User identity identification method and device based on tooth point cloud data

Abstract

The invention discloses a user identity identification method and device based on tooth point cloud data. The method comprises the following steps: acquiring a tooth point cloud data set and a user tooth standard point cloud data set; the tooth point cloud data set comprises tooth point cloud data; the user tooth standard point cloud data set comprises tooth point cloud data pre-collected by a plurality of users; preprocessing the tooth point cloud data set to obtain a preprocessed data set; performing identification processing on the preprocessed data set and the user tooth standard point cloud data set to obtain user identification information; the user identification information is used for representing user identity information corresponding to the tooth point cloud data set. According to the method, accurate extraction of the user tooth features is effectively achieved by establishing the first distance calculation model and the second distance calculation model, comprehensive analysis of the user identity features is achieved through fusion weighting processing, and the accuracy and efficiency of user identity recognition are improved.

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 of tooth point cloud 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, and it is not suitable for large-scale matching. Information such as fingerprints and faces is easily destroyed. Teeth are the hardest and most indestructible part of the human body, so they are considered the best choice for identity recognition.

[0003] How to achieve fast and accurate user identity recognition based on dental data is an urgent problem that needs 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 data, the present invention discloses a user identity recognition method and device based on tooth point cloud data.

[0005] In a first aspect of an embodiment of the present application, a method for user identification of tooth point cloud data is disclosed, comprising:

[0006] S1, obtaining a tooth point cloud data set and a user tooth standard point cloud data set; the tooth point cloud data set includes tooth point cloud data; the user tooth standard point cloud data set includes a number of user pre-collected tooth point cloud data;

[0007] S2, preprocessing the tooth point cloud dataset to obtain a preprocessed dataset;

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

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

[0010] S21, performing noise reduction processing on the tooth point cloud dataset to obtain a noise reduction dataset;

[0011] S22, performing anomaly detection processing on the denoised data set to obtain a first data set;

[0012] S23, performing point cloud registration processing on the first data set to obtain a preprocessed data set.

[0013] The performing anomaly detection processing on the denoised data set to obtain a first data set includes:

[0014] S221, for each type of data attribute of the denoised data set, using data collection information of the data as an independent variable and data values ​​of the data as a dependent variable, perform autoregression-sliding average modeling to obtain regression models of the data attributes of each type;

[0015] S222, using the regression model, calculating and processing the independent variable to obtain a regression data value; determining whether the absolute value of the difference between the regression data value and the corresponding dependent variable value 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;

[0016] S223, fusing all data of the denoised data set after executing S221 to S222 to obtain a first data set.

[0017] The identification processing of the preprocessed data set and the user's tooth standard point cloud data set to obtain user identification information includes:

[0018] S31, representing the preprocessed data set as a vector to be identified; the elements of the vector to be identified are tooth point cloud data;

[0019] S32, representing the user's tooth standard point cloud data set as a standard point cloud matrix; the row vector of the standard point cloud matrix is ​​the pre-collected tooth point cloud data of each user; the column dimension of the standard point cloud matrix is ​​the same as the dimension of the vector to be identified; the row dimension of the standard point cloud matrix is ​​the number of users;

[0020] S33, performing identification calculation processing on the vector to be identified and the standard point cloud matrix to obtain user identification information.

[0021] The step of performing identification calculation processing on the vector to be identified and the standard point cloud matrix to obtain user identification information includes:

[0022] Performing a first distance calculation process on the vector to be identified and the standard point cloud matrix to obtain a first distance vector;

[0023] Performing a second distance calculation process on the vector to be identified and the standard point cloud matrix to obtain a second distance vector;

[0024] Performing weighted fusion processing on the first distance vector and the second distance vector to obtain a difference vector;

[0025] The user serial number corresponding to the element serial number with the smallest value in the difference vector is determined as the user identification information.

[0026] The expression of the first distance calculation process is:

[0027]

[0028] Among them, a j is the jth element of the vector to be identified, A kj is the element of the kth row and jth column of the standard point cloud matrix, ξ is the preset adjustment factor, c k represents the kth element of the first distance vector, N is the dimension of the vector to be identified;

[0029] The expression of the second distance calculation process is:

[0030]

[0031] Among them, μ1 and μ2 are preset weighting coefficients, d k Represents the kth element of the second distance vector.

[0032] The calculation expression of the fusion weighted processing is:

[0033] e k =λ k c k +ν k / d k +η k | c k -d k | ,

[0034] Among them, e k is the kth element of the difference vector, λ k is the kth element of the preset first weighted vector, ν k is the kth element of the preset second weighted vector, η k is the kth element of the preset third weighted vector, and M is the row dimension of the standard point cloud matrix.

[0035] In a second aspect of the embodiment of the present application, a user identification device for tooth point cloud data is disclosed, the device comprising:

[0036] A memory storing executable program code;

[0037] a processor coupled to the memory;

[0038] The processor calls the executable program code stored in the memory to execute the user identity recognition method for tooth point cloud data.

[0039] 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 for tooth point cloud data.

[0040] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, and the information data processing terminal is used to implement the user identity recognition method of the tooth point cloud data.

[0041] The beneficial effects of the present invention are:

[0042] The method of the present invention effectively realizes the accurate extraction of user tooth features by establishing a first distance calculation model and a second distance calculation model, and realizes the comprehensive analysis of user identity features through the fusion weighted processing, thereby improving the accuracy and efficiency of user identity recognition.

[0043] The present invention realizes effective suppression of interference and noise by performing noise reduction and anomaly detection processing on the collected dental data, thereby effectively improving the accuracy of user identity recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0045] In order to better understand the content of the present invention, an embodiment is given here.

[0046] Figure 1 It is a flow chart for implementing the method of the present invention.

[0047] In a first aspect of an embodiment of the present application, a method for user identification of tooth point cloud data is disclosed, comprising:

[0048] S1, obtaining a tooth point cloud data set and a user tooth standard point cloud data set; the tooth point cloud data set includes tooth point cloud data; the user tooth standard point cloud data set includes a number of user pre-collected tooth point cloud data;

[0049] S2, preprocessing the tooth point cloud dataset to obtain a preprocessed dataset;

[0050] S3, performing recognition processing on the preprocessed data set and the user's tooth standard point cloud data set to obtain user recognition information; the user recognition information is used to represent the user identity information corresponding to the tooth point cloud data set;

[0051] The preprocessing of the tooth point cloud data set to obtain a preprocessed data set includes:

[0052] S21, performing noise reduction processing on the tooth point cloud dataset to obtain a noise reduction dataset;

[0053] S22, performing anomaly detection processing on the denoised data set to obtain a first data set;

[0054] S23, performing point cloud registration processing on the first data set to obtain a preprocessed data set;

[0055] The performing anomaly detection processing on the denoised data set to obtain a first data set includes:

[0056] S221, for each type of data attribute of the denoised data set, using data collection information of the data as an independent variable and data values ​​of the data as a dependent variable, perform autoregression-sliding average modeling to obtain regression models of the data attributes of each type;

[0057] S222, using the regression model, calculating and processing the independent variable to obtain a regression data value; determining whether the absolute value of the difference between the regression data value and the corresponding dependent variable value 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;

[0058] S223, performing fusion processing on all data of the denoised data set after executing S221 to S222 to obtain a first data set;

[0059] The identification processing of the preprocessed data set and the user's tooth standard point cloud data set to obtain user identification information includes:

[0060] S31, representing the preprocessed data set as a vector to be identified; the elements of the vector to be identified are tooth point cloud data;

[0061] S32, representing the user's tooth standard point cloud data set as a standard point cloud matrix; the row vector of the standard point cloud matrix is ​​the pre-collected tooth point cloud data of each user; the column dimension of the standard point cloud matrix is ​​the same as the dimension of the vector to be identified; the row dimension of the standard point cloud matrix is ​​the number of users;

[0062] S33, performing identification calculation processing on the vector to be identified and the standard point cloud matrix to obtain user identification information;

[0063] The step of performing identification calculation processing on the vector to be identified and the standard point cloud matrix to obtain user identification information includes:

[0064] Performing a first distance calculation process on the vector to be identified and the standard point cloud matrix to obtain a first distance vector;

[0065] Performing a second distance calculation process on the vector to be identified and the standard point cloud matrix to obtain a second distance vector;

[0066] Performing weighted fusion processing on the first distance vector and the second distance vector to obtain a difference vector;

[0067] Determine the user serial number corresponding to the element serial number with the smallest value in the difference vector as the user identification information;

[0068] The expression of the first distance calculation process is:

[0069]

[0070] Among them, a j is the jth element of the vector to be identified, A kj is the element of the kth row and jth column of the standard point cloud matrix, ξ is the preset adjustment factor, c k represents the kth element of the first distance vector, N is the dimension of the vector to be identified;

[0071] The expression of the second distance calculation process is:

[0072]

[0073] Among them, μ1 and μ2 are preset weighting coefficients, d k represents the kth element of the second distance vector. The preset weighting coefficient has a value range of [0.1, 0.5].

[0074] The calculation expression of the fusion weighted processing is:

[0075] e k =λ k c k +ν k / d k +η k | c k -d k | ,

[0076] Among them, e k is the kth element of the difference vector, λ k is the kth element of the preset first weighted vector, ν k is the kth element of the preset second weighted vector, η k is the kth element of the preset third weighted vector, and M is the row dimension of the standard point cloud matrix.

[0077] The tooth point cloud data set is obtained by scanning the user's tooth area using a 3D laser radar.

[0078] The user number corresponding to the element number with the smallest value in the difference vector is determined to obtain the user number for identifying the element number with the smallest value in the difference vector; the user number is the row number of the row vector of the standard point cloud matrix.

[0079] The data collection information includes time information, space information or capability type information corresponding to the data collection; when performing autoregression-moving average modeling, any of the above types of information can be used as an independent variable, and the corresponding data value can be used as a dependent variable.

[0080] The noise reduction process can be implemented by using the DeNoise command in MATLAB.

[0081] The point cloud registration process can be implemented by using the FastMAC algorithm or the RegFormer algorithm.

[0082] The step of fusing and weighting the first distance vector and the second distance vector to obtain a difference vector includes:

[0083] Perform logarithmic accumulation processing on the standard point cloud matrix to construct a first weighted vector;

[0084] The expression of the logarithmic accumulation process is:

[0085]

[0086] Performing standard calculation processing on the first distance vector and the second distance vector to construct a second weighted vector;

[0087] The expression of the standard calculation process is:

[0088]

[0089] Presetting a third weighting vector;

[0090] The first distance vector and the second distance vector are weighted to obtain a difference vector; the weighted processing is calculated as follows:

[0091] e k =λ k c k +ν k / d k +η k | c k -d k | ,

[0092] Among them, e k is the kth element of the difference vector, λ k is the kth element of the first weighted vector, ν k is the kth element of the second weighted vector, η k is the kth element of the preset third weighted vector, and M is the row dimension of the standard point cloud matrix.

[0093] In a second aspect of the embodiment of the present application, a user identification device for tooth point cloud data is disclosed, the device comprising:

[0094] A memory storing executable program code;

[0095] a processor coupled to the memory;

[0096] The processor calls the executable program code stored in the memory to execute the user identity recognition method for tooth point cloud data.

[0097] 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 for tooth point cloud data.

[0098] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, and the information data processing terminal is used to implement the user identity recognition method of the tooth point cloud data.

[0099] 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 method for user identification of tooth point cloud data, characterized in that: include: S1, obtaining a tooth point cloud dataset and a user tooth standard point cloud dataset; The tooth point cloud data set includes tooth point cloud data; The user tooth standard point cloud data set includes a plurality of tooth point cloud data collected in advance by the user; S2, preprocessing the tooth point cloud dataset to obtain a preprocessed dataset; S3, performing recognition processing on the preprocessed data set and the user's tooth standard point cloud data set to obtain user recognition information; The user identification information is used to represent the user identity information corresponding to the tooth point cloud data set.

2. The method for user identification of tooth point cloud data according to claim 1, characterized in that: The preprocessing of the tooth point cloud data set to obtain a preprocessed data set includes: S21, performing noise reduction processing on the tooth point cloud dataset to obtain a noise reduction dataset; S22, performing anomaly detection processing on the denoised data set to obtain a first data set; S23, performing point cloud registration processing on the first data set to obtain a preprocessed data set.

3. The method for user identification of tooth point cloud data according to claim 2, characterized in that: The performing anomaly detection processing on the denoised data set to obtain a first data set includes: S221, for each type of data attribute of the denoised data set, using data collection information of the data as an independent variable and data values ​​of the data as a dependent variable, perform autoregression-sliding average modeling to obtain regression models of the data attributes of each type; S222, using the regression model, calculating and processing the independent variable to obtain a regression data value; determining whether the absolute value of the difference between the regression data value and the corresponding dependent variable value 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; S223, fusing all data of the denoised data set after executing S221 to S222 to obtain a first data set.

4. The method for user identification of tooth point cloud data according to claim 1, characterized in that: The identification processing of the preprocessed data set and the user's tooth standard point cloud 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 point cloud data; S32, representing the user's tooth standard point cloud data set as a standard point cloud matrix; the row vector of the standard point cloud matrix is ​​the pre-collected tooth point cloud data of each user; the column dimension of the standard point cloud matrix is ​​the same as the dimension of the vector to be identified; the row dimension of the standard point cloud matrix is ​​the number of users; S33, performing identification calculation processing on the vector to be identified and the standard point cloud matrix to obtain user identification information.

5. The method for user identification of tooth point cloud data according to claim 4, characterized in that: The step of performing identification calculation processing on the vector to be identified and the standard point cloud matrix to obtain user identification information includes: Performing a first distance calculation process on the vector to be identified and the standard point cloud matrix to obtain a first distance vector; Performing a second distance calculation process on the vector to be identified and the standard point cloud matrix to obtain a second distance vector; Performing weighted fusion processing on the first distance vector and the second distance vector to obtain a difference vector; The user serial number corresponding to the element serial number with the smallest value in the difference vector is determined as the user identification information.

6. The method for user identification of tooth point cloud data according to claim 5, characterized in that: The expression of the first distance calculation process is: Among them, a j is the jth element of the vector to be identified, A kj is the element of the kth row and jth column of the standard point cloud matrix, ξ is the preset adjustment factor, c k represents the kth element of the first distance vector, N is the dimension of the vector to be identified; The expression of the second distance calculation process is: Among them, μ1 and μ2 are preset weighting coefficients, d k Represents the kth element of the second distance vector.

7. The method for user identification of tooth point cloud data according to claim 5, characterized in that: The calculation expression of the fusion weighted processing is: e k =λ k c k +n k / d k +n k | c k -d k | , Among them, e k is the kth element of the difference vector, λ k is the kth element of the preset first weighted vector, ν k is the kth element of the preset second weighted vector, η k is the kth element of the preset third weighted vector, and M is the row dimension of the standard point cloud matrix.

8. A user identification device for tooth point cloud 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 identification method for tooth point cloud 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 for tooth point cloud 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 for tooth point cloud data according to any one of claims 1 to 7.

Images