A face authentication method, device and equipment based on a WebPortal and a switch application face middle station grouping, and a medium

Abstract

The application discloses a face authentication method, device and equipment based on a WebPortal and a switch application face middle platform grouping, and a medium, relates to the technical field of face authentication, and the method receives an authentication request sent by a user terminal redirected to an access switch; the authentication request is realized through a redirection uniform resource locator, and the uniform resource locator carries a user group parameter; the user group parameter is used for identifying a user group corresponding to a port accessed by the user terminal; face information uploaded by the user terminal is collected according to the authentication request; the face information and the user group parameter are sent to a face recognition middle platform, so that the face recognition middle platform performs 1:N comparison on the face information in a user group corresponding to the user group parameter; an authentication result returned by the middle platform is received; when the authentication result is authentication passed, a release instruction is issued to the access switch, so that the access switch releases a MAC address corresponding to the user terminal. The method can perform grouped face authentication in a specified user group.

Description

Technical Field

[0001] This application relates to the field of face authentication technology, and in particular to a method, apparatus, device and medium for group face authentication based on a face middleware platform for WebPortal and switch applications. Background Technology

[0002] With the continuous development of information technology, the demand for security management of access users in scenarios such as campus networks, enterprise intranets, and other similar environments is increasing. Face recognition-based passwordless authentication for internet access, due to its combination of security and convenience, is gradually becoming one of the important technical means in the field of network access control. In a typical web authentication internet access scenario, the user terminal connects to the network through an access switch. After successful authentication, the switch allows the user terminal's media access control address, enabling the user to access network resources normally.

[0003] Currently, existing access authentication schemes combining facial recognition and WebPortal typically employ the following process: When a user terminal accesses a webpage, the access switch redirects the request to the WebPortal server. After completing face capture and liveness detection, the WebPortal server sends the facial information to the facial recognition platform. The facial recognition platform performs a 1:N comparison against the full facial database. Upon successful authentication, the WebPortal server notifies the access switch to grant the user terminal's Media Access Control (MAC) address. This scheme is suitable for general access scenarios with a unified database and unified authentication policy. Furthermore, although the facial recognition platform supports classifying users into different groups and maintaining independent facial feature databases, this capability is not effectively utilized in the access authentication process.

[0004] However, in the above-mentioned scenarios, the face recognition platform can only perform full-database 1:N comparisons and cannot perform grouped face authentication within a specified user group. Summary of the Invention

[0005] This application provides a method, apparatus, device, and medium for group face authentication based on a WebPortal and switch application face middleware, which can perform group face authentication within a specified user group.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, this application provides a grouped face authentication method based on a face recognition platform for WebPortal and switch applications, applicable to WebPortal server and switch authentication internet access scenarios, including: The system receives an authentication request redirected from the access switch to the Internet terminal. The authentication request is implemented by redirecting a Uniform Resource Locator (URL) and the URL carries a user group parameter. The user group parameter is used to identify the user group corresponding to the port accessed by the user terminal. Based on the authentication request, the facial information uploaded by the user terminal is collected; The facial information and the user group parameters are sent to the facial recognition platform so that the facial recognition platform can perform a 1:N comparison of the facial information within the user group corresponding to the user group parameters. Receive the authentication result returned by the face recognition platform; When the authentication result is successful, a pass command is issued to the access switch so that the access switch can allow the MAC address corresponding to the user terminal.

[0007] Optionally, when the authentication result is successful, it includes: The face recognition platform compares the face information with the face database of each face in the user group in a 1:N ratio to obtain N similarity scores. The face recognition platform selects the highest score from N similarity scores; When the highest score is greater than or equal to the preset threshold, the authentication result is successful.

[0008] Optionally, the method further includes: When the highest score is less than the preset threshold, or when there is no face database in the user group that matches the face information, the authentication result is authentication failure.

[0009] Optionally, before sending the facial information and the user group parameters to the facial recognition platform, the method further includes: The collected facial information is subjected to image quality detection; If the facial information fails the image quality detection, a prompt to re-collect the image is returned to the user terminal.

[0010] Optionally, the step of performing image quality detection on the collected facial information includes: Calculate the image sharpness score, face pose score, illumination uniformity score, and occlusion ratio score of the facial information; The comprehensive quality score of the facial information is obtained based on the image sharpness score, the first weighting coefficient, the facial pose score, the second weighting coefficient, the illumination uniformity score, the third weighting coefficient, the occlusion ratio score, and the fourth weighting coefficient.

[0011] Optionally, when the facial information fails the image quality detection, returning a prompt to the user terminal for re-collection includes: The overall quality score is compared with a preset overall quality threshold. When the overall quality score is less than the preset overall quality threshold, it is determined that the face information has failed the image quality detection, and a prompt to re-collect is returned to the user terminal.

[0012] Optionally, the method further includes: When the authentication result is that the authentication fails, a blocking command is sent to the access switch so that the access switch maintains the blocking state against the user terminal.

[0013] Secondly, this application provides a grouped face authentication device based on a WebPortal and switch application face middleware platform, comprising: The receiving module is used to receive authentication requests sent by internet access terminals via redirection from the access switch; the authentication request is implemented through a redirected Uniform Resource Locator (URL) and the URL carries user group parameters; the user group parameters are used to identify the user group corresponding to the port accessed by the user terminal. The data acquisition module is used to acquire the facial information uploaded by the user terminal according to the authentication request. The sending module is used to send the face information and the user group parameters to the face recognition platform, so that the face recognition platform can perform a 1:N comparison of the face information within the user group corresponding to the user group parameters; The receiving module is used to receive the authentication result returned by the face recognition platform; The processing module is used to issue a pass command to the access switch when the authentication result is successful, so that the access switch can allow the MAC address corresponding to the user terminal.

[0014] Thirdly, this application provides a computing device, including a memory and a processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of the first aspects.

[0015] Fourthly, this application provides a computer-readable storage medium for storing a computer program for performing the method as described in any one of the first aspects.

[0016] As can be seen from the above technical solution, this application has at least the following beneficial effects: This application provides a group-based face authentication method using a face recognition platform based on WebPortal and a switch. The access switch adds user group parameters to the redirected Uniform Resource Locator (URI) according to the nass-group field configured on its port. The WebPortal server extracts these user group parameters from the received URI and sends them along with the collected face information to the face recognition platform. This allows the face recognition platform to perform a 1:N comparison of the face information within the user group corresponding to the user group parameter. Compared to existing technologies, this application, by carrying user group parameters in the redirected URI, enables the group information configured on the access switch port to be transmitted to both the WebPortal server and the face recognition platform. This allows the face recognition platform to perform authentication within a specified user group, avoiding the problem of only being able to perform a full-database 1:N comparison and not being able to perform group-based face authentication within a specified user group. This satisfies the requirements for fine-grained access control based on region and identity.

[0017] Furthermore, before sending face information to the face recognition platform, the WebPortal server performs image quality checks on the collected face information. It calculates a comprehensive quality score by weighting and summing image sharpness, face pose, illumination uniformity, and occlusion ratio scores. Face information is only sent to the face recognition platform when the comprehensive quality score reaches a preset threshold, preventing low-quality images from consuming comparison resources. After receiving the authentication result from the face recognition platform, the WebPortal server determines authentication success by checking if the highest similarity score among the N similarity scores obtained from a 1:N comparison of face information with various face databases within a specified user group is greater than or equal to a preset threshold. Authentication fails if the highest score is less than the preset threshold or if no matching database exists within the user group, avoiding mismatches and incorrect access caused by searching the entire database. When authentication fails, the WebPortal server sends a blocking command to the access switch, maintaining the access switch's blocking status for the user terminal and ensuring that users who fail group authentication cannot access network resources.

[0018] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0019] Figure 1 A schematic diagram illustrating an application scenario provided in an embodiment of this application; Figure 2 A flowchart illustrating a grouped face authentication method based on a face middleware platform for WebPortal and switch applications, provided in this application embodiment; Figure 3 A schematic diagram of a grouped face authentication device based on a WebPortal and switch application face middleware provided in this application embodiment; Figure 4 This is a schematic diagram of a computing device provided in an embodiment of this application. Detailed Implementation

[0020] The terms "first," "second," and "third," etc., used in this application specification and accompanying drawings are used to distinguish different objects, not to limit a specific order.

[0021] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0022] To ensure clarity and conciseness in the description of the following embodiments, a brief introduction to the related technologies is given first: The WebPortal server is a server device that provides the network access authentication page, responsible for authentication interaction with user terminals and data communication with the face recognition platform. The access switch is a switching device located at the network access layer, used to connect user terminals and perform port-level flow control.

[0023] In the scenario of group face authentication using a face recognition platform in WebPortal and switch applications, the user group information of the user terminal's access port cannot be carried during the redirection of the access switch. As a result, the face recognition platform can only perform full database 1:N comparison and cannot perform group face authentication within a specified user group.

[0024] The technical problem arises because when the access switch redirects the user terminal's Hypertext Transfer Protocol (HTTP) request to the WebPortal server, it only points the request to the WebPortal server's Uniform Resource Locator (URL) without setting parameters for transmitting port group information in the redirected URL. As a result, the user group identifier of the port accessed by the user terminal cannot reach the WebPortal server along with the authentication request. Because the WebPortal server cannot obtain this user group identifier, it can only transmit face information and not group parameters when sending a comparison request to the face recognition platform. Consequently, the face recognition platform cannot determine the comparison range and can only perform a 1:N search in the global face database, ultimately leading to the inability to achieve group-level face authentication.

[0025] In view of this, this application provides a grouped face authentication method based on WebPortal and a switch application face middleware, which can be executed by the WebPortal server.

[0026] To address the technical issue that the access group identifier cannot be transmitted to the face recognition platform in existing WebPortal face access authentication schemes, this application proposes to carry user group parameters in the redirected Uniform Resource Locator (URL) of the access switch. These user group parameters are then sent to the WebPortal server along with the face information, enabling the face recognition platform to perform a 1:N comparison of the face information within the user group corresponding to the user group parameter. This invention achieves the integration of access switch port grouping configuration with the face recognition platform's user group capabilities, thereby meeting the requirements for fine-grained access control based on region and identity.

[0027] To make the technical solution of this application clearer and easier to understand, the application scenarios of the technical solution of this application are described below with reference to the accompanying drawings. Figure 1 As shown in the figure, this figure is a schematic diagram of an application scenario provided by an embodiment of this application.

[0028] In this application scenario, the user terminal connects to an access switch. The access switch is configured with a `nass-group` field, which identifies the user group corresponding to the port the user terminal is connected to. When the user terminal accesses a webpage, the access switch intercepts the user terminal's Hypertext Transfer Protocol (HTTP) request and returns a Redirect Uniform Resource Locator (URL) to the user terminal. This URL carries user group parameters generated by the access switch based on the `nass-group` field. The user terminal initiates an authentication request to the WebPortal server based on the URL. The WebPortal server extracts the user group parameters from the authentication request and provides a face capture page to the user terminal. The user terminal uploads facial information through the face capture page. After collecting the facial information, the WebPortal server sends the facial information and user group parameters to the face recognition platform. The face recognition platform determines the corresponding user group based on the user group parameters and performs a 1:N comparison of the facial information in the face database within that user group to obtain the authentication result, which is then returned to the WebPortal server. When the authentication result is successful, the WebPortal server issues a pass command to the access switch, and the access switch allows the MAC address corresponding to the user terminal to pass according to the pass command.

[0029] To make the technical solution of this application clearer and easier to understand, the following describes a grouped face authentication method based on a face middleware platform for WebPortal and switch applications, using the above application scenarios as an example. Figure 2 As shown, this figure is a flowchart of a grouped face authentication method based on a face recognition platform for WebPortal and switch applications provided in an embodiment of this application. In this embodiment, the method includes: S201. The WebPortal server receives the authentication request redirected to the user terminal by the access switch. The authentication request is implemented through a redirected Uniform Resource Locator (URL), and the URL carries user group parameters. The user group parameters are used to identify the user group corresponding to the port accessed by the user terminal.

[0030] The authentication request is initiated when a user terminal accesses a webpage through a browser. The access switch redirects this access request to the WebPortal server, which then treats the received redirected request as an authentication request. The redirection Uniform Resource Locator (URL) is the URL returned by the access switch to the user terminal. This URL points to the WebPortal server, and the user terminal is automatically redirected to this address to access the WebPortal server. The user group parameter is generated by the access switch based on the nass-group field configured on its port. It identifies the user group corresponding to the port the user terminal is connected to. A user group is a collection of users categorized by access area or identity type, and each user group corresponds to an independent facial feature database within the face recognition platform.

[0031] The access switch intercepts Hypertext Transfer Protocol (HTTP) requests sent by user terminals when accessing web pages. Based on the nass-group field configured on its port, the access switch generates a redirected Uniform Resource Locator (URI), which carries user group parameters. The access switch returns this redirected URI to the user terminal. The user terminal then initiates a request to the WebPortal server based on this redirected URI. The WebPortal server receives this request as an authentication request. Upon receiving the authentication request, the WebPortal server extracts the user group parameters from the URI contained in the authentication request, thereby determining the user group corresponding to the port accessed by the user terminal.

[0032] S202. The WebPortal server collects facial information uploaded by the user terminal based on the authentication request.

[0033] Facial information is facial image data that is collected and uploaded by the user terminal through the camera.

[0034] After receiving the authentication request, the WebPortal server returns a face capture page to the user terminal. Upon receiving the face capture page, the user terminal uses the camera's image capture function to capture an image of the user's face and uploads the captured facial information to the WebPortal server.

[0035] The method also includes: The WebPortal server performs image quality checks on the collected facial information; if the facial information fails the image quality check, it returns a prompt to the user terminal to re-collect the information.

[0036] In some embodiments, the WebPortal server calculates image sharpness score, face pose score, illumination uniformity score, and occlusion ratio score for the face information; based on the image sharpness score, a first weighting coefficient, face pose score, a second weighting coefficient, illumination uniformity score, a third weighting coefficient, occlusion ratio score, and a fourth weighting coefficient, it obtains a comprehensive quality score for the face information. The comprehensive quality score is compared with a preset comprehensive quality threshold; if the comprehensive quality score is less than the preset comprehensive quality threshold, it is determined that the face information has failed the image quality detection, and a prompt for re-collection is returned to the user terminal.

[0037] Image sharpness score is a numerical value used to evaluate the sharpness of a facial image, representing the degree to which facial texture details are discernible. Face pose score is a numerical value used to evaluate the degree of facial deflection in an image, representing whether the user's face orientation relative to the camera is within a recognizable range. Illumination uniformity score is a numerical value used to evaluate the uniformity of illumination distribution in a facial image, representing whether there is overexposure, underexposure, or uneven brightness in the image. Occlusion ratio score is a numerical value used to evaluate the degree of facial occlusion in a facial image, representing whether there are missing facial areas due to masks, glasses, hair, or other objects. The first weighting coefficient is the weight of the image sharpness score in the overall quality score. The second weighting coefficient is the weight of the face pose score in the overall quality score. The third weighting coefficient is the weight of the illumination uniformity score in the overall quality score. The fourth weighting coefficient is the weight of the occlusion ratio score in the overall quality score. The overall quality score is a weighted sum of image sharpness, face pose, illumination uniformity, and occlusion ratio scores, representing the overall quality level of the face image. The preset overall quality threshold is a pre-defined lower limit for the overall quality score, used to determine whether the face information meets the comparison requirements.

[0038] The WebPortal server first calculates the image sharpness score, face pose score, illumination uniformity score, and occlusion ratio score for the facial information. When calculating the image sharpness score, the WebPortal server iterates through every pixel in the face image, calculates the grayscale change rate of each pixel in the horizontal and vertical directions, squares the grayscale change rates of all pixels, and then averages the sum to obtain the image sharpness score. The expression for the image sharpness score is:

[0039] in, Indicates the image sharpness score. Represents the number of pixels in a face image. grayscale value at that location The height of the face image, in pixels. The width of the face image, in pixels. Represents pixels The gradient in the horizontal direction, Represents pixels The gradient in the vertical direction.

[0040] When calculating the facial pose score, the WebPortal server locates key points such as the eyes, nose tip, and mouth in the facial image. Based on the two-dimensional coordinates of these key points, it calculates the yaw, pitch, and roll angles of the user's face relative to the camera. The facial pose score is obtained based on the degree of deviation of these angles from the maximum pose score. The maximum pose score is a preset value.

[0041] The expression for face pose scoring is:

[0042] in, This indicates the facial pose score. This represents the maximum value of the posture score. This indicates the yaw angle, representing the angle by which the face deflects left or right around the vertical axis. This represents the pitch angle, which indicates the angle by which the face rotates up and down around the horizontal axis. The roll angle indicates the angle at which the face tilts around its front-to-back axis. The scale parameter represents the attitude score and is used to adjust the sensitivity of the attitude score to changes in angle.

[0043] When calculating the illumination uniformity score, the WebPortal server extracts all pixels in the face region, calculates the mean and variance of the pixel grayscale values, and obtains the illumination uniformity score based on how well the mean and variance of the face region's pixel grayscale values ​​satisfy the maximum illumination uniformity score. The maximum illumination uniformity score is a preset value.

[0044] The expression for the illumination uniformity score is:

[0045] in, This indicates the score for uniformity of illumination. This represents the average grayscale value of all pixels in the face region. This represents the variance of the grayscale values ​​of all pixels in the face region. This represents the maximum value of the illumination uniformity score.

[0046] When calculating the occlusion ratio score, the WebPortal server identifies facial gaps caused by masks, glasses, hair, or other objects. It calculates the proportion of the occluded area to the total face area and multiplies this proportion by the maximum occlusion ratio score to obtain the final occlusion ratio score. This maximum occlusion ratio score is a preset value.

[0047] The expression for the occlusion ratio score is:

[0048] in, The score indicates the occlusion ratio. This indicates the area of ​​the obscured region within the face area. This represents the area of ​​the entire face region. This represents the maximum value of the occlusion ratio score.

[0049] The WebPortal server performs a weighted summation of the product of image sharpness score and a first weighting coefficient, the product of face pose score and a second weighting coefficient, the product of illumination uniformity score and a third weighting coefficient, and the product of occlusion ratio score and a fourth weighting coefficient to obtain a comprehensive quality score for the face information. This comprehensive quality score characterizes the overall quality level of the face image.

[0050] The expression for the overall quality score is:

[0051] in, This indicates the overall quality score. Indicates the image sharpness score. This indicates the facial pose score. This indicates the score for uniformity of illumination. The score indicates the occlusion ratio. This represents the first weighting coefficient. This represents the second weighting coefficient. This represents the third weighting coefficient. This represents the fourth weighting coefficient.

[0052] The WebPortal server compares the overall quality score with a preset overall quality threshold. When the overall quality score is less than the preset threshold, it indicates that the overall quality of the face image does not meet the acceptable standard, and the WebPortal server determines that the face information has failed the image quality detection and returns a prompt to the user terminal to re-capture the image. When the overall quality score is greater than or equal to the preset overall quality threshold, it indicates that the overall quality of the face image meets the acceptable standard, and the WebPortal server determines that the face information has passed the image quality detection.

[0053] S203. The WebPortal server sends the face information and user group parameters to the face recognition platform, so that the face recognition platform can perform a 1:N comparison of the face information within the user group corresponding to the user group parameters.

[0054] 1:N comparison is the process of comparing a face image with N face databases one by one to obtain N similarity scores.

[0055] The WebPortal server sends the collected facial information and user group parameters extracted from the redirected Uniform Resource Locator (URL) to the face recognition platform. Upon receiving the user group parameters, the face recognition platform determines the corresponding user group and defines the facial feature database corresponding to that user group as the retrieval scope for face comparison. The face recognition platform uses each face database within this feature database as a comparison object, performing a 1:N comparison between the collected facial information and each face database within the user group, calculating the similarity between the collected facial information and each face database, and obtaining N similarity scores. These N similarity scores respectively represent the degree of similarity between the collected facial information and each face database within the user group.

[0056] S204. The WebPortal server receives the authentication result returned by the face recognition platform.

[0057] After performing a 1:N comparison of facial information within a user group, the face recognition platform generates an authentication result based on the relationship between the highest similarity score among the N similarity scores obtained and a preset threshold. The face recognition platform then returns this authentication result to the WebPortal server, which receives it. This authentication result indicates whether the collected facial information has passed the authentication process of the face recognition platform.

[0058] S205. When the authentication result is successful, the WebPortal server issues a pass command to the access switch so that the access switch can allow the MAC address corresponding to the user terminal.

[0059] In some embodiments, the face recognition platform compares the face information with the face database of each user group in a 1:N ratio to obtain N similarity scores; the face recognition platform selects the highest score from the N similarity scores; when the highest score is greater than or equal to a preset threshold, the authentication result is successful.

[0060] The similarity score is a numerical value representing the degree of similarity between facial information and a single facial database. A higher similarity score indicates that the collected facial information is more similar to the faces in the database; a lower similarity score indicates that the collected facial information is less similar to the faces in the database.

[0061] The face recognition platform extracts feature vectors from the collected facial information and calculates the cosine similarity between each feature vector and the feature vectors of each face database within the user group, resulting in N similarity scores. The face recognition platform selects the score with the highest value from the N similarity scores as the best match between the facial information and the entire user group.

[0062] Calculate the similarity score between the collected facial information and the facial databases of each user group:

[0063] in, This indicates that the facial information is related to the first user in the user group. Similarity scores between individual face databases The feature vector representing the collected facial information. Indicates the number of users in the group Feature vectors from a personal face database Representing the eigenvector With feature vectors dot product, Representing the eigenvector The length of the mold, Representing the eigenvector The length of the module.

[0064] Select the highest score from N similarity scores:

[0065] in, This represents the highest score selected from N similarity scores.

[0066] The face recognition platform compares the highest score with a preset threshold. When the highest score is greater than or equal to the preset threshold, it indicates that the collected face information exists in the face database within the user group, and the face recognition platform determines the authentication result as successful. When the WebPortal server receives the authentication result as successful, it generates a permission command, which contains the MAC address corresponding to the user terminal. The WebPortal server sends this permission command to the access switch. After receiving the permission command, the access switch determines the user terminal that needs to be allowed access based on the MAC address carried in the permission command and allows the network traffic of the user terminal corresponding to that MAC address.

[0067] When the highest score is less than the preset threshold, or when there is no matching face database within the user group, the authentication result is "authentication failed." When the highest score is less than the preset threshold, it means that the similarity between the collected face information and all face databases within the user group does not meet the judgment criteria, and the face recognition platform determines the authentication result as "authentication failed."

[0068] Furthermore, before performing a 1:N comparison between the collected facial information and the facial databases within the user group, the facial recognition platform first determines whether a matching facial database exists within the user group. If no matching facial database exists within the user group, it indicates that the user is not registered in that user group, and the facial recognition platform directly determines the authentication result as unsuccessful, without needing to perform subsequent 1:N comparison operations.

[0069] When authentication fails, a blocking command is sent to the access switch to maintain the blocking status for the user terminal. When the WebPortal server receives an authentication failure result, it generates a blocking command and sends it to the access switch. Upon receiving the blocking command, the access switch maintains the blocking status for the user terminal, preventing network traffic from passing through.

[0070] Based on the above description, this application has the following beneficial effects: This application provides a group-based face authentication method using a face recognition platform based on WebPortal and a switch. The access switch adds user group parameters to the redirected Uniform Resource Locator (URI) according to the nass-group field configured on its port. The WebPortal server extracts these user group parameters from the received URI and sends them along with the collected face information to the face recognition platform. This allows the face recognition platform to perform a 1:N comparison of the face information within the user group corresponding to the user group parameter. Compared to existing technologies, this application, by carrying user group parameters in the redirected URI, enables the group information configured on the access switch port to be transmitted to both the WebPortal server and the face recognition platform. This allows the face recognition platform to perform authentication within a specified user group, avoiding the problem of only being able to perform a full-database 1:N comparison and not being able to perform group-based face authentication within a specified user group. This satisfies the requirements for fine-grained access control based on region and identity.

[0071] The above text combined Figures 1 to 2 This application provides a detailed description of the face authentication method based on WebPortal and switch application face middleware provided in the embodiments of this application. The apparatus and devices provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0072] like Figure 3 As shown in the figure, this is a schematic diagram of a group face authentication device based on a WebPortal and switch application face middleware according to an embodiment of this application. The device includes: The receiving module 301 is used to receive an authentication request sent by a user terminal via a redirection from the access switch; the authentication request is implemented by redirecting a Uniform Resource Locator (URL) and the URL carries a user group parameter; the user group parameter is used to identify the user group corresponding to the port accessed by the user terminal. The acquisition module 302 is used to acquire the facial information uploaded by the user terminal according to the authentication request; The sending module 303 is used to send the face information and the user group parameters to the face recognition platform, so that the face recognition platform can perform a 1:N comparison of the face information in the user group corresponding to the user group parameters; The receiving module 301 is used to receive the authentication result returned by the face recognition platform; The processing module 304 is used to issue a pass command to the access switch when the authentication result is successful, so that the access switch can allow the MAC address corresponding to the user terminal.

[0073] Optionally, the processing module 304 is specifically used for the face recognition platform to perform a 1:N comparison between the face information and the face database of each face in the user group to obtain N similarity scores; The face recognition platform selects the highest score from N similarity scores; When the highest score is greater than or equal to the preset threshold, the authentication result is successful.

[0074] Optionally, the processing module 304 is also configured to determine that the authentication result is unsuccessful when the highest score is less than a preset threshold or when there is no face database matching the face information in the user group.

[0075] Optionally, the processing module 304 is also used to perform image quality detection on the collected face information; If the facial information fails the image quality detection, a prompt to re-collect the image is returned to the user terminal.

[0076] Optionally, the processing module 304 is specifically used to calculate the image sharpness score, face pose score, illumination uniformity score, and occlusion ratio score of the face information. The comprehensive quality score of the facial information is obtained based on the image sharpness score, the first weighting coefficient, the facial pose score, the second weighting coefficient, the illumination uniformity score, the third weighting coefficient, the occlusion ratio score, and the fourth weighting coefficient.

[0077] Optionally, the processing module 304 is specifically used to compare the comprehensive quality score with a preset comprehensive quality threshold. When the overall quality score is less than the preset overall quality threshold, it is determined that the face information has failed the image quality detection, and a prompt to re-collect is returned to the user terminal.

[0078] Optionally, the processing module 304 is further configured to send a blocking command to the access switch when the authentication result is authentication failure, so that the access switch maintains the blocking state against the user terminal.

[0079] The face authentication device based on WebPortal and switch application face middleware according to the embodiments of this application can correspondingly execute the method described in the embodiments of this application, and the other operations and / or functions of each module / unit of the face authentication device based on WebPortal and switch application face middleware are respectively for implementing Figure 2 For the sake of brevity, the corresponding processes of each method in the illustrated embodiments will not be described in detail here.

[0080] This application also provides a computing device. For example... Figure 4 As shown in the figure, this is a schematic diagram of a computing device provided in an embodiment of this application. The computing device 400 includes a bus 401, a processor 402, a communication interface 403, and a memory 404. The processor 402, the memory 404, and the communication interface 403 communicate with each other via the bus 401.

[0081] Bus 401 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0082] Processor 402 can be any one or more of the following processors: central processing unit (CPU), graphics processing unit (GPU), microprocessor (MP), or digital signal processor (DSP).

[0083] Communication interface 403 is used for communication with external devices.

[0084] Memory 404 may include volatile memory, such as random access memory (RAM). Memory 404 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0085] The memory 404 stores executable code, and the processor 402 executes the executable code to perform the aforementioned group face authentication method based on the face middleware of WebPortal and switch application.

[0086] Specifically, in achieving Figure 3 In the case of the illustrated embodiment, and Figure 3 When the modules or units of the face authentication device based on WebPortal and switch application grouping described in the embodiments are implemented in software, the execution... Figure 3 The software or program code required for the functions of each module / unit can be partially or entirely stored in memory 404. Processor 402 executes the program code corresponding to each unit stored in memory 404, and executes the aforementioned group face authentication method based on WebPortal and switch application face middleware.

[0087] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct the computing device to execute the aforementioned grouped face authentication method based on the WebPortal and switch application face middleware platform.

[0088] This application also provides a computer program product comprising one or more computer instructions. When the computer instructions are loaded and executed on a computing device, all or part of the processes or functions described in this application are generated.

[0089] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, or data center to another website, computer, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0090] When the computer program product is executed by a computer, the computer executes any of the aforementioned methods of the face authentication method based on WebPortal and switch application face middleware. The computer program product can be a software installation package; when any of the aforementioned methods of the face authentication method based on WebPortal and switch application face middleware are required, the computer program product can be downloaded and executed on the computer.

[0091] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0092] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.

Claims

1. A group-based face authentication method based on a face recognition platform using WebPortal and a switch, applied to a WebPortal server and switch authentication internet access scenario, characterized in that... The method includes: The system receives an authentication request redirected to the user terminal by the access switch. The authentication request is implemented through a redirected Uniform Resource Locator (URL) and the URL carries a user group parameter. The user group parameter is used to identify the user group corresponding to the port accessed by the user terminal. Based on the authentication request, the facial information uploaded by the user terminal is collected; The facial information and the user group parameters are sent to the facial recognition platform so that the facial recognition platform can perform a 1:N comparison of the facial information within the user group corresponding to the user group parameters. Receive the authentication result returned by the face recognition platform; When the authentication result is successful, a pass command is issued to the access switch so that the access switch can allow the MAC address corresponding to the user terminal.

2. The method according to claim 1, characterized in that, When the authentication result is successful, it includes: The face recognition platform compares the face information with the face database of each face in the user group in a 1:N ratio to obtain N similarity scores. The face recognition platform selects the highest score from N similarity scores; When the highest score is greater than or equal to the preset threshold, the authentication result is successful.

3. The method according to claim 2, characterized in that, The method further includes: When the highest score is less than the preset threshold, or when there is no face database in the user group that matches the face information, the authentication result is authentication failure.

4. The method according to claim 1, characterized in that, Before sending the facial information and the user group parameters to the facial recognition platform, the method further includes: The collected facial information is subjected to image quality detection; If the facial information fails the image quality detection, a prompt to re-collect the image is returned to the user terminal.

5. The method according to claim 4, characterized in that, The step of performing image quality detection on the collected facial information includes: Calculate the image sharpness score, face pose score, illumination uniformity score, and occlusion ratio score of the facial information; The comprehensive quality score of the facial information is obtained based on the image sharpness score, the first weighting coefficient, the facial pose score, the second weighting coefficient, the illumination uniformity score, the third weighting coefficient, the occlusion ratio score, and the fourth weighting coefficient.

6. The method according to claim 4, characterized in that, The step of returning a prompt for re-collection to the user terminal when the facial information fails the image quality detection includes: The overall quality score is compared with a preset overall quality threshold. When the overall quality score is less than the preset overall quality threshold, it is determined that the face information has failed the image quality detection, and a prompt to re-collect is returned to the user terminal.

7. The method according to claim 1, characterized in that, The method further includes: When the authentication result is that the authentication fails, a blocking command is sent to the access switch so that the access switch maintains the blocking state against the user terminal.

8. A face authentication device based on a WebPortal and switch application face middleware, applied to WebPortal server and switch authentication internet access scenarios, characterized in that, The device includes: The receiving module is used to receive authentication requests sent by user terminals via redirection from the access switch; the authentication request is implemented through a redirected Uniform Resource Locator (URL) and the URL carries user group parameters; the user group parameters are used to identify the user group corresponding to the port accessed by the user terminal. The data acquisition module is used to acquire the facial information uploaded by the user terminal according to the authentication request. The sending module is used to send the face information and the user group parameters to the face recognition platform, so that the face recognition platform can perform a 1:N comparison of the face information within the user group corresponding to the user group parameters; The receiving module is used to receive the authentication result returned by the face recognition platform; The processing module is used to issue a pass command to the access switch when the authentication result is successful, so that the access switch can allow the MAC address corresponding to the user terminal.

9. A computing device, characterized in that, Including memory and processor; The memory stores one or more computer programs, the one or more computer programs including instructions; when the instructions are executed by the processor, the computing device performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for performing the method as described in any one of claims 1 to 7.

Images