CN113033466B - A face recognition method and device - Google Patents

Abstract

The face recognition method comprises the steps that a server receives first base station data sent by mobile terminal equipment of a user, the base station where the user is located is determined according to the first base station data, the server receives a face recognition request sent by scanning equipment, the face recognition request comprises detected face data and second base station data, the base station where the scanning equipment is located is determined according to the second base station data, all users of the base station where the scanning equipment is located are obtained, the server adds the face data of all the users of the base station where the scanning equipment is located into a matching candidate set of the scanning equipment, the server compares the detected face data with the face data in the matching candidate set, and user identity information corresponding to the detected face data is determined according to a comparison result. Compared with the method that the identity information is filled in the mobile terminal equipment and the face data of all users of the face data are stored as the comparison face data, the comparison face data are reduced, and the speed and the accuracy of face identification are improved.

Description

A face recognition method and device

technical field

The present application relates to the technical field of face recognition, and in particular to a face recognition method and device.

Background technique

Electronic payment refers to the use of secure electronic means between consumers, merchants and financial institutions to securely transmit payment information to banks or corresponding processing institutions through information networks to realize monetary payment or capital transfer. Scanning code payment is an electronic payment A common method. In some scan code payment scenarios, users need to scan the QR code of the merchant through the camera of the mobile terminal device. After the QR code is successfully recognized, the user completes the payment process by entering the payment amount and password; in other scan code payment scenarios , the user needs to show the payment code in the electronic device, and the merchant completes the payment process by scanning the user's payment code to deduct money. It can be seen that the process of scanning code payment requires user operations, and the payment process takes a long time.

In order to solve the time-consuming payment method of scan code payment, people use face recognition payment. Before face recognition payment, users fill in identity information and store face data on the program on the mobile terminal device. The server of the face recognition system will add the face data stored by the user into the face database. When paying with face recognition, the user just needs to stand in front of the camera of the face scanning device, and the server of the face recognition system will scan the face The face image collected by the camera of the device is compared with the face data in the face database, and the identity information of the user is confirmed, and the money in the user account is deducted to complete the payment process. It can be seen that face recognition payment does not require user operations, which shortens the time-consuming payment process.

However, in the related technology, in the process of face recognition payment, since the server of the face recognition system needs to compare the face images collected by the camera of the face scanning device with the faces in the face database one by one, Therefore, when the number of faces in the face database of the face recognition system is on the scale of tens of millions or even billions, the speed of face recognition will decrease, and the accuracy rate will also decrease.

Contents of the invention

This application provides a face recognition method and device to solve the technical problems that the speed of face recognition decreases and the accuracy rate drops when the number of faces in the face database of the face recognition system is on the scale of tens of millions or even billions .

In order to solve the above technical problems, the embodiment of the present application discloses the following technical solutions:

In the first aspect, the embodiment of the present application discloses a face recognition method, including the server receiving the first base station data sent by the user's mobile terminal device, and determining the base station where the user is located according to the first base station data;

The server receives the face recognition request sent by the scanning device, the face recognition request includes the measured face data and the second base station data, and determines the base station where the scanning device is located according to the second base station data, and obtains all users of the base station where the scanning device is located;

The server adds the face data of all users of the base station where the scanning device is located to the matching candidate set of the scanning device;

The server compares the tested face data with the face data in the matching candidate set, and confirms the user identity information corresponding to the tested face data according to the comparison result.

Optionally, before the server receives the first base station data sent by the user's mobile terminal equipment, and determines the base station where the user is located according to the first base station data, further includes:

The user's mobile terminal equipment acquires the first base station data, and sends the first base station data to the server;

The scanning device acquires the tested face data and the second base station data, and sends the tested face data and the second base station data to the server.

Optionally, the user's mobile terminal equipment obtains the first base station data, and sends the first base station data to the server, including:

The first program on the user's mobile terminal equipment obtains in real time the mobile network number of the first base station where the mobile terminal equipment is located and the base station number of the first base station by calling the interface provided by the mobile terminal equipment for acquiring base station information, and sends the First base station data including mobile network number and base station number.

Optionally, the user's mobile terminal equipment obtains the first base station data, and sends the first base station data to the server, which also includes:

The user fills in the user's identity information and stores the user's face data on the first program on the mobile terminal device;

The first program sends identity data including identity information and face data to the server.

Optionally, the scanning device obtains the tested face data and the second base station data, and sends the tested face data and the second base station data to the server, including:

The camera on the scanning device collects images containing faces to obtain the face data to be tested. The second program on the scanning device obtains the movement of the second base station where the scanning device is located in real time by calling the interface provided by the scanning device to obtain base station information. the network number, and the base station number of the second base station;

The second program sends the second base station data including the mobile network number and the base station number to the server, and the second program is a matching program with the first program.

Optionally, obtain all users of the base station where the scanning device is located, including:

The server uses the mobile network number and base station number of the base station where the scanning device is located as an index, and obtains all users of the base station where the scanning device is located according to the base stations where all users are located.

In the second aspect, the embodiment of the present application discloses a face recognition device, including a mobile terminal device, a scanning device and a server, a communication connection between the mobile terminal device and the server, a communication connection between the scanning device and the server, and a mobile terminal device, the scanning device and the server It is used to realize the face recognition method in the first aspect.

The beneficial effect of this application is:

The face recognition method provided by the embodiment of the present application includes that the server receives the first base station data sent by the user's mobile terminal device, and determines the base station where the user is located according to the first base station data, and the server receives the face recognition request sent by the scanning device, and the face The recognition request includes the measured face data and the data of the second base station, and the base station where the scanning device is located is determined according to the data of the second base station, and all users of the base station where the scanning device is located are obtained, and the server adds the face data of all users of the base station where the scanning device is located to the scan The matching candidate set of the device, the server compares the tested face data with the face data in the matching candidate set, and confirms the user identity information corresponding to the tested face data according to the comparison result. Since the first base station data corresponds to the mobile terminal equipment including user identity information and face data, the face recognition method provided in the embodiment of the present application determines the base station where the scanning device is located according to the second base station data of the base station where the scanning device is located , in the received first base station data, the server searches for the first base station data that is the same as the mobile network number and base station number of the base station where the scanning device is located, and determines all users of the base station where the scanning device is located, so as to identify all users of the base station where the mobile terminal device is located Face data is filtered to obtain the face data of all users of the base station where the scanning device is located. Compared with the face data of all users who fill in identity information and store face data on the mobile terminal device as comparison face data, it reduces The compared face data improves the face recognition speed and accuracy of the face recognition method provided in the embodiment of the present application.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Description of drawings

In order to illustrate the technical solution of the present application more clearly, the accompanying drawings that need to be used in the embodiments will be briefly introduced below. Obviously, for those of ordinary skill in the art, on the premise of not paying creative work, there are also Additional figures can be derived from these figures.

FIG. 1 is a schematic flow chart of a face recognition method provided in an embodiment of the present application;

FIG. 2 is a schematic structural diagram of a face recognition device provided in an embodiment of the present application;

in:

1-mobile terminal equipment, 2-scanning equipment, 3-server.

Detailed ways

In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described The embodiments are only some of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

Referring to Fig. 1, the embodiment of the present application provides a face recognition method, which can solve the problem that the speed of face recognition decreases and the accuracy rate decreases when the number of faces in the face database of the face recognition system is in the scale of tens of millions or even hundreds of millions. For the problem of descending, for example, the method may include steps S100-S160.

Step S100: the user registers on the mobile terminal device and uploads the face.

The user fills in the user's identity information and stores the user's face data on the first program on the mobile terminal device, and the first program sends the identity data including the identity information and face data to the server.

The user only needs to register once, and there is no need to perform this step in the subsequent face recognition process. The server stores the user's identity data and uses the face data in the stored user identity data as the matching candidate set for comparison, which improves the Confirm user identity speed.

Step S110: The user's mobile terminal device uploads the data of the first base station in real time.

In some embodiments, the user's mobile terminal device includes but is not limited to a mobile phone, and the first program on the user's mobile terminal device obtains the first base station information of the mobile terminal device in real time by calling the interface provided by the mobile terminal device to obtain base station information. The mobile network number of the base station, and the base station number of the first base station, and send the first base station data including the mobile network number and the base station number to the server, and the server receives the first base station data, and determines the base station where the user is based on the first base station data.

Since the first program on the mobile terminal device sends the first base station data including the mobile network number and the base station number to the server in real time, the first base station data acquired by the server is updated in real time, and the server can determine the location of the user in real time according to the first base station data. The base station, thereby determining the location of the user, improves the accuracy of detecting the location of the user.

In some embodiments, the first program on the user's mobile terminal device sends the first base station data to the server in real time, and sends the mobile network number, base station number and signal strength of the first base station adjacent to the mobile terminal device in real time .

When the user is in the middle of the first base station, the first program on the mobile terminal device cannot detect the adjacent base stations of the first base station, and the mobile network number, base station number and signal strength of the adjacent base stations of the first base station are sent to the server in real time Is a null value; when the user is within the range of the first base station and is close to the adjacent base station detected by the first program on the mobile terminal device, the mobile network number, base station number and signal of the first base station's adjacent base station will be sent to the server in real time Strength is a valid value. And according to the signal strength of the adjacent base stations of the first base station, the distance between the user and the adjacent base stations of the first base station can be determined.

Compared with only sending the first base station data to the server in real time, the more detailed location of the user can be determined, which improves the accuracy of detecting the user's location.

In some embodiments, the first program on the mobile terminal device sends the first base station data to the server every 10s, and the second program on the scanning device sends the second base station data to the server every 10s. The location of the scanning device will not change in distance beyond the range of a base station. Therefore, the power consumption of the mobile terminal device and the scanning device is reduced while ensuring the detection accuracy of the location of the user and the scanning device.

Step S120: The scanning device collects the tested face data, obtains the number of the second base station in real time, and sends a face recognition request including the tested face data and the second base station data.

In some embodiments, when the user stands in front of the camera on the scanning device, the camera captures an image containing a face to obtain the face data to be tested, and the second program on the scanning device calls the method provided by the scanning device to obtain base station information. Interface, real-time acquisition of the mobile network number of the second base station where the scanning device is located, and the base station number of the second base station, the second program is a matching program with the first program, and the scanning device obtains the measured face data and the second base station data , and send the measured face data and the second base station data to the server, and the server receives the face recognition request sent by the scanning device, the face recognition request includes the measured face data and the second base station data, and determines according to the second base station data Scan the base station where the device is located, and obtain all users of the base station where the device is scanned.

Since the second program on the scanning device sends the second base station data including the mobile network number and the base station number to the server in real time, the second base station data acquired by the server is updated in real time, and the server can determine the location of the scanning device in real time according to the second base station data. The base station, thereby determining the location of the scanning device, improves the accuracy of detecting the location of the scanning device.

In some embodiments, the second program on the scanning device sends the data of the second base station to the server in real time, and sends the mobile network number, base station number and signal strength of the adjacent base station of the second base station where the scanning device is located in real time.

When the mobile network number, base station number and signal strength of the adjacent base station of the second base station sent to the server in real time are null, it indicates that the scanning device is in the middle of the second base station, and the second program on the scanning device cannot detect the second base station. The adjacent base station of the base station; when the mobile network number, base station number and signal strength of the adjacent base station of the second base station sent to the server in real time are valid values, it can be determined that the scanning device is within the range of the second base station and close to the The adjacent base stations detected by the second program can determine the distance between the scanning device and the adjacent base stations of the second base station according to the signal strength of the adjacent base stations of the second base station. Compared with only sending the data of the second base station to the server in real time, the more detailed location of the scanning device can be determined, which improves the accuracy of detecting the location of the scanning device.

Step S130: the server receives the first base station data sent by the user's mobile terminal device, and determines the base station where the user is located according to the first base station data.

In some embodiments, the server obtains the corresponding base station information according to the base station number in the first base station data, and determines the base station where the user is located. Since the first base station data received by the server is updated in real time, the base station where the user is located can be determined in real time, thereby determining The location of the user improves the accuracy of detecting the location of the user.

Step S140: The server receives the face recognition request sent by the scanning device. The face recognition request includes the measured face data and the data of the second base station, and determines the base station where the scanning device is located according to the data of the second base station, and obtains all users of the base station where the scanning device is located. .

In some embodiments, the server uses the mobile network number and the base station number of the base station where the scanning device is located as an index, and obtains all users of the base station where the scanning device is located according to the base stations where all users are located, and will fill in the identity information and store on the mobile terminal equipment. Compared with the face data of all users of the face data as the comparison face data, the comparison face data is reduced, and the speed and accuracy of the face recognition method provided by the embodiment of the present application are improved.

Step S150: the server adds the face data of all users of the base station where the scanning device is located to the matching candidate set of the scanning device.

In some embodiments, the server adds the face data of all users of the base station where the scanning device is located to the matching candidate set of the scanning device, and compares the face data in the matching candidate set with the face data in the user identity data stored in the server. Compared with the face data of all users who fill in the identity information and store the face data on the mobile terminal equipment as the comparison face data, the comparison face data has been reduced, and the implementation of the application has been improved. The face recognition method provided by the example provides the speed and accuracy of face recognition.

Step S160: The server compares the tested face data with the face data in the matching candidate set, and confirms the user identity information corresponding to the tested face data according to the comparison result.

In some embodiments, the server compares the face data under test with the face data in the matching candidate set until the face data in the matching candidate set finds the face data matching the face under test to confirm that the person under test The user identity information corresponding to the face data, compared with the face data of all users who fill in the identity information and store the face data on the mobile terminal device as the comparison face data, reduces the comparison face data and improves the cost. The speed and accuracy of the face recognition method provided in the embodiment of the application.

In order to further explain the method introduced above, the embodiment of the present application also provides a schematic diagram of a face recognition device, see Figure 2, the face recognition device includes a mobile terminal device 1, a scanning device 2 and a server 3, mobile The terminal device 1 is connected to the server 3 in communication, and the scanning device 2 is connected to the server 3 in communication. The mobile terminal device 1, the scanning device 2 and the server 3 are used to realize the face recognition method, and the server 3 obtains the scanning device 2 according to the base stations where all users are located. All the users of the base station, compared with the face data of all users who will fill in the identity information and store the face data on the mobile terminal equipment 1 as the comparison face data, reduce the comparison face data and improve the application performance. The face recognition method provided in the embodiment provides the speed and accuracy of face recognition.

Based on the face recognition device shown in Figure 2, a face recognition process is as follows: the user fills in the user's identity information and stores the user's face data on the first program of the mobile terminal device 1, and the first program calls the mobile terminal The interface provided by device 1 for acquiring base station information obtains the mobile network number of the first base station where mobile terminal device 1 is located and the base station number of the first base station in real time, and sends the first base station number including the mobile network number and base station number to the server 3 data. The second program is a matching program with the first program. The second program on the scanning device 2 obtains in real time the mobile network number of the second base station where the scanning device 2 is located by calling the interface for obtaining base station information provided by the scanning device 2. and the base station number of the second base station, and send the second base station data including the mobile network number and the base station number to the server 3 . When the user comes to the camera on the scanning device 2 , the camera captures an image containing a human face, and sends the detected face data containing the human face image to the server 3 . The server 3 determines the base station where the user is located according to the data of the first base station, determines the base station where the scanning device 2 is located according to the data of the second base station, obtains all users of the base station where the scanning device 2 is located, and adds the face data of all users of the base station where the scanning device 2 is located to scan Device 2 matches the candidate set, compares the tested face data with the face data in the matching candidate set, and confirms the user identity information corresponding to the tested face data according to the comparison result.

It can be seen from the above embodiments that the face recognition method provided by the embodiment of the present application includes that the server 3 receives the first base station data sent by the user's mobile terminal device 1, and determines the base station where the user is located according to the first base station data, and the server 3 receives the scanning device data. The face recognition request sent by 2, the face recognition request includes the measured face data and the second base station data, and according to the second base station data to determine the base station where the scanning device 2 is located, and obtain all users of the base station where the scanning device 2 is located, the server 3 will The face data of all users of the base station where the scanning device 2 is located is added to the matching candidate set of the scanning device 2, and the server 3 compares the tested face data with the face data in the matching candidate set, and confirms the tested face according to the comparison result. The user identity information corresponding to the data. Since the first base station data corresponds to the mobile terminal device 1 that contains user identity information and face data, the face recognition method provided in the embodiment of the present application determines the location of the scanning device 2 according to the second base station data of the base station where the scanning device 2 is located. Base station, in the first base station data received, the server 3 searches for the first base station data that is identical to the mobile network number and the base station number of the base station where the scanning device 2 is located, and determines all users of the base station where the scanning device 2 is located, so that the mobile terminal device The face data of the base station where 1 is located is filtered, and the face data of all users of the base station where the scanning device 2 is located is obtained, and the face data of all users who fill in the identity information and store face data on the mobile terminal device 1 are used as comparison persons. Compared with face data, the number of compared face data is reduced, and the speed and accuracy of the face recognition method provided by the embodiment of the present application are improved.

Since the above implementation methods are described in conjunction with reference to other methods, different embodiments have the same parts, and the same and similar parts between the various embodiments in this specification can be referred to each other. No further elaboration here.

It should be noted that in this specification, relative terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply No such actual relationship or order exists between these entities or operations. Moreover, the terms "comprises", "comprises" or any other variation thereof are intended to cover a non-exclusive inclusion such that a circuit arrangement, article or apparatus comprising a set of elements includes not only those elements but also elements not expressly listed Other elements, or also include elements inherent in such circuit structures, articles or equipment. Without further limitations, the presence of an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in a circuit arrangement, article or device comprising said element.

Other embodiments of the present application will be readily apparent to those skilled in the art from consideration of the specification and practice of the inventive disclosure herein. This application is intended to cover any modification, use or adaptation of the present invention, these modifications, uses or adaptations follow the general principles of the application and include common knowledge or conventional technical means in the technical field not disclosed in the application . The specification and examples are to be considered exemplary only, with the true scope and spirit of the application indicated by the contents of the appended claims.

The embodiments of the present application described above are not intended to limit the scope of protection of the present application.

Claims (6)

1. A face recognition method, characterized in that, comprising: The user's mobile terminal equipment obtains and sends to the server the data of the first base station and the mobile network number, base station number and signal strength of the adjacent base station of the first base station where the mobile terminal equipment is located. the distance from the base station; When the user is in the middle of the first base station, the mobile network number, base station number and signal strength of the adjacent base station of the first base station sent by the mobile terminal device to the server in real time are null values; When the user is within the range of the first base station and is close to the adjacent base station detected by the mobile terminal device, the mobile network number, base station number and signal strength of the adjacent base station of the first base station sent to the server in real time are effective values; The scanning device acquires and sends to the server the measured face data, the second base station data, and the mobile network number, base station number and signal strength of the adjacent base station of the second base station where the scanning device is located, and the signal strength is used to determine whether the scanning device is connected to the second base station. The distance between the adjacent base stations of the two base stations; When the mobile network number, base station number and signal strength of the adjacent base station of the second base station sent to the server in real time are null, it indicates that the scanning device is in the middle of the second base station; When the mobile network number, base station number and signal strength of the adjacent base station of the second base station sent to the server in real time are effective values, it can be determined that the scanning device is within the range of the second base station and is close to the adjacent base station detected by the scanning device; The server receives the first base station data sent by the user's mobile terminal equipment, and determines the base station where the user is located according to the first base station data; The server receives the face recognition request sent by the scanning device, the face recognition request includes the measured face data and the second base station data, and determines the base station where the scanning device is located according to the second base station data, and obtains the Scan all users of the base station where the device is located; The server adds the face data of all users of the base station where the scanning device is located to the matching candidate set of the scanning device; The server compares the tested human face data with the human face data in the matching candidate set, and confirms the user identity information corresponding to the tested human face data according to the comparison result. 2. The face recognition method according to claim 1, wherein said user's mobile terminal equipment acquires said first base station data, and sends said first base station data to a server, comprising: The first program on the user's mobile terminal equipment obtains in real time the mobile network number of the first base station where the mobile terminal equipment is located, and the first The base station number of the base station, and sending the first base station data including the mobile network number and the base station number to the server. 3. The face recognition method according to claim 1, wherein the user's mobile terminal equipment obtains the first base station data, and sends the first base station data to the server, and also includes before: The user fills in the user's identity information and stores the user's face data on the first program on the mobile terminal device; The first program sends identity data including the identity information and face data to the server. 4. The face recognition method according to claim 1, wherein the scanning device obtains the measured face data and the second base station data, and sends the measured face data and the second base station data to the server. Second base station data, including: The camera on the scanning device collects an image containing a human face to obtain the measured face data, and the second program on the scanning device obtains the base station information in real time by calling an interface provided by the scanning device for obtaining base station information. The mobile network number of the second base station where the scanning device is located, and the base station number of the second base station; The second program sends second base station data including the mobile network number and base station number to the server, and the second program is a program that matches the first program. 5. The face recognition method according to claim 1, wherein the obtaining all users of the base station where the scanning device is located comprises: The server uses the mobile network number and base station number of the base station where the scanning device is located as an index, and obtains all users of the base station where the scanning device is located according to the base stations where all users are located. 6. A face recognition device, characterized in that it comprises: The mobile terminal device (1), the scanning device (2) and the server (3), the mobile terminal device (1) and the server (3) are connected in communication, and the scanning device (2) is connected in communication with the server (3), so The mobile terminal device (1), the scanning device (2) and the server (3) are used to implement the face recognition method described in any one of claims 1-5.

Images