A method and device for user identification based on dental scan data

Abstract

This invention discloses a user identification method and apparatus based on dental scan data. The method includes: acquiring a dental scan dataset and a user dental standard dataset; the dental scan dataset includes dental scan data; the user dental standard dataset includes dental scan data pre-collected from several users; preprocessing the dental scan dataset to obtain a preprocessed dataset; performing identification processing on the preprocessed dataset and the user dental standard dataset to obtain user identification information; the user identification information is used to represent the user identity information corresponding to the dental scan dataset. This invention achieves fast and accurate user identification based on dental scan image data.

Description

Technical Field

[0001] This invention relates to the fields of identity recognition and medical information processing, and in particular to a method and apparatus for user identity recognition based on dental scan data. Background Technology

[0002] Currently, the main methods for user identification include DNA recognition, fingerprint recognition, and facial recognition. While DNA recognition is highly accurate, its implementation is complex and time-consuming, making it unsuitable for situations requiring rapid identification. Furthermore, fingerprints and facial information are easily compromised in demanding environments. Teeth are the hardest and most indestructible part of the human body; therefore, finding a fast and accurate method for identification based on teeth is a pressing issue that needs to be addressed.

[0003] In the past decade or so, oral imaging has developed rapidly, with digital imaging technology playing a crucial role in the diagnosis and treatment of periodontal disease and peri-implant diseases. With the aid of computer imaging technologies, such as X-rays, computed tomography (CT) scans, and laser scans, three-dimensional images of teeth can be acquired. How to achieve rapid and accurate user identification based on these three-dimensional dental images is a pressing issue that needs to be addressed. Summary of the Invention

[0004] To address the problem of how to achieve fast and accurate user identification based on dental scan image data, this invention discloses a user identification method and apparatus based on dental scan data.

[0005] In a first aspect, this application discloses a user identification method based on dental scan data, comprising:

[0006] S1, acquire a dental scan dataset and a user dental standard dataset; the dental scan dataset includes dental scan data; the user dental standard dataset includes dental scan data pre-collected from several users;

[0007] S2, preprocess the tooth scan dataset to obtain a preprocessed dataset;

[0008] S3, perform identification processing on the preprocessed dataset and the user's standard dental dataset to obtain user identification information; the user identification information is used to represent the user identity information corresponding to the dental scan dataset.

[0009] The preprocessing of the tooth scan dataset to obtain a preprocessed dataset includes:

[0010] S21, Denoise the dental scan dataset to obtain a denoised dataset;

[0011] S22, the noise reduction dataset is processed to obtain a preprocessed dataset.

[0012] The step of performing detection processing on the noise-reduced dataset to obtain a preprocessed dataset includes:

[0013] S221, for each type of data attribute in the noise reduction dataset, the data acquisition information of the data is used as the known independent variable and the data value of the data is used as the known dependent variable. The curve to be approximated is constructed using the known independent variable and the known dependent variable.

[0014] S222, The curve to be approximated is fitted using the function approximation method to obtain the best uniform approximation polynomial of the class data attribute;

[0015] S223, Using the best uniform approximation polynomial, the known independent variable is calculated to obtain an approximate dependent variable;

[0016] S224, determine whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the noise reduction dataset; if it is less than or equal to the first regression discrimination threshold, do not process the data.

[0017] S225, perform fusion processing on all data in the noise reduction dataset after performing S221 to S224 to obtain a preprocessed dataset.

[0018] The process of identifying the preprocessed dataset and the user's standard dental dataset to obtain user identification information includes:

[0019] S31, the preprocessed dataset is represented as a vector to be identified; the elements of the vector to be identified are dental scan data;

[0020] S32, the user's standard dental dataset is represented as a standard data matrix; the row vector of the standard data matrix is ​​the pre-collected dental scan data for each user; the column dimension of the standard data matrix is ​​the same as the dimension of the vector to be identified; the row dimension of the standard data matrix is ​​the number of users.

[0021] S33, perform difference calculation processing on the vector to be identified and the standard data matrix to obtain the first set of difference vectors;

[0022] S34, perform weight calculation processing on the vector to be identified and the standard data matrix to obtain the weight calculation vector;

[0023] S35, the first set of difference vectors is weighted using the weight calculation vector to obtain the recognition vector;

[0024] S36, determine the index of the smallest element of the identification vector, which is the identified user index; determine the identified user index as user identification information.

[0025] The difference calculation process includes:

[0026] Perform cross-correlation operation on each row vector of the vector to be identified and the standard data matrix to obtain the corresponding cross-correlation sequence;

[0027] Each cross-correlation sequence is subjected to time-frequency transformation to obtain the corresponding time-frequency sequence;

[0028] The time-frequency sequence is processed by distribution calculation to obtain the distribution sequence;

[0029] Logarithmic summation is performed on all distribution sequences to obtain a first set of difference vectors; the first set of difference vectors includes the first difference vector.

[0030] The expression for the distributed computation processing is:

[0031]

[0032] Where, p ki Let z represent the value of the i-th element in the k-th distribution sequence. ki This represents the i-th value of the k-th time-frequency sequence, where n is the total number of elements in the time-frequency sequence.

[0033] The expression for the logarithmic accumulation process is:

[0034] h ki =|p ki log2p ki |,

[0035] Among them, h k It is the i-th element of the k-th first difference vector.

[0036] The step of performing weight calculation processing on the vector to be identified and the standard data matrix to obtain a weight calculation vector includes:

[0037] Perform column optimization processing on the standard data matrix to obtain the optimal solution vector;

[0038] The optimal processing of the columns involves extracting the largest number from each column to form the optimal solution vector z. + The expression for the optimal solution vector is:

[0039]

[0040] Where m represents the row dimension of the standard data matrix;

[0041] Perform column worst-case processing on the standard data matrix to obtain the worst-case solution vector;

[0042] The worst-case scenario processing described above involves extracting the smallest number from each column to form the worst-case solution vector z. - The expression for the worst-case solution vector is:

[0043]

[0044] The worst-case solution vector and the best-case solution vector are subjected to feature calculation processing to obtain the weight calculation vector; the expression for the feature calculation processing is:

[0045]

[0046] In the formula, ω j ω is the preset importance weight for the j-th element; j s is obtained either through pre-setting or by calculating the variance of each column of a standard data matrix. j This represents the j-th element of the weight calculation vector.

[0047] A second aspect of this application discloses a user identification device based on dental scan data, the device comprising:

[0048] Memory containing executable program code;

[0049] A processor coupled to the memory;

[0050] The processor calls the executable program code stored in the memory to execute the user identification method based on dental scan data.

[0051] A third aspect of this application discloses a computer-storable medium storing computer instructions, which, when invoked, are used to execute the user identification method based on dental scan data.

[0052] In a fourth aspect of this application, an information data processing terminal is disclosed, which is used to implement the user identification method based on dental scan data.

[0053] The beneficial effects of this invention are as follows:

[0054] This invention represents the preprocessed dataset as a vector to be identified and the user's standard tooth dataset as a standard data matrix. Specifically, it constructs methods for difference calculation and weight calculation based on data features. The difference calculation method can accurately extract and retain differential features; the weight calculation method amplifies important differential features. Furthermore, the above difference calculation, weight calculation, and weighted calculation processes can be implemented in real time, facilitating the integration of this method into application software in embedded systems or PC systems, enabling rapid and accurate user identification.

[0055] In summary, the method of the present invention enables rapid and accurate identification of user identity based on dental scan data. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating the implementation of the method of the present invention. Detailed Implementation

[0057] To better understand the content of this invention, an embodiment is provided here.

[0058] Figure 1 This is a flowchart illustrating the implementation of the method of the present invention.

[0059] In a first aspect, this application discloses a user identification method based on dental scan data, comprising:

[0060] S1, acquire a dental scan dataset and a user dental standard dataset; the dental scan dataset includes dental scan data; the user dental standard dataset includes dental scan data pre-collected from several users;

[0061] S2, preprocess the tooth scan dataset to obtain a preprocessed dataset;

[0062] S3, perform identification processing on the preprocessed dataset and the user's standard dental dataset to obtain user identification information; the user identification information is used to represent the user's identity information corresponding to the dental scan dataset;

[0063] The preprocessing of the tooth scan dataset to obtain a preprocessed dataset includes:

[0064] S21, Denoise the dental scan dataset to obtain a denoised dataset;

[0065] S22, Perform detection processing on the noise reduction dataset to obtain a preprocessed dataset;

[0066] The step of performing detection processing on the noise-reduced dataset to obtain a preprocessed dataset includes:

[0067] S221, for each type of data attribute in the noise reduction dataset, the data acquisition information of the data is used as the known independent variable and the data value of the data is used as the known dependent variable. The curve to be approximated is constructed using the known independent variable and the known dependent variable.

[0068] S222, The curve to be approximated is fitted using the function approximation method to obtain the best uniform approximation polynomial of the class data attribute;

[0069] S223, Using the best uniform approximation polynomial, the known independent variable is calculated to obtain an approximate dependent variable;

[0070] S224, determine whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the noise reduction dataset; if it is less than or equal to the first regression discrimination threshold, do not process the data.

[0071] S225, perform fusion processing on all data in the noise reduction dataset after executing S221 to S224 to obtain a preprocessed dataset;

[0072] The process of identifying the preprocessed dataset and the user's standard dental dataset to obtain user identification information includes:

[0073] S31, the preprocessed dataset is represented as a vector to be identified; the elements of the vector to be identified are dental scan data;

[0074] S32, the user's standard dental dataset is represented as a standard data matrix; the row vector of the standard data matrix is ​​the pre-collected dental scan data for each user; the column dimension of the standard data matrix is ​​the same as the dimension of the vector to be identified; the row dimension of the standard data matrix is ​​the number of users.

[0075] S33, perform difference calculation processing on the vector to be identified and the standard data matrix to obtain the first set of difference vectors;

[0076] S34, perform weight calculation processing on the vector to be identified and the standard data matrix to obtain the weight calculation vector;

[0077] S35, the first set of difference vectors is weighted using the weight calculation vector to obtain the recognition vector;

[0078] S36, determine the index of the smallest element of the identification vector, which is the identified user index; determine the identified user index as user identification information;

[0079] The difference calculation process includes:

[0080] Perform cross-correlation operation on each row vector of the vector to be identified and the standard data matrix to obtain the corresponding cross-correlation sequence;

[0081] Each cross-correlation sequence is subjected to time-frequency transformation to obtain the corresponding time-frequency sequence;

[0082] The time-frequency sequence is processed by distribution calculation to obtain the distribution sequence;

[0083] Logarithmic summation is performed on all distribution sequences to obtain a first set of difference vectors; the first set of difference vectors includes the first difference vector.

[0084] The expression for the distributed computation processing is:

[0085]

[0086] Where, p ki Let z represent the value of the i-th element in the k-th distribution sequence. ki This represents the i-th value of the k-th time-frequency sequence, where n is the total number of elements in the time-frequency sequence.

[0087] The expression for the logarithmic accumulation process is:

[0088] h ki =|p ki log2p ki |,

[0089] Among them, h k It is the i-th element of the k-th first difference vector.

[0090] The step of performing weight calculation processing on the vector to be identified and the standard data matrix to obtain a weight calculation vector includes:

[0091] Perform column optimization processing on the standard data matrix to obtain the optimal solution vector;

[0092] The optimal processing of the columns involves extracting the largest number from each column to form the optimal solution vector z. + The expression for the optimal solution vector is:

[0093]

[0094] Where m represents the row dimension of the standard data matrix;

[0095] Perform column worst-case processing on the standard data matrix to obtain the worst-case solution vector;

[0096] The worst-case scenario processing described above involves extracting the smallest number from each column to form the worst-case solution vector z. -The expression for the worst-case solution vector is:

[0097]

[0098] The worst-case solution vector and the best-case solution vector are subjected to feature calculation processing to obtain the weight calculation vector; the expression for the feature calculation processing is:

[0099]

[0100] In the formula, ωj is the preset importance weight of the j-th element; ωj is obtained by presetting or by calculating the variance of each column of the standard data matrix, s j This represents the i-th element of the weight calculation vector.

[0101] The weighted calculation of the first set of difference vectors using the weighted calculation vector is expressed as follows:

[0102]

[0103] Among them, e i Let i be the i-th element of the identification vector.

[0104] The time-frequency transformation process can be implemented using Gabor transform, wavelet transform, etc.

[0105] The preset importance weight has a value range of [0.01, 0.2].

[0106] The noise reduction process can be implemented using the DeNoise command in MATLAB.

[0107] The acquisition of the tooth scan dataset can be achieved using X-rays, computed tomography (CT) scans, and laser scans.

[0108] The curve fitting of the curve to be approximated using the function approximation method can employ the best uniform linear approximation method. The best uniform approximation polynomial f(Ix) is expressed as:

[0109] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0110] Where P1 is the order of the best uniform approximation polynomial f(Ix), α0, α1, α2, ..., α P1 The coefficients of the best uniform approximation polynomial f(Ix);

[0111] The data acquisition information includes the time information and spatial information corresponding to the data acquisition; when performing data fitting, any of the above types of information can be used as the independent variable and the corresponding data value as the dependent variable.

[0112] A second aspect of this application discloses a user identification device based on dental scan data, the device comprising:

[0113] Memory containing executable program code;

[0114] A processor coupled to the memory;

[0115] The processor calls the executable program code stored in the memory to execute the user identification method based on dental scan data.

[0116] A third aspect of this application discloses a computer-storable medium storing computer instructions, which, when invoked, are used to execute the user identification method based on dental scan data.

[0117] In a fourth aspect of this application, an information data processing terminal is disclosed, which is used to implement the user identification method based on dental scan data.

[0118] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A user identification method based on dental scan data, characterized in that, include: S1, Obtain the dental scan dataset and the user's standard dental dataset; The dental scan dataset includes dental scan data; The user dental standard dataset includes dental scan data pre-collected from several users; S2, preprocess the tooth scan dataset to obtain a preprocessed dataset; S3 performs recognition processing on the preprocessed dataset and the user's standard tooth dataset to obtain user identification information; The user identification information is used to represent the user identity information corresponding to the dental scan dataset; The process of identifying the preprocessed dataset and the user's standard dental dataset to obtain user identification information includes: S31, the preprocessed dataset is represented as a vector to be identified; the elements of the vector to be identified are dental scan data; S32, the user's standard dental dataset is represented as a standard data matrix; the row vector of the standard data matrix is ​​the pre-collected dental scan data for each user; the column dimension of the standard data matrix is ​​the same as the dimension of the vector to be identified; the row dimension of the standard data matrix is ​​the number of users. S33, perform difference calculation processing on the vector to be identified and the standard data matrix to obtain the first set of difference vectors; S34, perform weight calculation processing on the vector to be identified and the standard data matrix to obtain the weight calculation vector; S35, the first set of difference vectors is weighted using the weight calculation vector to obtain the recognition vector; S36, determine the index of the smallest element of the identification vector, which is the identified user index; determine the identified user index as user identification information; The difference calculation process includes: Perform cross-correlation operation on each row vector of the vector to be identified and the standard data matrix to obtain the corresponding cross-correlation sequence; Each cross-correlation sequence is subjected to time-frequency transformation to obtain the corresponding time-frequency sequence; The time-frequency sequence is processed by distribution calculation to obtain the distribution sequence; Logarithmic summation is performed on all distribution sequences to obtain a first set of difference vectors; the first set of difference vectors includes the first difference vector. The expression for the distributed computation processing is: Where, p ki Let z represent the value of the i-th element in the k-th distribution sequence. ki This represents the i-th value of the k-th time-frequency sequence, where n is the total number of elements in the time-frequency sequence. The expression for the logarithmic accumulation process is: h ki =|p ki log2p ki |, Among them, h ki It is the i-th element of the k-th first difference vector.

2. The user identification method based on dental scan data as described in claim 1, characterized in that, The preprocessing of the tooth scan dataset to obtain a preprocessed dataset includes: S21, Denoise the dental scan dataset to obtain a denoised dataset; S22, the noise reduction dataset is processed to obtain a preprocessed dataset.

3. The user identification method based on dental scan data as described in claim 2, characterized in that, The step of performing detection processing on the noise-reduced dataset to obtain a preprocessed dataset includes: S221, for each type of data attribute in the noise reduction dataset, the data acquisition information of the data is used as the known independent variable and the data value of the data is used as the known dependent variable. The curve to be approximated is constructed using the known independent variable and the known dependent variable. S222, The curve to be approximated is fitted using the function approximation method to obtain the best uniform approximation polynomial of the class data attribute; S223, Using the best uniform approximation polynomial, the known independent variable is calculated to obtain an approximate dependent variable; S224, determine whether the absolute value of the difference between the approximate dependent variable and the corresponding known dependent variable is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the noise reduction dataset; if it is less than or equal to the first regression discrimination threshold, do not process the data. S225, perform fusion processing on all data in the noise reduction dataset after performing S221 to S224 to obtain a preprocessed dataset.

4. The user identification method based on dental scan data as described in claim 1, characterized in that, The step of performing weight calculation processing on the vector to be identified and the standard data matrix to obtain a weight calculation vector includes: Perform column optimization processing on the standard data matrix to obtain the optimal solution vector; The optimal processing of the columns involves extracting the largest number from each column to form the optimal solution vector z. + The expression for the optimal solution vector is: Where m represents the row dimension of the standard data matrix; Perform column worst-case processing on the standard data matrix to obtain the worst-case solution vector; The worst-case scenario processing described above involves extracting the smallest number from each column to form the worst-case solution vector z. - The expression for the worst-case solution vector is: The worst-case solution vector and the best-case solution vector are subjected to feature calculation processing to obtain the weight calculation vector; the expression for the feature calculation processing is: In the formula, ω j ω is the preset importance weight for the j-th element; j s is obtained either through pre-setting or by calculating the variance of each column of a standard data matrix. j This represents the j-th element of the weight calculation vector.

5. A user identification device based on dental scan data, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the user identification method based on dental scan data as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked, are used to execute the user identification method based on dental scan data as described in any one of claims 1 to 4.

7. An information data processing terminal, characterized in that, The information data processing terminal is used to implement the user identification method based on dental scan data as described in any one of claims 1 to 4.

Images