CN111679988B - Face recognition system testing method and device and related equipment - Google Patents
Face recognition system testing method and device and related equipment Download PDFInfo
- Publication number
- CN111679988B CN111679988B CN202010533765.7A CN202010533765A CN111679988B CN 111679988 B CN111679988 B CN 111679988B CN 202010533765 A CN202010533765 A CN 202010533765A CN 111679988 B CN111679988 B CN 111679988B
- Authority
- CN
- China
- Prior art keywords
- picture
- test
- server
- target test
- tested
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3604—Software analysis for verifying properties of programs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Facsimiles In General (AREA)
Abstract
The application provides a testing method, a testing device and related equipment of a face recognition system, which are used for receiving a picture acquisition request of a server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture; searching by using the picture identification to obtain a target test picture; and adjusting the target test picture according to the test requirement to obtain an adjusted target test picture meeting the test requirement, and sending the adjusted target test picture to the server to be tested. According to the scheme, the target test picture is adjusted according to the test requirement, so that the test picture of the face recognition system input into the server to be tested can meet the specific test requirement, the test result can truly reflect the performance of the face recognition system, and the accuracy of the test result is improved.
Description
Technical Field
The present application relates to the field of testing technologies, and in particular, to a method and an apparatus for testing a face recognition system, and related devices.
Background
The face recognition system is an identity authentication system which is widely used, and can compare a face image of a current user obtained by real-time shooting with a face image stored in advance, so that the identity authentication of the current user is performed.
The conventional method for testing the face recognition system generally establishes a database with a large number of test pictures in advance, and when in testing, the face recognition system directly obtains the test pictures from the database and compares the test pictures with the pictures obtained by shooting, thereby obtaining a test result.
In order to ensure the accuracy of the test result, multiple different test requirements are often required to be set during the test to observe the performance of the face recognition system under the test requirements, but the conventional method for directly providing the test pictures by the database is difficult to provide the face recognition system with the test pictures meeting the diversified test requirements, so that the accuracy of the obtained test result is low, and the performance of the face recognition system cannot be truly reflected.
Disclosure of Invention
Based on the defects in the prior art, the application provides a testing method, a testing device and related equipment of a face recognition system, so as to improve the accuracy of testing the face recognition system.
The first aspect of the present application provides a method for testing a face recognition system, including:
receiving a picture acquisition request of a server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture;
searching a plurality of pre-stored test pictures by using the picture identification to obtain the target test picture;
if the target test picture does not meet the test requirement, adjusting the target test picture according to the test requirement to obtain an adjusted target test picture; the adjusted target test picture meets the test requirement;
and sending the adjusted target test picture to the server to be tested.
Optionally, before the target test picture is obtained by searching from a plurality of pre-stored test pictures by using the picture identifier, the method further includes:
receiving the identity information and the IP address of the server to be tested;
judging whether the server to be tested has the picture acquisition authority according to the identity information and the IP address of the server to be tested;
if the server to be tested does not have the picture acquisition permission, rejecting a picture acquisition request of the server to be tested, and sending acquisition failure prompt information to the server to be tested;
the searching the target test picture from a plurality of pre-stored test pictures by using the picture identification comprises the following steps:
and if the server to be tested has the picture acquisition authority, searching a plurality of pre-stored test pictures by using the picture identification to obtain the target test picture.
Optionally, after the sending the adjusted target test picture to the server to be tested, the method further includes:
and combining the time for sending the adjusted target test picture, the picture acquisition request, the identity information of the server to be tested and the IP address to obtain a picture transmission record, and storing the picture transmission record.
Optionally, the test requirement includes: the picture size of the test picture is equal to a preset test size;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
if the picture size of the target test picture is larger than the test size, cutting the target test picture based on the test size to obtain an adjusted target test picture; and the picture size of the adjusted target test picture is equal to the test size.
Optionally, the test requirement includes: the resolution ratio of the test picture is positioned in a preset resolution ratio interval;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
if the resolution of the target test picture is larger than the upper limit of the resolution interval, compressing the target test picture based on the upper limit of the resolution interval to obtain an adjusted target test picture; the resolution of the adjusted target test picture is located in the resolution interval.
Optionally, before receiving the image acquisition request of the server to be tested, the method further includes:
establishing communication connection with terminal equipment;
and receiving and storing the test picture uploaded by the terminal equipment.
A second aspect of the present application provides a test apparatus for a face recognition system, including:
the receiving unit is used for receiving a picture acquisition request of the server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture;
the searching unit is used for searching the target test picture from a plurality of pre-stored test pictures by utilizing the picture identification;
the adjusting unit is used for adjusting the target test picture according to the test requirement if the target test picture does not meet the test requirement, so as to obtain an adjusted target test picture; the adjusted target test picture meets the test requirement;
and the sending unit is used for sending the adjusted target test picture to the server to be tested.
Optionally, the receiving unit is further configured to receive identity information and an IP address of the server to be tested;
wherein, the testing device further comprises an authentication unit for:
judging whether the server to be tested has the picture acquisition authority according to the identity information and the IP address of the server to be tested;
if the server to be tested does not have the picture acquisition permission, rejecting a picture acquisition request of the server to be tested, and triggering the sending unit to send acquisition failure prompt information to the server to be tested;
the searching unit is specifically configured to, when searching the target test picture from a plurality of pre-stored test pictures by using the picture identifier:
and if the server to be tested has the picture acquisition authority, searching a plurality of pre-stored test pictures by using the picture identification to obtain the target test picture.
A third aspect of the present application provides a computer storage medium storing a program, which when executed is specifically configured to implement the method for testing a face recognition system provided in any one of the first aspects of the present application.
A fourth aspect of the present application provides a server comprising a memory and a processor;
wherein the memory is used for storing programs;
the processor is configured to execute the program, and specifically is configured to implement a method for testing a face recognition system provided by any one of the first aspects of the present application.
The application provides a testing method, a testing device and related equipment of a face recognition system, which are used for receiving a picture acquisition request of a server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture; searching a plurality of pre-stored test pictures by using picture identification to obtain a target test picture; and adjusting the target test picture according to the test requirement to obtain an adjusted target test picture meeting the test requirement, and finally sending the adjusted target test picture to the server to be tested. According to the scheme, the target test picture is adjusted according to the test requirement, so that the test picture of the face recognition system input into the server to be tested can meet the specific test requirement, the test result can truly reflect the performance of the face recognition system, and the accuracy of the test result is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a testing method of a face recognition system according to an embodiment of the present application;
fig. 2 is a flowchart of a testing method of a face recognition system according to another embodiment of the present application;
fig. 3 is a flowchart of a testing method of a face recognition system according to another embodiment of the present application;
fig. 4 is a schematic structural diagram of a testing device of a face recognition system according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The main purpose of the test of the face recognition system is to detect whether the face recognition system can correctly match the captured face image with the test pictures in the database, for example, if the captured face image of the user a, two test pictures are obtained from the database, wherein the first test picture comprises the face image of the user a, the second test picture comprises the face image of the user b, the face recognition system matches the captured face image with the two test pictures, and if the face recognition system matches, the test result obtained is: the face image obtained by shooting and the first test picture belong to the same user (namely user A), and the face image obtained by shooting and the second test picture do not belong to the same user, the test is successful, otherwise, if the test result output by the face recognition system is different from the test result, the test is failed.
Therefore, the performance of the face recognition system for recognizing the face image can be primarily determined by controlling the face recognition system to execute a plurality of tests and then counting the proportion of successful tests.
When testing a face recognition system, different testing requirements are often put forward in order to ensure that the testing result can truly reflect the performance of the face recognition system.
For example, in order to detect the recognition performance of the face recognition system for test pictures of different picture sizes, it is specified in the test requirement that the size of the test picture input to the face recognition system is equal to the pre-specified test size. If the recognition performance of the face recognition system on test pictures with different resolutions is to be detected, it is required to specify in the test requirement that the resolution of the picture input to the face recognition system is within a certain specified resolution range. Of course, other testing requirements are also possible according to practical situations, and are not listed here.
In order to realize timely providing test pictures meeting preset test requirements when testing a face recognition system, the embodiment of the application provides the following test method of the face recognition system.
It should be noted that, in the method for testing a face recognition system according to any one of the embodiments of the present application, the execution subject may be considered as a proxy server that stores a large number of test pictures and is communicatively connected to a server configured with the face recognition system to be tested.
Referring to fig. 1, a method for testing a face recognition system according to a first embodiment of the present application may include the following steps:
s101, receiving a picture acquisition request of a server to be tested.
The server to be tested refers to any one server provided with a face recognition system. In the practical application process of the face recognition system, the face recognition system may need to meet face recognition requests of a large number of users at the same time, or need to perform face recognition on a plurality of users at the same time, so as to meet such use requirements, the face recognition system needs to be configured on a plurality of servers at the same time, and each server can be used for responding to the requests of the users and performing face recognition on the users. Therefore, when testing the face recognition system, the face recognition system operated by any one or more servers can be tested, and the tested server is the server to be tested in the step S101.
The picture acquisition request comprises a picture identifier and a test requirement of the target test picture.
The plurality of test pictures stored by the proxy server may use the name of the corresponding user as a picture identifier, for example, a certain test picture contains a face image of the user who is about three (for example, the test picture may be a certificate of about three), the picture identifier of the test picture is about three, a certain test picture contains a face image of the user who is about less bright, and the picture identifier of the test picture is about less bright.
The picture identification of the target test picture is pre-designated by a tester, and according to actual conditions, one or more picture identifications of the target test picture can be provided, and one or more corresponding target test pictures obtained through final searching can be provided.
For example, the tester specifies that the photograph of the third picture shot by the terminal device needs to be matched with the test photograph of the third picture and the test photograph of the fourth picture stored in the proxy server, and then the photograph identification of the target test photograph in step S101 is "third picture" and "fourth picture".
As previously mentioned, there may be a number of different test requirements during the test, several examples of which are given below:
the first test requirement may specify that the picture size of the target test picture is equal to the preset test size or is located in the preset test size interval;
the second test requirement may specify that the resolution of the target test picture is equal to the preset test resolution or is within a preset resolution range;
the third test requirement may specify that the target test picture is added with interference in a preset manner, for example, shielding a partial area of the face image in the test picture.
Of course, in other embodiments of the present application, there may be other testing requirements other than the above three testing requirements, which is not limited by the present application.
The server to be tested may execute step S101 after obtaining the photograph of the specific user taken by the terminal device. For example, in the foregoing example, the server to be tested may execute step S101 after obtaining the photograph of the three pieces taken by the terminal device.
S102, searching a target test picture from a plurality of pre-stored test pictures by using a picture identifier.
As described above, the plurality of test pictures stored in the proxy server may use the name of the corresponding user as a tag, and the picture identifier sent by the server to be tested is the name pre-specified by one or more testers.
Therefore, the proxy server can search a plurality of test pictures stored in the proxy server for each target identifier after obtaining the picture identifiers of a plurality of target test pictures provided by the server to be tested (the picture identifiers of the target test pictures can be marked as target identifiers), and find all the test pictures corresponding to the target identifier, namely the target test picture in the current test process.
For example, the target identifiers designated by the tester are Zhang San and Liqu, and after obtaining the two target identifiers, the proxy server searches for test pictures of all face images containing Zhang San and test pictures of all face images containing Liqu, and the test pictures are the target test pictures of the test.
The test pictures stored by the proxy server can be obtained by: the tester can access the proxy server through the terminal equipment for uploading the test pictures, such as a smart phone, a desktop computer, a notebook computer and the like, then perform picture uploading operation on the graphical user interface of the terminal equipment, so that the test pictures in the terminal equipment are sent to the proxy server and then stored by the proxy server, and a large number of test pictures can be stored in the proxy server in this way.
S103, detecting whether the target test picture meets the test requirement.
If the target test picture does not meet the test requirement, step S104 is executed, and if the target test picture meets the test requirement, step S106 is executed.
It should be noted that, the process described in steps S103 to S106 needs to be performed for each target test picture obtained by searching. In other words, the proxy server detects whether each target test picture meets the test requirement provided by the server to be tested, if any target test picture meets the test requirement, the target test picture is directly sent to the server to be tested, if the target test picture does not meet the test requirement, the target test picture is adjusted, and then the adjusted target test picture is sent to the server to be tested.
For easy understanding, the following steps are described by taking a certain target test picture as an example.
The specific method of detection described in step S103 is also different for different test requirements, and is described below in connection with the above three test requirements.
For the first test requirement, the test requirement provided by the server to be tested may include a specified test size or test size interval, and when executing step S103, the server to be tested only needs to obtain the picture size of the target test picture, and then compares the picture size of the target test picture with the specified test size or test size interval in the test requirement.
The test requirement comprises the condition of the test size, if the picture size of the target test picture is not equal to the test size, the target test picture is determined to not meet the test requirement, otherwise, the picture size of the target test picture is equal to the test size, and the target test picture meets the test requirement.
And if the picture size of the target test picture is outside the test size interval, the target test picture does not meet the test requirement.
For the second test requirement, similarly, the proxy server may detect whether the resolution of the target test picture is equal to the test resolution specified by the test requirement, or detect whether the resolution of the target test picture is within the resolution range specified by the test requirement, if the resolution of the target test picture meets the above condition, determine that the target test picture meets the test requirement, otherwise, if the resolution of the target test picture does not meet the above condition, determine that the target test picture does not meet the test requirement.
For the third test requirement, since each target test picture needs to be added with interference, when the test requirement provided by the server to be tested is the aforementioned third test requirement, each target test picture can be directly determined as a target test picture which does not meet the test requirement.
S104, adjusting the target test picture to obtain an adjusted target test picture.
The adjusted target test picture meets the test requirement.
For the three foregoing test requirements, the specific execution procedure of step S104 is as follows:
and if the picture size of the target test picture is larger than the preset test size or the picture size is larger than the upper limit of the test size interval, the target test picture can be cut according to the first test requirement, so that an adjusted target test picture with the picture size equal to the preset test size or the picture size within the test size interval is obtained.
The clipping should ensure that the adjusted target test picture obtained after clipping contains the complete face image in the original target test picture. To achieve this effect, the region in which the face image is located in the target test picture may be detected, and then clipping may be performed in the region based on the face image.
If the picture size of the target test picture is smaller than the preset test size or the picture size is smaller than the lower limit of the preset test size interval, the picture size of the target test picture can be increased, so that the adjusted picture size of the target test picture is equal to the preset test size or is located in the test size interval.
The second method for adjusting the test requirement is similar to the first method for adjusting the test requirement, if the resolution of the target test picture is too large (larger than the preset test resolution or larger than the upper limit of the resolution interval), the target test picture is compressed, so that an adjusted target test picture with the resolution meeting the test requirement is obtained. On the contrary, if the resolution is too small, pixel points can be inserted into the target test picture by an interpolation method, so that the resolution of the target test picture is increased, and the adjusted resolution of the target test picture is ensured to meet the test requirement.
For the third test requirement, the proxy server can add interference to the target test picture according to the set adjustment mode so as to obtain the adjusted target test picture. For example, the set adjustment mode may be that a specified area of a face image included in the target test picture is blocked (for example, a mouth is blocked), so that the proxy server may first detect an area where the face image in the target test picture is located, and then cover the specified area of the face image with a monochrome layer (for example, a white layer or a black layer) that matches in size and shape, so as to obtain the adjusted target test image.
S105, sending the adjusted target test picture to the server to be tested.
S106, sending the target test picture to the server to be tested.
The proxy server can send the adjusted target test picture through communication connection with the server to be tested, and the target test picture meeting the test requirement is determined after detection.
After the server to be tested obtains the target test picture (or the adjusted target test picture), the server to be tested can test based on the target test picture to obtain a corresponding test result.
The application provides a testing method of a face recognition system, which is used for receiving a picture acquisition request of a server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture; searching by using the picture identification to obtain a target test picture; and adjusting the target test picture according to the test requirement to obtain an adjusted target test picture meeting the test requirement, and sending the adjusted target test picture to the server to be tested. According to the scheme, the target test picture is adjusted according to the test requirement, so that the test picture of the face recognition system input into the server to be tested can meet the specific test requirement, the test result can truly reflect the performance of the face recognition system, and the accuracy of the test result is improved.
Referring to fig. 2, the test method provided in the second embodiment of the present application may include the following steps:
s201, receiving a picture acquisition request and authentication information of a server to be tested.
The server to be tested is any server provided with a face recognition system. The picture acquisition request comprises a picture identifier and a test requirement of the target test picture.
The server to be tested can send the authentication information of the server to be tested and the picture acquisition request to the proxy server together when sending the picture acquisition request. The authentication information of the server to be tested may include identity information and an internet protocol (InternetProtocol, IP) address of the server to be tested.
The identity information of the server to be tested may be a character string pre-assigned to the server to be tested, for uniquely identifying the server to be tested.
Further, if the proxy server receives the picture acquisition request, but does not receive the valid identity information and the IP address provided by the test server, it may be directly determined that the server to be tested does not have the picture acquisition right, and step S203 is directly executed.
S202, judging whether the server to be tested has the picture acquisition authority according to the identity information and the IP address of the server to be tested.
The proxy server may maintain a rights list in which the identity information and IP address of each server equipped with the face recognition system having the picture acquisition rights are recorded. Based on the above, after obtaining the identity information and the IP address provided by the server to be tested, the proxy server may search the authority list for the identity information and the IP address provided by the server to be tested, if the authority list records the identity information and the IP address provided by the server to be tested, it is determined that the server to be tested has the picture acquisition authority, otherwise, if the authority list does not have the identity information and the IP address provided by the server to be tested, it is determined that the server to be tested does not have the picture acquisition authority.
If the server to be tested does not have the picture acquisition right, the step S203 is executed, otherwise, if the server to be tested has the picture acquisition right, the step S204 is executed.
S203, rejecting the picture acquisition request of the server to be tested, and sending acquisition failure prompt information to the server to be tested.
The acquisition failure prompt information is used for indicating to the server to be tested that the server to be tested does not have the picture acquisition authority for acquiring the picture from the proxy server, so that the proxy server cannot provide the target test picture for the server to be tested.
After rejecting the image acquisition request of the server to be tested, the image acquisition request of the server to be tested can be directly deleted.
S204, searching a target test picture from a plurality of pre-stored test pictures by using a picture identifier.
And S205, adjusting the target test picture according to the test requirement to obtain the target test picture meeting the test requirement.
The adjusted target test picture meets the test requirement.
Step S205 corresponds to step S103 and step S104 in the foregoing embodiment, in other words, the specific implementation process of step S205 in this embodiment is to detect, for each target test picture, whether the target test picture meets the test requirement, and if not, adjust the target test picture to obtain an adjusted target test picture meeting the test requirement, otherwise, if the target test picture meets the test requirement, no adjustment is needed, and directly determine the target test picture as the target test picture meeting the test requirement.
S206, a target test picture meeting the test requirement is sent to the server to be tested.
Step S206 corresponds to the combination of step S105 and step S106 in the foregoing embodiment, that is, the target test picture directly meeting the test requirement without adjustment and the adjusted target test picture meeting the test requirement are sent to the server to be tested.
According to the testing method of the face recognition system, authentication is firstly carried out according to the authentication information provided by the server to be tested before the target test picture is provided for the server to be tested, and the picture is provided for the server to be tested only after the fact that the server to be tested has the picture acquisition authority is determined.
Referring to fig. 3, the test method provided in the third embodiment of the present application may include the following steps:
s301, receiving a picture acquisition request and authentication information of a server to be tested.
The server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture.
The authentication information of the server to be tested comprises the identity information and the IP address of the server to be tested.
S302, judging whether the server to be tested has the picture acquisition authority according to the identity information and the IP address of the server to be tested.
If the server to be tested has the picture acquisition permission, the step S304 is executed, otherwise, if the server to be tested does not have the picture acquisition permission, the step S303 is executed.
S303, rejecting the picture acquisition request of the server to be tested, and sending acquisition failure prompt information to the server to be tested.
S304, searching a target test picture from a plurality of pre-stored test pictures by using a picture identifier.
And S305, adjusting the target test picture according to the test requirement to obtain the target test picture meeting the test requirement.
The specific implementation procedure of step S305 is identical to that of step S205 in the foregoing second embodiment, and will not be described herein.
S306, a target test picture meeting the test requirement is given to the server to be tested.
The specific execution process of step S306 is identical to that of step S306 in the aforementioned second embodiment, and will not be repeated here.
S307, generating and storing a picture transmission record.
The picture transmission record includes: and sending the time of a target test picture meeting the test requirement, and obtaining a request of the picture received by the proxy server, wherein the identity information and the IP address are provided by the server to be tested. In other words, when step S307 is performed, the above information may be combined, and the result is a piece of picture transmission record.
According to the testing method of the face recognition system, after each time of transmitting the target test picture meeting the testing requirement, the corresponding picture transmission record is generated and stored. Therefore, a tester can determine which servers with face recognition systems are specifically configured to perform testing in a past period of time by detecting the picture transmission records, so as to determine whether a preset test plan is normally executed.
In combination with the method for testing the face recognition system provided by any one of the embodiments of the present application, the embodiment of the present application further provides a device for testing the face recognition system, where the device may be considered as a proxy server for executing the method for testing the face recognition system provided by the present application, and referring to fig. 4, the device for testing the face recognition system provided by the present application may include the following units:
the receiving unit 401 is configured to receive a picture acquisition request of a server to be tested.
The server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture.
And the searching unit 402 is configured to search for the target test picture from a plurality of pre-stored test pictures by using the picture identifier.
And the adjusting unit 403 is configured to adjust the target test picture according to the test requirement, so as to obtain a target test picture that meets the test requirement.
The operation principle of the adjustment unit 403 may refer to step S205 and step S305 in the methods provided in the foregoing second and third embodiments.
And the sending unit 404 is configured to send the adjusted target test picture to the server to be tested.
Optionally, the receiving unit 401 is further configured to receive authentication information of the server to be tested, where the authentication information may include identity information and an IP address of the server to be tested.
Wherein the testing device further comprises an authentication unit 405 for:
judging whether the server to be tested has the picture acquisition authority according to the identity information and the IP address of the server to be tested;
if the server to be tested does not have the picture acquisition permission, rejecting the picture acquisition request of the server to be tested, and triggering the sending unit 404 to send acquisition failure prompt information to the server to be tested.
The searching unit 402 performs the operation of searching for the target test picture from the pre-stored multiple test pictures by using the picture identifier after the authentication unit 405 determines that the server to be tested has the picture acquisition authority.
Optionally, the test apparatus provided in this embodiment further includes a recording unit 406, configured to:
and combining the time for sending the adjusted target test picture, the picture acquisition request, the identity information of the server to be tested and the IP address to obtain a picture transmission record, and storing the picture transmission record.
The test requirements may be: the picture size of the test picture is equal to a preset test size;
the adjusting unit 403 adjusts the target test picture according to the test requirement, and when obtaining the adjusted target test picture, the adjusting unit may be specifically configured to:
if the picture size of the target test picture is larger than the test size, cutting the target test picture based on the test size to obtain an adjusted target test picture; the picture size of the adjusted target test picture is equal to the test size.
The test requirements may be: the resolution ratio of the test picture is positioned in a preset resolution ratio interval;
the adjusting unit 403 adjusts the target test picture according to the test requirement, and when obtaining the adjusted target test picture, the adjusting unit may be specifically configured to:
if the resolution of the target test picture is larger than the upper limit of the resolution interval, compressing the target test picture based on the upper limit of the resolution interval to obtain an adjusted target test picture; the resolution of the adjusted target test picture is located in a resolution interval.
Optionally, the receiving unit 401 may be further configured to:
and establishing communication connection with the terminal equipment, receiving the test picture uploaded by the terminal equipment, and then storing the test picture in a storage medium of the proxy server.
The specific working principle of the testing device of the face recognition system provided by the embodiment of the application can refer to the testing method of the face recognition system provided by any embodiment of the application, and the detailed description is omitted herein.
The application provides a testing device of a face recognition system.A receiving unit 401 receives a picture acquisition request of a server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture; the searching unit 402 searches to obtain a target test picture by using the picture identification; the adjusting unit 403 adjusts the target test picture according to the test requirement, so as to obtain an adjusted target test picture meeting the test requirement, and the sending unit 404 sends the adjusted target test picture to the server to be tested. According to the scheme, the target test picture is adjusted according to the test requirement, so that the test picture of the face recognition system input into the server to be tested can meet the specific test requirement, the test result can truly reflect the performance of the face recognition system, and the accuracy of the test result is improved.
The embodiment of the application also provides a computer storage medium for storing a computer program, and the stored computer program is particularly used for realizing the testing method of the face recognition system provided by any embodiment of the application when being executed.
The embodiment of the present application further provides a server, please refer to fig. 5, where the server includes a memory 501 and a processor 502, where the memory 501 is configured to store a program, and the processor 502 is configured to execute the program stored in the memory 501, and when the program is executed, the program is specifically configured to implement the method for testing the face recognition system provided by any embodiment of the present application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
It should be noted that the terms "first," "second," and the like herein are merely used for distinguishing between different devices, modules, or units and not for limiting the order or interdependence of the functions performed by such devices, modules, or units.
Those skilled in the art will be able to make or use the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method for testing a face recognition system, comprising:
receiving a picture acquisition request of a server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture;
searching a plurality of pre-stored test pictures by using the picture identification to obtain the target test picture;
if the target test picture does not meet the test requirement, adjusting the target test picture according to the test requirement to obtain an adjusted target test picture; the adjusted target test picture meets the test requirement;
sending the adjusted target test picture to the server to be tested;
wherein the test requirements include: the picture size of the test picture is equal to a preset test size;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
if the picture size of the target test picture is larger than the test size, cutting the target test picture based on the test size to obtain an adjusted target test picture; the picture size of the adjusted target test picture is equal to the test size; or alternatively, the first and second heat exchangers may be,
the test requirements include: the resolution ratio of the test picture is positioned in a preset resolution ratio interval;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
if the resolution of the target test picture is larger than the upper limit of the resolution interval, compressing the target test picture based on the upper limit of the resolution interval to obtain an adjusted target test picture; the resolution of the adjusted target test picture is located in the resolution interval; or alternatively, the first and second heat exchangers may be,
the test requirements include: adding interference to the test picture in a preset mode;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
and adding interference to the target test picture according to the set adjustment mode to obtain an adjusted target test picture.
2. The method according to claim 1, wherein before searching for the target test picture from the pre-stored plurality of test pictures by using the picture identifier, the method further comprises:
receiving the identity information and the IP address of the server to be tested;
judging whether the server to be tested has the picture acquisition authority according to the identity information and the IP address of the server to be tested;
if the server to be tested does not have the picture acquisition permission, rejecting a picture acquisition request of the server to be tested, and sending acquisition failure prompt information to the server to be tested;
the searching the target test picture from a plurality of pre-stored test pictures by using the picture identification comprises the following steps:
and if the server to be tested has the picture acquisition authority, searching a plurality of pre-stored test pictures by using the picture identification to obtain the target test picture.
3. The method according to claim 2, wherein after the sending the adjusted target test picture to the server to be tested, further comprises:
and combining the time for sending the adjusted target test picture, the picture acquisition request, the identity information of the server to be tested and the IP address to obtain a picture transmission record, and storing the picture transmission record.
4. The method according to claim 1, wherein before receiving the picture acquisition request of the server to be tested, further comprises:
establishing communication connection with terminal equipment;
and receiving and storing the test picture uploaded by the terminal equipment.
5. A test device for a face recognition system, comprising:
the receiving unit is used for receiving a picture acquisition request of the server to be tested; the server to be tested is any server provided with a face recognition system, and the picture acquisition request comprises a picture identifier and a test requirement of a target test picture;
the searching unit is used for searching the target test picture from a plurality of pre-stored test pictures by utilizing the picture identification;
the adjusting unit is used for adjusting the target test picture according to the test requirement if the target test picture does not meet the test requirement, so as to obtain an adjusted target test picture; the adjusted target test picture meets the test requirement;
the sending unit is used for sending the adjusted target test picture to the server to be tested;
wherein the test requirements include: the picture size of the test picture is equal to a preset test size;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
if the picture size of the target test picture is larger than the test size, cutting the target test picture based on the test size to obtain an adjusted target test picture; the picture size of the adjusted target test picture is equal to the test size; or alternatively, the first and second heat exchangers may be,
the test requirements include: the resolution ratio of the test picture is positioned in a preset resolution ratio interval;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
if the resolution of the target test picture is larger than the upper limit of the resolution interval, compressing the target test picture based on the upper limit of the resolution interval to obtain an adjusted target test picture; the resolution of the adjusted target test picture is located in the resolution interval; or alternatively, the first and second heat exchangers may be,
the test requirements include: adding interference to the test picture in a preset mode;
the step of adjusting the target test picture according to the test requirement to obtain an adjusted target test picture comprises the following steps:
and adding interference to the target test picture according to the set adjustment mode to obtain an adjusted target test picture.
6. The test device according to claim 5, wherein the receiving unit is further configured to receive identity information and an IP address of the server under test;
wherein, the testing device further comprises an authentication unit for:
judging whether the server to be tested has the picture acquisition authority according to the identity information and the IP address of the server to be tested;
if the server to be tested does not have the picture acquisition permission, rejecting a picture acquisition request of the server to be tested, and triggering the sending unit to send acquisition failure prompt information to the server to be tested;
the searching unit is specifically configured to, when searching the target test picture from a plurality of pre-stored test pictures by using the picture identifier:
and if the server to be tested has the picture acquisition authority, searching a plurality of pre-stored test pictures by using the picture identification to obtain the target test picture.
7. A computer storage medium storing a program which, when executed, is particularly adapted to carry out a method of testing a face recognition system as claimed in any one of claims 1 to 4.
8. A server comprising a memory and a processor;
wherein the memory is used for storing programs;
the processor is configured to execute the program, in particular to implement a method of testing a face recognition system according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010533765.7A CN111679988B (en) | 2020-06-12 | 2020-06-12 | Face recognition system testing method and device and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010533765.7A CN111679988B (en) | 2020-06-12 | 2020-06-12 | Face recognition system testing method and device and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111679988A CN111679988A (en) | 2020-09-18 |
| CN111679988B true CN111679988B (en) | 2023-10-10 |
Family
ID=72454678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010533765.7A Active CN111679988B (en) | 2020-06-12 | 2020-06-12 | Face recognition system testing method and device and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111679988B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10334236A1 (en) * | 2003-07-28 | 2005-03-03 | Robert Bosch Gmbh | Object recognition system e.g. for biometric recognition of persons, compares stored reference objects and function module for production of illustrations of reference objects in several different situations |
| CN109492523A (en) * | 2018-09-17 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Face identification system performance test methods, device, equipment and storage medium |
| CN110209266A (en) * | 2019-04-23 | 2019-09-06 | 平安科技（深圳）有限公司 | A kind of size fit method and device of image |
| CN110706392A (en) * | 2019-10-14 | 2020-01-17 | 重庆紫光华山智安科技有限公司 | Security platform test method and device, storage medium and server |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9542755B2 (en) * | 2012-10-22 | 2017-01-10 | Sony Corporation | Image processor and image processing method |
-
2020
- 2020-06-12 CN CN202010533765.7A patent/CN111679988B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10334236A1 (en) * | 2003-07-28 | 2005-03-03 | Robert Bosch Gmbh | Object recognition system e.g. for biometric recognition of persons, compares stored reference objects and function module for production of illustrations of reference objects in several different situations |
| CN109492523A (en) * | 2018-09-17 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Face identification system performance test methods, device, equipment and storage medium |
| CN110209266A (en) * | 2019-04-23 | 2019-09-06 | 平安科技（深圳）有限公司 | A kind of size fit method and device of image |
| CN110706392A (en) * | 2019-10-14 | 2020-01-17 | 重庆紫光华山智安科技有限公司 | Security platform test method and device, storage medium and server |
Non-Patent Citations (1)
| Title |
|---|
| 谢兰迟 等.基于三种类型图像数据的人脸识别测试.《刑事技术》.2016,第41卷(第6期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111679988A (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106303515B (en) | A kind of online live video quality detecting method and device | |
| US10176654B2 (en) | Suspicious person detection system, suspicious person detection method | |
| CN106878108B (en) | Network flow playback test method and device | |
| CN108616389B (en) | Network evaluation method, equipment, storage medium and device based on cloud server | |
| CN111711533B (en) | Fault diagnosis method, fault diagnosis device, electronic device and storage medium | |
| CN112015510B (en) | Examination system management method and examination system | |
| CN109656800B (en) | Method and device for testing image recognition application, terminal and storage medium | |
| CN109413760B (en) | Wireless connection method and device | |
| CN108055455A (en) | Method for secret protection, device and the computer readable storage medium of family's monitoring | |
| CN110806965A (en) | Automatic test method, device, equipment and medium | |
| WO2017054307A1 (en) | Recognition method and apparatus for user information | |
| CN114610605A (en) | Test method, test device, terminal equipment and storage medium | |
| CN111679988B (en) | Face recognition system testing method and device and related equipment | |
| CN111386711A (en) | Method, device and system for managing electronic fingerprints of electronic files | |
| CN113239333A (en) | Browser user identity authentication method and system based on cross-domain resource access | |
| CN110046068B (en) | Test method, device and equipment | |
| CN113296660A (en) | Image processing method and device and electronic equipment | |
| CN108075932B (en) | Data monitoring method and device | |
| CN105095711B (en) | Data transmission method and device | |
| CN110543751A (en) | Data processing method and device and server | |
| CN115052174B (en) | Resource transfer method, device, electronic equipment and storage medium | |
| CN117010011B (en) | Data protection system and method | |
| CN116361847B (en) | Mobile device-based screen capturing prevention method and system | |
| KR20200014610A (en) | Server for providing online bulletin board | |
| CN109089132A (en) | A kind of information search method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |