Face recognition CTF competition anti-cheating method and device

By using face recognition technology in the competition platform, the problem of participating in the competition as others is solved, the fairness of the competition and cheat monitoring ability is improved, and cheating behavior is prevented.

CN119007263APending Publication Date: 2024-11-22INTEGRITY TECH GRP INC
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411090121.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing technology cannot effectively prevent the problem of participating in the competition as others in the competition, which undermines the fairness of the competition.

Method used

By introducing facial recognition technology into the competition platform, using cameras to take photos to obtain facial information, extract facial features through algorithm models and compare them with the players' reserved information to ensure that the operator is himself, and perform sensorless snapshots and answering questions. Authentication and identification to prevent cheating.

Benefits of technology

It improves the fairness of the game, effectively prevents the behavior of participating in the game as others, and enhances the ability to monitor cheats.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007263A_ABST
    Figure CN119007263A_ABST
Patent Text Reader

Abstract

The invention provides a face recognition CTF competition anti-cheating method, which comprises the steps that a competition platform enters a login interface, receives account information and enters a face authentication interface; the competition platform turns on a camera, and the camera is used for taking a picture of a human face to obtain human face information; the competition platform extracts face features in the face information through an algorithm model, and performs face comparison on the face features and reserved information of players; the competition platform enters a competition interface after the comparison is passed; when the match platform submits answers, non-inductive snapshot is carried out through a camera, and snapshot face information is obtained; when the match platform judges that the answer is correct, the snapshot face information is authenticated and recognized; and when the answer is judged to be wrong, the snapshot face information and an error result are sent to the monitoring platform. The competition platform performs face authentication at key nodes such as login, answering and the like, and can confirm whether the operation is performed by the user, so that the fairness of the competition is improved, and the cheating behavior is effectively prevented.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for preventing cheating in a face recognition CTF competition. Background Art

[0002] In the competition, it is difficult to avoid using various means to pretend to be someone else to participate in the competition. This behavior seriously undermines the fairness and justice of the competition. In the prior art, only the account password login method is often used for authentication, which cannot avoid the problem of pretending to be someone else to participate in the competition.

[0003] Therefore, providing an anti-cheating solution that can avoid the problem of participating in the game on behalf of others has become an urgent problem to be solved. Summary of the invention

[0004] The present invention aims to provide a method and device for preventing cheating in face recognition CTF competitions that overcome the above problems or at least partially solve the above problems.

[0005] To achieve the above object, the technical solution of the present invention is specifically implemented as follows:

[0006] One aspect of the present invention provides a method for preventing cheating in a face recognition CTF competition, comprising:

[0007] Enter the login interface of the competition platform, receive account information, and enter the face recognition interface;

[0008] The competition platform turns on a camera and uses the camera to take a photo of a face to obtain face information;

[0009] The competition platform extracts facial features from the facial information through an algorithm model, and performs facial comparison between the facial features and the player's reserved information;

[0010] After the match is passed, the competition platform enters the competition interface;

[0011] When the contestant submits an answer, the contest platform uses a camera to capture the person's face without any sense of touch, and obtains the captured face information;

[0012] When the game platform determines that the answer is correct, it authenticates and identifies the captured face information; when the game platform determines that the answer is wrong, it sends the captured face information and the error result to the monitoring platform.

[0013] Optionally, the method further includes: after the comparison fails, the competition platform opens a personal green channel and closes the login interface.

[0014] Optionally, the method also includes: the monitoring platform synchronizing the captured facial information and error results into abnormal monitoring data.

[0015] Optionally, the competition platform extracting facial features from the facial information through an algorithm model includes: the competition platform extracting facial contour, eyes, nose and / or mouth information from the facial information through an algorithm model.

[0016] Optionally, the facial comparison between the facial features and the player reserved information includes: calculating a first threshold based on the facial features, and calculating a second threshold information based on the player reserved information; calculating the difference between the first threshold and the second threshold, and if the absolute value of the difference is less than a preset value, the comparison passes.

[0017] Another aspect of the present invention provides a face recognition CTF competition anti-cheating device, comprising:

[0018] Login module, used to enter the login interface, receive account information, and enter the face authentication interface;

[0019] A camera module is used to open a camera and use the camera to take a photo of a face to obtain face information;

[0020] A comparison module, used for extracting facial features from the facial information through an algorithm model, and performing facial comparison between the facial features and the player's reserved information;

[0021] A competition module, used for entering a competition interface after the comparison in the comparison module passes the comparison;

[0022] The camera module is also used to capture the face of the person by a camera when the answer is submitted in the competition module, so as to obtain the captured face information;

[0023] The competition module is also used to authenticate and identify the captured facial information when the answer is judged to be correct; when the answer is judged to be wrong, the captured facial information and the error result are sent to the monitoring platform.

[0024] Optionally, the competition module is further used to open a personal green channel after the comparison fails, and notify the login module to close the login interface.

[0025] Optionally, the monitoring platform is used to synchronize the captured facial information and error results into abnormal monitoring data.

[0026] Optionally, the comparison module extracts facial features from the facial information through an algorithm model in the following manner: the competition platform extracts facial contour, eyes, nose and / or mouth information from the facial information through an algorithm model.

[0027] Optionally, the comparison module performs a facial comparison between the facial features and the player reserved information in the following manner: calculating a first threshold based on the facial features, and calculating a second threshold information based on the player reserved information; calculating a difference between the first threshold and the second threshold, and if the absolute value of the difference is less than a preset value, the comparison passes.

[0028] It can be seen that through the face recognition CTF competition anti-cheating method and device provided by the present invention, the competition platform performs face authentication at key nodes such as login and answering questions, and can confirm whether the operation is performed by the person himself, thereby improving the fairness of the competition and effectively preventing cheating. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0030] Figure 1 A flow chart of the anti-cheating method for face recognition CTF competition provided by an embodiment of the present invention;

[0031] Figure 2 A schematic diagram of the structure of a face recognition CTF competition anti-cheating device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0033] Figure 1 FIG. 1 is a flowchart showing a method for preventing cheating in a face recognition CTF competition provided by an embodiment of the present invention, see Figure 1 The anti-cheating method for face recognition CTF competition provided by the embodiment of the present invention includes:

[0034] S1, the competition platform enters the login interface, receives account information, and enters the face recognition interface.

[0035] Specifically, in the management backend, configure whether to enable login / question answering authentication for the competition. The competition can be conducted without enabling the login platform.

[0036] The present invention configures the game to start login / question answering authentication in the management background, so as to enter the face authentication interface after receiving the account information.

[0037] Specifically, the competition platform of the present invention adds a face recognition function at the login. When the face authentication login is turned on, the contestant enters the account number and enters the face authentication interface. The contestant has a preset number of authentication opportunities. If the preset number of authentication failures is reached, the account will be locked for a preset period of time. For example: the contestant has 2 authentication opportunities. After 2 consecutive authentication failures, the account will be locked for 10 minutes. Among them, special accounts are not subject to this restriction and can log in directly successfully.

[0038] S2, the competition platform turns on the camera and uses the camera to take a picture of the face to obtain the face information;

[0039] S3, the competition platform extracts facial features from facial information through an algorithm model and compares the facial features with the contestant's reserved information;

[0040] S4, after the comparison is passed, the competition platform enters the competition interface.

[0041] As an optional implementation of the embodiment of the present invention, the face recognition CTF competition anti-cheating method provided by the embodiment of the present invention also includes: after the comparison fails, the competition platform opens a personal green channel and closes the login interface.

[0042] Specifically, after entering the face authentication interface, the present invention opens the camera to take a photo and uploads it to the server. The algorithm model extracts the face features and compares them with the reserved photo information on the contestant's ID card to perform facial comparison detection. The highest matching result is used to determine whether they are the same person. Only after passing the authentication can the contestant enter the competition platform. If someone does not match the reserved photo information on the ID card and fails to pass the authentication, a green channel can be opened for the individual, and the login / answer authentication can be closed.

[0043] Among them, face recognition of the present invention is to collect image information containing a face by calling a camera, extract facial features from it, and compare it with known facial features to identify the identity. It usually includes face detection, face alignment, feature extraction, etc.

[0044] In specific implementation, multiple personal feature information in the original facial information (such as the distance between the eyes, nose and lips, etc.) can be converted into facial print geometry data and stored as samples, and the scanned facial print information can be compared with the stored facial print samples for errors.

[0045] The present invention enhances the cheating monitoring capability of the competition platform through face recognition, enriches cheating monitoring items, improves the fairness of the competition, and prevents behaviors such as impersonation and cheating.

[0046] S5, when the contest platform submits the answer, the camera will capture the face information without any sense;

[0047] S6, when the competition platform determines that the answer is correct, it authenticates and identifies the captured face information; when it determines that the answer is wrong, it sends the captured face information and the error result to the monitoring platform.

[0048] As an optional implementation manner of the embodiment of the present invention, the anti-cheating method for face recognition CTF competition provided by the embodiment of the present invention also includes: the monitoring platform synchronizes the captured face information and error results into abnormal monitoring data.

[0049] Specifically, during the process of answering questions in the present invention, contestants will take unconscious snapshots when submitting answers. If the answer is correct, the snapshot will be authenticated and recognized. If the answer is wrong, only the snapshot will be taken without authentication. The abnormal authentication results will be synchronized to the monitoring platform. The monitoring platform monitors facial abnormalities and can synchronize facial abnormality data to the abnormal monitoring data of the competition platform according to the situation.

[0050] As an optional implementation manner of an embodiment of the present invention, the competition platform extracts facial features from facial information through an algorithm model, including: the competition platform extracts facial contour, eyes, nose and / or mouth information from facial information through an algorithm model.

[0051] Specifically, the camera of the present invention requires the browser to authorize the platform to enable the camera access rights and enable the camera for face recognition. The model is loaded, and after the face model is imported, the face position and size information is detected by the camera for subsequent analysis. The camera captures and uploads the image with the face for authentication. The facial features extracted by the present invention include: identifying the main feature points of the face and the main facial information, such as facial contour, eyes, nose, mouth, etc. At the same time, the present invention also performs non-sensing snapshots, and completes the photo upload in the background when the contestant answers the questions and submits the answers.

[0052] As an optional implementation of an embodiment of the present invention, performing facial comparison between facial features and player reserved information includes: calculating a first threshold based on the facial features, and calculating a second threshold information based on the player reserved information; calculating the difference between the first threshold and the second threshold, and if the absolute value of the difference is less than a preset value, the comparison passes.

[0053] Specifically, when the present invention performs facial comparison, the extracted facial features are compared with known facial data. During the comparison process, a threshold between two faces is calculated to determine whether they are the same face. The smaller the threshold, the higher the facial similarity.

[0054] It can be seen that the face recognition CTF competition anti-cheating method provided by the embodiment of the present invention can confirm whether it is the person operating by comparing the face information of the operating player with the photo information reserved by the player in the Ministry of Public Security, so as to prevent the person from pretending to be a cheater. At the same time, the present invention can be flexibly configured, and the authentication of the designated player can be turned off or on at any time for face monitoring of login and answering questions, which can better meet the randomness and flexibility requirements during the competition. In addition, real-time monitoring can be performed, abnormal face monitoring data can be viewed in real time, and the abnormal data can be effectively verified.

[0055] Figure 2 The structure diagram of the face recognition CTF competition anti-cheating device provided by the embodiment of the present invention is shown. The face recognition CTF competition anti-cheating device applies the above method. The following is only a brief description of the structure of the face recognition CTF competition anti-cheating device. For other matters not covered, please refer to the relevant description in the above face recognition CTF competition anti-cheating method. Figure 2 The face recognition CTF competition anti-cheating device provided by the embodiment of the present invention includes:

[0056] Login module, used to enter the login interface, receive account information, and enter the face authentication interface;

[0057] The camera module is used to open the camera, take a picture of a face using the camera, and obtain face information;

[0058] The comparison module is used to extract facial features from facial information through an algorithm model and compare the facial features with the reserved information of the contestants;

[0059] The competition module is used to enter the competition interface after the comparison module passes the comparison;

[0060] The camera module is also used to capture the face of the person without any sense through the camera when submitting the answer in the competition module;

[0061] The competition module is also used to authenticate and identify the captured facial information when the answer is judged to be correct; when the answer is judged to be wrong, the captured facial information and the error result are sent to the monitoring platform.

[0062] As an optional implementation of the embodiment of the present invention, the competition module is also used to open a personal green channel and notify the login module to close the login interface after the comparison fails.

[0063] As an optional implementation of an embodiment of the present invention, the monitoring platform is used to synchronize the captured facial information and error results into abnormal monitoring data.

[0064] As an optional implementation of the embodiment of the present invention, the comparison module extracts facial features from the facial information through an algorithm model in the following manner:

[0065] The competition platform extracts facial contours, eyes, nose and / or mouth information from facial information through an algorithm model.

[0066] As an optional implementation of the embodiment of the present invention, the comparison module compares the facial features with the player's reserved information in the following manner:

[0067] Calculate a first threshold value based on facial features, and calculate second threshold information based on player reserved information;

[0068] The difference between the first threshold and the second threshold is calculated, and if the absolute value of the difference is less than a preset value, the comparison passes.

[0069] It can be seen that the face recognition CTF competition anti-cheating device provided by the embodiment of the present invention can identify the face information of the operating player and compare it with the photo information of the player reserved in the Ministry of Public Security to confirm whether it is the person operating, and prevent the person from pretending to be cheating. At the same time, the present invention can be flexibly configured, and the face monitoring for logging in and answering questions can be turned off or on at any time to better meet the randomness and flexibility requirements during the competition. In addition, it can also monitor in real time, view abnormal face monitoring data in real time, and effectively verify the abnormal data.

[0070] The above are only embodiments of the present application and are 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 within the scope of the claims of the present application.

Claims

1. A method for preventing cheating in face recognition CTF competition, characterized in that: include: Enter the login interface of the competition platform, receive account information, and enter the face recognition interface; The competition platform turns on a camera and uses the camera to take a photo of a face to obtain face information; The competition platform extracts facial features from the facial information through an algorithm model, and performs facial comparison between the facial features and the player's reserved information; After the comparison is passed, the competition platform enters the competition interface; When the contestant submits an answer, the contest platform uses a camera to capture the person's face without any sense of touch, and obtains the captured face information; When the competition platform determines that the answer is correct, the captured facial information is authenticated and identified; When the answer is judged to be wrong, the captured face information and the error result are sent to the monitoring platform.

2. The method according to claim 1, characterized in that: Also includes: After the comparison fails, the competition platform opens a personal green channel and closes the login interface.

3. The method according to claim 2, characterized in that Also includes: The monitoring platform synchronizes the captured facial information and error results into abnormal monitoring data.

4. The method according to claim 3, characterized in that The facial features extracted by the competition platform from the facial information through an algorithm model include: The competition platform extracts facial contour, eyes, nose and / or mouth information from the face information through an algorithm model.

5. The method according to claim 4, characterized in that The facial comparison between the facial features and the reserved information of the players includes: Calculate a first threshold value according to the facial features, and calculate a second threshold value information according to the player reserved information; The difference between the first threshold and the second threshold is calculated, and if the absolute value of the difference is less than a preset value, the comparison is passed.

6. A face recognition CTF competition anti-cheating device, characterized in that: include: Login module, used to enter the login interface, receive account information, and enter the face authentication interface; A camera module is used to open a camera and use the camera to take a photo of a face to obtain face information; A comparison module, used for extracting facial features from the facial information through an algorithm model, and performing facial comparison between the facial features and the player's reserved information; A competition module, used for entering a competition interface after the comparison in the comparison module passes the comparison; The camera module is also used to capture the face of the person without any sense through the camera when the answer is submitted in the competition module, so as to obtain the captured face information; The competition module is also used to authenticate and identify the captured facial information when the answer is judged to be correct; when the answer is judged to be wrong, the captured facial information and the error result are sent to the monitoring platform.

7. The device according to claim 6, characterized in that The competition module is also used to open a personal green channel and notify the login module to close the login interface after the comparison fails.

8. The device according to claim 7, characterized in that The monitoring platform is used to synchronize the captured facial information and error results into abnormal monitoring data.

9. The device according to claim 8, characterized in that The comparison module extracts the facial features in the facial information through an algorithm model in the following manner: The competition platform extracts facial contour, eyes, nose and / or mouth information from the face information through an algorithm model.

10. The device according to claim 9, characterized in that The comparison module compares the facial features with the player's reserved information in the following manner: Calculate a first threshold value according to the facial features, and calculate a second threshold value information according to the player reserved information; The difference between the first threshold and the second threshold is calculated, and if the absolute value of the difference is less than a preset value, the comparison is passed.

Citation Information

Patent Citations

  • Anti-cheating remote online examination method and system

    CN103208212A

  • A dynamic face recognition and comparison method

    CN109670490A

  • Online examination cheating monitoring method and device

    CN111382672A

  • Method and device for preventing examination cheating, electronic equipment and computer readable medium

    CN112633189A

  • Examination monitoring method and device, examination computer and storage medium

    CN114550106A