Face image acquisition equipment and its control method and face image acquisition system

Abstract

This application provides a face image acquisition device and its control method, as well as a face image acquisition system. The device includes: a camera for acquiring a face image of a target person, the target person being the person whose face image is to be acquired; a first rotation mechanism for connecting the camera, the first rotation mechanism being used to drive the camera to rotate along a first direction, the first direction being parallel to a horizontal plane; and a second rotation mechanism for connecting the camera, the second rotation mechanism being used to drive the camera to rotate along a second direction, the second direction being parallel to a vertical plane. This solves the problem in the prior art where the positional offset of the acquired face image leads to difficulty in face recognition.

Description

Technical Field

[0001] This application relates to the field of facial recognition technology, and more specifically, to a facial image acquisition device, a control method for the facial image acquisition device, a control device, a computer-readable storage medium, and a facial image acquisition system. Background Technology

[0002] With the digital transformation of bank branches, reducing the number of teller counters and freeing up more branch staff to engage in external marketing has become an industry trend, leading to the migration of more and more business products to self-service machines. Based on the objective requirements for customer information security and authenticity, scenarios involving facial recognition have become increasingly diverse, and the application of facial recognition technology has become more widespread. During customer transactions, bank self-service machines such as ATMs and ITMs use their cameras to collect, compare, identify, and store customer facial information. This method of data collection meets regulatory compliance requirements while also providing convenient and considerate services to customers.

[0003] However, with the increasing use of facial recognition on self-service devices and customers' dual demands for service quality and efficiency, the mechanical facial recognition method has gradually revealed many shortcomings. In the traditional model, most front-facing cameras are directly and fixedly embedded in the self-service device for mechanical data collection, lacking flexibility. Furthermore, the varying heights of customers create the problem of customers repeatedly adjusting their position and posture to match the effective area captured by the camera during the facial recognition process. Although bank self-service devices are constantly being upgraded, facial information collection still typically requires bank staff to provide one-on-one assistance to customers, which is both time-consuming and labor-intensive. To better meet customers' requirements for the speed and quality of facial information collection, it is urgent to improve and optimize the equipment and methods used for information collection.

[0004] The information disclosed above in the background section is only intended to enhance the understanding of the background art of the art described herein. Therefore, the background art may contain certain information that does not constitute prior art known to those skilled in the art in this country. Summary of the Invention

[0005] The main objective of this application is to provide a face image acquisition device, a control method for the face image acquisition device, a control device, a computer-readable storage medium, and a face image acquisition system to solve the problem that the positional offset of the acquired face image in the prior art leads to the difficulty of face recognition.

[0006] According to one aspect of the present invention, a face image acquisition device is provided, comprising: a camera for acquiring a face image of a target person, the target person being the person whose face image is to be acquired; a first rotation mechanism for connecting the camera, the first rotation mechanism being used to drive the camera to rotate along a first direction, the first direction being parallel to a horizontal plane; and a second rotation mechanism for connecting the camera, the second rotation mechanism being used to drive the camera to rotate along a second direction, the second direction being parallel to a vertical plane.

[0007] Optionally, the second rotating mechanism includes a first rotating body, and the device further includes: a first ultrasonic sensor located on the first rotating body and on one side of the camera, the first ultrasonic sensor being used to detect the distance between the target person and the first ultrasonic sensor, the second rotating mechanism being used to drive the first rotating body to rotate along the second direction; and a second ultrasonic sensor located on the first rotating body and on the other side of the camera, the second ultrasonic sensor being used to detect the distance between the target person and the second ultrasonic sensor.

[0008] Optionally, the device further includes: a chassis located on the side of the first rotating body away from the camera; and a telescopic mechanism connected to the chassis and the first rotating body, the telescopic mechanism being used to drive the first rotating body away from or towards the chassis.

[0009] According to another aspect of the present invention, a control method for a face image acquisition device is also provided. The method includes: controlling a camera to acquire a face image of a target person to obtain a first reference face image; determining a first distance and a second distance based on the first reference face image, wherein the first distance is the distance between the midpoint of the face image and a first central axis, and the second distance is the distance between the midpoint of the face image and a second central axis, wherein the first central axis is the major axis of a standard elliptical outline of the screen, and the second central axis is the minor axis of the standard elliptical outline of the screen; controlling a first rotation mechanism to drive the camera to rotate along a first direction until the first distance is less than a predetermined value, and controlling a second rotation mechanism to drive the camera to rotate along a second direction until the second distance is less than the predetermined value; and controlling the camera to acquire a face image of the target person to obtain a standard face image.

[0010] Optionally, the second rotating mechanism includes a first rotating body, and the device further includes a first ultrasonic sensor and a second ultrasonic sensor. The first ultrasonic sensor is located on the first rotating body and on one side of the camera. The first ultrasonic sensor is used to detect the distance between the target person and the first ultrasonic sensor. The second rotating mechanism is used to drive the first rotating body to rotate along the second direction. The second ultrasonic sensor is located on the first rotating body and on the other side of the camera. The second ultrasonic sensor is used to detect the distance between the target person and the second ultrasonic sensor. Before controlling the camera to acquire the facial image of the target person, the method further includes: controlling the first ultrasonic sensor to detect the distance between the target person and the camera. The distance between the first ultrasonic sensors is measured to obtain a third distance. The second ultrasonic sensor is controlled to detect the distance between the target person and the second ultrasonic sensor to obtain a fourth distance. If the distance difference is greater than a first distance threshold, a first prompt message is issued, which prompts the target person to move to reduce the distance difference, where the distance difference is the absolute value of the difference between the third distance and the fourth distance. If the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval, a second prompt message is issued, which prompts the target person to move so that the average distance is within the distance interval, where the average distance is the average of the third distance and the fourth distance.

[0011] Optionally, when the distance difference is greater than a first distance threshold, a first prompt message is issued, including: when the distance difference is greater than the first distance threshold and the third distance is greater than the fourth distance, the first prompt message is issued to prompt the target person to move along a third direction, the third direction being the direction in which the first ultrasonic sensor moves away from the camera; when the distance difference is greater than the first distance threshold and the third distance is less than the fourth distance, the first prompt message is issued to prompt the target person to move along a fourth direction, the fourth direction being the direction in which the second ultrasonic sensor moves away from the camera.

[0012] Optionally, when the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval, a second prompt message is issued, including: when the distance difference is less than or equal to the first distance threshold and the average distance is greater than a second distance threshold, the second prompt message is issued to prompt the target person to move in a direction closer to the camera, and the second distance threshold is the maximum value of the distance interval; when the distance difference is less than or equal to the first distance threshold and the average distance is less than a third distance threshold, the second prompt message is issued to prompt the target person to move in a direction away from the camera, and the third distance threshold is the minimum value of the distance interval.

[0013] Optionally, after issuing a second prompt message when the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval, the method further includes: controlling the second rotating mechanism to drive the camera to rotate along the second direction, and controlling the first ultrasonic sensor and the second ultrasonic sensor to collect the third distance and the fourth distance once at predetermined angle intervals, respectively, to obtain multiple three-distances and multiple fourth distances, each of which corresponds one-to-one with the rotation angle of the camera; calculating multiple average distances based on the multiple three-distances and multiple fourth distances, each of which corresponds one-to-one with the rotation angle; issuing a third prompt message when the rotation angle corresponding to the largest average distance is not within the rotation angle interval, until the rotation angle corresponding to the largest average distance is within the rotation angle interval and the minimum distance is within the distance interval, the third prompt message being used to prompt the target person to move in a direction away from the camera, the minimum distance being the minimum value of the components of each average distance on the horizontal plane.

[0014] Optionally, controlling a first rotating mechanism to drive the camera to rotate along a first direction until the first distance is less than a predetermined value, and controlling a second rotating mechanism to drive the camera to rotate along a second direction until the second distance is less than the predetermined value, includes: when the first distance is greater than the second distance, controlling the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than the predetermined value, and when the first distance is less than the predetermined value, controlling the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value; when the first distance is less than the second distance, controlling the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value, and when the second distance is less than the predetermined value, controlling the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than the predetermined value.

[0015] Optionally, the device further includes a chassis and a telescopic mechanism. The chassis is located on the side of the first rotating body away from the camera. The telescopic mechanism is connected to the chassis and the first rotating body. The telescopic mechanism is used to drive the first rotating body away from or towards the chassis. Before controlling the camera to acquire the face image of the target person and obtain a standard face image, after controlling the first rotating mechanism to drive the camera to rotate along a first direction until the first distance is less than a predetermined value, and controlling the second rotating mechanism to drive the camera to rotate along a second direction until the second distance is less than the predetermined value, the method further includes: controlling the camera to acquire the face image of the target person and obtain a second reference face image; calculating the ratio of the area of ​​the first circumscribed rectangle to the area of ​​the second circumscribed rectangle to obtain the face image proportion, wherein the first circumscribed rectangle is the circumscribed rectangle of the second reference face image, and the second circumscribed rectangle is the circumscribed rectangle of the standard elliptical frame of the screen; if the face image proportion is not within the proportion range, controlling the telescopic mechanism to drive the first rotating body to move so that the face image proportion is within the proportion range.

[0016] Optionally, if the proportion of the face image is not within the proportion range, controlling the telescopic mechanism to drive the first rotating body to move so that the proportion of the face image is within the proportion range includes: if the proportion of the face image is less than the minimum value of the proportion range, controlling the telescopic mechanism to drive the first rotating body away from the chassis; if the proportion of the face image is greater than the maximum value of the proportion range, controlling the telescopic mechanism to drive the first rotating body closer to the chassis.

[0017] According to another aspect of the present invention, a control device for a face image acquisition device is also provided. The device includes: a first control unit, configured to control a camera to acquire a face image of a target person to obtain a first reference face image; a determining unit, configured to determine a first distance and a second distance based on the first reference face image, wherein the first distance is the distance between the midpoint of the face image and a first central axis, and the second distance is the distance between the midpoint of the face image and a second central axis, wherein the first central axis is the major axis of a standard elliptical outline of the screen, and the second central axis is the minor axis of the standard elliptical outline of the screen; a second control unit, configured to control a first rotating mechanism to drive the camera to rotate along a first direction until the first distance is less than a predetermined value, and to control a second rotating mechanism to drive the camera to rotate along a second direction until the second distance is less than the predetermined value; and a third control unit, configured to control the camera to acquire the face image of the target person to obtain a standard face image.

[0018] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein when the program is executed by a processor, the processor performs any one of the methods described.

[0019] According to another aspect of the present invention, a face image acquisition system is also provided, comprising: a face image acquisition device, one or more processors, a memory, a display device, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any one of the methods described.

[0020] In this embodiment of the invention, the aforementioned face image acquisition device includes a camera, a first rotation mechanism, and a second rotation mechanism. The camera is used to acquire a face image of a target person, where the target person is the person whose face image is to be acquired. The first rotation mechanism is connected to the camera and drives the camera to rotate along a first direction, which is parallel to a horizontal plane. The second rotation mechanism is also connected to the camera and drives the camera to rotate along a second direction, which is parallel to a vertical plane. This face image acquisition device, by using the first rotation mechanism to drive the camera to rotate along the first direction and the second rotation mechanism to drive the camera to rotate along the second direction, ensures that the face image acquired by the camera is located within the standard elliptical outline of the screen, avoiding large positional offsets in the acquired face image. This solves the problem in the prior art where positional offsets in the acquired face image lead to significant difficulties in face recognition. Attached Figure Description

[0021] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0022] Figure 1 A schematic diagram of a face image acquisition device according to an embodiment of this application is shown;

[0023] Figure 2 A partial schematic diagram of a face image acquisition device according to an embodiment of this application is shown;

[0024] Figure 3 A partial schematic diagram of a face image acquisition device according to another embodiment of this application is shown;

[0025] Figure 4 A partial schematic diagram of a face image acquisition device according to another embodiment of this application is shown;

[0026] Figure 5 A flowchart is shown of a control method for a face image acquisition device according to an embodiment of this application;

[0027] Figure 6 A schematic diagram of scanning distance measurement using a first ultrasonic sensor and a second ultrasonic sensor according to another embodiment of this application is shown.

[0028] Figure 7 A schematic diagram of a face image wireframe and a standard elliptical wireframe for a screen, according to another embodiment of this application, is shown.

[0029] Figure 8 A schematic diagram of the control device of a face image acquisition device according to an embodiment of this application is shown.

[0030] The above figures include the following reference numerals:

[0031] 1. First ultrasonic receiver; 2. Camera; 3. First rotating body positioning hole; 4. Adaptive acquisition device housing; 5. First stepper motor; 6. Chassis; 7. Chassis telescopic motion slide; 8. First telescopic link; 9. First ultrasonic transmitter; 10. Face image camera fill light; 11. Second rotating body angular displacement sensor; 12. Second rotating body; 13. Second ultrasonic transmitter; 14. Second ultrasonic receiver; 15. First meshing gear; 16. First 17. Rotating body; 18. Telescopic cavity; 19. Telescopic cavity movement slide; 20. Telescopic rod hinge hole; 21. Second telescopic link; 22. Third telescopic link; 23. Fourth telescopic link; 24. Built-in rotating cavity; 25. First rotating body angular displacement sensor; 26. Slide slide block; 27. Hinge sleeve; 28. Slide slide fixed block; 29. ​​Lead screw; 30. "U"-shaped moving distance extender plate; 31. Fixed baffle; 32. Second meshing gear; 33. Second stepper motor. Detailed Implementation

[0032] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of this application. Unless otherwise specified, 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 pertains.

[0033] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0034] It should be understood that when an element (such as a layer, film, region, or substrate) is described as being "on" another element, the element may be directly on the other element, or there may be an intermediate element present. Furthermore, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element, or "connected" to the other element via a third element.

[0035] As mentioned in the background section, the positional offset of the facial images acquired in the prior art makes facial recognition difficult. In order to solve the above problems, in a typical embodiment of this application, a facial image acquisition device, a control method for the facial image acquisition device, a control device, a computer-readable storage medium, and a facial image acquisition system are provided.

[0036] According to embodiments of this application, a face image acquisition device is provided, such as... Figure 1 and Figure 2As shown, the face image acquisition device includes:

[0037] Camera 2 is used to capture facial images of the target person, which is the person whose facial image is to be captured;

[0038] A first rotating mechanism is used to connect the camera 2. The first rotating mechanism is used to drive the camera 2 to rotate along a first direction, which is parallel to the horizontal plane.

[0039] The second rotating mechanism is used to connect the camera 2 and to drive the camera 2 to rotate along a second direction, which is parallel to the vertical plane.

[0040] The aforementioned face image acquisition device includes a camera, a first rotation mechanism, and a second rotation mechanism. The camera is used to acquire a face image of a target person, which is the person whose face image is to be acquired. The first rotation mechanism is connected to the camera and drives the camera to rotate along a first direction, which is parallel to the horizontal plane. The second rotation mechanism is also connected to the camera and drives it to rotate along a second direction, which is parallel to the vertical plane. This face image acquisition device, by using the first rotation mechanism to drive the camera to rotate along the first direction and the second rotation mechanism to drive it to rotate along the second direction, ensures that the face image acquired by the camera is located within a standard elliptical frame on the screen. This avoids large positional offsets in the acquired face image and solves the problem of difficult face recognition caused by positional offsets in existing technologies.

[0041] To determine whether the distance between the target person and the facial image acquisition device is appropriate, one possible implementation is as follows: Figure 2 As shown, the second rotating mechanism includes a first rotating body 16, and the device further includes:

[0042] The first ultrasonic sensor is located on the first rotating body 16 and on one side of the camera 2. The first ultrasonic sensor is used to detect the distance between the target person and the first ultrasonic sensor. The second rotating mechanism is used to drive the first rotating body to rotate along the second direction.

[0043] The second ultrasonic sensor is located on the first rotating body 16 and on the other side of the camera 2. The second ultrasonic sensor is used to detect the distance between the target person and the second ultrasonic sensor.

[0044] In the above embodiments, the first ultrasonic sensor includes a first ultrasonic receiver 1 and a first ultrasonic transmitter 9, and the second ultrasonic sensor includes a second ultrasonic transmitter 13 and a second ultrasonic receiver 14. The distance between the first ultrasonic sensor and the second ultrasonic sensor is 15-20cm, mainly determined by the width range of a human face. Typically, the horizontal distance between the camera of a bank branch self-service device and the customer is controlled within 30cm-40cm. Both the first and second ultrasonic sensors can collect the distance between the target person and the face image acquisition device to determine whether it is within this range.

[0045] It should be noted that, as Figures 1 to 4As shown, the face image acquisition device is a face image position adaptive acquisition device. Besides the sensor and camera, it mainly consists of three modules: a first rotating mechanism, a second rotating mechanism, and a telescopic mechanism. The second rotating mechanism includes a first meshing gear 15, a first rotating body 16, an internal rotating cavity 23, a first rotating body angular displacement sensor 24, a second meshing gear 31, and a second stepper motor 32. The first rotating body angular displacement sensor 24 is coaxially aligned with the first rotating body 16 and fixed to the internal rotating cavity 23. Under the rotational action of the second stepper motor 32, the first meshing gear 15 and the second meshing gear 31 mesh with each other, driving the first rotating body 16 to perform circular motion within the internal rotating cavity 23, thus achieving the up-and-down rotation function. The first rotating mechanism includes the second rotating body angular displacement sensor... The camera 2 has a sensor 11 and a second rotating body 12. A face image camera filler 10 is also located on one side of the camera 2. The concentric hole of the second rotating body angular displacement sensor 11 is interference-fitted with the output shaft of a small stepper motor (not shown) inside the second rotating body 12 and is fixed to the first rotating body 16. The camera 2 and the face image camera filler 10 are driven by the rotation of the second rotating body 12 to perform circular motion, thereby achieving left and right rotation. The telescopic mechanism includes a first stepper motor 5, a chassis telescopic motion slide 7, a first telescopic link 8, a telescopic cavity 17, a telescopic cavity motion slide 18, a second telescopic link 20, a third telescopic link 21, a fourth telescopic link 22, a slide sliding block 25, a hinge sleeve 26, a slide fixing block 27, a lead screw 28, a "U"-shaped moving distance extender plate 29, and a fixed baffle 30. The first telescopic link 8, the second telescopic link 20, the third telescopic link 21, and the fourth telescopic link 22 are hinged to each other through the telescopic link hinge hole 19 to form an "X"-shaped scissor telescopic component. They are also hinged to the "U"-shaped moving distance plate 29 and the fixed baffle 30 through the hinge sleeve 26, and to the slide rail fixed block 27, so that the slide rail sliding block 25 can move horizontally and linearly within the chassis telescopic motion slide rail 7 and the telescopic cavity motion slide rail 18. The first stepper motor 5 drives the lead screw 28 to make a spiral motion, and the "U"-shaped moving distance plate 29 and the fixed baffle 30 contract. The distance between the telescopic cavity motion slide rail 18 and the chassis 6 used for external connection increases, and then the telescopic motion function is realized within the telescopic cavity 17. In addition, the face image position adaptive acquisition device also includes a first rotating body positioning hole 3 and an adaptive acquisition device housing 4. The first rotating body 16 is fixed to the adaptive acquisition device housing 4 through the first rotating body positioning hole 3.

[0046] To determine whether the distance between the target person and the facial image acquisition device is appropriate, one possible implementation is as follows: Figure 1 and Figure 2 As shown, the above-mentioned equipment also includes:

[0047] The chassis 6 is located on the side of the first rotating body 16 away from the camera 2;

[0048] The telescopic mechanism is connected to the chassis 6 and the first rotating body 16. The telescopic mechanism is used to drive the first rotating body 16 away from or closer to the chassis 6.

[0049] In the above embodiments, the telescopic mechanism can move the first rotating body 16 away from or closer to the chassis 6, that is, it can adjust the distance between the camera 2 on the first rotating body 16 and the target person, thereby adjusting the size of the captured image.

[0050] According to an embodiment of this application, a control method for a face image acquisition device is provided.

[0051] Figure 5 This is a flowchart of a control method for a face image acquisition device according to an embodiment of this application. Figure 5 As shown, the method includes the following steps:

[0052] Step S101: Control the camera to capture the face image of the target person to obtain the first reference face image;

[0053] Step S102: Determine a first distance and a second distance based on the first reference face image. The first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis. The first central axis is the major axis of the standard elliptical frame of the screen, and the second central axis is the minor axis of the standard elliptical frame of the screen.

[0054] Step S103: Control the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than a predetermined value, and control the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value.

[0055] Step S104: Control the camera to capture the facial image of the target person to obtain a standard facial image.

[0056] In the control method of the aforementioned face image acquisition device, firstly, the camera is controlled to acquire a face image of the target person to obtain a first reference face image; then, a first distance and a second distance are determined based on the first reference face image, wherein the first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis, wherein the first central axis is the major axis of the standard elliptical outline of the screen, and the second central axis is the minor axis of the standard elliptical outline of the screen; subsequently, a first rotation mechanism is controlled to drive the camera to rotate along a first direction until the first distance is less than a predetermined value, and a second rotation mechanism is controlled to drive the camera to rotate along a second direction until the second distance is less than a predetermined value; finally, the camera is controlled to acquire a face image of the target person to obtain a standard face image. The control method of this face image acquisition device drives the camera to rotate in a first direction through a first rotating mechanism and drives the camera to rotate in a second direction through a second rotating mechanism, so that the face image acquired by the camera is located in the standard elliptical frame of the screen, avoiding large positional offset of the acquired face image, thereby obtaining a standard face image that is easy to recognize, and solving the problem of face recognition difficulty caused by positional offset of the acquired face image in the prior art.

[0057] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0058] To ensure the target person is within a suitable photographing area, one possible implementation method is as follows: Figure 2 As shown, the second rotating mechanism includes a first rotating body 16, and the device further includes a first ultrasonic sensor and a second ultrasonic sensor. The first ultrasonic sensor is located on the first rotating body 16 and on one side of the camera 2. The first ultrasonic sensor is used to detect the distance between the target person and the first ultrasonic sensor. The second rotating mechanism is used to drive the first rotating body 16 to rotate along the second direction. The second ultrasonic sensor is located on the first rotating body 16 and on the other side of the camera. The second ultrasonic sensor is used to detect the distance between the target person and the second ultrasonic sensor. Before step S101, the method further includes:

[0059] Step S201: Control the first ultrasonic sensor to detect the distance between the target person and the first ultrasonic sensor to obtain a third distance; control the second ultrasonic sensor to detect the distance between the target person and the second ultrasonic sensor to obtain a fourth distance.

[0060] Step S202: If the distance difference is greater than the first distance threshold, issue a first prompt message. The first prompt message is used to prompt the target person to move in order to reduce the distance difference. The distance difference is the absolute value of the difference between the third distance and the fourth distance.

[0061] Step S203: When the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval, a second prompt message is issued. The second prompt message is used to prompt the target person to move so that the average distance is within the distance interval. The average distance is the average of the third distance and the fourth distance.

[0062] In the above embodiments, the third distance and the fourth distance The distance is calculated by averaging three horizontally emitted ultrasonic waves from the first and second ultrasonic transmitters to ensure accuracy. The difference between these two distance values ​​determines whether the target person is positioned along the central axis. Considering that a person cannot always maintain perfect parallelism relative to the machine, the range of distance for body tilt fluctuations is defined as follows: The actual range of body tilt is controlled between 0cm and 2.5cm, within the distance difference. Greater than the first distance threshold E max If it is determined that the target person is not located on the central axis, a first alert is issued, prompting the target person to move to reduce the aforementioned distance difference. until satisfied At this point, the target person is assumed to be positioned on the center line of the screen of the facial image acquisition device. Next, the average distance is determined. Is it between ,if At this point, the target person has entered the optimal shooting area, for example, at an average distance. The optimal range is controlled between 30cm and 40cm, among which, , , The average distance between the target person and the camera of the facial image acquisition device. The distance between the first ultrasonic sensor and the target person is the average distance under different rotation angles. This represents the average distance between the second ultrasonic sensor and the target person at different rotation angles. This is the absolute value of the distance difference between the first and second ultrasonic receivers in the horizontal direction. Let be the rotation angle of the first rotating body.

[0063] To further ensure that the target person is in the optimal shooting area, in one optional implementation, step S202 includes:

[0064] Step S2021: When the distance difference is greater than the first distance threshold and the third distance is greater than the fourth distance, the first prompt message is issued. The first prompt message is used to prompt the target person to move along a third direction, which is the direction in which the first ultrasonic sensor moves away from the camera.

[0065] Step S2022: When the distance difference is greater than the first distance threshold and the third distance is less than the fourth distance, the first prompt message is issued. The first prompt message is used to prompt the target person to move along the fourth direction, which is the direction in which the second ultrasonic sensor moves away from the camera.

[0066] In the above embodiments, in the aforementioned distance difference Greater than the first distance threshold E mentioned above max And the aforementioned third distance Greater than the fourth distance mentioned above In this situation, the target person is prompted to move in a third direction, that is, to suggest the customer move slightly to the left, within the aforementioned distance difference. Greater than the first distance threshold E mentioned above max And the aforementioned third distance Smaller than the fourth distance mentioned above In this case, the target person is prompted to move along the fourth direction, that is, to move slightly to the right so that the target person is positioned on the center line of the screen of the face image acquisition device.

[0067] To further ensure that the target person is in the optimal photo-taking area, in one optional implementation, step S203 includes:

[0068] Step S2031: When the distance difference is less than or equal to the first distance threshold and the average distance is greater than the second distance threshold, the second prompt message is issued. The second prompt message is used to prompt the target person to move in the direction closer to the camera. The second distance threshold is the maximum value of the distance interval.

[0069] Step S2032: When the distance difference is less than or equal to the first distance threshold and the average distance is less than the third distance threshold, the second prompt message is issued. The second prompt message is used to prompt the target person to move away from the camera. The third distance threshold is the minimum value of the distance interval.

[0070] In the above embodiments, in the aforementioned distance difference Less than the first distance threshold E mentioned above max In the case where the target person is located at the center line of the screen of the facial image acquisition device, the above average distance Greater than the second distance threshold F max This will prompt the customer to move forward a little, to the average distance mentioned above. Less than the third distance threshold F min It will automatically prompt the customer to move back a little to enter the best photo area.

[0071] To further determine the optimal area for capturing the face, in one optional implementation, after step S203, the method further includes:

[0072] Step S301: Control the second rotating mechanism to drive the camera to rotate along the second direction, and control the first ultrasonic sensor and the second ultrasonic sensor to collect the third distance and the fourth distance once at a predetermined angle, respectively, to obtain multiple three distances and multiple fourth distances, and the three distances and the fourth distances correspond one-to-one with the rotation angle of the camera.

[0073] Step S302: Calculate multiple average distances based on multiple of the above three distances and multiple of the above fourth distances, wherein each of the average distances corresponds to one of the rotation angles.

[0074] Step S303: If the rotation angle corresponding to the largest average distance is not within the rotation angle range, a third prompt message is issued until the rotation angle corresponding to the largest average distance is within the rotation angle range and the minimum distance is within the distance range. The third prompt message is used to prompt the target person to move in a direction away from the camera. The minimum distance is the minimum value of the components of each of the average distances on the horizontal plane.

[0075] In the above embodiment, the first and second ultrasonic sensors are activated. Simultaneously, the first rotating body, driven by gear meshing, drives the first and second ultrasonic sensors to synchronously scan upwards in a circular motion. For each unit angle of rotation, the first and second ultrasonic sensors emit three sound waves respectively. At this time, the computer CPU processing unit records the rotation angle sequentially. And the third distance calculated and measured by the corresponding ultrasonic receiver. and the fourth distance And calculate multiple average distances The rotation angle corresponding to the largest of the above average distances. If the requirement is met within the 0~60° range, and not met, the target personnel are prompted to step back to meet the requirement, thus reducing the number of times the ultrasonic sensor is used on the side of the face and reducing workload. Additionally, if... Figure 6 As shown, the nasal alae and cheekbones on both sides of the face are the near-central areas of the face. Furthermore, based on actual research, it was found that the nasal alae and cheekbones on both sides of the face are relatively prominent. Therefore, the shortest lateral component value of the return distance was selected as [value missing]. The measurement point is located near the center of the face, and the angle value corresponding to the shortest component of the average distance is recorded as follows. The first rotating body resets and returns to its initial position. , This represents the shortest lateral component of the distance returned by the sensor at a certain angle. The distance from the nose and cheekbones of the client at a certain angle is determined. The corresponding angle is the optimal rotation angle, which further ensures that the captured face image does not shift.

[0076] To further ensure that standard facial images are easy to recognize, in an optional implementation, step S103 above includes:

[0077] Step S1031: When the first distance is greater than the second distance, control the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than the predetermined value; and when the first distance is less than the predetermined value, control the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value.

[0078] Step S1032: When the first distance is less than the second distance, control the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value. When the second distance is less than the predetermined value, control the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than the predetermined value.

[0079] In the above implementation, it is necessary to perform pixel calibration and matching between the image captured by the face capture camera and the screen size of the self-service machine, as well as the length and width information of the outer rectangle Rect2 of the standard elliptical wireframe on the screen. This mainly involves measuring face data from the image. Figure 7This refers to the actual data values ​​obtained after calibrating and converting the pixels of the captured face image. After the acquisition process begins, the face capture camera is turned on. First, the mature commercial dlib algorithm library from OpenCV is used to traverse the image captured by the face capture camera to find the location of the customer's face. Then, dlib.shape_predictor is used as the facial landmark detection model. This invention combines this algorithm model to calculate the deflection angle by comparing the deviation of the line connecting the two eyes from the horizontal line, thus achieving automatic facial correction and laying the groundwork for finally obtaining a standard face. Secondly, dlib.get_frontal_face_detector is also a pre-trained face detector from dlib. The input parameters of the detectMultiScale() function include the image captured from the screen of the self-service device, and it can also detect the minimum bounding rectangle Rect1 of the face image, such as... Figure 7 As shown in (a); secondly, if multiple face images appear in the camera's capture, the face image with the largest area of ​​the smallest bounding rectangle Rect1 is selected as the tracking target. Then, the length of the Rect2 standard elliptical outline of the face in the center area of ​​the screen. ,width Given all the data, based on the proportional relationship between the pixels of the smallest bounding rectangle of the real-time face image and the pixels of the standard elliptical outline of the face on the screen, the direction and magnitude of the offset required in the X and Y directions can be derived. and , , ,like Figure 7 As shown, at the aforementioned first distance Greater than the second distance mentioned above In the case of, when When the vertical center line of the smallest bounding rectangle of the target person's face moves less than the vertical center line of the bounding rectangle of the standard face in the center of the screen, the algorithm will prioritize horizontal movement, then vertical movement, until the two lines coincide. Figure 7 As shown in (b) above, at the aforementioned first distance Smaller than the second distance mentioned above In the case that, when When the vertical center line of the smallest bounding rectangle of the target person's face moves a distance greater than or equal to the horizontal center line of the bounding rectangle of the standard face in the center of the screen, the algorithm will prioritize vertical movement, followed by horizontal movement, until the two lines coincide. Figure 7 As shown in (b), in order to make the face image coincide as much as possible with the standard elliptical wireframe, it is necessary to and While approaching zero, considering the stepper motor and systemic travel error of the device, a reasonable error range needs to be given and set. , That is, the aforementioned predetermined value is equal to 10mm.

[0080] To further ensure that the standard facial image is easy to recognize, in an optional embodiment, the device further includes a chassis and a telescopic mechanism. The chassis is located on the side of the first rotating body away from the camera. The telescopic mechanism is connected to the chassis and the first rotating body. The telescopic mechanism is used to drive the first rotating body away from or towards the chassis. Before controlling the camera to acquire the facial image of the target person and obtaining the standard facial image, after step S103, the method further includes:

[0081] Step S401: Control the camera to capture the face image of the target person to obtain a second reference face image;

[0082] Step S402: Calculate the ratio of the area of ​​the first bounding rectangle to the area of ​​the second bounding rectangle to obtain the proportion of the face image. The first bounding rectangle is the bounding rectangle of the second reference face image, and the second bounding rectangle is the bounding rectangle of the standard elliptical frame of the screen.

[0083] Step S403: If the proportion of the face image is not within the proportion range, control the telescopic mechanism to drive the first rotating body to move so that the proportion of the face image is within the proportion range.

[0084] In the above embodiments, the proportion of facial images The range of values ​​is between ,Right now , and These are the length and width values ​​of the bounding rectangle of the face captured by the camera. and These are the length and width values ​​of the rectangle circumscribed by the standard elliptical wireframe on the screen.

[0085] To further ensure that standard facial images are easy to recognize, in an optional implementation, step S403 above includes:

[0086] Step S4031: When the proportion of the face image is less than the minimum value of the proportion range, control the telescopic mechanism to drive the first rotating body away from the chassis.

[0087] Step S4032: When the proportion of the face image is greater than the maximum value of the proportion range, control the telescopic mechanism to drive the first rotating body to approach the chassis.

[0088] In the above embodiments, when the proportion of the face image When the ratio is greater than 1, it is determined that the customer is too close to the screen. At this time, the camera needs to retract inward, until the program loops and stops when the ratio is less than 1; when the proportion of the face image is greater than 1... If the ratio is less than 0.9, it is determined that the customer is too far from the screen. At this time, the camera needs to extend outward until the program loops and stops when the ratio is greater than 0.9. Once the above range requirements are met, it can be determined that the customer's face is in the optimal acquisition position, and the camera will capture the customer's face. This completes a bank adaptive acquisition operation process based on facial images.

[0089] This application also provides a control device for a face image acquisition device. It should be noted that the control device for the face image acquisition device in this application can be used to execute the control method for the face image acquisition device provided in this application. The control device for the face image acquisition device provided in this application is described below.

[0090] Figure 8 This is a schematic diagram of the control device of a face image acquisition device according to an embodiment of this application. Figure 8 As shown, the device includes:

[0091] The first control unit 100 is used to control the camera to acquire the facial image of the target person and obtain the first reference facial image;

[0092] The determining unit 200 is used to determine a first distance and a second distance based on the first reference face image. The first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis. The first central axis is the major axis of the standard elliptical frame of the screen, and the second central axis is the minor axis of the standard elliptical frame of the screen.

[0093] The second control unit 300 is used to control the first rotating mechanism to drive the camera to rotate in a first direction until the first distance is less than a predetermined value, and to control the second rotating mechanism to drive the camera to rotate in a second direction until the second distance is less than the predetermined value.

[0094] The third control unit 400 is used to control the camera to capture the facial image of the target person and obtain a standard facial image.

[0095] In the control device of the aforementioned face image acquisition equipment, a first control unit controls a camera to acquire a face image of a target person, obtaining a first reference face image; a determining unit determines a first distance and a second distance based on the first reference face image, wherein the first distance is the distance between the midpoint of the face image and a first central axis, and the second distance is the distance between the midpoint of the face image and a second central axis, wherein the first central axis is the major axis of the standard elliptical outline of the screen, and the second central axis is the minor axis of the standard elliptical outline of the screen; a second control unit controls a first rotation mechanism to drive the camera to rotate in a first direction until the first distance is less than a predetermined value, and controls a second rotation mechanism to drive the camera to rotate in a second direction until the second distance is less than a predetermined value; a third control unit controls the camera to acquire a face image of the target person, obtaining a standard face image. The control device of this face image acquisition device drives the camera to rotate in a first direction through a first rotating mechanism and drives the camera to rotate in a second direction through a second rotating mechanism, so that the face image acquired by the camera is located in the standard elliptical frame of the screen, avoiding large positional offset of the acquired face image, thereby obtaining a standard face image that is easy to recognize, and solving the problem of face recognition difficulty caused by positional offset of the acquired face image in the prior art.

[0096] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0097] To ensure the target person is within a suitable photographing area, one possible implementation method is as follows: Figure 2 As shown, the second rotating mechanism includes a first rotating body 16, and the device further includes a first ultrasonic sensor and a second ultrasonic sensor. The first ultrasonic sensor is located on the first rotating body 16 and on one side of the camera 2. The first ultrasonic sensor is used to detect the distance between the target person and the first ultrasonic sensor. The second rotating mechanism is used to drive the first rotating body 16 to rotate along the second direction. The second ultrasonic sensor is located on the first rotating body 16 and on the other side of the camera. The second ultrasonic sensor is used to detect the distance between the target person and the second ultrasonic sensor. Before controlling the camera to acquire the facial image of the target person, the device further includes:

[0098] The fourth control unit is used to control the first ultrasonic sensor to detect the distance between the target person and the first ultrasonic sensor to obtain a third distance, and to control the second ultrasonic sensor to detect the distance between the target person and the second ultrasonic sensor to obtain a fourth distance;

[0099] The first sending unit is configured to issue a first prompt message when the distance difference is greater than a first distance threshold. The first prompt message is used to prompt the target person to move in order to reduce the distance difference. The distance difference is the absolute value of the difference between the third distance and the fourth distance.

[0100] The second sending unit is used to issue a second prompt message when the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval. The second prompt message is used to prompt the target person to move so that the average distance is within the distance interval. The average distance is the average of the third distance and the fourth distance.

[0101] In the above embodiments, the third distance and the fourth distance The distance is calculated by averaging three horizontally emitted ultrasonic waves from the first and second ultrasonic transmitters to ensure accuracy. The difference between these two distance values ​​determines whether the target person is positioned along the central axis. Considering that a person cannot always maintain perfect parallelism relative to the machine, the range of distance for body tilt fluctuations is defined as follows: The actual range of body tilt is controlled between 0cm and 2.5cm, within the distance difference. Greater than the first distance threshold E max If it is determined that the target person is not located on the central axis, a first alert is issued, prompting the target person to move to reduce the aforementioned distance difference. until satisfied At this point, the target person is assumed to be positioned on the center line of the screen of the facial image acquisition device. Next, the average distance is determined. Is it between ,if At this point, the target person has entered the optimal shooting area, for example, at an average distance. The optimal range is controlled between 30cm and 40cm, among which, , , The average distance between the target person and the camera of the facial image acquisition device. The distance between the first ultrasonic sensor and the target person is the average distance under different rotation angles. This represents the average distance between the second ultrasonic sensor and the target person at different rotation angles. This is the absolute value of the distance difference between the first and second ultrasonic receivers in the horizontal direction. Let be the rotation angle of the first rotating body.

[0102] To further ensure that the target person is in the optimal shooting area, in one optional implementation, the first sending unit includes:

[0103] The first transmitting module is used to send the first prompt information when the distance difference is greater than the first distance threshold and the third distance is greater than the fourth distance. The first prompt information is used to prompt the target person to move along a third direction, where the third direction is the direction in which the first ultrasonic sensor moves away from the camera.

[0104] The second transmitting module is used to send the first prompt information when the distance difference is greater than the first distance threshold and the third distance is less than the fourth distance. The first prompt information is used to prompt the target person to move along the fourth direction, which is the direction in which the second ultrasonic sensor moves away from the camera.

[0105] In the above embodiments, in the aforementioned distance difference Greater than the first distance threshold E mentioned above max And the aforementioned third distance Greater than the fourth distance mentioned above In this situation, the target person is prompted to move in a third direction, that is, to suggest the customer move slightly to the left, within the aforementioned distance difference. Greater than the first distance threshold E mentioned above max And the aforementioned third distance Smaller than the fourth distance mentioned above In this case, the target person is prompted to move along the fourth direction, that is, to move slightly to the right so that the target person is positioned on the center line of the screen of the face image acquisition device.

[0106] To further ensure that the target person is in the optimal shooting area, in one optional implementation, the second sending unit includes:

[0107] The third sending module is used to send the second prompt information when the distance difference is less than or equal to the first distance threshold and the average distance is greater than the second distance threshold. The second prompt information is used to prompt the target person to move in the direction closer to the camera. The second distance threshold is the maximum value of the distance interval.

[0108] The fourth sending module is used to send the second prompt information when the distance difference is less than or equal to the first distance threshold and the average distance is less than the third distance threshold. The second prompt information is used to prompt the target person to move away from the camera. The third distance threshold is the minimum value of the distance interval.

[0109] In the above embodiments, in the aforementioned distance difference Less than the first distance threshold E mentioned above max In the case where the target person is located at the center line of the screen of the facial image acquisition device, the above average distance Greater than the second distance threshold F max This will prompt the customer to move forward a little, to the average distance mentioned above. Less than the third distance threshold F min It will automatically prompt the customer to move back a little to enter the best photo area.

[0110] To further determine the optimal area for capturing a face, in one optional embodiment, the above-mentioned device further includes:

[0111] The fifth control unit is configured to, after controlling the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than a predetermined value, and controlling the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value, and after issuing a second prompt message when the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance range, control the second rotating mechanism to drive the camera to rotate along the second direction, and control the first ultrasonic sensor and the second ultrasonic sensor to collect the third distance and the fourth distance once at predetermined angle intervals, respectively, to obtain multiple three-distances and multiple fourth distances, wherein each of the three-distances and the fourth distance corresponds one-to-one with the rotation angle of the camera;

[0112] The first calculation unit is used to calculate multiple average distances based on multiple of the above three distances and multiple of the above fourth distances, wherein each of the average distances corresponds to one of the rotation angles.

[0113] The third sending unit is used to issue a third prompt message when the rotation angle corresponding to the largest average distance is not within the rotation angle range, until the rotation angle corresponding to the largest average distance is within the rotation angle range and the minimum distance is within the distance range. The third prompt message is used to prompt the target person to move in a direction away from the camera. The minimum distance is the minimum value of the components of each of the average distances on the horizontal plane.

[0114] In the above embodiment, the first and second ultrasonic sensors are activated. Simultaneously, the first rotating body, driven by gear meshing, drives the first and second ultrasonic sensors to synchronously scan upwards in a circular motion. For each unit angle of rotation, the first and second ultrasonic sensors emit three sound waves respectively. At this time, the computer CPU processing unit records the rotation angle sequentially. And the third distance calculated and measured by the corresponding ultrasonic receiver. and the fourth distance And calculate multiple average distances The rotation angle corresponding to the largest of the above average distances. If the requirement is met within the 0~60° range, and not met, the target personnel are prompted to step back to meet the requirement, thus reducing the number of times the ultrasonic sensor is used on the side of the face and reducing workload. Additionally, if... Figure 6 As shown, the nasal alae and cheekbones on both sides of the face are the near-central areas of the face. Furthermore, based on actual research, it was found that the nasal alae and cheekbones on both sides of the face are relatively prominent. Therefore, the shortest lateral component value of the return distance was selected as [value missing]. The measurement point is located near the center of the face, and the angle value corresponding to the shortest component of the average distance is recorded as follows. The first rotating body resets and returns to its initial position. , This represents the shortest lateral component of the distance returned by the sensor at a certain angle. The distance from the nose and cheekbones of the client at a certain angle is determined. The corresponding angle is the optimal rotation angle, which further ensures that the captured face image does not shift.

[0115] To further ensure that standard facial images are easy to recognize, in one optional implementation, the second control unit includes:

[0116] The first control module is configured to control the first rotating mechanism to drive the camera to rotate along the first direction when the first distance is greater than the second distance, until the first distance is less than the predetermined value, and to control the second rotating mechanism to drive the camera to rotate along the second direction when the first distance is less than the predetermined value, until the second distance is less than the predetermined value.

[0117] The second control module is configured to control the second rotating mechanism to drive the camera to rotate along the second direction when the first distance is less than the second distance, until the second distance is less than the predetermined value, and to control the first rotating mechanism to drive the camera to rotate along the first direction when the second distance is less than the predetermined value, until the first distance is less than the predetermined value.

[0118] In the above implementation, it is necessary to perform pixel calibration and matching between the image captured by the face capture camera and the screen size of the self-service machine, as well as the length and width information of the outer rectangle Rect2 of the standard elliptical wireframe on the screen. This mainly involves measuring face data from the image. Figure 7This refers to the actual data values ​​obtained after calibrating and converting the pixels of the captured face image. After the acquisition process begins, the face capture camera is turned on. First, the mature commercial dlib algorithm library from OpenCV is used to traverse the image captured by the face capture camera to find the location of the customer's face. Then, dlib.shape_predictor is used as the facial landmark detection model. This invention combines this algorithm model to calculate the deflection angle by comparing the deviation of the line connecting the two eyes from the horizontal line, thus achieving automatic facial correction and laying the groundwork for finally obtaining a standard face. Secondly, dlib.get_frontal_face_detector is also a pre-trained face detector from dlib. The input parameters of the detectMultiScale() function include the image captured from the screen of the self-service device, and it can also detect the minimum bounding rectangle Rect1 of the face image, such as... Figure 7 As shown in (a); secondly, if multiple face images appear in the camera's capture, the face image with the largest area of ​​the smallest bounding rectangle Rect1 is selected as the tracking target. Then, the length of the Rect2 standard elliptical outline of the face in the center area of ​​the screen. ,width Given all the data, based on the proportional relationship between the pixels of the smallest bounding rectangle of the real-time face image and the pixels of the standard elliptical outline of the face on the screen, the direction and magnitude of the offset required in the X and Y directions can be derived. and , , ,like Figure 7 As shown, at the aforementioned first distance Greater than the second distance mentioned above In the case of, when When the vertical center line of the smallest bounding rectangle of the target person's face moves less than the vertical center line of the bounding rectangle of the standard face in the center of the screen, the algorithm will prioritize horizontal movement, then vertical movement, until the two lines coincide. Figure 7 As shown in (b) above, at the aforementioned first distance Smaller than the second distance mentioned above In the case that, when When the vertical center line of the smallest bounding rectangle of the target person's face moves a distance greater than or equal to the horizontal center line of the bounding rectangle of the standard face in the center of the screen, the algorithm will prioritize vertical movement, followed by horizontal movement, until the two lines coincide. Figure 7 As shown in (b), in order to make the face image coincide as much as possible with the standard elliptical wireframe, it is necessary to and While approaching zero, considering the stepper motor and systemic travel error of the device, a reasonable error range needs to be given and set. , That is, the aforementioned predetermined value is equal to 10mm.

[0119] To further ensure that standard facial images are easy to recognize, in an optional embodiment, the device further includes a chassis and a telescopic mechanism. The chassis is located on the side of the first rotating body away from the camera. The telescopic mechanism is connected to the chassis and the first rotating body, and is used to drive the first rotating body away from or towards the chassis. The device further includes:

[0120] The sixth control unit is used to control the camera to acquire the face image of the target person and obtain a second reference face image before controlling the camera to acquire the face image of the target person and obtain a standard face image;

[0121] The second calculation unit is used to calculate the ratio of the area of ​​the first bounding rectangle to the area of ​​the second bounding rectangle to obtain the proportion of the face image. The first bounding rectangle is the bounding rectangle of the second reference face image, and the second bounding rectangle is the bounding rectangle of the standard elliptical frame of the screen.

[0122] The seventh control unit is used to control the telescopic mechanism to drive the first rotating body to move when the proportion of the face image is not within the proportion range, so that the proportion of the face image is within the proportion range.

[0123] In the above embodiments, the proportion of facial images The range of values ​​is between ,Right now , and These are the length and width values ​​of the bounding rectangle of the face captured by the camera. and These are the length and width values ​​of the rectangle circumscribed by the standard elliptical wireframe on the screen.

[0124] To further ensure that standard facial images are easy to recognize, in one optional implementation, the seventh control unit includes:

[0125] The third control module is used to control the telescopic mechanism to drive the first rotating body away from the chassis when the proportion of the face image is less than the minimum value of the proportion range.

[0126] The fourth control module is used to control the telescopic mechanism to drive the first rotating body closer to the chassis when the proportion of the face image is greater than the maximum value of the proportion range.

[0127] In the above embodiments, when the proportion of the face image When the ratio is greater than 1, it is determined that the customer is too close to the screen. At this time, the camera needs to retract inward, until the program loops and stops when the ratio is less than 1; when the proportion of the face image is greater than 1... If the ratio is less than 0.9, it is determined that the customer is too far from the screen. At this time, the camera needs to extend outward until the program loops and stops when the ratio is greater than 0.9. Once the above range requirements are met, it can be determined that the customer's face is in the optimal acquisition position, and the camera will capture the customer's face. This completes a bank adaptive acquisition operation process based on facial images.

[0128] This application also provides a face image acquisition system, including: a face image acquisition device, one or more processors, a memory, a display device, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the above-described methods.

[0129] The aforementioned face image acquisition system includes a face image acquisition device. The face image acquisition system drives the camera to rotate in a first direction through a first rotation mechanism of the face image acquisition device and drives the camera to rotate in a second direction through a second rotation mechanism of the face image acquisition device. This ensures that the face image acquired by the camera is located within the standard elliptical frame of the screen, avoiding large positional offsets of the acquired face image. This results in a standard face image that is easy to recognize, solving the problem of difficult face recognition caused by positional offsets of the acquired face image in the prior art.

[0130] The control device of the aforementioned face image acquisition device includes a processor and a memory. The first control unit, the determining unit, the second control unit, and the third control unit are all stored in the memory as program units. The processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0131] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and their parameters can be adjusted (for the purposes of this invention).

[0132] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0133] This invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the above-described method.

[0134] This invention provides a processor for running a program, wherein the program executes the method described above when it runs.

[0135] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0136] Step S101: Control the camera to capture the face image of the target person to obtain the first reference face image;

[0137] Step S102: Determine a first distance and a second distance based on the first reference face image. The first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis. The first central axis is the major axis of the standard elliptical frame of the screen, and the second central axis is the minor axis of the standard elliptical frame of the screen.

[0138] Step S103: Control the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than a predetermined value, and control the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value.

[0139] Step S104: Control the camera to capture the facial image of the target person to obtain a standard facial image.

[0140] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0141] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0142] Step S101: Control the camera to capture the face image of the target person to obtain the first reference face image;

[0143] Step S102: Determine a first distance and a second distance based on the first reference face image. The first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis. The first central axis is the major axis of the standard elliptical frame of the screen, and the second central axis is the minor axis of the standard elliptical frame of the screen.

[0144] Step S103: Control the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than a predetermined value, and control the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value.

[0145] Step S104: Control the camera to capture the facial image of the target person to obtain a standard facial image.

[0146] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0147] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0148] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0149] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0150] If the aforementioned integrated units are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0151] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0152] 1) The face image acquisition device of this application includes a camera, a first rotation mechanism, and a second rotation mechanism. The camera is used to acquire a face image of a target person, which is the person whose face image is to be acquired. The first rotation mechanism is used to connect to the camera and to drive the camera to rotate in a first direction, which is parallel to the horizontal plane. The second rotation mechanism is also used to connect to the camera and to drive the camera to rotate in a second direction, which is parallel to the vertical plane. This face image acquisition device, by using the first rotation mechanism to drive the camera to rotate in the first direction and the second rotation mechanism to drive the camera to rotate in the second direction, ensures that the face image acquired by the camera is located within the standard elliptical frame of the screen, avoiding large positional offsets in the acquired face image and solving the problem of difficult face recognition caused by positional offsets in the acquired face image in the prior art.

[0153] 2) In the control method of the face image acquisition device of this application, firstly, the camera is controlled to acquire the face image of the target person to obtain a first reference face image; then, a first distance and a second distance are determined based on the first reference face image, wherein the first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis, wherein the first central axis is the major axis of the standard elliptical frame of the screen, and the second central axis is the minor axis of the standard elliptical frame of the screen; then, the first rotation mechanism is controlled to drive the camera to rotate in a first direction until the first distance is less than a predetermined value, and the second rotation mechanism is controlled to drive the camera to rotate in a second direction until the second distance is less than the predetermined value; finally, the camera is controlled to acquire the face image of the target person to obtain a standard face image. The control method of this face image acquisition device drives the camera to rotate in a first direction through a first rotating mechanism and drives the camera to rotate in a second direction through a second rotating mechanism, so that the face image acquired by the camera is located in the standard elliptical frame of the screen, avoiding large positional offset of the acquired face image, thereby obtaining a standard face image that is easy to recognize, and solving the problem of face recognition difficulty caused by positional offset of the acquired face image in the prior art.

[0154] 3) In the control device of the face image acquisition device of this application, the first control unit controls the camera to acquire the face image of the target person to obtain a first reference face image; the determining unit determines a first distance and a second distance based on the first reference face image, wherein the first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis, wherein the first central axis is the major axis of the standard elliptical frame of the screen, and the second central axis is the minor axis of the standard elliptical frame of the screen; the second control unit controls the first rotating mechanism to drive the camera to rotate in a first direction until the first distance is less than a predetermined value, and controls the second rotating mechanism to drive the camera to rotate in a second direction until the second distance is less than the predetermined value; the third control unit controls the camera to acquire the face image of the target person to obtain a standard face image. The control device of this face image acquisition device drives the camera to rotate in a first direction through a first rotating mechanism and drives the camera to rotate in a second direction through a second rotating mechanism, so that the face image acquired by the camera is located in the standard elliptical frame of the screen, avoiding large positional offset of the acquired face image, thereby obtaining a standard face image that is easy to recognize, and solving the problem of face recognition difficulty caused by positional offset of the acquired face image in the prior art.

[0155] 4) The face image acquisition system of this application includes a face image acquisition device. The face image acquisition system drives the camera to rotate in a first direction through a first rotation mechanism of the face image acquisition device and drives the camera to rotate in a second direction through a second rotation mechanism of the face image acquisition device. This makes the face image acquired by the camera located in the standard elliptical frame of the screen, avoiding large positional offset of the acquired face image, thereby obtaining a standard face image, which is easy to recognize. This solves the problem of face recognition difficulty caused by positional offset of the acquired face image in the prior art.

[0156] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for a face image acquisition device, characterized in that, The control method is applied to a face image acquisition device, which includes: a camera for acquiring a face image of a target person, the target person being the person whose face image is to be acquired; a first rotation mechanism for connecting the camera, the first rotation mechanism being used to drive the camera to rotate along a first direction, the first direction being parallel to a horizontal plane; and a second rotation mechanism for connecting the camera, the second rotation mechanism being used to drive the camera to rotate along a second direction, the second direction being parallel to a vertical plane. The method includes: Control the camera to capture facial images of the target person to obtain the first reference facial image; A first distance and a second distance are determined based on the first reference face image. The first distance is the distance between the midpoint of the face image and the first central axis, and the second distance is the distance between the midpoint of the face image and the second central axis. The first central axis is the major axis of the standard elliptical outline of the screen, and the second central axis is the minor axis of the standard elliptical outline of the screen. The first rotating mechanism is controlled to drive the camera to rotate in a first direction until the first distance is less than a predetermined value, and the second rotating mechanism is controlled to drive the camera to rotate in a second direction until the second distance is less than the predetermined value; The camera is controlled to capture the facial image of the target person to obtain a standard facial image; The second rotating mechanism includes a first rotating body. The face image acquisition device further includes a first ultrasonic sensor and a second ultrasonic sensor. The first ultrasonic sensor is located on the first rotating body and on one side of the camera. The first ultrasonic sensor is used to detect the distance between the target person and the first ultrasonic sensor. The second rotating mechanism is used to drive the first rotating body to rotate along the second direction. The second ultrasonic sensor is located on the first rotating body and on the other side of the camera. The second ultrasonic sensor is used to detect the distance between the target person and the second ultrasonic sensor. Before controlling the camera to acquire the face image of the target person, the method further includes: The first ultrasonic sensor is controlled to detect the distance between the target person and the first ultrasonic sensor to obtain a third distance; the second ultrasonic sensor is controlled to detect the distance between the target person and the second ultrasonic sensor to obtain a fourth distance. If the distance difference is greater than the first distance threshold, a first prompt message is issued. The first prompt message is used to prompt the target person to move in order to reduce the distance difference. The distance difference is the absolute value of the difference between the third distance and the fourth distance. If the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval, a second prompt message is issued. The second prompt message is used to prompt the target person to move so that the average distance is within the distance interval. The average distance is the average of the third distance and the fourth distance.

2. The method according to claim 1, characterized in that, If the distance difference is greater than a first distance threshold, issue a first prompt message, including: If the distance difference is greater than the first distance threshold and the third distance is greater than the fourth distance, the first prompt message is issued. The first prompt message is used to prompt the target person to move along a third direction, where the third direction is the direction in which the first ultrasonic sensor moves away from the camera. If the distance difference is greater than the first distance threshold and the third distance is less than the fourth distance, the first prompt message is issued. The first prompt message is used to prompt the target person to move along the fourth direction, which is the direction in which the second ultrasonic sensor moves away from the camera.

3. The method according to claim 1, characterized in that, If the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval, a second prompt message is issued, including: If the distance difference is less than or equal to the first distance threshold and the average distance is greater than the second distance threshold, the second prompt message is issued. The second prompt message is used to prompt the target person to move in the direction closer to the camera. The second distance threshold is the maximum value of the distance range. If the distance difference is less than or equal to the first distance threshold and the average distance is less than the third distance threshold, a second prompt message is issued. The second prompt message is used to prompt the target person to move in a direction away from the camera. The third distance threshold is the minimum value of the distance interval.

4. The method according to claim 3, characterized in that, After issuing a second prompt message when the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval, the method further includes: The second rotating mechanism is controlled to drive the camera to rotate along the second direction, and the first ultrasonic sensor and the second ultrasonic sensor are controlled to collect the third distance and the fourth distance once at predetermined angles, respectively, to obtain multiple three distances and multiple fourth distances. The three distances and the fourth distances correspond one-to-one with the rotation angle of the camera. Multiple average distances are calculated based on multiple three-distances and multiple fourth-distances, and each average distance corresponds to a rotation angle. If the rotation angle corresponding to the largest average distance is not within the rotation angle range, a third prompt message is issued until the rotation angle corresponding to the largest average distance is within the rotation angle range and the minimum distance is within the distance range. The third prompt message is used to prompt the target person to move in a direction away from the camera. The minimum distance is the minimum value of the components of each average distance on the horizontal plane.

5. The method according to any one of claims 1 to 4, characterized in that, Controlling a first rotating mechanism to drive the camera to rotate along a first direction until the first distance is less than a predetermined value, and controlling a second rotating mechanism to drive the camera to rotate along a second direction until the second distance is less than the predetermined value, includes: If the first distance is greater than the second distance, control the first rotating mechanism to drive the camera to rotate along the first direction until the first distance is less than the predetermined value; and if the first distance is less than the predetermined value, control the second rotating mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value. If the first distance is less than the second distance, control the second rotation mechanism to drive the camera to rotate along the second direction until the second distance is less than the predetermined value, and if the second distance is less than the predetermined value, control the first rotation mechanism to drive the camera to rotate along the first direction until the first distance is less than the predetermined value.

6. The method according to any one of claims 1 to 4, characterized in that, The face image acquisition device further includes a chassis and a telescopic mechanism. The chassis is located on the side of the first rotating body away from the camera. The telescopic mechanism is connected to the chassis and the first rotating body. The telescopic mechanism is used to drive the first rotating body away from or towards the chassis. Before controlling the camera to acquire the face image of the target person and obtain a standard face image, after controlling the first rotating mechanism to drive the camera to rotate along a first direction until the first distance is less than a predetermined value, and controlling the second rotating mechanism to drive the camera to rotate along a second direction until the second distance is less than the predetermined value, the method further includes: Control the camera to capture facial images of the target person to obtain a second reference facial image; The ratio of the area of ​​the first bounding rectangle to the area of ​​the second bounding rectangle is calculated to obtain the proportion of the face image. The first bounding rectangle is the bounding rectangle of the second reference face image, and the second bounding rectangle is the bounding rectangle of the standard elliptical frame of the screen. If the proportion of the face image is not within the proportion range, the telescopic mechanism is controlled to drive the first rotating body to move so that the proportion of the face image is within the proportion range.

7. The method according to claim 6, characterized in that, When the proportion of the face image is not within the proportion range, controlling the telescopic mechanism to drive the first rotating body to move so that the proportion of the face image is within the proportion range includes: When the proportion of the face image is less than the minimum value of the proportion range, the telescopic mechanism is controlled to drive the first rotating body away from the chassis; When the proportion of the face image is greater than the maximum value of the proportion range, the telescopic mechanism is controlled to drive the first rotating body closer to the chassis.

8. A control device for a face image acquisition equipment, characterized in that, The control device is applied to a face image acquisition device, which includes: a camera for acquiring a face image of a target person, the target person being the person whose face image is to be acquired; a first rotation mechanism for connecting the camera, the first rotation mechanism being used to drive the camera to rotate along a first direction, the first direction being parallel to a horizontal plane; and a second rotation mechanism for connecting the camera, the second rotation mechanism being used to drive the camera to rotate along a second direction, the second direction being parallel to a vertical plane. The device includes: The first control unit is used to control the camera to capture the facial image of the target person and obtain the first reference facial image; The determining unit is configured to determine a first distance and a second distance based on the first reference face image, wherein the first distance is the distance between the midpoint of the face image and a first central axis, and the second distance is the distance between the midpoint of the face image and a second central axis, wherein the first central axis is the major axis of the standard elliptical frame of the screen, and the second central axis is the minor axis of the standard elliptical frame of the screen. The second control unit is used to control the first rotating mechanism to drive the camera to rotate in a first direction until the first distance is less than a predetermined value, and to control the second rotating mechanism to drive the camera to rotate in a second direction until the second distance is less than the predetermined value. The third control unit is used to control the camera to capture the facial image of the target person and obtain a standard facial image; The second rotating mechanism includes a first rotating body. The face image acquisition device further includes a first ultrasonic sensor and a second ultrasonic sensor. The first ultrasonic sensor is located on the first rotating body and on one side of the camera. The first ultrasonic sensor is used to detect the distance between the target person and the first ultrasonic sensor. The second rotating mechanism is used to drive the first rotating body to rotate along the second direction. The second ultrasonic sensor is located on the first rotating body and on the other side of the camera. The second ultrasonic sensor is used to detect the distance between the target person and the second ultrasonic sensor. Before controlling the camera to acquire the face image of the target person, the device further includes: The fourth control unit is used to control the first ultrasonic sensor to detect the distance between the target person and the first ultrasonic sensor to obtain a third distance, and to control the second ultrasonic sensor to detect the distance between the target person and the second ultrasonic sensor to obtain a fourth distance; The first sending unit is configured to issue a first prompt message when the distance difference is greater than a first distance threshold. The first prompt message is configured to prompt the target person to move in order to reduce the distance difference, wherein the distance difference is the absolute value of the difference between the third distance and the fourth distance. The second sending unit is configured to issue a second prompt message when the distance difference is less than or equal to the first distance threshold and the average distance is not within the distance interval. The second prompt message is configured to prompt the target person to move so that the average distance is within the distance interval, and the average distance is the average of the third distance and the fourth distance.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein when the program is executed by a processor, the processor performs the method according to any one of claims 1 to 7.

10. A face image acquisition system, characterized in that, include: A face image acquisition device, one or more processors, a memory, a display device, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 7.

Images