Automatic tracking face recognition device and method

Abstract

The application discloses an automatic tracking face recognition device and a recognition method. The device comprises a device body, wherein the device body comprises a left shell, a position sensor mounting seat, a position sensor, a middle shell, a camera module mounting rack, a camera module, a right shell and a stepping motor; the position sensor is fixedly installed in the left shell; the camera module is fixedly installed in the middle shell; and the stepping motor is fixedly installed in the right shell. The left end of the camera module mounting rack is provided with a position detection shaft, the right end is fixedly assembled with an output shaft of the stepping motor, the position detection shaft is rotationally assembled with the side wall of the position sensor mounting seat and penetrates between a position sensor signal transmitting end and a position sensor signal receiving end, and a signal through hole is formed in the position detection shaft. The left and right ends of the middle shell are rotationally assembled with the left and right shells respectively. The recognition device and the recognition method improve the face recognition efficiency and user experience.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of face recognition, and particularly relates to an automatic tracking face recognition device and a recognition method. BACKGROUND

[0002] At present, the face recognition device applied to financial equipment is generally designed with a manual adjusting lever for users to adjust the angle of a camera to capture a face in order to meet the face recognition needs of customers with different heights.

[0003] This mode has the following defects:

[0004] 1. The user needs to adjust it by himself, which is not good for user experience;

[0005] 2. When manually adjusting, the user cannot know the best shooting angle, which affects the success rate of face recognition. It often needs to be guided by a business staff, which increases the use cost of the device.

[0006] Chinese patent CN 212617320 U discloses a face recognition all-in-one machine camera angle adjusting device, which comprises a photosensitive sensor, a rotating part and a camera. The camera angle adjusting device comprises a pitch angle adjusting part and a left-right angle adjusting part. The pitch angle adjusting part comprises a first driving motor, which is used to drive the rotating part to rotate in a gap, so as to drive the camera to adjust the pitch angle. The left-right angle adjusting part comprises a vertical rotating shaft, a first gear, a second gear and a second driving motor. One end of the vertical rotating shaft is fixed on the body of the all-in-one machine, and the first gear is fixed on the other end of the vertical rotating shaft. The second gear is fixed on the output shaft of the second driving motor, and the first gear is engaged with the second gear. The utility model directly adjusts the camera angle according to light sensing by using the photosensitive sensor, effectively overcomes the defects of the prior art, does not need to manually adjust the screen angle and the camera angle, and improves the checking speed and customer experience. The technical scheme has the disadvantage that the camera cannot be reset to the default best shooting angle after each recognition, which affects the efficiency of the next face recognition. SUMMARY

[0007] Therefore, the present application aims to provide an automatic tracking face recognition device and a recognition method to improve the efficiency of face recognition and user experience.

[0008] The present application solves the above problems through the following technical means:

[0009] The utility model provides an automatic tracking face recognition device, including device body, the device body includes left casing, position sensor mounting seat, position sensor, intermediate casing, camera module mounting frame, camera module, right casing and step motor, position sensor is fixedly installed in left casing through position sensor mounting seat, and position sensor includes position sensor signal emission end and position sensor signal receiving end, camera module is fixedly installed in intermediate casing through camera module mounting frame, and step motor is fixedly installed in right casing, the left end of camera module mounting frame is fixedly provided with position detection shaft, and the right end of camera module mounting frame is fixedly assembled with the output shaft of step motor, the side wall of position detection shaft is rotatably assembled with the position sensor mounting seat and passes between position sensor signal emission end and position sensor signal receiving end, and signal through -hole is set up on position detection shaft, the left and right both ends of intermediate casing are rotatably assembled with left and right casing respectively.

[0010] Further, one side wall top end of the signal through-hole extends a signal shielding upper stop edge, and the opposite other side wall bottom end extends a signal shielding lower stop edge.

[0011] Further, the left and right both ends of the intermediate casing are fixedly provided with arc pieces, the left arc piece is rotatably assembled with the left casing, the right arc piece is rotatably assembled with the right casing, and the left and right casings are fixedly provided with arc piece rotation limit limit tables between corresponding arc piece notches.

[0012] Further, the outer side wall of the arc piece is provided with a plurality of protrusions.

[0013] Further, the intermediate casing is provided with a camera window at a position corresponding to the camera module, and the camera window is provided with a transparent lens.

[0014] Further, the position detection shaft is rotatably assembled with the side wall of the position sensor mounting seat through a bearing.

[0015] Further, the bottom of the left and right casings is provided with a mounting boss.

[0016] Further, the utility model also includes a magnetic attraction mounting assembly fixedly assembled with the device body by a fixing screw.

[0017] Further, the magnetic attraction mounting assembly includes a magnetic attraction mounting assembly shell, a magnetic attraction mounting assembly cover plate, and a magnetic attraction connecting terminal.

[0018] A recognition method using the above face recognition device, comprising the following steps:

[0019] S1 camera module reset to the default best shooting angle: the stepping motor drives the camera module to rotate in the direction of the pitch angle, when the position sensor signal light beam transmits through the signal through hole and makes the position sensor conduct, it indicates that the camera module rotates to the maximum pitch angle position, at this time, the stepping motor drives the camera module to rotate reversely by a preset pitch angle value, so that the camera module resets to the pitch angle 0° position, i.e. the default best shooting angle;

[0020] S2 automatic face tracking recognition: when the customer triggers the face recognition instruction, if the customer's portrait is in the shooting picture of the camera module, the host computer processor will calculate the deviation of the position of the face and the center position of the picture, and send the deviation signal to the driver, the driver sends the driving instruction to the stepping motor, and the stepping motor completes the rotation to make the camera module shoot the customer's picture portrait in the center; if the customer's portrait is not in the shooting picture of the camera module, the host computer processor will trigger the stepping motor to perform the traversal pitch adjustment in the maximum angle range until the customer's portrait is shot in the center.

[0021] The beneficial effects of the present application are:

[0022] The automatic face tracking recognition device and method of the present application, on the one hand, when the face photographing is triggered by the business, the device can automatically adjust the shooting angle and position in the best shooting position by rotating the camera module through the stepping motor according to different customer heights to complete the face photographing, realize the automatic face tracking recognition, and improve the intelligent degree and user experience; on the other hand, by arranging the position sensor combined with the position detection shaft rotating synchronously with the camera module, the reset instruction will be triggered after the power-on or after the user completes the photographing, so that the camera module resets to the default best shooting angle, reduces the adjustment time, and improves the efficiency and user experience of face recognition. BRIEF DESCRIPTION OF DRAWINGS

[0023] The present application will be further described below in combination with the drawings and embodiments.

[0024] Figure 1 It is an assembly schematic diagram of the preferred embodiment of the present application;

[0025] Figure 2 It is a disassembly schematic diagram of the magnetic attraction mounting assembly and the device body;

[0026] Figure 3 It is a schematic diagram of the mounting boss;

[0027] Figure 4 It is an explosion schematic diagram of the preferred embodiment of the present application;

[0028] Figure 5 It is a local schematic diagram of the position detection shaft part;

[0029] Figure 6A schematic diagram for the position sensor sensing light beam being blocked by the position detection shaft;

[0030] Figure 7 A schematic diagram for the position sensor sensing light beam passing through the signal through hole;

[0031] Figure 8 A schematic diagram for the disassembly of the arc piece and the left and right shells;

[0032] Figure 9 A schematic diagram of the application of the present application;

[0033] Figure 10 A flowchart of the identification method of the present application.

[0034] In the figure, 1 is the device body, 2 is the magnetic mounting assembly, 3 is the fixing screw, 10 is the transparent lens, 11 is the camera module, 12 is the camera module mounting bracket, 13 is the bearing, 14 is the position sensor, 15 is the left shell, 16 is the position sensor mounting seat, 17 is the intermediate shell, 18 is the stepping motor, 19 is the right shell, 21 is the magnetic mounting assembly shell, 22 is the magnetic mounting assembly cover plate, 23 is the magnetic connection terminal, 121 is the position detection shaft, 122 is the signal through hole, 1211 is the signal blocking upper edge, 1212 is the signal blocking lower edge, 141 is the position sensor sensing light beam, 142 is the position sensor signal transmitting end, 143 is the position sensor signal receiving end, 151 is the mounting boss, 152 is the arc piece rotation limit limit table, 171 is the protrusion, 172 is the arc piece end, 1721 is the arc piece rotation upper limit edge, and 1722 is the arc piece rotation lower limit edge. DETAILED DESCRIPTION

[0035] The present application will be described in detail below with reference to the accompanying drawings.

[0036] As Figures 1 to 8 shown, the present embodiment provides an automatic tracking face recognition device, which comprises a device body 1, the device body comprising a left shell 15, a position sensor mounting seat 16, a position sensor 14, an intermediate shell 17, a camera module mounting bracket 12, a camera module 11, a right shell 19 and a stepping motor 18, the left and right ends of the intermediate shell being respectively nested and rotationally assembled with the left and right shells; the device body can be mounted on the equipment through the mounting boss 151 provided on both sides, and then the mounting boss is directly mounted on the equipment through a screw; as Figure 3 shown, the mounting boss can have a gap H between the intermediate shell and the mounting surface, so as to rotate the intermediate shell. The device body can also be magnetically connected with the equipment through the magnetic mounting assembly 2, specifically, as Figure 1 , Figure 2 and Figure 4As shown, the magnetic mounting assembly is fixedly assembled with the device body by the fixing screw 3, and the magnetic mounting assembly comprises a magnetic mounting assembly shell 21, a magnetic mounting assembly cover plate 22 and a magnetic connection terminal 23.

[0037] The position sensor is fixedly installed in the left shell through a position sensor mounting seat, the position sensor comprises a position sensor signal emitting end 142 and a position sensor signal receiving end 143, the camera module is fixedly installed in the middle shell through a camera module mounting bracket, the stepping motor is fixedly installed in the right shell, the middle shell is provided with a camera window at a position corresponding to the camera module, and the camera window is provided with a transparent lens 10; a position detection shaft 121 is fixedly arranged at the left end of the camera module mounting bracket, the right end of the camera module mounting bracket is fixedly assembled with the output shaft of the stepping motor, the position detection shaft is rotatably assembled with the side wall of the position sensor mounting seat and penetrates between the position sensor signal emitting end and the position sensor signal receiving end, and a signal through hole 122 is formed in the position detection shaft; a signal shielding upper blocking edge 1211 is extended from the top end of one side wall of the signal through hole, and a signal shielding lower blocking edge 1212 is extended from the bottom end of the opposite side wall. The stepping motor drives the camera module, the camera module mounting bracket, the middle shell and the position detection shaft to rotate synchronously.

[0038] As Figure 9 As shown, the device of the present application is designed with a ±30° pitch adjustment angle, which can cover the capture of face information of 1.4 meters to 1.9 meters. When the customer triggers the face recognition instruction, if the customer's head portrait is in the shooting picture of the camera module 11, the host processor will calculate the deviation of the position of the face picture and the center position of the picture, and send the deviation signal to the driver, and the driver sends the driving instruction to the stepping motor, and the stepping motor completes the rotation to make the camera module shoot the customer's picture head portrait in the center. If the customer's head portrait is not in the shooting picture of the camera module 11, the host processor will trigger the stepping motor to perform a traversal pitch adjustment in the maximum angle range until the customer's head portrait is shot in the center.

[0039] To ensure the fastest face capture speed of the customer, the device of the present application can perform self-resetting action in any abnormal position (the camera is in the 0° position of the pitch adjustment). The device of the present application is designed to install a position sensor in the left shell and a stepping motor in the right shell. The middle shell is designed to have a camera module mounting bracket 12 and a camera module 11, wherein the right side of the camera module mounting bracket 12 is designed to have a D-shaped shaft hole for the stepping motor, the left side is designed to have a position detection shaft 123, the middle part of the position detection shaft is provided with a signal through hole 122, one side wall top end of the signal through hole is extended to form a signal shielding upper blocking edge, and the opposite side wall bottom end is extended to form a signal shielding lower blocking edge. Figure 6As shown, the position detection shaft 123 is just between the position sensor signal transmitting end 142 and the position sensor signal receiving end 143, at this time, the position sensor is in a signal off state; only when the step motor drives the camera module to the limit position of -30°, as shown in the figure, Figure 7 As shown, the position sensor sensing light beam 141 passes through the signal hole, so that the position sensor is in an on state. Other rotation angles, due to the blocking of the position detection shaft, the upper signal blocking side and the lower signal blocking side, the position sensor sensing light beam is interrupted. The upper computer processor reset operation logic is based on the above state, and the specific implementation is as follows: when the upper computer issues a reset instruction, the driver issues a default instruction to drive the step motor to rotate the camera module in the depression angle direction until the position sensor sensing light beam 141 can be connected, at this time, it has been judged that the camera has moved to the limit position of -30°. The upper computer triggers the driver to drive the step motor to reverse rotation +30°, to reach the default shooting position (0°) of the camera module.

[0040] As a further improvement of the above technical solution, as shown in the figure, Figure 8 As shown, the left and right ends of the intermediate shell are fixedly provided with arc pieces, the left arc piece is rotationally assembled with the left shell in a nested manner, and the right arc piece is rotationally assembled with the right shell in a nested manner. The left and right shells are both fixedly provided with arc piece rotation limit limiting tables 152 between the corresponding arc piece notches. Through the nested assembly of the arc pieces, the intermediate shell can be manually rotated in an emergency state to adjust the shooting angle of the camera module; during the rotation of the arc piece, the end portion 172 of the arc piece acts as a limiting piece, one side end portion is an arc piece rotation upper limiting edge 1721, and the other side end portion is an arc piece rotation lower limiting edge 1722. When the arc piece rotates forward and backward, the arc piece rotation upper limiting edge and the arc piece rotation lower limiting edge respectively contact the arc piece rotation limit limiting table to limit the forward and backward rotation of the arc piece, so that the range of the manually adjusted angle D is exactly the preset depression angle range. Preferably, the outer side wall of the arc piece is provided with a plurality of protrusions 171, which are between the rotation pairs. On the one hand, the protrusions can increase the strength of the intermediate shell as a whole, and on the other hand, the protrusions can reduce the friction between the intermediate shell and the left and right shells during rotation.

[0041] The embodiment further provides a recognition method using the face recognition device.

[0042] S1: the camera module is reset to the default optimal shooting angle: the step motor drives the camera module to rotate in the depression angle direction, and when the position sensor signal light beam passes through the signal hole to make the position sensor conduct, it indicates that the camera module has rotated to the maximum depression angle position, at this time, the step motor drives the camera module to reverse rotation by a preset depression angle value, so that the camera module is reset to the depression angle 0° position, i.e. the default optimal shooting angle;

[0043] S2 Automatic Face Tracking and Recognition: When a customer triggers a face recognition command, if the customer's image is in the camera module's field of view, the host computer processor will calculate the deviation between the position of the face in the field of view and the center position of the field of view, and send the deviation signal to the driver. The driver sends a drive command to the stepper motor, and the stepper motor completes the rotation to center the customer's image in the field of view captured by the camera module. If the customer's image is not in the field of view captured by the camera module, the host computer processor will trigger the stepper motor to perform a traversal pitch adjustment within the maximum angle range until the customer's image is centered in the field of view.

[0044] To make the above identification method clearer, a more specific implementation method is provided below:

[0045] like Figure 10 As shown, when the device is powered on, the driver sends a reset pulse data, the stepper motor rotates, and the camera module resets. When the service triggers a face capture, the camera module starts and takes a picture. If there is a face in the picture, the host computer calculates and returns the face position. If there is no face in the picture, the host computer sends a tilt adjustment command to locate the face and take a picture. The host computer then calculates and returns the face position. The driver sends a rotation pulse data, the stepper motor rotates, the face image is centered, a picture is taken, and then the process ends. After the process ends, the camera module is reset again.

[0046] It should be noted that in the description of this invention, the terms "upper end", "upper part", "upper section", "lower section", "axial direction", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0047] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An automatic tracking face recognition method, characterized in that, The device comprises a device body (1), the device body comprises a left shell (15), a position sensor mounting seat (16), a position sensor (14), an intermediate shell (17), a camera module mounting rack (12), a camera module (11), a right shell (19) and a stepping motor (18), the position sensor is fixedly installed in the left shell through the position sensor mounting seat, the position sensor comprises a position sensor signal emitting end (142) and a position sensor signal receiving end (143), the camera module is fixedly installed in the intermediate shell through the camera module mounting rack, and the stepping motor is fixedly installed in the right shell; a position detection shaft (121) is fixedly arranged at the left end of the camera module mounting rack, the right end of the camera module mounting rack is fixedly assembled with the output shaft of the stepping motor, the position detection shaft is rotatably assembled with the side wall corresponding to the position sensor mounting seat and penetrates between the position sensor signal emitting end and the position sensor signal receiving end, and a signal through hole (122) is formed in the position detection shaft; the left and right ends of the intermediate shell are rotatably assembled with the left and right shells respectively; the device comprises the following steps: S1, the camera module is reset to a default optimal shooting angle: the stepping motor (18) drives the camera module (11) to rotate in the direction of the pitch angle, when the position sensor signal light beam (141) penetrates through the signal through hole and makes the position sensor conduct, it indicates that the camera module rotates to the maximum pitch angle position, at this time, the stepping motor drives the camera module to reversely rotate a preset pitch angle value, so that the camera module is reset to the pitch angle 0° position, that is, the default optimal shooting angle; S2, automatic face tracking and recognition: when the customer triggers the face recognition instruction, if the customer's portrait is in the shooting picture of the camera module (11), the host computer processor calculates the deviation of the position of the face and the center position of the picture, sends the deviation signal to the driver, the driver sends the driving instruction to the stepping motor (18), and the stepping motor completes the rotation to make the camera module shoot the customer's picture portrait in the center; if the customer's portrait is not in the shooting picture of the camera module, the host computer processor will trigger the stepping motor to perform the traversal pitch adjustment in the maximum angle range until the customer's portrait is shot in the center of the picture. 2.The automatic tracking face recognition method of claim 1, wherein: One side wall top end of the signal through hole extends a signal shielding upper limit (1211), and the other side wall bottom end extends a signal shielding lower limit (1212). 3.The automatic tracking face recognition method of claim 2, wherein: The left and right ends of the intermediate shell are fixedly provided with arc pieces, the left arc piece is rotatably assembled with the left shell (15), the right arc piece is rotatably assembled with the right shell (19), and the left and right shells are fixedly provided with arc piece rotation limit limit tables (152) between the corresponding arc piece notches.

4. The automatic tracking face recognition method of claim 3, wherein: The outer side wall of the arc piece is provided with a plurality of protrusions (171).

5. The automatic tracking face recognition method of claim 4, wherein: The intermediate shell is provided with a camera window at a position corresponding to the camera module, and the camera window is provided with a transparent lens (10).

6. The automatic tracking face recognition method of claim 5, wherein: The position detection shaft is rotatably assembled with the side wall corresponding to the position sensor mounting seat through a bearing (13).

7. The automatic tracking face recognition method of claim 6, wherein: The bottom of the left and right shells is provided with a mounting boss (151).

8. The automatic tracking face recognition method according to any one of claims 1-7, characterized in that: Also include the magnetic installation assembly (2) fixedly assembled with the device body through the fixing screw (3). 9.The automatic tracking face recognition method of claim 8, wherein: The magnetic installation assembly includes a magnetic installation assembly shell (21), a magnetic installation assembly cover plate (22), and a magnetic connection terminal (23).

Images