CN114550265A - Image processing method, face recognition method and system - Google Patents

Abstract

The present disclosure relates to an image processing method, a face recognition method and a system, wherein the image processing method is applied to a server and comprises the following steps: receiving a feature extraction request sent by a data platform, wherein the feature extraction request comprises a target face image and a model version identifier, and the model version identifier is used for indicating a face recognition model; based on the model version identification, calling a corresponding feature extraction algorithm to extract features of the target face image to obtain reference face features of the target face image determined based on the model version identification, wherein the reference face features of the target face image determined based on the model version identification are used for carrying out face recognition on a target user corresponding to the target face image on a target terminal of a face recognition model indicated by the model version identification; and deleting the target face image in the local cache. The embodiment of the disclosure can effectively improve the data security in the face recognition process and reduce the risk of personal privacy leakage.

Description

Image processing method, face recognition method and system

technical field

The present disclosure relates to the technical field of computer vision, and in particular, to an image processing method, a face recognition method and a system.

Background technique

At present, in the face recognition application of the traffic scene, the reference face image needs to be sent to the server, the server stores the reference face image, and sends the reference face image to the front-end device synchronously, so that the front-end device can base on the reference face image. The images are compared with face features to realize face recognition.

SUMMARY OF THE INVENTION

The present disclosure provides technical solutions of an image processing method, a face recognition method and a system.

According to an aspect of the present disclosure, an image processing method is provided, the method is applied to a server, and the method includes: receiving a feature extraction request sent by a data platform, wherein the feature extraction request includes a target face image, Model version identification, the model version identification is used to indicate the face recognition model; based on the model version identification, call the corresponding feature extraction algorithm, perform feature extraction on the target face image, and obtain the target face image based on The reference face feature determined by the model version identifier, wherein the target face image is based on the reference face feature determined by the model version identifier, and is used in the target face recognition model with the model version identifier indicated. On the terminal, face recognition is performed on the target user corresponding to the target face image; and the target face image in the local cache is deleted.

In a possible implementation manner, the method further includes: sending the reference face feature determined by the target face image based on the model version identifier to the data platform; receiving the data platform sent by the data platform. The face recognition data of the target user and the permission information of the target user, wherein the face recognition data includes: the identity identifier of the target user, the model version identifier, the target user based on the model version Identify the determined reference facial features and the personal information of the target user.

In a possible implementation manner, the data platform includes: a portrait data platform and an information data platform; the face recognition data of the target user and the permission information of the target user sent by the data platform are received. , including: receiving the identity identifier of the target user, the model version identifier, and the reference face feature determined by the target user based on the model version identifier sent by the portrait data platform; receiving the information sent by the information data platform. Personal information of the target user, permission information of the target user

In a possible implementation manner, the method further includes: determining, based on the permission information of the target user, the target terminal to which the target user has face recognition authority; sending the face recognition data to the target terminal. the target terminal.

In a possible implementation manner, the method further includes: receiving a face recognition record of the target user sent by the target terminal, wherein the face recognition record includes: a snapshot of this face recognition The face map, the spatiotemporal information of this face recognition.

In a possible implementation manner, the method further includes: in the case of receiving the face recognition data of multiple target users sent by the data platform, according to the permission information of each target user The face recognition data of each target user is grouped and stored.

In a possible implementation manner, the method further includes: performing quality detection on the target face image; if the quality detection result of the target face image does not meet a preset quality condition, sending a The data platform sends an image update request. include:

According to an aspect of the present disclosure, an image processing method is provided, the method is applied to a data platform, and the method includes: acquiring a target face image of a target user; sending a feature extraction request to a server, wherein the feature extraction The request includes the target face image and the model version identification, the model version identification is used to indicate the face recognition model; the reference face determined based on the model version identification of the target face image sent by the server is received feature, wherein the target face image is based on the reference face feature determined by the model version ID, and is used to perform a human face recognition on the target user on the target terminal with the face recognition model indicated by the model version ID. face recognition; sending the target user's face recognition data and the target user's authority information to the server, wherein the face recognition data includes: the target user's identity identifier, the model version identifier , the reference face feature determined by the target user based on the model version identifier, and the personal information of the target user.

In a possible implementation manner, the data platform includes: a portrait data platform; the sending the face recognition data of the target user to the server includes: the portrait data platform determining the identity of the target user identification; the portrait data platform sends the identity identification of the target user, the model version identification, and the reference face feature determined by the target user based on the model version identification to the server.

In a possible implementation manner, the data platform includes: an information data platform; the sending to the server the face recognition data of the target user and the permission information of the target user includes: the information The data platform determines the personal information of the target user and the authority information of the target user based on the identity of the target user; the information data platform combines the personal information of the target user, the authority information of the target user, sent to the server.

In a possible implementation manner, the method further includes: receiving an image update request sent by the server; in response to the image update request, re-acquiring the face image of the target user, and using the re-acquired face image , and update the target face image.

According to an aspect of the present disclosure, a face recognition method is provided, the method is applied to a target terminal, the target terminal has a face recognition model indicated by the model version identifier, and the target user has a human face on the target terminal face recognition authority, the method includes: receiving the face recognition data of the target user sent by the server, the face recognition data including: the identity identifier of the target user, the model version identifier, the target user based on The model version identifies the determined reference face feature and the personal information of the target user; based on the face recognition data, face recognition is performed on the target user.

In a possible implementation manner, the performing face recognition on the target user based on the face recognition data includes: acquiring a captured face image of the user to be recognized for this face recognition; based on the face recognition data; For the face recognition model indicated by the model version identifier, feature extraction is performed on the captured face image of this face recognition to obtain the to-be-recognized face features of the to-be-recognized user; in the to-be-recognized user's to-be-recognized face, If it is successfully matched with the reference face feature of the target user, it is determined that the face recognition is successful this time.

In a possible implementation manner, the method further includes: desensitizing and displaying the personal information of the target user on the display screen of the target terminal.

In a possible implementation manner, the method further includes: generating a face recognition record of the target user based on the captured face image of this face recognition and the spatiotemporal information of this face recognition; The face recognition record of the target user is sent to the server.

According to an aspect of the present disclosure, a face recognition system is provided, wherein the face recognition system includes: a data platform, a server, and a target terminal, wherein: the target terminal obtains a target face image of a target user The target terminal sends a feature extraction request to the server, wherein the feature extraction request includes the target face image and the model version identifier; the server calls the corresponding feature extraction algorithm based on the model version identifier , perform feature extraction on the target face image, obtain the reference face feature determined by the target face image based on the model version identifier, and delete the target face image in the local cache; the target terminal receives The face recognition data of the target user sent by the server, where the face recognition data includes: the identity identifier of the target user, the model version identifier, and the reference determined by the target user based on the model version identifier face features and personal information of the target user; the target terminal performs face recognition on the target user based on the face recognition data.

In the embodiment of the present disclosure, the server receives the feature extraction request sent by the data platform, including the target face image and the model version identification, and calls the corresponding feature extraction algorithm based on the model version identification, performs feature extraction on the target face image, and obtains the target face image. The face image is based on the reference face feature determined by the model version ID, and the target face image in the local cache is deleted, wherein the target face image is based on the reference face feature determined by the model version ID. On the target terminal of the feature extraction algorithm, perform face recognition on the target user corresponding to the target face image. Because the server only performs feature extraction on the target face image based on the model version identification, and obtains the reference face features for subsequent face recognition without storing the target face image, so that only the target face image involving personal privacy is stored. Locally on the data platform, the data security in the face recognition process is effectively improved, and the risk of personal privacy leakage is reduced.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings.

Description of drawings

The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the technical solutions of the present disclosure.

1 shows a schematic diagram of a face recognition scene in the related art;

2 shows a schematic diagram of a face recognition scene according to an embodiment of the present disclosure;

FIG. 3 shows a flowchart of an image processing method according to an embodiment of the present disclosure;

4 shows a schematic diagram of a face recognition system according to an embodiment of the present disclosure;

FIG. 5 shows a flowchart of an image processing method according to an embodiment of the present disclosure;

FIG. 6 shows a flowchart of a face recognition method according to an embodiment of the present disclosure;

FIG. 7 shows a block diagram of a server according to an embodiment of the present disclosure;

8 shows a block diagram of a data platform according to an embodiment of the present disclosure;

FIG. 9 shows a block diagram of a target terminal according to an embodiment of the present disclosure;

10 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

FIG. 11 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures denote elements that have the same or similar functions. While various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" in this article is only an association relationship to describe the associated objects, indicating that there can be three kinds of relationships, for example, A and/or B, it can mean that A exists alone, A and B exist at the same time, and A and B exist independently B these three cases. In addition, the term "at least one" herein refers to any combination of any one of the plurality or at least two of the plurality, for example, including at least one of A, B, and C, and can mean including from A, B, and C. Any one or more elements selected from the set of B and C.

In addition, in order to better illustrate the present disclosure, numerous specific details are set forth in the following detailed description. It will be understood by those skilled in the art that the present disclosure may be practiced without certain specific details. In some instances, methods, means, components and circuits well known to those skilled in the art have not been described in detail so as not to obscure the subject matter of the present disclosure.

At present, in the face recognition application of the traffic scene, the reference face image needs to be sent to the server, the server stores the reference face image, and sends the reference face image to the front-end device synchronously, so that the front-end device can use the reference face image based on the reference face image. Perform face feature comparison to realize face recognition. Front-end equipment may refer to a target with face recognition function, such as face recognition access control machine, face recognition gate, etc.

FIG. 1 shows a schematic diagram of a face recognition scene in the related art. As shown in FIG. 1 , the face recognition scene includes a server 11 and a target terminal 12 . The reference face image is uploaded to the server 10 , the server 10 stores the reference face image, and sends the reference face image to the target terminal 20 synchronously. The target terminal 20 performs face feature comparison with the reference face image based on the face snapshot image collected by the user to be identified, so as to realize the face recognition of the user to be identified. However, since the reference face image needs to be stored in the server, there is a risk of personal privacy leakage.

FIG. 2 shows a schematic diagram of a face recognition scene according to an embodiment of the present disclosure. As shown in FIG. 2 , the face recognition scene in the embodiment of the present disclosure includes a server 21 , a data platform 22 , and a target terminal 23 . As shown in FIG. 2, the server 21 receives the feature extraction request sent by the data platform 22, including the target face image and the model version identification used to indicate the face recognition model, and the server 21 calls the corresponding feature extraction algorithm based on the model version identification. , perform feature extraction on the target face image to obtain the reference face feature determined based on the model version identification of the target face image, and the reference face feature determined based on the model version identification of the target face image is used for On the target terminal 23 of the face recognition model, face recognition is performed on the target user corresponding to the target face image.

Different target terminals may be produced by different manufacturers, resulting in different face recognition models in different target terminals. Therefore, in order to enable subsequent face recognition in the corresponding target terminals, the corresponding model version identification needs to be sent to the server. , so that the server extracts the corresponding reference face features based on the model version identifier.

In addition, after extracting and obtaining the reference face feature of the target face image determined based on the model version identifier, the server 21 deletes the target face image in the local cache, that is, the server 21 only performs the target face image based on the model version identifier. Feature extraction, without storing the target face image, nor sending the target face image to the target terminal 23, so that the target face image involving personal privacy is only stored locally on the data platform 22, effectively improving the face Data security in the identification process reduces the risk of personal privacy leakage.

The image processing method and the face recognition method provided by the embodiments of the present disclosure are described in detail below. The image processing method here is a method of preprocessing a face image to prepare for subsequent face recognition.

FIG. 3 shows a flowchart of an image processing method according to an embodiment of the present disclosure. This image processing method can be applied to the server 21 in FIG. 2 described above. As shown in Figure 3, the image processing method may include:

In step S31, a feature extraction request sent by the data platform is received, wherein the feature extraction request includes the target face image and the model version identifier.

The data platform here can be a platform dedicated to unified storage and management of data information, and the specific form of the data platform can be determined according to actual needs, which is not specifically limited in this disclosure.

In an example, when face recognition is applied to a school's passage of people, the data platform may be a school's student information management platform. FIG. 4 shows a schematic diagram of a face recognition system according to an embodiment of the present disclosure. The face recognition system shown in FIG. 4 is applied to the scene of people passing by the school. The data platform shown in FIG. 4 can be the student information management platform of the school, and students can upload their own face images and personal information to the data platform.

In order to achieve face recognition access, the data platform sends a feature extraction request to the server. Since the face recognition access scene may involve multiple different target terminals, that is, multiple face recognition models indicated by different model version identifiers, the feature In addition to the target face image, the extraction request also includes a model version identifier, so that the feature extraction algorithm corresponding to the face recognition model can be subsequently invoked to perform feature extraction.

In one example, the server may obtain multiple model version identifiers of all face recognition models included in its embedded or docked internal product/component/platform in advance, and send the multiple model version identifiers to the data platform, so that the When sending the feature extraction request, the data platform may select at least one model version identifier supported by the server and matching the target terminal.

In step S32, based on the model version identification, a corresponding feature extraction algorithm is invoked to perform feature extraction on the target face image to obtain a reference face feature determined based on the model version identification of the target face image, and the target face image is based on the model version identification. The determined reference face feature is used to perform face recognition on the target user corresponding to the target face image on the target terminal having the face recognition model indicated by the model version identifier.

Based on the model version ID included in the feature extraction, the server invokes the feature extraction algorithm corresponding to the face recognition model indicated by the model version ID, performs feature extraction on the target face image, and obtains the target face image determined based on the model version ID. With reference to the face feature, the reference face feature can be used subsequently to perform face recognition on the target user corresponding to the target face image on the target terminal having the face recognition model indicated by the model version identifier.

In one example, an extraction node is included in the server. The extraction node calls the corresponding feature extraction algorithm based on the model version identification to perform feature extraction on the target face image.

Taking the above FIG. 4 as an example, as shown in FIG. 4 , the server includes an extraction node, and the extraction node can directly call the feature extraction algorithm corresponding to the model version identifier embedded in the server to perform feature extraction on the target face image.

In an example, the server also includes an embedded intelligent IoT cloud platform. In the case where the server does not have a feature extraction algorithm corresponding to the embedded model version identifier, the extraction node can also call an external platform based on the intelligent IoT cloud platform. Connected with the server, the feature extraction algorithm corresponding to the face recognition model indicated by the model version identifier performs feature extraction on the target face image.

In step S33, delete the target face image in the local cache.

The server performs feature extraction on the target face image, and after obtaining the reference face feature of the target face image based on the model version identification, deletes the target face image in the local cache to ensure that the target face involving personal privacy is not stored in the server. images, reducing the risk of personal privacy leakage.

In the embodiment of the present disclosure, the server receives the feature extraction request sent by the data platform, including the target face image and the model version identification, and calls the corresponding feature extraction algorithm based on the model version identification, performs feature extraction on the target face image, and obtains the target face image. The face image is based on the reference face feature determined by the model version ID, and the target face image in the local cache is deleted, wherein the target face image is based on the reference face feature determined by the model version ID. On the target terminal of the face recognition model, perform face recognition on the target user corresponding to the target face image. Because the server only performs feature extraction on the target face image based on the model version identification, and obtains the reference face features for subsequent face recognition without storing the target face image, so that only the target face image involving personal privacy is stored. Locally on the data platform, the data security in the face recognition process is effectively improved, and the risk of personal privacy leakage is reduced.

In a possible implementation manner, the image processing method further includes: performing quality detection on the target face image; if the quality detection result of the target face image does not meet the preset quality conditions, sending an image update to the data platform ask.

After receiving the target face image included in the feature extraction request in the above step S31, before the feature extraction is performed, the quality detection of the target face image is performed first, and only if the quality detection result of the target face image meets the preset quality conditions In the case of , the subsequent feature extraction is performed to ensure the accuracy of the extracted reference face features.

In the case that the quality detection result of the target face image does not meet the preset quality conditions, the server may return an image update request to the data platform to request the data platform to resend the target face image until the quality of the latest sent target face image is reached. The test results meet the preset quality conditions.

The preset quality conditions may be set according to actual conditions, for example, face integrity, face clarity, etc., which are not specifically limited in the present disclosure.

In a possible implementation manner, the image processing method further includes: sending the reference face feature determined by the target face image based on the model version identification to the data platform; receiving the face recognition data of the target user sent by the data platform, and Permission information of the target user, wherein the face recognition data includes: the identity identifier of the target user, the model version identifier, the reference face feature determined by the target user based on the model version identifier, and the personal information of the target user.

The server returns the target face image based on the reference face features determined by the model version identification to the data platform. After the data integration of the data platform, the server receives the target user's face recognition data and the target user's permission information sent by the data platform. . The process of performing data integration on the data platform to determine the face recognition data of the target user and the permission information of the target user will be described in detail later in combination with possible implementations of the present disclosure, which will not be repeated here.

In a possible implementation manner, the data platform includes: a portrait data platform and an information data platform; receiving the face recognition data of the target user sent by the data platform and the permission information of the target user, including: receiving the target sent by the portrait data platform User's identity identifier, model version identifier, and reference face features determined by the target user based on the model version identifier; receive the personal information of the target user and the permission information of the target user sent by the information data platform.

The data platform may include a portrait data platform that specifically stores face images, and an information data platform that stores other information data. The server receives the target user's identity and model version identification sent by the portrait data platform, and the target user is determined based on the model version identification. Refer to the facial features, as well as the personal information of the target user and the permission information of the target user sent by the information data platform.

In an example, the data platform uses the identity identifier to distinguish the face images and other information data of different users stored in the portrait data platform and the information data platform.

Taking the above-mentioned Fig. 4 as an example, as shown in Fig. 4, the data platform (student information management platform) stores each student's student ID (identity identifier), model version identifier, and reference facial features determined based on the model version identifier in the portrait. The data platform stores each student's student number (identity identifier), name, ID number, access authority information (authority information), etc. on the information data platform.

Taking the above-mentioned FIG. 4 as an example, the server also includes an application node. After the application node receives the identity of the target user sent by the portrait data platform, the model version identifier, and the reference face feature determined by the target user based on the model version identifier, the target user The identity of the target user is returned to the data platform, so that the information data platform sends the personal information of the target user and the authority information of the target user to the server based on the identity of the target user, so that the server can complete the data of the target user's face recognition data. process, and store and store the face recognition data of the target user after the data is completed.

Taking the above-mentioned Fig. 4 as an example, as shown in Fig. 4, after the server receives the student numbers (identities) of multiple students sent by the portrait data platform, the model version identification, and the reference facial features determined based on the model version identification, the The student number of each student is returned to the student information management platform, so that the information data platform can search for the name, ID number, and access authority information of multiple students based on the student number of multiple students and send it to the server, so as to realize the server to multiple students. The face recognition data is processed for data completion.

The access authority information of different students may be different, and the communication authority information of different students may be set according to the actual situation, which is not specifically limited in this disclosure. For example, for student A (male), the access authority information includes: teaching building, library, male dormitory, etc.; for student B (female), the access authority information includes: teaching building, library, female dormitory, etc.

In a possible implementation manner, the image processing method further includes: in the case of receiving the face recognition data of multiple target users sent by the data platform, according to the permission information of each target user The face recognition data are grouped and stored.

In order to reasonably manage the face recognition data of multiple target users, the face recognition data of multiple target users may be grouped and stored according to the permission information of each target user.

In an example, face recognition data of target users with the same authority information are stored in the same group.

In an example, the server may receive a group identifier of each target user sent by the information data platform, and different group identifiers are used to indicate different groups. The server constructs different groups based on different group identifiers, and stores the face recognition data of each target user in the same group based on the group identifier of each user.

In a possible implementation manner, the image processing method further includes: determining, based on the permission information of the target user, a target terminal to which the target user has face recognition authority; and sending the face recognition data to the target terminal.

Based on the permission information of the target user, the server determines the target terminal to which the target user has face recognition authority, and then the server calls the intelligent IoT cloud platform to send the face recognition data to the target terminal, so that the target user can perform face recognition on the target terminal. identify.

For example, the target terminal is a face access control machine, and the target user can perform face recognition on the face access control machine, and pass after the recognition is successful.

In an example, the server may deliver all face recognition data in groups with the same authority information to the target terminal corresponding to the authority information.

In a possible implementation manner, the image processing method further includes: receiving a face recognition record of the target user sent by the target terminal, wherein the face recognition record includes: Spatiotemporal information of sub-face recognition.

After the target user performs face recognition on the target terminal, the target terminal can generate the face recognition record of this face recognition, and send the face recognition record of this face recognition to the server, so that the server can check the target user's face recognition record. The face recognition records are stored for subsequent review.

The spatiotemporal information of the current face recognition included in the face recognition record refers to the time information and spatial information of the current face recognition.

The face recognition record includes, in addition to the captured face image of this face recognition and the spatiotemporal information of this face recognition, other information that needs to be recorded and stored according to the actual situation, which is not specifically limited in this disclosure. .

FIG. 5 shows a flowchart of an image processing method according to an embodiment of the present disclosure. The image processing method can be applied to the data platform 22 in FIG. 2 described above. As shown in Figure 5, the image processing method may include:

In step S51, a target face image of the target user is acquired.

Target users collect face images based on their own terminal equipment and upload them to the data platform.

Taking the above Figure 4 as an example, as shown in Figure 4, students can use their own mobile phones to capture face images and upload them to the student information management platform.

In step S52, a feature extraction request is sent to the server, wherein the feature extraction request includes the target face image and the model version identifier, and the model version identifier is used to indicate the face recognition model.

In order to realize face recognition, the data platform sends a feature extraction request to the server. Since the face recognition scene may involve multiple different target terminals, that is, multiple face recognition models indicated by different model version identifiers, the feature extraction request In addition to the target face image, it also includes the model version identifier, so that the server can subsequently call the feature extraction algorithm corresponding to the face recognition model to perform feature extraction.

In step S53, the reference face feature determined based on the model version identifier of the target face image sent by the server is received, wherein the reference face feature determined based on the model version identifier of the target face image is used for On the target terminal of the feature extraction algorithm, face recognition is performed on the target user.

The process for the server to determine the reference face feature determined by the target face image based on the model version identifier may refer to the relevant content of the above-mentioned embodiment, which will not be repeated here.

In step S54, the face recognition data of the target user and the authority information of the target user are sent to the server, wherein the face recognition data includes: the identity identifier of the target user, the model version identifier, the reference determined by the target user based on the model version identifier Facial features, personal information of target users.

In the embodiment of the present disclosure, the data platform obtains the target face image of the target user, sends to the server a feature extraction request including the target face image and the model version identifier used to indicate the face recognition model, and receives the target person sent by the server. The reference face feature determined by the face image based on the model version identifier, wherein the target face image is based on the reference face feature determined by the model version identifier, and is used for the target terminal with the face recognition model indicated by the model version identifier. The target user performs face recognition, and then sends the target user's face recognition data and the target user's authority information to the server, wherein the face recognition data includes: the target user's identity identification, model version identification, target user-based model version identification The determined reference facial features and the personal information of the target user. Because the server only performs feature extraction on the target face image based on the model version identification, and obtains the reference face features for subsequent face recognition without storing the target face image, so that only the target face image involving personal privacy is stored. Locally on the data platform, the data security in the face recognition process is effectively improved, and the risk of personal privacy leakage is reduced.

In a possible implementation manner, the image processing method further includes: receiving an image update request sent by the server; in response to the image update request, re-acquiring the face image of the target user, and using the re-acquired face image to update the target face image.

In step S52, after the data platform sends the feature extraction request including the target face image to the server, the server can perform quality detection on the target face image, and in the case that the quality detection result of the target face image does not meet the preset quality conditions , the server returns an image update request to the data platform. For the process of performing quality detection on the target face image, reference may be made to the relevant content of the foregoing embodiments, which will not be repeated here.

In response to the image update request, the data platform re-acquires the face image of the target user, and uses the re-acquired face image to update the target face image, and sends the updated target face image to the server again until the latest sent target The quality detection result of the face image conforms to the preset quality condition.

In a possible implementation manner, the data platform includes: a portrait data platform; sending the permission information of the target user to the server, including: the portrait data platform determines the identity of the target user; the portrait data platform converts the identity of the target user, the model version The identifier and the reference face feature determined by the target user based on the model version identifier are sent to the server.

The data platform may include a portrait data platform that specifically stores face images. After the data platform receives the reference face features of the target face image returned by the server based on the model version identification, the data platform uses the target face image to determine the reference face based on the model version identification. The facial features are stored in the portrait data platform.

Further, the portrait data platform determines the identity of the target user, and sends the identity of the target user, the model version, and the reference face feature determined by the target user based on the model version to the server again, and the face recognition data is stored in the database. .

In a possible implementation manner, the data platform includes: an information data platform; sending the face recognition data of the target user and the permission information of the target user to the server, including: the information data platform determines the target user based on the identity of the target user The personal information of the target user and the authority information of the target user; the information data platform sends the personal information of the target user and the authority information of the target user to the server.

After the server receives the target user's identity identifier, model version identifier, and the reference face feature determined by the target user based on the model version identifier sent by the portrait data platform, the server returns the target user's identity identifier to the data platform, so that the information data platform is based on the target user. The user's identity identifier sends the personal information of the target user and the permission information of the target user to the server, so that the server can perform data completion processing on the face recognition data of the target user, and recognize the face recognition of the target user after the data is completed. Data is stored in the warehouse.

FIG. 6 shows a flowchart of a face recognition method according to an embodiment of the present disclosure. The face recognition method can be applied to the target terminal 23 in the above-mentioned FIG. 2 . The target terminal 23 has a face recognition model indicated by the model version identifier, and the target user has face recognition authority in the target terminal 23 . As shown in Figure 6, the face recognition method may include:

In step S61, the face recognition data of the target user sent by the server is received, and the face recognition data includes: the identity identifier of the target user, the model version identifier, the reference face feature determined by the target user based on the model version identifier, the target user personal information.

The server sends the face recognition data of the target user to the target terminal, so that the target user can perform face recognition on the target terminal. For the process of determining the target terminal corresponding to the target user by the server, reference may be made to the relevant content of the foregoing embodiment, which will not be repeated here.

In step S62, face recognition is performed on the target user based on the face recognition data.

The target terminal may perform face recognition on the target user based on the face recognition data. For example, the target terminal is a face access control machine, and the target user can perform face recognition on the face access control machine, and pass after the recognition is successful.

In a possible implementation manner, performing face recognition on the target user based on the face recognition data includes: obtaining a snapshot face image of the user to be identified for this face recognition; face recognition based on the indication of the model version identification Model, extract the features of the captured face image of this face recognition, and obtain the face features to be recognized of the user to be recognized; the face features to be recognized of the user to be recognized are successfully matched with the reference face features of the target user. In this case, it is determined that the face recognition is successful this time.

When the user to be identified performs face recognition in front of the target terminal, the target terminal obtains the face image captured by the face recognition of the user to be identified, and then based on the local face recognition model, the captured face image of the face recognition. Feature extraction is performed on the face image to obtain the to-be-recognized facial features of the to-be-identified user, and then, the to-be-identified facial features are matched with multiple reference facial features stored locally by the target terminal, and the to-be-identified facial features are matched with the target user's facial features. If the reference face feature is successfully matched, it is determined that the face recognition is successful this time, and the user to be identified is the target user.

For example, if the target terminal is a face access control machine, after the target user's face recognition on the face access control machine is successful, the face is turned on to allow the target user.

In a possible implementation manner, the face recognition method further includes: desensitizing and displaying the personal information of the target user on the display screen of the target terminal.

After the face recognition of the target user is successful, the personal information in the face recognition data of the target user can be desensitized and displayed on the display screen of the target terminal.

In an example, the name of the target user may be displayed by default, and the name of the target user may be desensitized and displayed. For example, the surname in the name is displayed normally, and the first name in the name is displayed with * to protect personal privacy.

In an example, the target terminal may choose to display more personal information according to actual needs. For example, the job number, department, ID number, etc. can be displayed. Among them, the ID number can also be desensitized and displayed to protect personal privacy.

The specific content of the personal information actually displayed by the target terminal may be set according to actual needs, which is not specifically limited in the present disclosure.

In a possible implementation manner, the face recognition method further includes: generating a face recognition record of the target user based on the captured face image of the face recognition and the spatiotemporal information of the face recognition; The facial recognition records are sent to the server.

After the target user performs face recognition on the target terminal, the target terminal can generate the face recognition record of this face recognition, and send the face recognition record of this face recognition to the server, so that the server can check the target user's face recognition record. The face recognition records are stored for subsequent review.

The spatiotemporal information of the current face recognition included in the face recognition record refers to the time information and spatial information of the current face recognition.

The face recognition record includes, in addition to the captured face image of this face recognition and the spatiotemporal information of this face recognition, other information that needs to be recorded and stored according to the actual situation, which is not specifically limited in this disclosure. .

An embodiment of the present disclosure further provides a face recognition system, which includes: a data platform, a server, and a target terminal, wherein: the target terminal obtains a target face image of a target user; the target terminal sends a feature extraction request to the server , wherein the feature extraction request includes the target face image and the model version ID; the server calls the corresponding feature extraction algorithm based on the model version ID, performs feature extraction on the target face image, and obtains the target face image determined based on the model version ID. Refer to the facial features, and delete the target face image in the local cache; the target terminal receives the target user's face recognition data sent by the server, and the face recognition data includes: the target user's identity identifier, model version identifier, target user based on the model The reference face features and the personal information of the target user determined by the version identification; the target terminal performs face recognition on the target user based on the face recognition data.

The specific form of the face recognition system may be the face recognition system shown in FIG. 4 above. For the specific processing flow of the server, the data platform, and the service terminal, reference may be made to the relevant content of the foregoing embodiments, which will not be repeated here.

FIG. 7 shows a block diagram of a server according to an embodiment of the present disclosure. As shown in FIG. 7, the server 70 includes:

The receiving module 71 is configured to receive a feature extraction request sent by the data platform, wherein the feature extraction request includes a target face image and a model version identifier, and the model version identifier is used to indicate the face recognition model;

The feature extraction module 72 is configured to call a corresponding feature extraction algorithm based on the model version identification, perform feature extraction on the target face image, and obtain the reference face feature determined by the target face image based on the model version identification, wherein the target face image The reference face feature determined based on the model version identifier is used to perform face recognition on the target user corresponding to the target face image on the target terminal having the face recognition model indicated by the model version identifier;

The deletion module 73 is used for deleting the target face image in the local cache.

In a possible implementation manner, the server 70 further includes:

The first sending module is used to send the reference face feature determined by the target face image based on the model version identification to the data platform;

The receiving module 71 is further configured to receive the face recognition data of the target user and the authority information of the target user sent by the data platform, wherein the face recognition data includes: the identity mark of the target user, the model version mark, the target user based on the model version Identify the determined reference facial features and the personal information of the target user.

In a possible implementation manner, the data platform includes: a portrait data platform and an information data platform;

The receiving module 71 is specifically used for:

Receive the target user's identity identifier, model version identifier, and reference facial features determined by the target user based on the model version identifier sent by the portrait data platform;

Receive the personal information of the target user and the permission information of the target user sent by the information data platform.

In a possible implementation manner, the server 70 further includes:

a determination module, used for determining the target terminal of the target user with the face recognition authority based on the authority information of the target user;

The second sending module is used for sending the face recognition data to the target terminal.

In a possible implementation manner, the receiving module 71 is further configured to receive the face recognition record of the target user sent by the target terminal, wherein the face recognition record includes: Spatiotemporal information of sub-face recognition.

In a possible implementation manner, the server 70 further includes:

The grouping module is used for grouping and storing the face recognition data of the multiple target users according to the permission information of each target user in the case of receiving the face recognition data of the multiple target users sent by the data platform.

In a possible implementation manner, the server 70 further includes:

The quality detection module is used to perform quality detection on the target face image;

The first sending module is further configured to send an image update request to the data platform when the quality detection result of the target face image does not meet the preset quality condition.

FIG. 8 shows a block diagram of a data platform according to an embodiment of the present disclosure. As shown in Figure 8, the data platform 80 includes:

an acquisition module 81, configured to acquire the target face image of the target user;

The first sending module 82 is configured to send a feature extraction request to the server, wherein the feature extraction request includes the target face image and the model version identifier, and the model version identifier is used to indicate the face recognition model;

The receiving module 83 is configured to receive the reference face feature determined based on the model version identification of the target face image sent by the server, wherein the reference face feature determined based on the model version identification of the target face image is used to indicate that the target face image is based on the model version identification. On the target terminal of the face recognition model, perform face recognition on the target user;

The second sending module 84 is further configured to send the face recognition data of the target user and the authority information of the target user to the server, wherein the face recognition data includes: the identity identification of the target user, the model version identification, the target user based on the model version Identify the determined reference facial features and the personal information of the target user.

In a possible implementation manner, the data platform 80 includes: a portrait data platform;

The second sending module 84 is specifically used for:

The first determination submodule is used to control the portrait data platform to determine the identity of the target user;

The first sending sub-module is used to control the portrait data platform to send the target user's identity identifier, model version identifier, and reference face features determined by the target user based on the model version identifier to the server.

In a possible implementation manner, the data platform 80 includes: an information data platform;

The second sending module 84 is specifically used for:

The second determination sub-module is used to control the information data platform to determine the personal information of the target user and the authority information of the target user based on the identity of the target user;

The second sending sub-module is used to control the information data platform to send the personal information of the target user and the permission information of the target user to the server.

In a possible implementation manner, the receiving module 83 is further configured to receive an image update request sent by the server;

The acquiring module 81 is further configured to re-acquire the face image of the target user in response to the image update request, and update the target face image using the re-acquired face image.

FIG. 9 shows a block diagram of a target terminal according to an embodiment of the present disclosure. The target terminal has the face recognition model indicated by the model version identifier, and the target user has face recognition authority on the target terminal. As shown in Figure 9, the target terminal 90 includes:

The receiving module 91 is used for receiving the face recognition data of the target user sent by the server. The face recognition data includes: the target user's identity mark, the model version mark, the reference face feature determined by the target user based on the model version mark, the target user's identity mark. Personal information;

The face recognition module 92 is configured to perform face recognition on the target user based on the face recognition data.

In a possible implementation, the face recognition module 92 is specifically used for:

Obtain the captured face image of the face recognition of the user to be identified;

Based on the face recognition model indicated by the model version identifier, feature extraction is performed on the captured face image of this face recognition, and the face features to be recognized of the user to be recognized are obtained;

In the case that the to-be-recognized face of the user to be recognized is successfully matched with the reference face feature of the target user, it is determined that the face recognition is successful this time.

In a possible implementation manner, the target terminal 90 further includes:

The display module is used to desensitize and display the personal information of the target user on the display screen of the target terminal.

In a possible implementation manner, the target terminal 90 further includes:

The record generation module is used to generate the face recognition record of the target user based on the captured face image of this face recognition and the spatiotemporal information of this face recognition;

The sending module is used to send the face recognition record of the target user to the server.

It can be understood that the above-mentioned method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle and logic. Those skilled in the art can understand that, in the above method of the specific embodiment, the specific execution order of each step should be determined by its function and possible internal logic.

The method has a specific technical relationship with the internal structure of the computer system, and can solve the technical problem of how to improve the hardware operation efficiency or execution effect (including reducing the amount of data storage, reducing the amount of data transmission, improving the hardware processing speed, etc.), so as to obtain a natural The technical effects of regular computer system internal performance improvements.

In some embodiments, the functions or modules included in the apparatuses provided in the embodiments of the present disclosure may be used to execute the methods described in the above method embodiments. For specific implementation, reference may be made to the descriptions of the above method embodiments. For brevity, here No longer.

Embodiments of the present disclosure further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing method is implemented. Computer-readable storage media can be volatile or non-volatile computer-readable storage media.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to invoke the instructions stored in the memory to execute the above method.

Embodiments of the present disclosure also provide a computer program product, including computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer-readable codes are stored in a processor of an electronic device When running in the electronic device, the processor in the electronic device executes the above method.

The electronic device may be provided as a terminal, server or other form of device.

FIG. 10 shows a block diagram of an electronic device according to an embodiment of the present disclosure. 10 , the electronic device 1000 may be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle Devices, wearable devices and other terminal equipment.

10, an electronic device 1000 may include one or more of the following components: a processing component 1002, a memory 1004, a power supply component 1006, a multimedia component 1008, an audio component 1010, an input/output (I/O) interface 1012, a sensor component 1014, and communication component 1016.

The processing component 1002 generally controls the overall operation of the electronic device 1000, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1002 can include one or more processors 1020 to execute instructions to perform all or some of the steps of the methods described above. Additionally, processing component 1002 may include one or more modules that facilitate interaction between processing component 1002 and other components. For example, processing component 1002 may include a multimedia module to facilitate interaction between multimedia component 1008 and processing component 1002.

The memory 1004 is configured to store various types of data to support the operation of the electronic device 1000 . Examples of such data include instructions for any application or method operating on the electronic device 1000, contact data, phonebook data, messages, pictures, videos, and the like. Memory 1004 may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

Power supply assembly 1006 provides power to various components of electronic device 1000 . Power supply components 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 1000 .

Multimedia component 1008 includes a screen that provides an output interface between the electronic device 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or swipe action, but also detect the duration and pressure associated with the touch or swipe action. In some embodiments, the multimedia component 1008 includes a front-facing camera and/or a rear-facing camera. When the electronic device 1000 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each of the front and rear cameras can be a fixed optical lens system or have focal length and optical zoom capability.

Audio component 1010 is configured to output and/or input audio signals. For example, audio component 1010 includes a microphone (MIC) that is configured to receive external audio signals when electronic device 1000 is in operating modes, such as call mode, recording mode, and voice recognition mode. The received audio signal may be further stored in memory 1004 or transmitted via communication component 1016 . In some embodiments, audio component 1010 also includes a speaker for outputting audio signals.

The I/O interface 1012 provides an interface between the processing component 1002 and a peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to: home button, volume buttons, start button, and lock button.

Sensor assembly 1014 includes one or more sensors for providing status assessment of various aspects of electronic device 1000 . For example, the sensor assembly 1014 can detect the open/closed state of the electronic device 1000, the relative positioning of the components, such as the display and the keypad of the electronic device 1000, the sensor assembly 1014 can also detect the electronic device 1000 or one of the electronic devices 1000 The position of components changes, the presence or absence of user contact with the electronic device 1000 , the orientation or acceleration/deceleration of the electronic device 1000 and the temperature of the electronic device 1000 changes. Sensor assembly 1014 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 1014 may also include a light sensor, such as a complementary metal oxide semiconductor (CMOS) or charge coupled device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communication component 1016 is configured to facilitate wired or wireless communication between electronic device 1000 and other devices. The electronic device 1000 can access a wireless network based on communication standards, such as wireless network (Wi-Fi), second generation mobile communication technology (2G), third generation mobile communication technology (3G), fourth generation mobile communication technology (4G) ), Long Term Evolution (LTE) of Universal Mobile Telecommunications Technology, Fifth Generation Mobile Telecommunications Technology (5G), or a combination thereof. In one exemplary embodiment, the communication component 1016 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, electronic device 1000 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A programmed gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation is used to perform the above method.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1004 comprising computer program instructions executable by the processor 1020 of the electronic device 1000 to perform the above method.

The present disclosure relates to the field of augmented reality. By acquiring the image information of the target object in the real environment, the relevant features, states and attributes of the target object can be detected or recognized with the help of various visual correlation algorithms, so as to obtain the image information matching the specific application. AR effect that combines virtual and reality. Exemplarily, the target object may involve faces, limbs, gestures, movements, etc. related to the human body, or objects, markers, or sandboxes, display areas, or display items related to venues or venues. Vision-related algorithms may involve visual localization, SLAM, 3D reconstruction, image registration, background segmentation, object keypoint extraction and tracking, object pose or depth detection, etc. The specific application can not only involve interactive scenes such as navigation, navigation, explanation, reconstruction, and virtual effect overlay display related to real scenes or items, but also special effects processing related to people, such as makeup beautification, body beautification, special effects display, virtual Model display and other interactive scenarios. The relevant features, states and attributes of the target object can be detected or recognized through the convolutional neural network. The above convolutional neural network is a network model obtained by model training based on a deep learning framework.

FIG. 11 shows a block diagram of an electronic device according to an embodiment of the present disclosure. Referring to FIG. 11, the electronic device 1900 may be provided as a server or a terminal device. 11, electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource, represented by memory 1932, for storing instructions executable by processing component 1922, such as applications. An application program stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Additionally, the processing component 1922 is configured to execute instructions to perform the above-described methods.

The electronic device 1900 may also include a power supply assembly 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 . The electronic device 1900 can operate based on an operating system stored in the memory 1932, such as a Microsoft server operating system (Windows Server ^™ ), a graphical user interface based operating system (Mac OSX ^™ ) introduced by Apple, a multi-user multi-process computer operating system ( Unix ^™ ), Free and Open Source Unix-like Operating System (Linux ^™ ), Open Source Unix-like Operating System (FreeBSD ^™ ) or the like.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as memory 1932 comprising computer program instructions executable by processing component 1922 of electronic device 1900 to perform the above-described method.

The present disclosure may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the present disclosure.

A computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above. Computer-readable storage media, as used herein, are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.

The computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .

Computer program instructions for carrying out operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or instructions in one or more programming languages. Source or object code, written in any combination, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect). In some embodiments, custom electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can be personalized by utilizing state information of computer readable program instructions. Computer readable program instructions are executed to implement various aspects of the present disclosure.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams. These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium on which the instructions are stored includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.

Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

The computer program product can be specifically implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.

The above descriptions of the various embodiments tend to emphasize the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, details are not repeated herein.

Those skilled in the art can understand that in the above method of the specific implementation, the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.

If the technical solution of this application involves personal information, the product applying the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing personal information. If the technical solution of the present application involves sensitive personal information, the product applying the technical solution of the present application has obtained the individual's individual consent before processing sensitive personal information, and at the same time satisfies the requirement of "express consent". For example, at the personal information collection device such as a camera, a clear and conspicuous sign is set to inform that the personal information has entered the collection range, and the personal information will be collected. If the individual voluntarily enters the collection range, it is deemed to agree to the collection of their personal information; or On the personal information processing device, if the personal information processing rules are informed by obvious signs/information, the personal authorization can be obtained by means of pop-up information or asking individuals to upload their personal information; among them, the personal information processing rules may include personal information Information processor, purpose of processing personal information, method of processing, and types of personal information processed.

Various embodiments of the present disclosure have been described above, and the foregoing descriptions are exemplary, not exhaustive, and not limiting of the disclosed embodiments. Numerous modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the various embodiments, the practical application or improvement over the technology in the marketplace, or to enable others of ordinary skill in the art to understand the various embodiments disclosed herein.

Claims (16)

1. An image processing method, wherein the method is applied to a server, and the method comprises: receiving a feature extraction request sent by the data platform, wherein the feature extraction request includes a target face image and a model version identifier, where the model version identifier is used to indicate a face recognition model; Based on the model version identification, the corresponding feature extraction algorithm is invoked to perform feature extraction on the target face image to obtain the reference face feature determined by the target face image based on the model version identification, wherein the target face image The reference face feature determined by the face image based on the model version identifier is used to perform face recognition on the target user corresponding to the target face image on the target terminal having the face recognition model indicated by the model version identifier. identify; Delete the target face image in the local cache. 2. The method according to claim 1, wherein the method further comprises: sending the target face image to the data platform based on the reference face feature determined by the model version identifier; Receive the face recognition data of the target user and the permission information of the target user sent by the data platform, wherein the face recognition data includes: the identity identifier of the target user, the model version identifier, The target user is based on the reference face feature determined by the model version identification and the personal information of the target user. 3. The method according to claim 2, wherein the data platform comprises: a portrait data platform and an information data platform; The receiving the face recognition data of the target user and the permission information of the target user sent by the data platform includes: Receive the identity identifier of the target user, the model version identifier, and the reference face feature determined by the target user based on the model version identifier sent by the portrait data platform; Receive the personal information of the target user and the permission information of the target user sent by the information data platform. 4. The method according to claim 2 or 3, wherein the method further comprises: Determine, based on the permission information of the target user, the target terminal to which the target user has face recognition permission; Send the face recognition data to the target terminal. 5. The method according to claim 4, wherein the method further comprises: Receive the face recognition record of the target user sent by the target terminal, wherein the face recognition record includes: a snapshot of the face image of the current face recognition, and the spatiotemporal information of the current face recognition. 6. The method according to any one of claims 2 to 5, wherein the method further comprises: In the case of receiving the face recognition data of multiple target users sent by the data platform, the face recognition data of the multiple target users are grouped and stored according to the permission information of each target user. 7. The method according to any one of claims 1 to 6, wherein the method further comprises: performing quality detection on the target face image; In the case that the quality detection result of the target face image does not meet the preset quality condition, an image update request is sent to the data platform. 8. An image processing method, wherein the method is applied to a data platform, and the method comprises: Obtain the target face image of the target user; Sending a feature extraction request to the server, wherein the feature extraction request includes the target face image and a model version identifier, where the model version identifier is used to indicate a face recognition model; Receive the reference face feature determined based on the model version identifier of the target face image sent by the server, wherein the target face image is based on the model version identifier. performing face recognition on the target user on the target terminal of the face recognition model indicated by the model version identifier; Send the face recognition data of the target user and the permission information of the target user to the server, wherein the face recognition data includes: the identity identifier of the target user, the model version identifier, the The target user is based on the reference facial feature determined based on the model version identification, and the personal information of the target user. 9. The method according to claim 8, wherein the data platform comprises: a portrait data platform; The sending the face recognition data of the target user to the server includes: The portrait data platform determines the identity of the target user; The portrait data platform sends the identity identifier of the target user, the model version identifier, and the reference face feature determined by the target user based on the model version identifier to the server. 10. The method according to claim 9, wherein the data platform comprises: an information data platform; The sending the face recognition data of the target user and the permission information of the target user to the server includes: The information data platform determines the personal information of the target user and the permission information of the target user based on the identity of the target user; The information data platform sends the personal information of the target user and the permission information of the target user to the server. 11. The method according to any one of claims 8 to 10, wherein the method further comprises: receiving an image update request sent by the server; In response to the image update request, the face image of the target user is re-acquired, and the target face image is updated using the re-acquired face image. 12. A face recognition method, wherein the method is applied to a target terminal, the target terminal has a face recognition model indicated by the model version identifier, and the target user has a face recognition authority in the target terminal , the method includes: Receive the face recognition data of the target user sent by the server, where the face recognition data includes: the identity of the target user, the model version identifier, and the reference person determined by the target user based on the model version identifier facial features, personal information of the target user; Based on the face recognition data, face recognition is performed on the target user. 13. The method according to claim 12, wherein the performing face recognition on the target user based on the face recognition data comprises: Obtain the captured face image of the face recognition of the user to be identified; Based on the face recognition model indicated by the model version identifier, feature extraction is performed on the face image captured by this face recognition to obtain the face features to be recognized of the user to be recognized; In the case that the to-be-recognized face of the to-be-recognized user is successfully matched with the reference face feature of the target user, it is determined that the current face recognition is successful. 14. The method of claim 13, wherein the method further comprises: The personal information of the target user is desensitized and displayed on the display screen of the target terminal. 15. The method according to claim 13 or 14, wherein the method further comprises: Based on the face image captured by this face recognition and the spatiotemporal information of this face recognition, a face recognition record of the target user is generated; Send the face recognition record of the target user to the server. 16. A face recognition system, wherein the face recognition system comprises: a data platform, a server, and a target terminal, wherein: The target terminal acquires the target face image of the target user; The target terminal sends a feature extraction request to the server, wherein the feature extraction request includes the target face image and the model version identifier; The server invokes the corresponding feature extraction algorithm based on the model version identifier, performs feature extraction on the target face image, obtains the reference face feature determined by the target face image based on the model version identifier, and deletes the the target face image in the local cache; The target terminal receives the face recognition data of the target user sent by the server, and the face recognition data includes: the identity identifier of the target user, the model version identifier, the target user based on the model The reference facial features determined by the version identification, and the personal information of the target user; The target terminal performs face recognition on the target user based on the face recognition data.

Images