingerprint feature is used for authentication, the system will give priority to fingerprint features;
[0093] When the user selects facial features for authentication, if S facial ≤S f When the fingerprint quality S fingerprint ≤Iris quality S iris When , the system gives priority to iris quality S iris Authentication is performed, otherwise, the system gives priority to fingerprint quality S fingerprint Conduct certification;
[0094] If S facial >S f When , the system gives priority to facial features for authentication;
[0095] When the user selects iris quality for authentication, if S iris ≤S f When the fingerprint quality S fingerprint ≤Facial quality S facial When , the system gives priority to facial quality S facial Authentication is performed, otherwise, the system gives priority to fingerprint quality S fingerprint Conduct certification;
[0096] If S iris >S f , the system gives priority to iris quality for authentication.
[0097] Furthermore, by giving priority to user selection and feature quality, the system can dynamically select features with better quality for authentication during the authentication phase, thereby improving the accuracy and reliability of authentication. For example, when a user chooses to perform fingerprint feature authentication, the system will intelligently determine the optimal authentication method based on the quality scores of fingerprint, face, and iris: if the fingerprint quality is low, but the face and iris quality are good, the system will give priority to iris features for authentication to ensure the reliability of the authentication results. This design effectively overcomes the problem of insufficient quality of a single feature, improves the security and accuracy of the authentication system, and provides users with a more stable and convenient authentication experience.
[0098] S1.3: Preprocessing includes mapping the identity authentication results into a high-dimensional feature space and standardizing the biometric features. The standardization includes calculating the original values of fingerprint features, facial features, and iris features. The specific steps are as follows:
[0099] The specific formula for calculating the original value of the fingerprint feature is:
[0100]
[0101] Among them, Z fingerprint Represents the original value of fingerprint feature, μ fingerprint represents the mean value of fingerprint features, σ fngerprint Indicates the standard deviation of fingerprint features;
[0102] The specific calculation formula of the original value of facial features is:
[0103]
[0104] Among them, Zfacial Represents the original value of facial features, μ facial represents the mean of facial features, σ facial represents the standard deviation of facial features;
[0105] The calculation formula of the original value of iris feature is:
[0106]
[0107] Among them, Z iris Represents the original value of iris features, μ iris represents the mean of iris features, σ iris Represents the standard deviation of iris features.
[0108] The preprocessing stage plays an important role in the entire technical solution. It maps the identity authentication results into a high-dimensional feature space and standardizes the biometric features, which improves the reliability and stability of the authentication results. By calculating the original values of fingerprint, facial and iris features and performing standardization, the comparability between different features is ensured. This process provides an accurate and reliable data basis for subsequent identity authentication.
[0109] S2: The extracted user information and biometric features are integrated, and a comprehensive authentication algorithm is introduced to verify the biometric features.
[0110] Among them, extracting user information includes using sensors to extract bifurcation points of pre-processed information and calculating the similarity scores between each bifurcation point. The specific calculation formula is:
[0111]
[0112] Where n represents the number of fingerprint feature points, P(x i ,y i ) represents the coordinates of the i-th feature point in the user information, Q(x i ,y i ) represents the coordinates of the i-th feature point in the data storage layer, ω i Represents the weight of the i-th feature point;
[0113] Fusion involves combining the raw values or features extracted from different biometric fingerprints, faces, and irises. The specific steps are as follows:
[0114] The raw values of the features extracted from the fingerprint sensor are combined with the mean and standard deviation to obtain a comprehensive representation of the fingerprint features;
[0115] Combining the raw values of features extracted from the facial sensor with the mean and standard deviation to obtain a comprehensive representation of the facial features;
[0116] The raw values of the features extracted from the iris sensor are combined with the mean and standard deviation to obtain a comprehensive representation of the iris features.
[0117] In the user information extraction stage, the system calculates the similarity scores between each feature point through the pre-processed information collected by the sensor. For example, assuming that the coordinates of the first feature point in the user information are P(x i ,y i )=(3,5), the coordinates of the corresponding feature points in the data storage layer are Q(x i ,y i )=(4,6), and its weight is 0.7. By calculating the Euclidean distance between two feature points and performing weighted calculation according to the weight, the similarity score of the feature point is obtained. Similarly, the system will perform similar calculations on all feature points to obtain the similarity score of each feature point, thereby comprehensively considering each feature point in the user information.
[0118] In the fusion stage, the system combines the raw values or features extracted from different biometric features. For example, for fingerprint features, the system combines its feature raw value with the mean and standard deviation to obtain a comprehensive representation of the fingerprint feature. For example, if the fingerprint feature raw value is 80, the mean is 75, and the standard deviation is 5, then the system will fuse them into a comprehensive fingerprint feature representation. Similarly, facial and iris features will also undergo similar processing, thereby combining multiple biometric features to improve the accuracy and reliability of identity authentication. The authentication data is summarized in Table 1 below:
[0119] Table 1 Identity authentication data summary
[0120]
[0121] The table summarizes all the data used in the authentication process, including the coordinates, weights and similarity scores of the feature points, as well as the raw value, mean, standard deviation and composite representation of the biometric features.
[0122] S2.1: Verification of the biometric feature includes comparing the weighted sum to the similarity score Compare and determine the authentication result. If the weighted sum is greater than the similarity score, If the authentication succeeds, then the authentication fails.
[0123] Maintaining the mobile terminal system architecture includes extracting authentication failure frequencies and automating abnormal situations;
[0124] Automated processing includes establishing an exception identification and processing module to audit the system. The audit inspection includes deploying the results of the audit inspection into the actual environment for intelligent identity recognition.
[0125] In a preferred embodiment, a biometric multimodal-based intelligent identity recognition system for a mobile terminal includes a design module that uses sensors to extract user information, uses biometric technology to design a mobile terminal system architecture, and selects biometric features based on the system architecture;
[0126] The identification module introduces a comprehensive authentication algorithm to verify the biometric features and complete the intelligent identity recognition of the mobile terminal.
[0127] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.
[0128] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or may be a key, trackball or touchpad provided on the housing of the computer device, or may be an external keyboard, touchpad or mouse, etc.
[0129] In summary, the present invention effectively improves the security and accuracy of identity authentication by applying biometric multimodal recognition to intelligent identity recognition of mobile terminals. By integrating multiple biometric features, such as fingerprints, faces, and irises, the system can more comprehensively verify the identity of users and reduce the authentication risks brought by a single feature. At the same time, the strategy of comprehensive evaluation and dynamic selection of the best features makes the system more flexible and adaptable, and can dynamically adjust the authentication scheme according to actual conditions to ensure the accuracy of user identities. In addition, the system also improves the stability and reliability of the system through preprocessing and exception handling modules, thereby ensuring the security and convenience of intelligent identity recognition of mobile terminals and providing users with a more secure digital experience.
[0130] Example 2
[0131] Reference Figure 1 and Figure 2, which is the second embodiment of the present invention, and this embodiment provides a mobile terminal intelligent identity recognition method based on biometric multimodality. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.
[0132] During the experiment, multiple identity authentication experiments were conducted on three subjects. Taking subject A as an example, the similarity scores between its feature points were calculated, and its fingerprint, face and iris features were processed. Specifically, the original value of subject A's fingerprint feature was 80, the mean was 75, and the standard deviation was 5; the original value of the facial feature was 90, the mean was 85, and the standard deviation was 6; the original value of the iris feature was 95, the mean was 92, and the standard deviation was 4. By combining the original values of these features with the corresponding means and standard deviations, a comprehensive feature representation was obtained, and identity authentication was successfully performed. The identity authentication data of subject A is shown in Table 2 below:
[0133] Table 2 Identity authentication data table of subject A
[0134] feature Original value Mean Standard Deviation Comprehensive representation fingerprint 80 75 5 81 Face 90 85 6 91 Iris 95 92 4 94 fingerprint 85 78 7 84 Face 88 83 5 89 Iris 92 90 3 93 fingerprint 78 76 4 79 Face 92 88 5 93 Iris 94 91 4 95
[0135] This table shows the data of subject A in three identity authentication experiments, including the original value, mean, standard deviation and comprehensive representation of fingerprint, face and iris features in each experiment. The comparison with the existing technology is shown in Table 3 below:
[0136] Table 3 Comparison with existing technology
[0137]
[0138] Compared with the existing technology, the technical solution of the present invention is more comprehensive, intelligent and accurate. Through a multi-level system architecture and a user-friendly interface, it realizes biometric feature selection, optimizes the identity authentication stage, and selects features based on quality; it introduces preprocessing, standardization and data fusion to improve intelligence and accuracy.
[0139] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A mobile terminal intelligent identity recognition method based on biometric multimodality, Features: include, Use sensors to extract user information, use biometric technology to design the mobile terminal system architecture, and select biometric features based on the system architecture; The extracted user information and biometric features are integrated, and a comprehensive authentication algorithm is introduced to verify the biometric features to complete the intelligent identity recognition of the mobile terminal.
2. The method for intelligent identity recognition of a mobile terminal based on biometric multimodality according to claim 1, Features: The mobile terminal system architecture includes an application layer, a business logic layer, a biometric engine layer, and a data storage layer, wherein the application layer includes establishing a user-friendly interface, allowing user information to select biometric features through the user-friendly interface; The business logic layer includes identity authentication based on the selected biometric features based on the feature selection algorithm; The biometric engine layer includes pre-processing the results after identity authentication using a feature extraction algorithm; The data storage layer includes storing the preprocessed information through a storage layer structure.
3. The mobile terminal intelligent identity recognition method based on biometric multimodality as claimed in claim 2, Features: The identity authentication includes evaluating the biometric features based on historical records and feature collection quality, and the evaluation includes a feature quality evaluation stage, a feature selection decision stage, a feature selection decision explanation stage, and an identity authentication stage; The feature quality assessment stage includes the user fingerprint quality score Q fingerprint , user facial quality score Q facial and user iris quality score Q iris ; The feature selection decision stage includes the user fingerprint feature weight W fingerprint , user facial feature weight W facial and user iris feature weight W iris ; The feature selection decision explanation stage includes calculating the weighted quality score of the biometric feature according to the feature quality assessment stage and the feature selection decision stage, and calculating the weighted quality score of the biometric feature, and the specific steps are as follows: The specific calculation formula for calculating the fingerprint quality of the weighted quality score is: The specific calculation formula for calculating the weighted quality score of the face quality is: The specific calculation formula for calculating the weighted quality score of the iris quality is: Among them, Q fj represents the weight of the i-th biometric feature, W fi represents the quality score of the i-th biometric feature; The specific calculation formula for calculating the weighted quality score of the biometric feature is: Among them, S f represents the weighted quality score of the biometric feature, Represents feature quality considerations.
4. The method for intelligent identity recognition of a mobile terminal based on biometric multimodality according to claim 3, Features: The identity authentication stage includes the system giving priority to selecting features with better quality for authentication according to different selection situations between users; When the user selects fingerprint feature for authentication, if S fingerprint ≤S f When the face quality S facial ≤Iris quality S iris When , the system gives priority to iris quality S iris Conduct certification; If S fingerprint >S f When the fingerprint feature is used for authentication, the system will give priority to fingerprint features; When the user selects facial features for authentication, if S facial ≤S f When the fingerprint quality S fingerprint ≤Iris quality S iris When , the system gives priority to iris quality S iris Authentication is performed, otherwise, the system gives priority to fingerprint quality S fingerprint Conduct certification; If S facial >S f When , the system gives priority to facial features for authentication; When the user selects iris quality for authentication, if S iris ≤S f When the fingerprint quality S fingerprint ≤Facial quality S facial When , the system gives priority to facial quality S facial Authentication is performed, otherwise, the system gives priority to fingerprint quality S fingerprint Conduct certification; If S iris >S f , the system gives priority to iris quality for authentication.
5. The method for intelligent identity recognition of a mobile terminal based on biometric multimodality according to claim 4, Features: The preprocessing includes mapping the identity authentication result into a high-dimensional feature space and performing standardization processing on the biometric features. The standardization processing includes calculating the original value of the fingerprint feature, the original value of the facial feature and the original value of the iris feature. The specific steps are as follows: The specific formula for calculating the original value of the fingerprint feature is: Among them, Z fingerprint Represents the original value of fingerprint feature, μ fingerprint represents the mean value of fingerprint features, σ fingerprint Indicates the standard deviation of fingerprint features; The specific calculation formula of the original value of the facial feature is: Among them, Z facial Represents the original value of facial features, μ facial represents the mean of facial features, σ facial represents the standard deviation of facial features; The calculation formula of the original value of the iris feature is: Among them, Z iris Represents the original value of iris features, μ iris represents the mean of iris features, σ iris Represents the standard deviation of iris features.
6. The method for intelligent identity recognition of a mobile terminal based on biometric multimodality according to claim 5, Features: The extracting of user information includes using a sensor to extract bifurcation points of pre-processed information and calculating similarity scores between bifurcation points. The specific calculation formula is: Where n represents the number of fingerprint feature points, P(x i ,y i ) represents the coordinates of the i-th feature point in the user information, Q(x i ,y i ) represents the coordinates of the i-th feature point in the data storage layer, ω i Represents the weight of the i-th feature point; The fusion includes combining the original values or features extracted from different biometric fingerprints, faces and irises, and the specific steps are as follows: Combining the original value of the feature extracted from the fingerprint sensor with the mean and standard deviation to obtain a comprehensive representation of the fingerprint feature; Combining the raw values of features extracted from the facial sensor with the mean and standard deviation to obtain a comprehensive representation of the facial features; The raw values of the features extracted from the iris sensor are combined with the mean and standard deviation to obtain a comprehensive representation of the iris features.
7. The method for intelligent identity recognition of a mobile terminal based on biometric multimodality according to claim 6, Features: The verification of the biometric feature includes adding the weighted sum to the similarity score Compare and determine the authentication result. If the weighted sum is greater than the similarity score, If the authentication succeeds, then the authentication fails. Extract authentication failure frequency and automate abnormal situations; The automated processing includes establishing an abnormal identification processing module to audit the system, and the audit inspection includes deploying the results of the audit inspection to an actual environment for intelligent identity recognition.
8. A mobile terminal intelligent identity recognition system based on biometric multimodality, based on the mobile terminal intelligent identity recognition method based on biometric multimodality according to any one of claims 1 to 7, Features: include, Design module, which uses sensors to extract user information, uses biometric technology to design the mobile terminal system architecture, and selects biometric features based on the system architecture; The identification module introduces a comprehensive authentication algorithm to verify the biometric features and complete the intelligent identity recognition of the mobile terminal.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. Features: When the processor executes the computer program, the steps of the mobile terminal intelligent identity recognition method based on biometric multimodality are implemented as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, Features: When the computer program is executed by a processor, the steps of the mobile terminal intelligent identity recognition method based on biometric multimodality are implemented as described in any one of claims 1 to 7.
Citation Information
Cited By
Identity verification method and system based on multi-modal data fusion
CN119442204A
Multi-biological feature integrated user identity recognition method and system
CN120068041A
A method and system for user identification integrating multiple biometric features
CN120068041B
Identity authentication method based on multi-modal features and multiple factors
CN121864331A
