CN117472677A - Face recognition equipment testing method and testing system - Google Patents
Face recognition equipment testing method and testing system Download PDFInfo
- Publication number
- CN117472677A CN117472677A CN202311804362.1A CN202311804362A CN117472677A CN 117472677 A CN117472677 A CN 117472677A CN 202311804362 A CN202311804362 A CN 202311804362A CN 117472677 A CN117472677 A CN 117472677A
- Authority
- CN
- China
- Prior art keywords
- test
- face recognition
- recognition device
- pixel point
- identification image
- 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.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 246
- 238000013507 mapping Methods 0.000 claims description 37
- 238000001514 detection method Methods 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 9
- 238000010998 test method Methods 0.000 claims description 9
- 239000000523 sample Substances 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/26—Functional testing
- G06F11/273—Tester hardware, i.e. output processing circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
Abstract
The application relates to the technical field of automatic testing, and discloses a testing method and a testing system of face recognition equipment. The test system comprises a test jig, a test board and a test terminal; the test jig is used for focusing the face recognition equipment; the test board is electrically connected with the test jig and is configured to drive the test jig so that the test jig focuses on the face recognition equipment; the test terminal is electrically connected with the test board and is configured to judge whether the focal length of the face recognition device is debugged according to the definition of the identification image, and when the definition of the identification image does not meet the preset definition condition, the test board is used for driving the test jig to enable the test jig to focus the face recognition device so that the definition of the identification image meets the preset definition condition. According to the embodiment of the application, the testing efficiency of the face recognition device and the accuracy of the testing result can be improved.
Description
Technical Field
The application relates to the technical field of automatic testing, in particular to a testing method and a testing system of face recognition equipment.
Background
Face recognition is a biological recognition technology for carrying out identity recognition based on facial feature information of people, and face recognition equipment is equipment based on the face recognition technology commonly used for entrance guard, attendance checking and the like.
When the face recognition device is used daily, the functions of the face recognition device, such as hardware, interfaces, snap-shot functions and the like of the face recognition device, are required to be tested, but in the prior art, the function test of the face recognition device is required to be completed manually in a step-by-step manner. Therefore, the prior art has the problems of complicated steps, high cost, high error rate and the like in the test of the face recognition equipment.
Disclosure of Invention
The purpose of the application is to provide a testing method and a testing system of face recognition equipment, and aims to improve the testing efficiency of the face recognition equipment and the accuracy of a testing result.
The embodiment of the application provides a test system, which is applied to face recognition equipment and comprises:
the test jig is used for focusing the face recognition equipment;
the test board is electrically connected with the test jig and is configured to drive the test jig so that the test jig focuses on the face recognition equipment; and
the test terminal is electrically connected with the test board and is configured to judge whether the focal length of the face recognition device is debugged according to the definition of the identification image, and when the definition of the identification image does not meet the preset definition condition, the test board is used for driving the test jig to enable the test jig to focus the face recognition device so as to enable the definition of the identification image to meet the preset definition condition; the identification image is an image obtained by shooting a test picture in the effective identification range of the face identification equipment.
In some embodiments, the test terminal is configured to communicate and interact with the test board when the test board is identified, so as to obtain current information of the face recognition device through the test board, and communicate and interact with the face recognition device through the test board when the face recognition device is identified to be powered on normally.
In some embodiments, the test terminal is configured to determine whether the target gray level difference value is greater than a preset gray level threshold, if not, determine that the sharpness of the identification image does not meet the preset sharpness condition, and if so, determine that the sharpness of the identification image meets the preset sharpness condition;
the target gray level difference value is the difference of gray level values between a first pixel point and a second pixel point, the first pixel point is a pixel point at the edge position of a first color region, the second pixel point is a pixel point at the edge position of a second color region, and the first color region and the second color region are regions which are different in color and mutually adjacent in the identification image.
In some embodiments, the test fixture comprises:
a first bracket;
the support plate is fixedly connected with the first bracket, is provided with a lens hole for avoiding the lens of the face recognition device, and is provided with a focusing toothed ring for being clamped with a focusing knob of the face recognition device;
the focusing motor is electrically connected with the test board, is provided with a gear meshed with the focusing toothed ring and is in transmission connection with the focusing toothed ring through the gear; and
and the second bracket is detachably connected with the first bracket, is positioned on one side of the bearing plate away from the first bracket, and is provided with a test probe for electrically connecting the face recognition device.
In some embodiments, the test board is configured to output a pulse width modulation signal to the test fixture, so that the test fixture rotates the focusing knob of the face recognition device by a corresponding angle according to the duty cycle of the pulse width modulation signal;
the duty cycle of the pulse width modulated signal decreases as the sharpness of the identification image increases.
In some embodiments, the test plate comprises:
the driving module is configured to receive the control signal of the test terminal and output a corresponding pulse width modulation signal to the test jig so as to drive the test jig to execute a corresponding focusing operation;
the serial port communication module is configured to acquire model information and version information of the face recognition equipment;
the voltage detection module is configured to acquire voltage information of the face recognition device; and
and the current detection module is configured to acquire current information of the face recognition device.
The embodiment of the application also provides a test method, which is applied to the test system, and the test terminal executes the test method and comprises the following steps:
acquiring the identification image;
calculating a target gray level difference value; the target gray level difference value is the difference of gray level values between a first pixel point and a second pixel point, the first pixel point is a pixel point at the edge position of a first color region, the second pixel point is a pixel point at the edge position of a second color region, and the first color region and the second color region are regions which are different in color and mutually adjacent in the identification image;
judging whether the target gray level difference value is larger than a preset gray level threshold value or not;
if the face recognition device is not larger than the preset value, outputting a control signal to the test board, and enabling the test board to drive the test jig so as to focus the face recognition device; returning to the step of acquiring the identification image;
if the focal length of the face recognition device is larger than the focal length of the face recognition device, the focal length of the face recognition device is determined to be accurate.
In some embodiments, the calculating the target gray scale difference value comprises:
determining a first mapping relation according to the optical parameters of the face recognition equipment and the shooting distance of the test picture; the first mapping relation is a mapping relation of the size of the pixel point of the identification image relative to the actual distance on the test picture;
determining a second mapping relation according to the first mapping relation; the first color area and the second color area are sector areas obtained by dividing the same circle, and the second mapping relation is a mapping relation of the width and the height of the pixel points in the first color area in the vertical direction;
selecting a pixel point which is positioned at an edge position and is completely positioned in the first color area from the first color area according to the first mapping relation and the second mapping relation, and selecting a pixel point which is positioned at the edge position and is adjacent to the first pixel point from the second color area as the second pixel point, wherein the pixel point is positioned at the edge position and is completely positioned in the first color area and is used as the first pixel point;
and calculating the difference of gray values of the first pixel point and the second pixel point to obtain the target gray difference value.
In some embodiments, the first mapping relationship is:
F=C/(2*E*tan(A/2))，
G=D/(2*E*tan(B/2))，
wherein A is the horizontal view angle of the face recognition device, B is the vertical view angle of the face recognition device, C is the horizontal direction pixel of the face recognition device, D is the vertical direction pixel of the face recognition device, E is the shooting distance of the test picture, F is the width of the pixel point of the identification picture corresponding to the test picture, and G is the height of the pixel point of the identification picture corresponding to the test picture;
the second mapping relation is as follows:
K≈n*N*F/2π，
H=K/G，
wherein K is the height of the first pixel point, N is the sum of the numbers of the first color area and the second color area, N is the number of the pixel points with the height of K, and H is the number of the pixel points between the pixel points with the height of K and the circle center of the first color area in the vertical direction.
In some embodiments, the test method further comprises: when the target gray level difference value is reduced, a control signal is output to the test board, so that the test board drives the test jig to focus the face recognition device in the opposite focusing direction.
The beneficial effects of this application: the test board drives the test fixture so that the test fixture focuses on the face recognition device, the test terminal judges whether the focal length of the face recognition device is debugged according to the definition of the identification image, and when the definition of the identification image does not meet the preset definition condition, the test board drives the test fixture so that the test fixture focuses on the face recognition device so that the definition of the identification image meets the preset definition condition, and the test efficiency of the face recognition device and the accuracy of the test result can be improved.
Drawings
FIG. 1 is a schematic diagram of an alternative configuration of a test system provided in an embodiment of the present application.
Fig. 2 is an exploded schematic view of a test fixture according to an embodiment of the present application.
Fig. 3 is a schematic structural view of an alternative test board provided in an embodiment of the present application.
Fig. 4 is an alternative flow chart of a test method provided by an embodiment of the present application.
Fig. 5 is a schematic diagram of an identification image provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or circuits is not necessarily limited to those steps or circuits that are expressly listed or inherent to such process, method, article, or apparatus.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the present application.
The embodiment of the application provides a test system which is applied to face recognition equipment. Referring to fig. 1, in an embodiment, the test system includes a test fixture 100, a test board 200, and a test terminal 300, wherein the test board 200 is electrically connected to the test fixture 100, and the test terminal 300 is electrically connected to the test board 200.
The test fixture 100 is used for focusing the face recognition device; the test board 200 is configured to drive the test fixture 100, so that the test fixture 100 focuses on the face recognition device; the test terminal 300 is configured to determine whether the focal length of the face recognition device is debugged according to the definition of the recognition image, and drive the test jig 100 through the test board 200 when the definition of the recognition image does not meet the preset definition condition, so that the test jig 100 focuses the face recognition device to enable the definition of the recognition image to meet the preset definition condition. The identification image is an image obtained by shooting a test picture in the effective identification range of the face identification device.
According to the test system provided by the embodiment of the application, the test terminal 300 determines whether the focal length of the face recognition device accords with the use scene according to the definition of the recognition image, if the definition of the recognition image does not accord with the preset definition condition, the test terminal 300 sends a control signal to the test board 200, and the test board 200 drives the test jig 100 to perform corresponding focusing operation on the face recognition device until the definition of the recognition image accords with the preset definition condition. Specifically, firstly, the face recognition device is assembled on the test fixture 100, a test picture is placed in the effective recognition range of the face recognition device, then the test terminal 300 is respectively in communication interaction with the test board 200 and the face recognition device, the test terminal 300 controls the face recognition device to shoot the test picture so as to generate a recognition image, the test terminal 300 obtains the recognition image and then carries out definition analysis on the recognition image, when the definition of the recognition picture does not meet the preset definition condition, the test terminal 300 sends a control signal to the test board 200, the test fixture 100 is driven by the test board 200 to carry out corresponding focusing operation on the face recognition device, and after each focusing, the test terminal 300 carries out definition analysis on the recognition image generated after focusing until the definition of the recognition image meets the preset definition condition.
In some embodiments, the test terminal 300 is configured to communicatively interact with the test board 200 upon identification of the test board 200 to obtain current information of the face recognition device through the test board 200, and to communicatively interact with the face recognition device through the test board 200 upon identification of normal power-up of the face recognition device.
Specifically, when the information such as the hardware ID and description of the port device is the test board 200, which is identified by the test program of the test terminal 300, handshake communication is performed with the test board 200, and configuration information on the test board 200 is read, after the test board 200 and the test terminal 300 are successfully communicated, the test board 200 receives a control signal of the test terminal 300, continuously detects whether a current flows through a port connected with the face recognition device, if the current changes, handshake communication is attempted between the port and the face recognition device through the UART port, and if the communication is successful, an automatic test flow starts.
In some embodiments, the test terminal 300 is configured to determine whether the target gray level difference is greater than a preset gray level threshold, if not, determine that the sharpness of the identification image does not meet the preset sharpness condition, and if so, determine that the sharpness of the identification image meets the preset sharpness condition. The target gray level difference value is the difference of gray level values between a first pixel point and a second pixel point, the first pixel point is a pixel point at the edge position of a first color area, the second pixel point is a pixel point at the edge position of a second color area, and the first color area and the second color area are areas which are different in color and mutually adjacent in the identification image.
As shown in fig. 5, the identification image is composed of a plurality of first color regions (regions denoted by reference numeral 501 in fig. 5, the same applies hereinafter) and second color regions (regions denoted by reference numeral 502 in fig. 5, the same applies hereinafter) which are different in color and adjacent to each other, each of the first color regions and the second color regions is arc-shaped, the circular angle is 5 °, 32 are provided, and each of the first color regions and each of the second color regions is formed into a circle.
Specifically, the first pixel is located at an edge position of the first color area, the second pixel is located at an edge position of the second color area, the first pixel and the second pixel are adjacent to each other, the test terminal 300 determines positions of the first pixel and the second pixel according to an actual resolution of a camera of the face recognition device and a size of the recognition image, if a difference between gray values of the first pixel and the second pixel is greater than a preset gray threshold, it is determined that the definition of the recognition image meets a preset definition condition, and if a difference between gray values of the first pixel and the second pixel is not greater than the preset gray threshold, it is determined that the definition of the recognition image does not meet the preset definition condition. The preset gray threshold is obtained after debugging according to actual parameters of a camera of the face recognition device.
As shown in fig. 2, in some embodiments, the test fixture 100 includes a first bracket 110, a carrier plate 120, a focus motor 130, and a second bracket 140. The bearing plate 120 is fixedly connected with the first bracket 110, is provided with a lens hole 121 for avoiding a lens of face recognition equipment, and is provided with a focusing toothed ring 122 for being clamped with a focusing knob of the face recognition equipment; the focusing motor 130 is electrically connected with the test board 200, is provided with a gear 131 meshed with the focusing toothed ring 122, and is in transmission connection with the focusing toothed ring 122 through the gear 131; the second bracket 140 is detachably connected to the first bracket 110, and is disposed at a side of the support plate 120 away from the first bracket 110, and is provided with a test probe 141 for electrically connecting with the face recognition device.
The first bracket 110 is used as a base of the test fixture 100, and is configured with a plurality of assembly columns, and the first bracket 110 is sequentially inserted and connected with the support plate 120 and the second bracket 140 through the assembly columns thereof so as to fix the support plate 120 and the second bracket 140. The second bracket 140 is detachably connected with the first bracket 110, and in actual use, the second bracket 140 is detached first, then the face recognition device is placed on the supporting plate 120, and finally the second bracket 140 is reinstalled with the first bracket 110, so that the face recognition device is fixed between the supporting plate 120 and the second bracket 140.
The support plate 120 is used for carrying face recognition equipment, two lens holes 121 are formed, two cameras respectively used for the face recognition equipment penetrate through, the focusing toothed ring 122 is arranged on the outer edge of the lens holes 121, the focusing toothed ring 122 is rotatably mounted on the support plate 120, and an inner hole of the focusing toothed ring 122 is clamped with a focusing knob of the face recognition equipment, so that the focusing knob of the face recognition equipment rotates along with the rotation of the focusing toothed ring 122.
In actual use, after the face recognition device is fixed between the support plate 120 and the second bracket 140, the test probe 141 is electrically connected with the face recognition device, the test probe 141 is electrically connected with the test board 200, and the test terminal 300 communicates with the face recognition device through the USB interface, so that the test terminal 300 can obtain the identification image obtained by shooting the face recognition device, the test terminal 300 controls the focusing motor 130 according to the definition judgment result of the identification image, and a control signal is sent to the test board 200, so that the test board 200 drives the focusing motor 130 to rotate, and the gear 131 drives the focusing toothed ring 122 to rotate, so as to focus the face recognition device.
In some embodiments, the test board 200 is configured to output a pulse width modulation signal to the test fixture 100, such that the test fixture 100 rotates the focus knob of the face recognition device by a corresponding angle according to the duty cycle of the pulse width modulation signal. Wherein the duty cycle of the pulse width modulated signal decreases as the sharpness of the identification image increases.
Specifically, the test board 200 outputs a pulse width modulation signal to the motor driving chip controlling the test fixture 100, and the rotation speed of the motor of the face recognition device can be set to be in three steps of high, medium and low by adjusting the duty ratio of the waveform of the pulse width modulation signal. When focusing is started, a high gear is used first, the motor is controlled to rotate for a certain interval time to achieve rough adjustment, when the target gray level difference value is gradually increased, the duty ratio of the pulse width modulation signal is decreased along with the increasing of the definition of the identification image, the gear is gradually reduced to achieve fine adjustment of the lens, in the process of controlling the motor to rotate and focus, if the target gray level difference value is judged to be smaller, the rotating direction of the motor is changed, the target gray level difference value is made to be larger, and the motor rotating direction is indicated to be correct.
As shown in fig. 3, in some embodiments, the test board 200 includes a drive module 210, a serial port communication module 220, a voltage detection module 230, and a current detection module 240. The driving module 210 is configured to receive the control signal of the test terminal 300 and output a corresponding pulse width modulation signal to the test fixture 100, so as to drive the test fixture 100 to perform a corresponding focusing operation; the serial communication module 220 is configured to obtain model information and version information of the face recognition device; the voltage detection module 230 is configured to obtain voltage information of the face recognition device; the current detection module 240 is configured to obtain current information of the face recognition device.
Specifically, when the test process starts, the test board 200 firstly queries model information, software version information, hardware version information and the like of the face recognition device through the serial port communication module 220 to determine whether the information of the face recognition device to be tested is correct, then the voltage detection module 230 detects each voltage on the face recognition device through the test fixture 100 to determine whether the voltage is correct, a focusing test picture is placed in front of the face recognition device, the driving module 210 controls the motor of the test fixture 100 to realize focusing of the face recognition device, the power line of the test board 200 for supplying power to the face recognition device has a current detection function, the current detection module 240 can continuously detect the current information of the face recognition device and record the current of the face recognition device in the test stage, and if the current exceeds the normal range, the face recognition device is determined to be abnormal. After the testing steps are finished, if the data are normal, the face recognition equipment is judged to be normal, if abnormal data are present, the corresponding testing steps are judged to be abnormal, and a corresponding abnormal label can be attached to a tester, so that maintenance personnel can conveniently maintain the equipment.
The embodiment of the application also provides a testing method which is applied to the testing system and executed by the testing terminal of the embodiment.
Referring to fig. 4, fig. 4 is an alternative flowchart of a testing method according to an embodiment of the present application. In some embodiments of the present application, the method in fig. 4 may specifically include, but is not limited to, steps S401 to S405, and these five steps are described in detail below in conjunction with fig. 4.
Step S401, an identification image is acquired.
In step S402, a target gray scale difference is calculated.
The target gray level difference value is the difference of gray level values between a first pixel point and a second pixel point, the first pixel point is a pixel point at the edge position of a first color area, the second pixel point is a pixel point at the edge position of a second color area, and the first color area and the second color area are areas which are different in color and mutually adjacent in the identification image.
Step S403, determining whether the target gray level difference is greater than a preset gray level threshold. If not, executing step S404; if yes, step S405 is executed.
Step S404, a control signal is output to the test board, so that the test board drives the test jig to focus the face recognition device. Returning to step S401.
Step S405, determining that the focal length of the face recognition device is accurate.
In some embodiments, step S402 specifically includes:
determining a first mapping relation according to the optical parameters of the face recognition equipment and the shooting distance of the test picture;
determining a second mapping relation according to the first mapping relation;
selecting a pixel point which is positioned at the edge position and is completely positioned in the first color area from the first color area according to the first mapping relation and the second mapping relation, and selecting a pixel point which is positioned at the edge position and is adjacent to the first pixel point from the second color area as a second pixel point, wherein the pixel point is positioned at the edge position and is completely positioned in the first color area and is used as the first pixel point;
and calculating the difference of gray values of the first pixel point and the second pixel point to obtain a target gray difference value.
The first mapping relationship is a mapping relationship of the size of the pixel point of the identification image relative to the actual distance on the test image, the first color region and the second color region are sector regions obtained by dividing the same circle, and the second mapping relationship is a mapping relationship of the width and the height of the pixel point in the first color region in the vertical direction.
The first mapping relation is:
F=C/(2*E*tan(A/2))，
G=D/(2*E*tan(B/2))，
wherein A is the horizontal view angle of the face recognition device, B is the vertical view angle of the face recognition device, C is the horizontal direction pixel of the face recognition device, D is the vertical direction pixel of the face recognition device, E is the shooting distance of the test picture, F is the width of the pixel point of the identification picture corresponding to the test picture, and G is the height of the pixel point of the identification picture corresponding to the test picture.
The visual range of the face recognition device may be represented by a horizontal view angle a and a vertical view angle B, for a camera with a pixel J, a pixel in a horizontal direction is C, and a pixel in a vertical direction is D, j=c×d, a photographing distance E of a test picture of the face recognition device is set according to an applicable scene of the face recognition device, and then the test picture is placed at a position with a distance E from the camera of the face recognition device to photograph, so that the first mapping relationship may be obtained.
The second mapping relation is:
K≈n*N*F/2π，
H=K/G，
wherein K is the height of the first pixel point, N is the sum of the numbers of the first color area and the second color area, N is the number of the pixel points with the height of K, and H is the number of the pixel points between the pixel points with the height of K and the circle center of the first color area in the vertical direction.
For the identification image, the first color area and the second color area are formed by a plurality of first color areas and second color areas which are different in color and mutually adjacent, the first color areas and the second color areas are arc-shaped, the round angle is 5 degrees, 32 first color areas and 32 second color areas form a circle. And selecting pixel points in a first color area with the boundary line parallel to the vertical direction, selecting pixel points which are positioned at the edge position of the first color area and completely belong to the first color area, and determining the coordinate position of the pixel points, wherein in the horizontal direction corresponding to the pixel points, the sum of the widths of all the pixel points is equal to the arc length of a sector corresponding to the horizontal direction, an arc length formula expressed as a sector is N x F=2pi K/N, the arc length of each sector with different radiuses of the first color area can be determined by calculating the arc length of the sector, the arc length of the sector can be expressed by converting the arc length formula of the sector, the radius of the sector can be determined, and then the number of the pixel points required to be selected from the center of the circle can be determined according to the relation between the radius and the height of the pixel points, so that the second mapping relation can be obtained.
According to the first mapping relation and the second mapping relation, the pixel point which is located at the edge position on the first color area in the vertical direction and is completely located in the first color area can be determined to be used as a first pixel point, the position of the first pixel point in the horizontal direction and the vertical direction is further determined, then the pixel point adjacent to the first pixel point is selected on the adjacent second color area to be used as a second pixel point, the position of the second pixel point can be deduced according to the position of the first pixel point, and finally the difference of gray values between the first pixel point and the second pixel point is calculated to obtain the target gray difference value.
In some embodiments, the above test method further comprises the steps of: when the target gray level difference value is reduced, a control signal is output to the test board, so that the test board drives the test jig to focus the face recognition device along the opposite focusing direction.
Specifically, in the process that the test terminal controls the motor to rotate and focus through the test board, if the target gray level difference value is judged to be smaller, a control signal is output to the test board, so that the test board drives the test jig, the rotation direction of the motor is changed, the face recognition device is focused along the opposite focusing direction, and the target gray level difference value is made larger.
In summary, according to the testing method and the testing system for the face recognition device, the testing jig is driven by the testing board, so that the testing jig focuses on the face recognition device, the testing terminal judges whether the focal length of the face recognition device is debugged according to the definition of the identification image, when the definition of the identification image does not meet the preset definition condition, the testing jig is driven by the testing board, so that the testing jig focuses on the face recognition device, the definition of the identification image meets the preset definition condition, and the testing efficiency of the face recognition device and the accuracy of the testing result can be improved.
It should be understood that in this application, "at least one" means one or more, and "a plurality" means two or more. "and/or" for describing the association relationship of the association object, the representation may have three relationships, for example, "a and/or B" may represent: only a, only B and both a and B are present, wherein a, B may be singular or plural. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b or c may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
Preferred embodiments of the present application are described above with reference to the accompanying drawings, and thus do not limit the scope of the claims of the embodiments of the present application. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the embodiments of the present application shall fall within the scope of the claims of the embodiments of the present application.
Claims (10)
1. A test system for use with face recognition devices, comprising:
the test jig is used for focusing the face recognition equipment;
the test board is electrically connected with the test jig and is configured to drive the test jig so that the test jig focuses on the face recognition equipment; and
the test terminal is electrically connected with the test board and is configured to judge whether the focal length of the face recognition device is debugged according to the definition of the identification image, and when the definition of the identification image does not meet the preset definition condition, the test board is used for driving the test jig to enable the test jig to focus the face recognition device so as to enable the definition of the identification image to meet the preset definition condition; the identification image is an image obtained by shooting a test picture in the effective identification range of the face identification equipment.
2. The test system of claim 1, wherein the test terminal is configured to communicatively interact with the test board when the test board is identified, to obtain current information of the face recognition device through the test board, and to communicatively interact with the face recognition device through the test board when the face recognition device is identified as being powered up normally.
3. The test system according to claim 1, wherein the test terminal is configured to determine whether the target gray level difference is greater than a preset gray level threshold, if not, determine that the sharpness of the identification image does not meet the preset sharpness condition, and if so, determine that the sharpness of the identification image meets the preset sharpness condition;
the target gray level difference value is the difference of gray level values between a first pixel point and a second pixel point, the first pixel point is a pixel point at the edge position of a first color region, the second pixel point is a pixel point at the edge position of a second color region, and the first color region and the second color region are regions which are different in color and mutually adjacent in the identification image.
4. The test system of claim 1, wherein the test fixture comprises:
a first bracket;
the support plate is fixedly connected with the first bracket, is provided with a lens hole for avoiding the lens of the face recognition device, and is provided with a focusing toothed ring for being clamped with a focusing knob of the face recognition device;
the focusing motor is electrically connected with the test board, is provided with a gear meshed with the focusing toothed ring and is in transmission connection with the focusing toothed ring through the gear; and
and the second bracket is detachably connected with the first bracket, is positioned on one side of the bearing plate away from the first bracket, and is provided with a test probe for electrically connecting the face recognition device.
5. The test system of claim 1, wherein the test board is configured to output a pulse width modulation signal to the test fixture, such that the test fixture rotates a focus knob of the face recognition device by a corresponding angle according to a duty cycle of the pulse width modulation signal;
the duty cycle of the pulse width modulated signal decreases as the sharpness of the identification image increases.
6. The test system of claim 1 or 5, wherein the test plate comprises:
the driving module is configured to receive the control signal of the test terminal and output a corresponding pulse width modulation signal to the test jig so as to drive the test jig to execute a corresponding focusing operation;
the serial port communication module is configured to acquire model information and version information of the face recognition equipment;
the voltage detection module is configured to acquire voltage information of the face recognition device; and
and the current detection module is configured to acquire current information of the face recognition device.
7. A test method applied to the test system of any one of claims 1 to 6, wherein the test terminal performs the test method comprising:
acquiring the identification image;
calculating a target gray level difference value; the target gray level difference value is the difference of gray level values between a first pixel point and a second pixel point, the first pixel point is a pixel point at the edge position of a first color region, the second pixel point is a pixel point at the edge position of a second color region, and the first color region and the second color region are regions which are different in color and mutually adjacent in the identification image;
judging whether the target gray level difference value is larger than a preset gray level threshold value or not;
if the face recognition device is not larger than the preset value, outputting a control signal to the test board, and enabling the test board to drive the test jig so as to focus the face recognition device; returning to the step of acquiring the identification image;
if the focal length of the face recognition device is larger than the focal length of the face recognition device, the focal length of the face recognition device is determined to be accurate.
8. The method of testing according to claim 7, wherein said calculating a target gray scale difference value comprises:
determining a first mapping relation according to the optical parameters of the face recognition equipment and the shooting distance of the test picture; the first mapping relation is a mapping relation of the size of the pixel point of the identification image relative to the actual distance on the test picture;
determining a second mapping relation according to the first mapping relation; the first color area and the second color area are sector areas obtained by dividing the same circle, and the second mapping relation is a mapping relation of the width and the height of the pixel points in the first color area in the vertical direction;
selecting a pixel point which is positioned at an edge position and is completely positioned in the first color area from the first color area according to the first mapping relation and the second mapping relation, and selecting a pixel point which is positioned at the edge position and is adjacent to the first pixel point from the second color area as the second pixel point, wherein the pixel point is positioned at the edge position and is completely positioned in the first color area and is used as the first pixel point;
and calculating the difference of gray values of the first pixel point and the second pixel point to obtain the target gray difference value.
9. The method of claim 7, wherein the first mapping relationship is:
F=C/(2*E*tan(A/2))，
G=D/(2*E*tan(B/2))，
wherein A is the horizontal view angle of the face recognition device, B is the vertical view angle of the face recognition device, C is the horizontal direction pixel of the face recognition device, D is the vertical direction pixel of the face recognition device, E is the shooting distance of the test picture, F is the width of the pixel point of the identification picture corresponding to the test picture, and G is the height of the pixel point of the identification picture corresponding to the test picture;
the second mapping relation is as follows:
K≈n*N*F/2π，
H=K/G，
wherein K is the height of the first pixel point, N is the sum of the numbers of the first color area and the second color area, N is the number of the pixel points with the height of K, and H is the number of the pixel points between the pixel points with the height of K and the circle center of the first color area in the vertical direction.
10. The test method of claim 7, further comprising: when the target gray level difference value is reduced, a control signal is output to the test board, so that the test board drives the test jig to focus the face recognition device in the opposite focusing direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311804362.1A CN117472677B (en) | 2023-12-26 | 2023-12-26 | Face recognition equipment testing method and testing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311804362.1A CN117472677B (en) | 2023-12-26 | 2023-12-26 | Face recognition equipment testing method and testing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117472677A true CN117472677A (en) | 2024-01-30 |
| CN117472677B CN117472677B (en) | 2024-03-08 |
Family
ID=89623750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311804362.1A Active CN117472677B (en) | 2023-12-26 | 2023-12-26 | Face recognition equipment testing method and testing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117472677B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090047177A (en) * | 2007-11-07 | 2009-05-12 | 삼성디지털이미징 주식회사 | Apparatus and method for adjusting focus by face detection in digital image processing device |
| CN102364369A (en) * | 2011-02-28 | 2012-02-29 | 深圳市大族激光科技股份有限公司 | Focusing method of focusing device |
| CN102368134A (en) * | 2011-10-05 | 2012-03-07 | 深圳市联德合微电子有限公司 | Automatic focusing method of cell phone camera module, apparatus thereof and system thereof |
| CN104639937A (en) * | 2015-02-06 | 2015-05-20 | 苏州艾微视图像科技有限公司 | Automatic test device of camera |
| CN104639936A (en) * | 2015-02-06 | 2015-05-20 | 苏州艾微视图像科技有限公司 | Automatic test method of camera |
| CN108833770A (en) * | 2018-05-23 | 2018-11-16 | 释码融和（上海）信息科技有限公司 | Image definition calculation method, calculating equipment and focusing system for focusing |
| CN109451244A (en) * | 2018-12-21 | 2019-03-08 | 广州医软智能科技有限公司 | A kind of automatic focusing method and system based on liquid lens |
| CN110519588A (en) * | 2019-09-05 | 2019-11-29 | 普联技术有限公司 | For the Approach for detecting image sharpness of focusing, device and photographic device |
| WO2020087434A1 (en) * | 2018-11-01 | 2020-05-07 | 深圳技术大学（筹） | Method and device for evaluating resolution of face image |
| CN112468804A (en) * | 2020-12-22 | 2021-03-09 | 深圳中科精工科技有限公司 | Camera test equipment |
| CN113407395A (en) * | 2021-06-08 | 2021-09-17 | 深圳市海清视讯科技有限公司 | Testing method and device of face recognition equipment |
| CN215647135U (en) * | 2021-08-12 | 2022-01-25 | 惠州市众兴圆科技有限公司 | A test fixture for camera focusing |
-
2023
- 2023-12-26 CN CN202311804362.1A patent/CN117472677B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090047177A (en) * | 2007-11-07 | 2009-05-12 | 삼성디지털이미징 주식회사 | Apparatus and method for adjusting focus by face detection in digital image processing device |
| CN102364369A (en) * | 2011-02-28 | 2012-02-29 | 深圳市大族激光科技股份有限公司 | Focusing method of focusing device |
| CN102368134A (en) * | 2011-10-05 | 2012-03-07 | 深圳市联德合微电子有限公司 | Automatic focusing method of cell phone camera module, apparatus thereof and system thereof |
| CN104639937A (en) * | 2015-02-06 | 2015-05-20 | 苏州艾微视图像科技有限公司 | Automatic test device of camera |
| CN104639936A (en) * | 2015-02-06 | 2015-05-20 | 苏州艾微视图像科技有限公司 | Automatic test method of camera |
| CN108833770A (en) * | 2018-05-23 | 2018-11-16 | 释码融和（上海）信息科技有限公司 | Image definition calculation method, calculating equipment and focusing system for focusing |
| WO2020087434A1 (en) * | 2018-11-01 | 2020-05-07 | 深圳技术大学（筹） | Method and device for evaluating resolution of face image |
| CN109451244A (en) * | 2018-12-21 | 2019-03-08 | 广州医软智能科技有限公司 | A kind of automatic focusing method and system based on liquid lens |
| CN110519588A (en) * | 2019-09-05 | 2019-11-29 | 普联技术有限公司 | For the Approach for detecting image sharpness of focusing, device and photographic device |
| CN112468804A (en) * | 2020-12-22 | 2021-03-09 | 深圳中科精工科技有限公司 | Camera test equipment |
| CN113407395A (en) * | 2021-06-08 | 2021-09-17 | 深圳市海清视讯科技有限公司 | Testing method and device of face recognition equipment |
| CN215647135U (en) * | 2021-08-12 | 2022-01-25 | 惠州市众兴圆科技有限公司 | A test fixture for camera focusing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117472677B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6606458B2 (en) | Automatic framing camera | |
| US20210358110A1 (en) | Device and Method for Processing at Least One Work Area With a Processing Tool | |
| CN112333443A (en) | Lens performance detection system and method | |
| CN105405115A (en) | Image module group alignment system and method thereof | |
| CN208366871U (en) | Detection system | |
| CN117472677B (en) | Face recognition equipment testing method and testing system | |
| CN108760059B (en) | Detection method, detection device and detection system of laser projector | |
| CN113143193A (en) | Intelligent vision testing method, device and system | |
| CN112643324A (en) | Automatic screw driving equipment and automatic screw driving method adopting same | |
| CN217739490U (en) | Gene sequencer and positioning precision detection equipment of motion platform module thereof | |
| CN112322713B (en) | Imaging method, device and system and storage medium | |
| CN110823276A (en) | Method, device and system for detecting vision sensor | |
| JP2008089811A (en) | Imaging apparatus and control method therefor | |
| CN109684935A (en) | A kind of acquisition of high-precision 3D face, payment system and method | |
| US11397417B2 (en) | Hybrid wide field of view target system | |
| JP2004101240A (en) | Stacked belt ring inspection method and device | |
| CN220380540U (en) | Calibration equipment and configuration system of visual inspection device | |
| CN112529855A (en) | Detection method and detection device for remote controller and computer readable storage medium | |
| CN112804439A (en) | Device and method for adaptively shooting moving target | |
| CN111336918A (en) | Plug-in clamping jaw detection process and system and clamping jaw | |
| CN114006999B (en) | Periscope type camera device processing method | |
| CN117054051B (en) | Debugging method of multi-station rotary platform control device and screen brightness testing system | |
| CN109862348A (en) | A kind of picture system parsing power test judgement method and device | |
| US7366327B2 (en) | System for recognizing wheels by artificial vision | |
| CN113466440B (en) | Biochemical analyzer positioning accuracy testing equipment and method |
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 |