A multi-dimensional identity recognition and authentication system and method

Abstract

The present invention discloses a multi-directional identity recognition and authentication system and method. The system includes a terminal and a server. After entering the identity recognition and authentication process, the server randomly generates a piece of authentication information, and sends the authentication information together with the preset guidance information to the terminal; after receiving the authentication information and guidance information sent by the server, the control information output component outputs the authentication information and guidance information; the terminal also includes a camera for obtaining video data of the person to be authenticated. During the authentication period, the present invention sends authentication information to the terminal of the person to be authenticated, guides the person to be authenticated to read the authentication information, collects the video data and voice data of the person to be authenticated through the camera and the receiver, and performs identity recognition and authentication based on face recognition, image comparison, lip recognition and voice recognition in multiple directions, which ensures the accuracy of the authentication while preventing illegal personnel from easily cracking it.

Description

Technical Field

[0001] The present invention relates to the technical field of identity recognition and authentication, and in particular to a multi-faceted identity recognition and authentication system and method. Background Art

[0002] During the online business process, the identity of the operator needs to be confirmed through identity recognition and authentication. The current identity recognition and authentication include SMS code authentication, ID card authentication and face recognition verification. Traditional face recognition and authentication technology is easily cracked by means of photos and other means, and its security is not high. In order to improve security, liveness detection was subsequently introduced, which is carried out by introducing actions such as shaking the head and blinking. However, this detection also has certain loopholes. It can be cracked by making a face mask through a 3D printer, or by making a head model and sticking the corresponding frontal face photo on the front side of the model and the side face photo on both sides of the model. When the liveness detection prompts to shake the head, the model can be rotated to pass the partial liveness detection. Summary of the invention

[0003] The purpose of the present invention is to provide a multi-faceted identity recognition and authentication system and method in view of the deficiencies in the prior art.

[0004] To achieve the above-mentioned object, in a first aspect, the present invention provides a multi-directional identity recognition and authentication system, comprising a terminal and a server. After entering the identity recognition and authentication process, the server randomly generates a piece of authentication information and sends the authentication information together with preset guidance information to the terminal;

[0005] The terminal includes an information output component, which controls the information output component to output the authentication information and the guidance information after receiving the authentication information and the guidance information sent by the server, so that the person to be authenticated can know the content of the authentication message, and the guidance information includes guiding the person to be authenticated to read the authentication message;

[0006] The terminal also includes a camera for acquiring video data of the person to be authenticated after receiving the authentication information and guidance information sent by the server;

[0007] The terminal further includes a communication module for receiving authentication information and guidance information sent by the server, and for sending the video data to the server;

[0008] The server extracts a plurality of consecutive frames of first image data from the video data, and performs face recognition authentication based on the first image data;

[0009] After the face recognition authentication is passed, the server also extracts a number of second image data at a set time interval, and compares the second image data with the first image data based on face recognition. If it is above the set threshold, the second image data are compared for image similarity. If the similarity is below the set threshold, the identity recognition authentication result is output.

[0010] Furthermore, the terminal also includes a receiver for obtaining voice data when the person to be authenticated reads the authentication message. The communication module sends the voice data to the server. The server compares the voice data with the authentication information based on voice recognition to determine whether the voice data is consistent with the authentication information. If they are consistent, the server outputs the identity authentication pass result.

[0011] Furthermore, the server recognizes the lip shape of the video data based on the lip shape recognition model, and synchronously compares the recognition result with the voice data to determine whether the voice data is uttered by the person in the current video.

[0012] Furthermore, the information output component includes a display screen, and the authentication information and the guidance information are displayed on the display screen in text form.

[0013] Furthermore, the information output component includes a display screen and a speaker, the authentication information is displayed on the display screen in the form of text, and the guidance information is output by the speaker in the form of voice.

[0014] In a second aspect, the present invention provides a multi-faceted identity recognition and authentication method, which is applied in the system composed of the above-mentioned terminal and server, comprising:

[0015] After entering the identity recognition and authentication process, the server randomly generates a piece of authentication information and sends the authentication information together with the preset guidance information to the terminal;

[0016] The terminal receives the authentication information and the guidance information sent by the server through the communication module. After receiving the authentication information and the guidance information sent by the server, the terminal controls its information output component to output the authentication information and the guidance information so that the person to be authenticated can know the content of the authentication message. The guidance information includes guiding the person to be authenticated to read the authentication message.

[0017] After receiving the authentication information and guidance information sent by the server, the terminal controls its camera to obtain video data of the person to be authenticated, and sends the video data to the server through the communication module;

[0018] The server extracts a plurality of consecutive frames of first image data from the video data, and performs face recognition authentication based on the first image data;

[0019] After the face recognition authentication is passed, the server also extracts a number of second image data at a set time interval, and compares the second image data with the first image data based on face recognition. If it is above the set threshold, the second image data are compared for image similarity. If the similarity is below the set threshold, the identity recognition authentication result is output.

[0020] Furthermore, the terminal obtains voice data of the person to be authenticated when reading the authentication message through the receiver, and the communication module sends the voice data to the server. The server compares the voice data with the authentication information based on voice recognition to determine whether the voice data is consistent with the authentication information. If they are consistent, the server outputs the identity authentication pass result.

[0021] Furthermore, the server recognizes the lip shape of the video data based on the lip shape recognition model, and synchronously compares the recognition result with the voice data to determine whether the voice data is uttered by the person in the current video.

[0022] Furthermore, the authentication information and the guidance information are both displayed in text form on a display screen of the terminal.

[0023] Furthermore, the authentication information is displayed in text form on a display screen of the terminal, and the guidance information is output in voice form by a speaker of the terminal.

[0024] Beneficial effects: During the authentication period, the present invention sends authentication information to the terminal of the person to be authenticated, and guides the person to be authenticated to read the authentication information. The video data and voice data of the person to be authenticated are collected through the camera and the receiver, and identity recognition and authentication are performed based on face recognition, image comparison, lip recognition and voice recognition in multiple aspects. While ensuring the accuracy of authentication, it can also prevent illegal persons from easily cracking it. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flowchart of a multi-faceted identity recognition and authentication method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The present invention is further explained below in conjunction with the accompanying drawings and specific embodiments. The embodiments are implemented based on the technical solution of the present invention. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention.

[0027] like Figure 1As shown, the embodiment of the present invention provides a multi-faceted identity recognition and authentication system, including a terminal and a server. After entering the identity recognition and authentication process, the server randomly generates a piece of authentication information and sends the authentication information together with the preset guidance information to the terminal. Specifically, the authentication information can be one or several complete sentences, and the meanings expressed by these sentences can be completely unrelated to the business itself, or can be multiple words without any rules.

[0028] The terminal includes an information output component. After receiving the authentication information and guidance information sent by the server, the terminal controls the information output component to output the authentication information and guidance information so that the person to be authenticated can know the content of the authentication message. The guidance information includes guiding the person to be authenticated to read the authentication message. Specifically, the information output component can use a display screen, and the authentication information and the guidance information are both displayed on the display screen in the form of text. The guidance information can be "Please read the following content" and the like. The information output component can also use a display screen and a speaker. The authentication information is preferably displayed on the display screen in the form of text, and the guidance information is output by the speaker in the form of voice.

[0029] The terminal also includes a camera, which is used to obtain video data of the person to be authenticated after receiving the authentication information and guidance information sent by the server. The video data can be specifically set for a time length, which can meet the reading speed requirements of most people and ensure that the authentication message can be easily read within the set time length.

[0030] The terminal also includes a communication module, which is used to receive authentication information and guidance information sent by the server, and to send video data to the server to meet the normal interaction function with the server.

[0031] After receiving the video data, the server extracts a plurality of consecutive frames of first image data from the video data, and performs face recognition authentication based on the first image data. The first image data can generally be extracted from the front part of the video data. At this time, the person to be authenticated has not read the authentication information, and the facial features and expressions will not change much, thereby improving the accuracy of face recognition authentication.

[0032] After the face recognition authentication is passed, the server also extracts a number of second image data at set time intervals, and compares the second image data with the first image data based on face recognition. If it is above the set threshold, it can be ensured that the person to be authenticated has not changed during the authentication period. Then the second image data are compared for image similarity. Since the person to be authenticated is in a reading state, his or her eyes, mouth, wrinkles and other facial conditions will inevitably change to a certain extent, so that the second image data at different time periods are not completely consistent. If the similarity is below the set threshold, the identity authentication result is output. If the similarity is above the set threshold, it means that the person to be authenticated currently appearing in the video may be a photo or a head model. The second image data can be multiple groups extracted at intervals, preferably evenly covering the entire video.

[0033] The terminal of the embodiment of the present invention also includes a receiver to obtain voice data when the person to be authenticated reads the authentication message. The communication module sends the voice data collected by the receiver to the server. The server compares the voice data with the authentication information based on voice recognition to determine whether the voice data and the authentication information are consistent. If they are consistent, the result of identity authentication passing is output. After combining the voice recognition judgment, the accuracy of identity authentication can be further improved.

[0034] After receiving the above video data and voice data, the server can recognize the lip shape of the video data based on the lip shape recognition model, and compare the recognition result with the voice data synchronously to determine whether the voice data is uttered by the person in the current video. This can further improve the accuracy of identity recognition and authentication, and avoid cracking by using head models.

[0035] Based on the above embodiments, it can be seen that the present invention also provides a multi-faceted identity recognition and authentication method, which is applied in a system composed of a terminal and a server, including:

[0036] After entering the identity authentication process, the server randomly generates a piece of authentication information and sends it to the terminal together with the preset guidance information. Specifically, the authentication information can be one or several complete sentences, the meaning of which can be completely unrelated to the business itself, or can be a random number of words.

[0037] The terminal receives the authentication information and guidance information sent by the server through the communication module. After receiving the authentication information and guidance information sent by the server, the terminal controls its information output component to output the authentication information and guidance information so that the person to be authenticated can know the content of the authentication message. The guidance information includes guiding the person to be authenticated to read the authentication message. Specifically, the information output component can use a display screen, and the authentication information and guidance information are both displayed on the display screen in the form of text. The guidance information can be "Please read the following content" and the like. The information output component can also use a display screen and a speaker. The authentication information is preferably displayed on the display screen in the form of text, and the guidance information is output by the speaker in the form of voice.

[0038] After receiving the authentication information and guidance information sent by the server, the terminal controls its camera to obtain the video data of the person to be authenticated, and sends the video data to the server through the communication module. The video data can be specifically set in duration, which can meet the reading speed requirements of most people and ensure that the authentication message can be easily read within the set duration.

[0039] After receiving the video data, the server extracts a plurality of consecutive frames of first image data from the video data, and performs face recognition authentication based on the first image data. The first image data can generally be extracted from the front part of the video data. At this time, the person to be authenticated has not read the authentication information, and the facial features and expressions will not change too much, thereby improving the accuracy of face recognition authentication.

[0040] After the face recognition authentication is passed, the server also extracts a number of second image data at set time intervals, and compares the second image data with the first image data based on face recognition. If it is above the set threshold, it can be ensured that the person to be authenticated has not changed during the authentication period. Then the second image data are compared for image similarity. Since the person to be authenticated is in a reading state, his or her eyes, mouth, wrinkles and other facial conditions will inevitably change to a certain extent, so that the second image data at different time periods are not completely consistent. If the similarity is below the set threshold, the identity authentication result is output. If the similarity is above the set threshold, it means that the person to be authenticated currently appearing in the video may be a photo or a head model. The second image data can be multiple groups extracted at intervals, preferably evenly covering the entire video.

[0041] The embodiment of the present invention obtains the voice data of the person to be authenticated when reading the authentication message through the receiver of the terminal, and the communication module sends the voice data collected by the receiver to the server. The server compares the voice data with the authentication information based on voice recognition to determine whether the voice data and the authentication information are consistent. If they are consistent, the result of identity authentication is output. After combining with the voice recognition judgment, the accuracy of identity authentication can be further improved.

[0042] After receiving the above video data and voice data, the server can also recognize the lip shape of the video data based on the lip shape recognition model, and compare the recognition result with the voice data synchronously to determine whether the voice data is uttered by the person in the current video. This can further improve the accuracy of identity recognition and authentication, and avoid cracking by using head models.

[0043] In the embodiment provided by the present invention, the image data is obtained with the consent of the user, and all the acquired user data complies with the relevant policies and legal provisions.

[0044] The above is only a preferred embodiment of the present invention. It should be noted that for ordinary technicians in this technical field, other parts not specifically described belong to the prior art or common knowledge. Several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention.

Claims

1. A multi-faceted identity recognition and authentication system, characterized in that: The system comprises a terminal and a server. After entering the identity recognition and authentication process, the server randomly generates a piece of authentication information and sends the authentication information together with preset guidance information to the terminal. The terminal includes an information output component, which controls the information output component to output the authentication information and the guidance information after receiving the authentication information and the guidance information sent by the server, so that the person to be authenticated can know the content of the authentication message, and the guidance information includes guiding the person to be authenticated to read the authentication message; The terminal also includes a camera for acquiring video data of the person to be authenticated after receiving the authentication information and guidance information sent by the server; The terminal further includes a communication module for receiving authentication information and guidance information sent by the server, and for sending the video data to the server; The server extracts a plurality of consecutive frames of first image data from the video data, and performs face recognition authentication based on the first image data; After the face recognition authentication is passed, the server also extracts a number of second image data at a set time interval, and compares the second image data with the first image data based on face recognition. If it is above the set threshold, the second image data are compared for image similarity. If the similarity is below the set threshold, the identity recognition authentication result is output.

2. The multi-directional identity recognition and authentication system according to claim 1, characterized in that: The terminal also includes a receiver for obtaining voice data when the person to be authenticated reads the authentication message. The communication module sends the voice data to the server. The server compares the voice data with the authentication information based on voice recognition to determine whether the voice data is consistent with the authentication information. If they are consistent, the server outputs the identity authentication pass result.

3. The multi-directional identity recognition and authentication system according to claim 2, characterized in that: The server recognizes the lip shape of the video data based on the lip shape recognition model, and synchronously compares the recognition result with the voice data to determine whether the voice data is uttered by the person in the current video.

4. The multi-directional identity recognition and authentication system according to claim 1, characterized in that: The information output component includes a display screen, and the authentication information and the guidance information are both displayed on the display screen in text form.

5. The multi-directional identity recognition and authentication system according to claim 1, characterized in that: The information output component includes a display screen and a speaker. The authentication information is displayed on the display screen in the form of text, and the guidance information is output by the speaker in the form of voice.

6. A multi-faceted identity recognition and authentication method, applied in the system consisting of a terminal and a server as claimed in claim 1, characterized in that: include: After entering the identity recognition and authentication process, the server randomly generates a piece of authentication information and sends the authentication information together with the preset guidance information to the terminal; The terminal receives the authentication information and the guidance information sent by the server through the communication module. After receiving the authentication information and the guidance information sent by the server, the terminal controls its information output component to output the authentication information and the guidance information so that the person to be authenticated can know the content of the authentication message. The guidance information includes guiding the person to be authenticated to read the authentication message. After receiving the authentication information and guidance information sent by the server, the terminal controls its camera to obtain video data of the person to be authenticated, and sends the video data to the server through the communication module; The server extracts a plurality of consecutive frames of first image data from the video data, and performs face recognition authentication based on the first image data; After the face recognition authentication is passed, the server also extracts a number of second image data at a set time interval, and compares the second image data with the first image data based on face recognition. If it is above the set threshold, the second image data are compared for image similarity. If the similarity is below the set threshold, the identity recognition authentication result is output.

7. The multi-directional identity recognition and authentication method according to claim 6, characterized in that: The terminal obtains voice data of the person to be authenticated when reading the authentication message through the receiver, and the communication module sends the voice data to the server. The server compares the voice data with the authentication information based on voice recognition to determine whether the voice data is consistent with the authentication information. If they are consistent, the server outputs the identity recognition authentication pass result.

8. The multi-directional identity recognition and authentication method according to claim 7, characterized in that: The server recognizes the lip shape of the video data based on the lip shape recognition model, and synchronously compares the recognition result with the voice data to determine whether the voice data is uttered by the person in the current video.

9. The multi-directional identity recognition and authentication method according to claim 6, characterized in that: The authentication information and the guidance information are both displayed in text form on the display screen of the terminal.

10. The multi-directional identity recognition and authentication method according to claim 6, characterized in that: The authentication information is displayed on the display screen of the terminal in the form of text, and the guidance information is output by the speaker of the terminal in the form of voice.

Images