User identity identification method and device based on tooth scanning data

Abstract

The invention discloses a user identity identification method and device based on tooth scanning data. The method comprises the following steps: acquiring a tooth scanning data set and a user tooth standard data set; the tooth scanning data set comprises tooth scanning data; the user tooth standard data set comprises tooth scanning data pre-collected by a plurality of users; preprocessing the tooth scanning data set to obtain a preprocessed data set; performing identification processing on the preprocessed data set and the user tooth standard data set to obtain user identification information; the user identification information is used for representing user identity information corresponding to the tooth scanning data set. According to the invention, based on the tooth scanning image data, rapid and accurate user identity identification is realized.

Description

Technical Field

[0001] The present invention relates to the fields of identity recognition and medical information processing, and in particular to a method and device for user identity recognition based on dental scanning data. Background Art

[0002] At present, the main methods for identifying user identities include DNA recognition, fingerprint recognition, and face recognition. Although the DNA recognition method has high accuracy, the technical implementation process is cumbersome and time-consuming. In some occasions that require rapid identity recognition, the DNA method cannot be used. In some scenes with harsh objective conditions, information such as fingerprints and faces are easily destroyed. Teeth are the hardest and most indestructible part of the human body. How to perform rapid and accurate identity recognition based on teeth is an urgent problem that needs to be solved.

[0003] In the past decade, oral imaging has developed rapidly, and digital imaging technology plays an important role in the diagnosis and treatment of periodontal disease and peri-implant diseases. With the help of computer imaging technology, such as X-ray, computed tomography (CT), and laser scanning, three-dimensional image data of teeth can be obtained. How to achieve fast and accurate user identity recognition based on three-dimensional image data of teeth is an urgent problem to be solved. Summary of the invention

[0004] In order to solve the problem of how to realize fast and accurate user identity recognition based on tooth scanning image data, the present invention discloses a user identity recognition method and device based on tooth scanning data.

[0005] In a first aspect of an embodiment of the present application, a method for identifying a user based on dental scan data is disclosed, comprising:

[0006] S1, obtaining a tooth scanning data set and a user tooth standard data set; the tooth scanning data set includes tooth scanning data; the user tooth standard data set includes tooth scanning data collected in advance by several users;

[0007] S2, preprocessing the tooth scan data set to obtain a preprocessed data set;

[0008] S3, performing recognition processing on the preprocessed data set and the user's tooth standard data set to obtain user recognition information; the user recognition information is used to represent the user identity information corresponding to the tooth scanning data set.

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

[0010] S21, performing noise reduction processing on the tooth scan data set to obtain a noise reduction data set;

[0011] S22, performing detection processing on the denoised data set to obtain a preprocessed data set.

[0012] The detecting and processing the noise reduction data set to obtain a preprocessed data set includes:

[0013] S221, for each type of data attribute of the denoised data set, using data collection information of the data as a known independent variable and data values ​​of the data as a known dependent variable, constructing a curve to be approximated using the known independent variables and the known dependent variables;

[0014] S222, performing curve fitting on the curve to be approximated by using a function approximation method to obtain an optimal consistent approximation polynomial for the class data attribute;

[0015] S223, using the best consistent approximation polynomial, calculating and processing the known independent variable to obtain an approximate dependent variable;

[0016] S224, determining 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, deleting the data from the denoised data set; if it is less than or equal to the first regression discrimination threshold, not processing the data;

[0017] S225, performing fusion processing on all data of the denoised data set after executing S221 to S224 to obtain a preprocessed data set.

[0018] The identification processing of the preprocessed data set and the user's tooth standard data set to obtain user identification information includes:

[0019] S31, representing the preprocessed data set as a vector to be identified; the elements of the vector to be identified are tooth scanning data;

[0020] S32, representing the user's dental standard data set as a standard data matrix; the row vector of the standard data matrix is ​​the pre-collected dental scan data of 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, performing difference calculation processing on the vector to be identified and the standard data matrix to obtain a first difference vector set;

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

[0023] S35, performing weighted calculation processing on the first difference vector set using the weight calculation vector to obtain a recognition vector;

[0024] S36, determining the serial number of the minimum element of the identification vector as the identified user serial number; determining the identified user serial number as user identification information.

[0025] The difference calculation process includes:

[0026] Performing cross-correlation operations on the vector to be identified and each row vector of the standard data matrix to obtain corresponding cross-correlation sequences;

[0027] Perform time-frequency transformation on each cross-correlation sequence to obtain the corresponding time-frequency sequence;

[0028] Perform distribution calculation on the time-frequency series to obtain a distribution sequence;

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

[0030] The expression of the distribution calculation process is:

[0031]

[0032] Among them, p ki represents the value of the ith element of the kth distribution sequence, z ki represents the i-th value of the k-th time-frequency sequence, and n is the total number of elements contained in the time-frequency sequence;

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

[0034] h ki =|p ki log 2 p ki |,

[0035] Among them, h k 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] Performing column optimization processing on the standard data matrix to obtain an optimal solution vector;

[0038] The column optimal processing is to take out the largest number in each column to form the optimal solution vector z + ; The expression of the optimal solution vector is:

[0039]

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

[0041] Performing column worst processing on the standard data matrix to obtain a worst solution vector;

[0042] The worst column processing is to take out the smallest number in each column to form the worst solution vector z - ; The expression of the worst solution vector is:

[0043]

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

[0045]

[0046] In the formula, ω j is the preset j-th importance weight; ω j It is obtained by presetting or by calculating the variance of each column of the standard data matrix, s j Represents the j-th element of the weight calculation vector.

[0047] In a second aspect of the embodiment of the present application, a user identity recognition device based on tooth scanning data is disclosed, the device comprising:

[0048] A memory storing 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 identity recognition method based on dental scanning data.

[0051] In a third aspect of the embodiments of the present application, a computer storable medium is disclosed, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the user identity recognition method based on dental scan data.

[0052] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, wherein the information data processing terminal is used to implement the user identity recognition method based on dental scanning data.

[0053] The beneficial effects of the present invention are:

[0054] The present invention represents the preprocessed data set as a vector to be identified, and represents the user's dental standard data set as a standard data matrix. According to the data features, a difference calculation and weight calculation method are specially constructed; the difference calculation method can realize the accurate extraction and retention of the difference features; the weight calculated by the weight calculation method can realize the amplification of important difference features. At the same time, the above-mentioned difference calculation, weight calculation and weighted calculation process can be realized in real time, which is convenient for the method to be integrated in the embedded system or the application software of the PC system to realize the rapid and accurate identification of the user's identity.

[0055] In summary, the method of the present invention realizes rapid and accurate identification of user identity based on dental scanning data. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0057] In order to better understand the content of the present invention, an embodiment is given here.

[0058] Figure 1 It is a flow chart for implementing the method of the present invention.

[0059] In a first aspect of an embodiment of the present application, a method for identifying a user based on dental scan data is disclosed, comprising:

[0060] S1, obtaining a tooth scanning data set and a user tooth standard data set; the tooth scanning data set includes tooth scanning data; the user tooth standard data set includes tooth scanning data collected in advance by several users;

[0061] S2, preprocessing the tooth scan data set to obtain a preprocessed data set;

[0062] S3, performing recognition processing on the preprocessed data set and the user's tooth standard data set to obtain user recognition information; the user recognition information is used to represent the user identity information corresponding to the tooth scan data set;

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

[0064] S21, performing noise reduction processing on the tooth scan data set to obtain a noise reduction data set;

[0065] S22, performing detection processing on the denoised data set to obtain a preprocessed data set;

[0066] The detecting and processing the noise reduction data set to obtain a preprocessed data set includes:

[0067] S221, for each type of data attribute of the denoised data set, using data collection information of the data as a known independent variable and data values ​​of the data as a known dependent variable, constructing a curve to be approximated using the known independent variables and the known dependent variables;

[0068] S222, performing curve fitting on the curve to be approximated by using a function approximation method to obtain an optimal consistent approximation polynomial for the class data attribute;

[0069] S223, using the best consistent approximation polynomial, calculating and processing the known independent variable to obtain an approximate dependent variable;

[0070] S224, determining 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, deleting the data from the denoised data set; if it is less than or equal to the first regression discrimination threshold, not processing the data;

[0071] S225, performing fusion processing on all data of the denoised data set after executing S221 to S224 to obtain a preprocessed data set;

[0072] The identification processing of the preprocessed data set and the user's tooth standard data set to obtain user identification information includes:

[0073] S31, representing the preprocessed data set as a vector to be identified; the elements of the vector to be identified are tooth scanning data;

[0074] S32, representing the user's dental standard data set as a standard data matrix; the row vector of the standard data matrix is ​​the pre-collected dental scan data of 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, performing difference calculation processing on the vector to be identified and the standard data matrix to obtain a first difference vector set;

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

[0077] S35, performing weighted calculation processing on the first difference vector set using the weight calculation vector to obtain a recognition vector;

[0078] S36, determining the serial number of the smallest element of the identification vector as the identified user serial number; determining the identified user serial number as user identification information;

[0079] The difference calculation process includes:

[0080] Performing cross-correlation operations on the vector to be identified and each row vector of the standard data matrix to obtain corresponding cross-correlation sequences;

[0081] Perform time-frequency transformation on each cross-correlation sequence to obtain the corresponding time-frequency sequence;

[0082] Perform distribution calculation on the time-frequency series to obtain a distribution sequence;

[0083] Performing logarithmic accumulation processing on all distribution sequences to obtain a first difference vector set; the first difference vector set includes the first difference vector;

[0084] The expression of the distribution calculation process is:

[0085]

[0086] Among them, p ki represents the value of the ith element of the kth distribution sequence, z ki represents the i-th value of the k-th time-frequency sequence, and n is the total number of elements contained in the time-frequency sequence;

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

[0088] h ki =|p ki log 2 p ki |,

[0089] Among them, h k 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] Performing column optimization processing on the standard data matrix to obtain an optimal solution vector;

[0092] The column optimal processing is to take out the largest number in each column to form the optimal solution vector z + ; The expression of the optimal solution vector is:

[0093]

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

[0095] Performing column worst processing on the standard data matrix to obtain a worst solution vector;

[0096] The worst column processing is to take out the smallest number in each column to form the worst solution vector z- ; The expression of the worst solution vector is:

[0097]

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

[0099]

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

[0101] The weighted calculation process of the first difference vector set is performed by using the weight calculation vector, and its expression is:

[0102]

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

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

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

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

[0107] The acquisition of the dental scan data set may be achieved by using x-rays, computer tomography (CT), laser scanning, and the like.

[0108] The curve fitting of the curve to be approximated by the function approximation method may be performed by using the best consistent linear approximation method. The best consistent approximation polynomial f(Ix) is expressed as:

[0109] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α 2 (Ix) 2 +α 1 (Ix)+α 0 ,

[0110] Where P1 is the order of the best consistent approximation polynomial f(Ix), α0, α1, α2, …, α P1are the coefficients of the optimal consistent approximation polynomial f(Ix);

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

[0112] In a second aspect of the embodiment of the present application, a user identity recognition device based on tooth scanning data is disclosed, the device comprising:

[0113] A memory storing 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 identity recognition method based on dental scanning data.

[0116] In a third aspect of the embodiments of the present application, a computer storable medium is disclosed, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the user identity recognition method based on dental scan data.

[0117] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, wherein the information data processing terminal is used to implement the user identity recognition method based on dental scanning data.

[0118] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A user identification method based on dental scanning data, characterized in that: include: S1, obtain a tooth scan dataset and a user tooth standard dataset; The dental scan data set comprises dental scan data; The user tooth standard data set includes a plurality of user tooth scan data collected in advance; S2, preprocessing the tooth scan data set to obtain a preprocessed data set; S3, performing recognition processing on the preprocessed data set and the user's tooth standard data set to obtain user recognition information; The user identification information is used to indicate the user identity information corresponding to the dental scan data set.

2. The user identification method based on dental scanning data according to claim 1, characterized in that: The preprocessing of the tooth scan data set to obtain a preprocessed data set includes: S21, performing noise reduction processing on the tooth scan data set to obtain a noise reduction data set; S22, performing detection processing on the denoised data set to obtain a preprocessed data set.

3. The user identification method based on dental scanning data according to claim 2, characterized in that: The detecting and processing the noise reduction data set to obtain a preprocessed data set includes: S221, for each type of data attribute of the denoised data set, using data collection information of the data as a known independent variable and data values ​​of the data as a known dependent variable, constructing a curve to be approximated using the known independent variables and the known dependent variables; S222, performing curve fitting on the curve to be approximated by using a function approximation method to obtain an optimal consistent approximation polynomial for the class data attribute; S223, using the best consistent approximation polynomial, calculating and processing the known independent variable to obtain an approximate dependent variable; S224, determining 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, deleting the data from the denoised data set; if it is less than or equal to the first regression discrimination threshold, not processing the data; S225, performing fusion processing on all data of the denoised data set after executing S221 to S224 to obtain a preprocessed data set.

4. The user identification method based on dental scanning data according to claim 2, characterized in that: The identification processing of the preprocessed data set and the user's tooth standard data set to obtain user identification information includes: S31, representing the preprocessed data set as a vector to be identified; the elements of the vector to be identified are tooth scanning data; S32, representing the user's dental standard data set as a standard data matrix; the row vector of the standard data matrix is ​​the pre-collected dental scan data of 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, performing difference calculation processing on the vector to be identified and the standard data matrix to obtain a first difference vector set; S34, performing weight calculation processing on the vector to be identified and the standard data matrix to obtain a weight calculation vector; S35, performing weighted calculation processing on the first difference vector set using the weight calculation vector to obtain a recognition vector; S36, determining the serial number of the minimum element of the identification vector as the identified user serial number; determining the identified user serial number as user identification information.

5. The user identification method based on dental scanning data according to claim 4, characterized in that: The difference calculation process includes: Performing cross-correlation operations on the vector to be identified and each row vector of the standard data matrix to obtain corresponding cross-correlation sequences; Perform time-frequency transformation on each cross-correlation sequence to obtain the corresponding time-frequency sequence; Perform distribution calculation on the time-frequency series to obtain a distribution sequence; Logarithmic accumulation processing is performed on all distribution sequences to obtain a first difference vector set; the first difference vector set includes the first difference vector.

6. The user identification method based on dental scanning data according to claim 5, characterized in that: The expression of the distribution calculation process is: Among them, p ki represents the value of the ith element of the kth distribution sequence, z ki represents the i-th value of the k-th time-frequency sequence, and n is the total number of elements contained in the time-frequency sequence; The expression of the logarithmic accumulation process is: h ki =|p ki log2 p ki |, Among them, h k is the i-th element of the k-th first difference vector.

7. The user identification method based on dental scanning data according to claim 5, 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: Performing column optimization processing on the standard data matrix to obtain an optimal solution vector; The column optimal processing is to take out the largest number in each column to form the optimal solution vector z + ; The expression of the optimal solution vector is: Where m represents the row dimension of the standard data matrix; Performing column worst processing on the standard data matrix to obtain a worst solution vector; The worst column processing is to take out the smallest number in each column to form the worst solution vector z - ; The expression of the worst solution vector is: The worst solution vector and the best solution vector are subjected to feature calculation processing to obtain a weight calculation vector; the expression of the feature calculation processing is: Where ωj is the preset jth importance weight; ωj is obtained by presetting or by calculating the variance of each column of the standard data matrix, s j Represents the j-th element of the weight calculation vector.

8. A user identification device based on dental scanning data, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the user identity recognition method based on dental scan data according to any one of claims 1 to 7.

9. A computer storable medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the user identity recognition method based on dental scanning data according to any one of claims 1 to 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the user identity recognition method based on dental scanning data as described in any one of claims 1 to 7.

Images