TWI822646B - Identity verification device and method based on dynamic lip image - Google Patents

Abstract

An identity verification device based on dynamic images includes a video recorder, a database and a processor. The video recorder is configured to capture a first lips dynamic image including a first voice message according to a control command, wherein the first voice message is related to a set of personal information to be verified. The database is configured to store a second lips dynamic image including a second voice message and a set of preset information. The process is connected to the video recorder and the database. The processor is configured to generate the control command according to a request command, and the processor further determines whether a similarity between the first lips dynamic image and the second lips dynamic image is greater than a threshold. The processor generates a successful verification message when the similarity is greater than the threshold.

Description

Identity verification device and method based on lip dynamic image

The present invention relates to an identity verification device and method, particularly an identity verification device and method using lip dynamic images and voice analysis.

With the vigorous development of biometric recognition technology, many industries (such as banking transactions) now often use fingerprint recognition or facial recognition as the basis for customer identification. For the former, only newer devices support the fingerprint recognition function, and older devices cannot provide the fingerprint recognition function. For the latter, there is not much difference between different individuals, and the same individual may not be accurately identified due to changes in external appearance.

For certain industries that focus on customer identity verification, if there are errors in financial transactions due to flaws in customer identity recognition, such as customer identity theft, it may not only cause customers to suffer monetary losses, but also affect the goodwill of the company. Therefore, in this type of industry, there is a need for a user's identity recognition device whose recognition method can take into account both accuracy and convenience, so that users can safely and efficiently perform transactions or business.

In view of this, the present invention proposes an identity verification device and method based on dynamic images. Through voice recognition and lip dynamic image analysis, the user's identity is confirmed in a double authentication method. This can greatly improve the accuracy of user identity recognition and user usage. convenience.

According to an embodiment of the present invention, an identity verification device based on dynamic images is disclosed, which includes a video recorder, a database and a computing unit. The video recorder is used to capture the first lip dynamic image including the first voice message according to the control instruction, wherein the first voice message is associated with the personal information to be verified. The database is used to store the second lip dynamic image including the second voice message and the default personal information. The operator is connected to the video recorder and the database. The operator is used to generate control instructions according to a request instruction, and the operator determines whether the information to be verified matches the preset information. When the personal information to be verified matches the preset personal information, the operator further determines whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold, and generates a verification success message when the similarity is greater than the verification threshold.

According to an embodiment of the present invention, an identity verification method based on dynamic images is disclosed, which includes using a computer to generate a control command based on a request command associated with a preset data; using a video recorder to capture the content containing A first lip dynamic image of a first voice message, wherein the first voice message is associated with a profile to be verified; using a computer to determine whether the profile to be verified matches the default profile; when the profile to be verified is When the preset personal information is met, the operator is used to determine whether a similarity between the first lip dynamic image and a second lip dynamic image in a database is greater than a verification threshold, wherein the second lip dynamic image The dynamic image includes a second voice message; and when the similarity is greater than the verification threshold, the operator is used to generate a verification success message.

To sum up, in the dynamic image-based identity verification device and method of the present invention, the semantic content of the voice message is first analyzed to match the preset personal information as the first verification. After passing this first verification , and then use the captured lip dynamic image to compare the similarity with the preset lip dynamic image as the second verification, and then generate a verification success message when the two verifications are passed. In this way, repeatedly confirming the user's identity through dual voice and dynamic image authentication can significantly improve the accuracy of user identity recognition and also increase the convenience of the user's verification process.

The above description of the present disclosure and the following description of the embodiments are used to demonstrate and explain the spirit and principles of the present invention, and to provide further explanation of the patent application scope of the present invention.

The detailed features and advantages of the present invention are described in detail below in the implementation mode. The content is sufficient to enable anyone skilled in the relevant art to understand the technical content of the present invention and implement it according to the content disclosed in this specification, the patent scope and the drawings. , anyone familiar with the relevant art can easily understand the relevant objectives and advantages of the present invention. The following examples further illustrate the aspects of the present invention in detail, but do not limit the scope of the present invention in any way.

Please refer to FIG. 1 , which is a functional block diagram of an identity verification device based on dynamic images according to an embodiment of the present invention. As shown in FIG. 1 , the identity verification device 1 includes a video recorder 10 , a database 11 and a calculator 12 , wherein the calculator 12 is connected to the video recorder 10 and the database 11 respectively. The video recorder 10 is used to capture the first lip dynamic image including the first voice message according to the control command. The control instructions are generated from the arithmetic unit 12 according to a request instruction. In practice, the request instruction can be a transaction request made by the user after logging into the online banking account on the device, or it can be a transaction request made by the user after inserting the card into the bank account at the automatic teller machine, where the request instruction It may be, for example, a request instruction for financial transaction activities such as transfer, remittance or deposit, but the invention is not limited to this. The database 11 stores the second lip dynamic image including the second voice message and the default personal information, wherein the second lip dynamic image with the second voice message and the default personal information are obtained in advance and stored in the database 11 as the basis for comparison. Although not shown in the figure, the database 11 is located in the memory or storage medium of the identity verification device 1 . In practice, the second lip dynamic image with the second voice message and the default profile stored in the database 11 are based on the information of the owner of the logged-in bank account (including lip dynamic image data and text data) preset.

The first voice message captured by the video recorder 10 is associated with the personal information to be verified, and the operator 12 can determine whether the personal information to be verified matches the default personal information in the database 11 . Specifically, the video recorder 10 will transmit the captured first lip dynamic image with the first voice message to the operator 12 . Through an external voice-to-text server (such as Google Cloud voice-to-text server) or a built-in function chip, the operator 12 can parse the first voice message and obtain the corresponding text message as the personal information to be verified (such as the user's personal information). ID number A123456789).

Then, the operator 12 determines whether the personal information to be verified matches the preset personal information. If the two match, the operator 12 further determines whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold. When the similarity is greater than the verification threshold, the operator 12 generates a verification success message. That is to say, in this embodiment, the operator 12 first determines whether the text message in the personal data to be verified is the same as the text message in the default personal data (for example, ID card number A123456789). If so, the operator 12 will further analyze the similarity between the user's current lip shape change and the preset lip shape change, and finally determine whether the verification is successful. In practice, the arithmetic unit 12 may be, for example, a processor, a microprocessor, a controller, or other chips with arithmetic functions.

In one embodiment, the first voice message corresponds to a first time sequence having a plurality of first unit times, and the second voice message corresponds to a second time sequence having a plurality of second unit times. For details, please further refer to FIG. 2 , which is a schematic diagram of a first voice message and a second voice message according to an embodiment of the present invention. As shown in Figure 2, in an embodiment of the present invention, the operator 12 captures the timing corresponding to the first syllable data d1~d5 of the first voice message DA1 as the first timing P1, and the operator 12 The timing corresponding to the second syllable data d1'~d5' of the second voice message DA2 is captured as the second timing P2. Specifically, the first voice message DA1 has first syllable data d1~d5 respectively corresponding to a plurality of first unit times t1~t5 of the first time sequence P1, and the second voice message DA2 has second syllable data d1'~ d5' respectively corresponds to multiple second unit times t1'~t5' of the second time sequence P2. In this embodiment, the first syllable data d1~d5 and the second syllable data d1'~d5' respectively indicate the same single character or word. For example, the first syllable data d1 and the second syllable data d1' indicate the same word or word, the first syllable data d2 and the second syllable data d2' indicate the same word or word, the first syllable data d3 and the second syllable data d3' indicate the same word or word. The syllable data d3' indicates the same single character or word, and so on.

In one embodiment, the operator 12 detects the first feature point of the first lip dynamic image at the Nth first unit time to calculate the value of the first feature point in the Nth first unit time. The first distance change. Further, the operator 12 detects the second feature point of the second lip dynamic image in the Nth second unit time to calculate the second distance of the second feature point in the Nth second unit time. Variation, where N is a positive integer. Then, the operator 12 can determine whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold based on the calculated first distance change amount and the second distance change amount.

The following will describe a specific implementation of how the above-mentioned operator 12 determines whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold using a first practical example. Please further refer to FIG. 3A and FIG. 3B. FIG. 3A is a schematic diagram of the first lip dynamic image of an individual user according to an embodiment of the present invention, and FIG. 3B is a pre-stored lip dynamic image according to an embodiment of the present invention. Schematic diagram of the second lip dynamic image. Figure 3A takes user individual A as an example. When user individual A speaks (for example, reads the corresponding ID card number), the video recorder 10 captures the first lip dynamic image of user individual A, and in the first ( For example, N is 1) The first lip dynamic image in the first unit time t1 is shown in Figure 3A. The operator 12 detects that the first feature point x1 (a reference point in the center of the upper lip is used as the first feature point x1) moves from the position L1 to the position L2 within the first first unit time t1, and therefore calculates the first distance. Change amount D1.

On the other hand, a preset second lip dynamic image is stored in the database 11 . As shown in FIG. 3B , the operator 12 detects that the second feature point x2 of the second lip dynamic image moves from the position L1' to the position L2' within the first (for example, N is 1) second unit time t2. The calculator 12 can calculate the second distance variation D2. Further, the operator 12 calculates the difference between the first distance change D1 and the second distance change D2 and compares it to a preset value. In this embodiment, when the difference is less than the preset value, the operator 12 determines that the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold. At this time, the operator 12 recognizes user individual A's A verification success message is generated corresponding to the identity. On the contrary, when the difference is greater than the preset value, the operator 12 determines that the similarity between the first lip dynamic image and the second lip dynamic image is less than the verification threshold. At this time, the operator 12 determines that the identity of the user individual A is doubtful and Corresponding to the message that the verification is unsuccessful.

The foregoing embodiment only analyzes a single feature point of the dynamic image of the lips within a unit of time. However, a single feature point may not be able to identify the effective distance change due to certain words or characters with specific pronunciations, causing the operator 12 to be unable to accurately to judge the similarity of lip dynamic images. In order to cope with this problem, the identity verification device of the present invention can analyze multiple feature points of the lip dynamic image within a unit of time. Specifically, in one embodiment, the operator 12 may be used to detect a plurality of first feature points of the first lip dynamic image at the Nth of a plurality of first unit times to calculate the first feature points. A plurality of first distance changes in the Nth first unit time, and the operator can be used to detect a plurality of second feature points of the second lip dynamic image in the Nth of a plurality of second unit times, To calculate a plurality of second distance changes of the second feature points in the N-th second unit time, where N is a positive integer. Then, the operator determines whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold based on the first distance changes and the second distance changes.

The following will describe a specific implementation of how the above-mentioned operator 12 determines whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold using a second practical example. Please further refer to FIG. 4A and FIG. 4B. FIG. 4A is a schematic diagram of a first lip dynamic image of an individual user according to another embodiment of the present invention, and FIG. 4B is a schematic diagram of a first lip dynamic image according to another embodiment of the present invention. A schematic diagram of the pre-stored second lip dynamic image. Figure 4A takes user B as an example. When user B speaks (for example, reads the corresponding ID card number), the video recorder 10 captures the first lip dynamic image of user B, and in the first ( For example, N is 1) The first lip dynamic image in the first unit time t1 is shown in Figure 4A. The operator 12 detects the first feature points x1 and x2 within the first unit time t1 (the reference points at the center and side of the upper lip are used as the first and second feature points x1 and x2), where the first feature Point x1 moves from position L1 to position L2, and the first feature point x2 moves from position L3 to position L4. Therefore, two first distance changes D1 and D2 are calculated.

On the other hand, a preset second lip dynamic image is stored in the database 11 . As shown in FIG. 4B , the operator 12 detects the second feature points x3 and x4 of the second lip dynamic image within the first (for example, N is 1) second unit time t2, where the second feature point x3 is determined by the position L1' moves to position L2', and the second feature point x4 moves from position L3' to position L4'. Correspondingly, the operator 12 can calculate the second distance changes D3 and D4. Further, the operator 12 calculates the first difference between the first distance change D1 and the second distance change D3 and compares it to the first preset value, and the operator 12 calculates the first distance change D2 and the second distance change D3. The second difference between the two distance changes D4 is compared to the second preset value.

In this embodiment, when the first and second differences are smaller than the first and second preset values respectively, the operator 12 determines that the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold, At this time, the computer 12 recognizes the identity of the user individual B and generates a verification success message accordingly. On the contrary, when the first difference value is greater than the first preset value or the second difference value is greater than the second preset value, the operator 12 determines that the similarity between the first lip dynamic image and the second lip dynamic image is less than the verification threshold, At this time, the calculator 12 determines that the identity of the user individual B is doubtful and accordingly generates a message that the verification is unsuccessful.

The foregoing two embodiments only analyze one or more feature points of the dynamic image of the lips within a unit of time. However, the identity verification device of the present invention can also analyze the position changes of the feature points of the dynamic image of the lips within a continuous unit of time. analyze. Specifically, in one embodiment, the operator 12 is used to sequentially detect a first feature point of the first lip dynamic image in each first unit time to calculate the first feature point at the first time. The first movement trajectory in the sequence, and the operator 12 is further used to sequentially detect the second feature points of the second lip dynamic image in each second unit time to calculate the position of the second feature point in the second time sequence. The operator 12 determines whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold based on the first movement trajectory and the second movement trajectory.

The following will describe a specific implementation of how the above-mentioned operator 12 determines whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold using a third practical example. Please further refer to FIG. 5A and FIG. 5B. FIG. 5A is a schematic diagram of a first lip dynamic image of an individual user according to another embodiment of the present invention, and FIG. 5B is a schematic diagram of a first lip dynamic image according to another embodiment of the present invention. A schematic diagram of the pre-stored second lip dynamic image. Figure 5A takes user individual C as an example. For convenience of explanation, this embodiment uses three unit times t1~t3 as the first time sequence, and uses three unit times t1'~t3' as the second time sequence. When the user individual C speaks (for example, reads the corresponding ID number), the video recorder 10 captures the first lip dynamic image of the user individual C. The changes of this first lip dynamic image at different consecutive first unit times t1~t3 are shown in Figure 5A. The operator 12 sequentially detects the first feature point of the first lip dynamic image in each first unit time t1~t3, and calculates and obtains the first feature point in the first time sequence (that is, the continuous first unit time t1 ~t3) the first movement trajectory R1.

On the other hand, the second lip dynamic image is stored in the database 11 . As shown in FIG. 5B , the operator 12 sequentially detects the second feature points of the second lip dynamic image in each first unit time t1'~t3', and calculates and obtains the second feature points in the second time sequence (i.e. The second movement trajectory R2 within the continuous second unit time t1'~t3'). Then, the operator 12 calculates the similarity between the first movement trajectory R1 and the second movement trajectory R2 by using, for example, a curve similarity algorithm and compares it to a preset value. In this embodiment, when the similarity of the movement trajectory reaches the preset value, the operator 12 determines that the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold, so the operator 12 recognizes the user individual C A verification success message is generated corresponding to the identity of the user. On the contrary, when the similarity of the movement trajectories does not reach the preset value, the operator 12 determines that the similarity of the first lip dynamic image and the second lip dynamic image is less than the verification threshold. At this time, the computer 12 determines that the identity of the user individual C is doubtful and accordingly generates a message that the verification is unsuccessful.

Please refer to FIG. 6 , which is a method flow chart of an identity verification method based on dynamic images according to an embodiment of the present invention. As shown in FIG. 6 , in step S1 , the arithmetic unit 12 generates a control instruction according to the request instruction. In step S2, the video recorder 10 is used to capture the first lip dynamic image including the first voice message according to the control instruction, wherein the first voice message is associated with the personal information to be verified. In step S3, the operator 12 is used to determine whether the personal data to be verified matches the preset personal data in the database.

When the personal information to be verified matches the preset personal information, in step S4, the operator 12 is used to determine whether the similarity between the first lip dynamic image and the second lip dynamic image in the database 11 is greater than the verification threshold, wherein the first lip dynamic image is greater than the verification threshold. The two lip dynamic images include the second voice message. When the similarity is greater than the verification threshold, in step S5, the operator 12 generates a verification success message.

In one embodiment, the first voice message corresponds to a first time sequence having a plurality of first unit times, and the second voice message corresponds to a second time sequence having a plurality of second unit times, wherein the first lip dynamic image is determined Whether the similarity with the second lip dynamic image is greater than the verification threshold includes: using the operator 12 to detect the first feature point of the first lip dynamic image at the Nth of the first unit times to calculate the first feature The first distance change amount of the point in the Nth first unit time; using the operator 12 to detect the second feature point of the second lip dynamic image at the Nth second unit time to calculate the second The second distance change amount of the feature point in the Nth second unit time, where N is a positive integer; and the operator 12 is used to calculate the difference between the first distance change amount and the second distance change amount.

In one embodiment, the first voice message corresponds to a first time sequence having a plurality of first unit times, and the second voice message corresponds to a second time sequence having a plurality of second unit times, wherein the first lip dynamic image is determined Whether the similarity to the second lip dynamic image is greater than the verification threshold includes using the operator 12 to detect a plurality of first feature points of the first lip dynamic image at the Nth of the first unit times to calculate the A plurality of first distance changes of the first feature point in the Nth first unit time; using the operator 12 to detect a plurality of second lip dynamic images in the Nth second unit time. feature points to calculate a plurality of second distance changes of the second feature points in the N-th second unit time, where N is a positive integer; and use the operator 12 to individually calculate the first distance changes and The difference between the second distance changes.

In one embodiment, the first voice message corresponds to a first time sequence having a plurality of first unit times, and the second voice message corresponds to a second time sequence having a plurality of second unit times, wherein the first lip dynamic image is determined Whether the similarity with the second lip dynamic image is greater than the verification threshold includes using the operator 12 to sequentially detect the first feature points of the first lip dynamic image in each first unit time to calculate the time of the first feature point. The first movement trajectory in the first time sequence; the operator 12 is used to sequentially detect the second feature points of the second lip dynamic image in each second unit time to calculate the position of the second feature point in the second time sequence. the second movement trajectory; and the operator 12 compares the first movement trajectory and the second movement trajectory.

To sum up, in the dynamic image-based identity verification device and method of the present invention, the semantic content of the voice message is first analyzed to match the preset personal information as the first verification. After passing this first verification , and then use the captured lip dynamic image to compare the similarity with the preset lip dynamic image as the second verification, and then generate a verification success message when the two verifications are passed. In this way, repeatedly confirming the user's identity through dual voice and dynamic image authentication can significantly improve the accuracy of user identity recognition and also increase the convenience of the user's verification process.

Although the present invention is disclosed in the foregoing embodiments, they are not intended to limit the present invention. All changes and modifications made without departing from the spirit and scope of the present invention shall fall within the scope of patent protection of the present invention. Regarding the protection scope defined by the present invention, please refer to the attached patent application scope.

1: Identity verification device 10:Video recorder 11:Database 12:Operator DA1: first voice message DA2: Second voice message d1~d5: first syllable data d1’~d5’: second syllable information t1~t5, t1’~t5’: unit time P1: first timing P2: Second timing L1~L4, L1’~L4’: position x1~x4: Feature points D1~D4: distance change amount R1: first movement trajectory R2: Second movement trajectory

FIG. 1 is a functional block diagram of an identity verification device based on dynamic images according to an embodiment of the present invention. FIG. 2 is a schematic diagram of a first voice message and a second voice message according to an embodiment of the present invention. FIG. 3A is a schematic diagram of a first lip dynamic image of an individual user according to an embodiment of the present invention. FIG. 3B is a schematic diagram of a pre-stored second lip dynamic image according to an embodiment of the present invention. FIG. 4A is a schematic diagram of a first lip dynamic image of an individual user according to another embodiment of the present invention. FIG. 4B is a schematic diagram of a pre-stored second lip dynamic image according to another embodiment of the present invention. FIG. 5A is a schematic diagram of a first lip dynamic image of an individual user according to another embodiment of the present invention. FIG. 5B is a schematic diagram of a pre-stored second lip dynamic image according to another embodiment of the present invention. FIG. 6 is a method flow chart of an identity verification method based on dynamic images according to an embodiment of the present invention.

1: Identity verification device

10:Video recorder

11:Database

12:Operator

Claims (8)

An identity verification device based on dynamic lip images, including: a video recorder for capturing a first dynamic image of lips including a first voice message according to a control instruction, wherein the first voice message is associated with a waiting Verify personal information; a database for storing a second lip dynamic image including a second voice message and a default personal data; and a operator connected to the video recorder and the database, the operator is used to The control instruction is generated according to a request instruction, and the operator determines whether the personal information to be verified matches the preset personal information. When the personal information to be verified matches the preset personal information, the operator further determines the first Whether a similarity between the lip dynamic image and the second lip dynamic image is greater than a verification threshold, and when the similarity is greater than the verification threshold, a verification success message is generated, wherein the first voice message corresponds to a plurality of first A first timing sequence of unit time and the second voice message corresponds to a second timing sequence of a plurality of second unit times. The operator is used to detect the first lip at the Nth of the first unit times. The center of the upper lip in the dynamic image is used as a first feature point to calculate a first distance change of the first feature point in the Nth first unit time, and the operator is used to calculate a first distance change in the second unit time The Nth detection center of the upper lip in the second lip dynamic image is used as a second feature point to calculate a second distance change of the second feature point in the Nth second unit time, where N is a positive integer. The operator calculates the difference between the first distance change and the second distance change, and determines the first lip dynamic image and the third lip dynamic image when the difference is less than a preset value. The similarity between the two lip dynamic images is greater than the verification threshold, wherein the operator is used to retrieve the timing corresponding to a first syllable data of the first voice message as the first timing, and the operator is used to The timing corresponding to a second syllable data of the second voice message is captured as the second timing, and the first syllable data and the second syllable data indicate the same single character or word. The identity verification device based on dynamic lip images as described in claim 1, wherein the operator is further configured to detect a plurality of first features of the first dynamic image of lips at the Nth of the first unit times. points to calculate a plurality of first distance changes of the first feature points in the Nth first unit time, and the operator is further used to detect the Nth of the second unit time. A plurality of second feature points of the second lip dynamic image to calculate a plurality of second distance changes of the second feature points in the N-th second unit time, where N is a positive integer, and the operator According to the first distance changes and the second distance changes, it is determined whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold. The identity verification device based on lip dynamic images as described in claim 2, wherein the operator calculates a plurality of first differences between the first distance changes and the second distance changes respectively, and divides the The first difference values are respectively compared to a plurality of first preset values. When the difference values are respectively smaller than the first preset values, the operator determines the first lip dynamic image and the second lip The similarity of the dynamic image is greater than the verification threshold. The identity verification device based on the lip dynamic image as described in claim 1, wherein the operator is further used to sequentially detect the first feature point of the first lip dynamic image in each first unit time. , to calculate a first movement trajectory of the first feature point in the first time sequence, and the operator is further used to sequentially detect the second lip dynamic image in each second unit time. The second feature point is used to calculate a second movement trajectory of the second feature point in the second time sequence. The operator determines the first lip dynamics based on the first movement trajectory and the second movement trajectory. Whether the similarity between the image and the second lip dynamic image is greater than the verification threshold. An identity verification method based on dynamic lip images, including: using a computer to generate a control instruction based on a request instruction; using a video recorder to capture a first lip movement including a first voice message based on the control instruction. Image, in which the first voice message is associated with a profile to be verified; the operator is used to determine whether the profile to be verified matches a default profile in a database; when the profile to be verified matches the default profile At this time, the operator is used to determine whether a similarity between the first lip dynamic image and a second lip dynamic image in the database is greater than a verification threshold, wherein the second lip dynamic image includes a second lip dynamic image. a voice message; and when the similarity is greater than the verification threshold, the operator generates a verification success message, wherein the first voice message corresponds to a first sequence with a plurality of first unit times and the second voice message Corresponding to a second time sequence with a plurality of second unit times, determining whether the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold includes: using the operator to calculate the first lip dynamic image. Detect a first feature point of the first lip dynamic image in the Nth unit time to calculate a first distance change amount of the first feature point in the Nth first unit time; use this operation The device detects a second feature point of the second lip dynamic image in the Nth second unit time to calculate a second distance of the second feature point in the Nth second unit time. The amount of change, where N is a positive integer; the operator is used to calculate the difference between the first distance change amount and the second distance change amount; and the operator is used to determine the first distance change amount when the difference is less than a preset value The similarity between the lip dynamic image and the second lip dynamic image is greater than the verification threshold, wherein the identity verification method further includes using the operator to capture a timing corresponding to a first syllable data of the first voice message to As the first time sequence, the time sequence corresponding to a second syllable data of the second voice message captured by the operator is used as the second time sequence, wherein the first syllable data and the second syllable data indicate the same of words or words. The identity verification method based on dynamic lip images as described in claim 5, wherein determining whether the similarity between the first dynamic image of lips and the second dynamic image of lips is greater than the verification threshold further includes: using the operator Detect a plurality of first feature points of the first lip dynamic image at the Nth first unit time to calculate a plurality of first feature points of the first feature points at the Nth first unit time. A distance variation; using the operator to detect a plurality of second feature points of the second lip dynamic image at the Nth of the second unit times, to calculate the second feature points of the second lip dynamic image at the Nth A plurality of second distance changes in the second unit time, where N is a positive integer; and the operator calculates a plurality of first differences between the first distance changes and the second distance changes respectively. The identity verification method based on lip dynamic images as described in claim 6, wherein the operator is used to determine the difference between the first lip dynamic image and the second lip dynamic image when the difference is less than the preset value. The similarity being greater than the verification threshold includes: comparing the first difference values to a plurality of first preset values, wherein the operator is when the first difference values are respectively smaller than the first preset values, It is determined that the similarity between the first lip dynamic image and the second lip dynamic image is greater than the verification threshold. The identity verification method based on dynamic lip images as described in claim 5, wherein determining whether the similarity between the first dynamic image of lips and the second dynamic image of lips is greater than the verification threshold further includes: using the operator Sequentially detecting the first feature point of the first lip dynamic image in each first unit time to calculate a first movement trajectory of the first feature point in the first time sequence; using the The operator sequentially detects the second feature point of the second lip dynamic image in each second unit time to calculate a second movement trajectory of the second feature point in the second time sequence; and The first movement trajectory and the second movement trajectory are compared with the operator.

Images