A video face recognition system and method based on artificial intelligence

Abstract

The present invention relates to a video face recognition system and method based on artificial intelligence, comprising: a support base, a support frame and a face recognition body. The support frame is vertically fixedly connected to the support base. The face recognition body is connected to the support frame. The face recognition body is equipped with a face recognition lens for identifying and shooting. A video face recognition system based on artificial intelligence also includes: a stepping longitudinal and transverse motion mechanism and a clamping mechanism. The stepping longitudinal and transverse motion mechanism includes: a stepping electric telescopic rod, a connecting guide rail, a driving motor, a first driving gear, a second driving gear, a connecting side plate, a first rack and a second rack. The benefit of the present invention is that there is no need to transmit the video to the face recognition system for identification, and video recognition is directly performed, thereby improving the recognition efficiency and having a large recognition range.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence face recognition, and in particular to a video face recognition system and method based on artificial intelligence. Background Art

[0002] Nowadays, face recognition system technology is becoming more and more mature, and its application fields are becoming more and more extensive. Moreover, face recognition systems are based on artificial intelligence technology and operate intelligently. Face recognition technology can be used for real face recognition or for faces in videos. Generally, when performing video face recognition, the captured video needs to be transmitted to the face recognition system for recognition, which requires a certain amount of transmission time. At the same time, the transmitted video may need to be formatted due to changes in the carrier, which affects the recognition efficiency. Summary of the invention

[0003] The purpose of the present invention is to provide a video face recognition system and method based on artificial intelligence to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A video face recognition system based on artificial intelligence includes: a support base, a support frame and a face recognition body. The support frame is vertically fixedly connected to the support base. The face recognition body is connected to the support frame. The face recognition body is equipped with a face recognition lens for identifying and shooting. A video face recognition system based on artificial intelligence also includes: a step-by-step longitudinal and transverse motion mechanism and a clamping mechanism. The step-by-step longitudinal and transverse motion mechanism includes: a step-by-step electric telescopic rod, a connecting guide rail, a driving motor, a first driving gear, a second driving gear, a connecting side plate, a first rack and a second rack. The step-by-step electric telescopic rod is connected to the support frame. The connecting guide rail is connected to the step-by-step electric telescopic rod. The face recognition body is slidably connected to the connecting guide rail. Two driving motors are provided, both connected to the face recognition body, the main shaft end of one driving motor is connected to the first driving gear, the main shaft end of the other driving motor is connected to the second driving gear, and the first driving gear and the second driving gear are staggered left and right. Two connecting side plates are provided, both connected to the support base. The first rack is connected to one of the connecting side plates through a rebound hinge, and the first rack is evenly distributed on the connecting side plate from top to bottom. The second rack is movably connected to the other connecting side plate through a rebound hinge, and the second rack is evenly distributed on the connecting side plate from top to bottom. The first rack and the second rack are staggered up and down. The clamping mechanism is connected to the support frame.

[0006] As a further solution of the present invention: the clamping mechanism comprises: a first electric guide rail and a lifting plate. The first electric guide rail is mounted on a support frame. The lifting plate is horizontally slidably connected to the first electric guide rail. The upper end of the support frame is bent to a horizontal position.

[0007] As a further solution of the present invention, the clamping mechanism further comprises: rubber teeth, which are evenly distributed on the lifting plate and the horizontal bending end of the support frame.

[0008] As a further solution of the present invention: A video face recognition system based on artificial intelligence also includes: an electromagnetic fixing mechanism. The electromagnetic fixing mechanism includes: a connecting vertical plate, an electromagnet, a laser sensor switch and a laser emitter. The connecting vertical plate is vertically connected to the left side of the connecting side plate. Each first rack and the second rack are fitted with an electromagnet. The first rack and the second rack are both made of iron material. The electromagnet is fixedly connected to the connecting vertical plate. The laser sensor switch is equidistantly installed on the connecting vertical plate, and the laser sensor switch and the electromagnet exist one-to-one, and the laser sensor switch is electrically connected to the electromagnet. The laser emitter is installed on the face recognition body.

[0009] As a further solution of the present invention: a video face recognition system based on artificial intelligence also includes: a reset mechanism. The reset mechanism includes: a second electric guide rail, a limit horizontal plate and a pressure sensing switch. The second electric guide rail is connected to the support base. The connecting vertical plate and the connecting side plate are both slidably connected to the second electric guide rail. The limit horizontal plate is horizontally fixedly connected to the lifting plate. The pressure sensing switch is installed on the limit horizontal plate. The pressure sensing switch is electrically connected to the second electric guide rail and the step-type electric telescopic rod.

[0010] As a further solution of the present invention: a video face recognition system based on artificial intelligence also includes: a cleaning mechanism. The cleaning mechanism includes: an air pump, a boost chamber, an electric valve, an air pressure sensing switch and a connecting tube. The air pump is fixedly mounted on the support frame. The connecting tube is connected to the air pump. The boost chamber is arranged in the connecting tube, and the boost chamber is connected to the air outlet of the air pump. The electric valve is installed in the boost chamber. The air pressure sensing switch is installed in the boost chamber. The air pressure sensing switch is electrically connected to the electric valve.

[0011] As a further solution of the present invention: the cleaning mechanism further includes: a small vacuum cleaner and a dust suction hole. The small vacuum cleaner is installed on the connecting tube. The air pressure sensing switch is electrically connected to the small vacuum cleaner. The dust suction hole is opened in the connecting tube, and the dust suction hole is connected to the dust suction end of the small vacuum cleaner.

[0012] As a further solution of the present invention: dust suction holes are arranged around the connecting tube at equal intervals.

[0013] As a further solution of the present invention: the connecting tube is cylindrical so as to facilitate the equidistant dust suction holes to be provided.

[0014] A video face recognition method based on artificial intelligence is implemented by the above-mentioned video face recognition system based on artificial intelligence, and the specific steps are as follows:

[0015] The first step is to place the video playing device on the lifting plate. Then, through the first electric guide rail, the lifting plate clamps the video playing device at the horizontal bending end of the support frame to achieve fixed clamping;

[0016] The second step is to use the step-by-step electric telescopic rod to drive the face recognition body to gradually descend in the vertical direction to identify the face in the video played by the device. In addition, during the vertical movement, the first drive gear and the first rack move in coordination with each other, and the second drive gear and the first rack move in coordination with each other, causing the face recognition body to move back and forth horizontally, making it easier to identify the horizontal range of the video being played. This allows the face recognition body to move in all directions, horizontally and vertically, ensuring that faces at different positions in the video being played can be identified.

[0017] Step 3: When the face recognition body descends to the position of the limit horizontal plate, the pressure sensing switch causes the second electric guide rail to drive the first rack and the second rack to deviate. At the same time, the face recognition body rises and resets;

[0018] The fourth step is face recognition. The recognition system in the body classifies and arranges the recognized face information through the artificial intelligence system and outputs it;

[0019] The fifth step is to start the air pump to increase the air pressure in the boost chamber. Then the electric valve opens. The high-pressure air rushes to the outside, blowing away the dust on the face recognition lens, and the dust is sucked away by a small vacuum cleaner.

[0020] Compared with the prior art, the beneficial effects of the present invention are: there is no need to transmit the video to the face recognition system for recognition, and video recognition can be performed directly, thereby improving recognition efficiency and increasing the recognition range.

[0021] The video player is installed in front of the recognition lens of the recognition system by means of a clamping mechanism, without transmitting the video into the recognition system. At the same time, the face recognition lens moves vertically while relying on the staggered distribution of driving gears and racks to make the lens reciprocate horizontally, so as to facilitate the recognition of a wide range of video images.

[0022] Other features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The figure is a schematic structural diagram of a video face recognition system based on artificial intelligence of the present invention.

[0024] Figure 2 for Figure 1 Enlarged structural diagram of point A in the middle.

[0025] Figure 3 for Figure 1A left view structural diagram of the first rack, the second rack and the connecting side plate of an artificial intelligence-based video face recognition system of the present invention.

[0026] Figure 4 for Figure 1 A top view of the structure of a first rack, a second rack, a connecting side plate, a connecting vertical plate and an electromagnet in a video face recognition system based on artificial intelligence of the present invention.

[0027] Figure 5 for Figure 1 A top view of the structure of a face recognition body, a first drive gear and a second drive gear in a video face recognition system based on artificial intelligence of the present invention.

[0028] Figure 6 for Figure 1 A left-side structural diagram of a stepping electric telescopic rod, a connecting guide rail and a face recognition body of a video face recognition system based on artificial intelligence of the present invention.

[0029] List of accompanying drawings: A video face recognition system based on artificial intelligence 100; supporting base 10; supporting frame 20; face recognition body 30; face recognition lens 31; step-by-step vertical and horizontal motion mechanism 40; step-by-step electric telescopic rod 41; connecting guide rail 42; driving motor 43; first driving gear 44; second driving gear 45; connecting side plate 46; first rack 47; second rack 48; clamping mechanism 50; first electric guide rail 51; lifting plate 52; rubber tooth body 53; electromagnetic fixing mechanism 60; connecting vertical plate 61; electromagnet 62; laser sensor switch 63; laser emitter 64; reset mechanism 70; second electric guide rail 71; limit horizontal plate 72; pressure sensor switch 73; cleaning mechanism 80; air pump 81; boost chamber 82; electric valve 83; air pressure sensor switch 84; connecting cylinder 85; small vacuum cleaner 86; dust suction hole 87. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] like Figures 1 to 6As shown, in an embodiment of the present invention, a video face recognition system 100 based on artificial intelligence includes: a support base 10, a support frame 20 and a face recognition body 30. The support frame 20 is vertically fixedly connected to the upper side of the right end of the support base 10. The face recognition body 30 is connected to the upper side of the support frame 20. The face recognition body 30 is equipped with a face recognition lens 31 for identifying and shooting. The face recognition lens 31 is horizontally facing right and is used to shoot a video screen showing a face, and then the face is analyzed and recognized by the face recognition system in the body 30. A video face recognition system 100 based on artificial intelligence also includes: a step-by-step longitudinal and transverse motion mechanism 40 and a clamping mechanism 50. The step-by-step longitudinal and transverse motion mechanism 40 includes: a step-by-step electric telescopic rod 41, a connecting guide rail 42, a driving motor 43, a first driving gear 44, a second driving gear 45, a connecting side plate 46, a first rack 47 and a second rack 48. The step-type electric telescopic rod 41 is vertically fixedly connected to the upper left side of the support frame 20, and the lower end of the step-type electric telescopic rod 41 is a telescopic end, and the step-type electric telescopic rod 41 performs telescopic movement in the vertical direction. The connecting guide rail 42 is horizontally fixedly connected to the lower end of the step-type electric telescopic rod 41, and the connecting guide rail 42 is in a forward and backward position. The face recognition body 30 is slidably connected to the lower side of the connecting guide rail 42. Since the connecting guide rail 42 is in a forward and backward position, the face recognition body 30 only performs lateral movement in the forward and backward direction. There are two drive motors 43, both of which are fixedly connected to the left outer wall of the face recognition body 30, wherein the main shaft end of one drive motor 43 is connected to the first drive gear 44, and the main shaft end of the other drive motor 43 is connected to the second drive gear 45, and the first drive gear 44 and the second drive gear 45 are staggered left and right. The first drive gear 44 and the second drive gear 45 are both rotated under the action of the normally open drive motor 43, and the first drive gear 44 and the second drive gear 45 rotate in opposite directions. Two connecting side panels 46 are provided, both of which are vertically fixed to the upper left end of the support base 10. The first rack 47 is horizontally movably connected to one of the connecting side panels 46 through a rebound hinge, and the first rack 47 is equidistantly distributed on the connecting side panels 46 from top to bottom. The second rack 48 is horizontally movably connected to the other connecting side panel 46 through a rebound hinge, and the second rack 48 is equidistantly distributed on the connecting side panel 46 from top to bottom. The first rack 47 and the second rack 48 are staggered up and down, and the first rack 47 is aligned with the first drive gear 44. The second rack 48 is aligned with the second drive gear 45. The clamping mechanism 50 is connected to the support frame 20, and the clamping mechanism 50 is used to clamp the device that plays the video and make the device display screen face the face recognition lens 31.

[0032] After the device for playing the video is fixedly mounted on the support frame 20 through the clamping mechanism 50, the step-by-step electric telescopic rod 41 and the face recognition body 30 are started. The step-by-step electric telescopic rod 41 drives the face recognition body 30 to gradually descend in the vertical direction to recognize the face in the video played by the device. And when the step-by-step electric telescopic rod 41 stops, the first driving gear 44 is just docked with the first rack 47, and the second driving gear 45 is in a suspended state. In this way, under the drive of the driving motor 43, the first driving gear 44 rolls forward along the first rack 47, thereby causing the face recognition body 30 to move forward horizontally along the connecting guide rail 42, so as to facilitate the recognition of the horizontal range of the video playing. When the first driving gear 44 moves to the end along the first rack 47, the step-type electric telescopic rod 41 performs the next round of movement, pushing the face recognition body 30 to continue to move downward. Since the first rack 47 is movably connected to the connecting side plate 46 through the rebound hinge, the first driving gear 44 facilitates the first rack 47 to be pushed open to the lower position during this process. Then the second driving gear 45 is docked with the second rack 48, and the first driving gear 44 is in a suspended state. Since the first driving gear 44 and the second driving gear 45 turn in opposite directions, the second driving gear 45 moves backward laterally along the second rack 48 at this time, so that the face recognition body 30 can move in all directions, ensuring the recognition of faces at different positions in the video playback screen.

[0033] The clamping mechanism 50 includes: a first electric guide rail 51 and a lifting plate 52. The first electric guide rail 51 is vertically fixedly installed on the support frame 20. The lifting plate 52 is horizontally slidably connected to the first electric guide rail 51. The upper end of the support frame 20 is bent to a horizontal position, and the lifting plate 52 is aligned parallel to the horizontal bending end of the support frame 20. When it is necessary to fix and clamp the video device, the video device is placed on the lifting plate 52. Then the first electric guide rail 51 is started, so that the first electric guide rail 51 drives the lifting plate 52 to rise upward, and the video device is clamped at the horizontal bending end of the support frame 20 to achieve fixed clamping.

[0034] The clamping mechanism 50 further includes rubber teeth 53. The rubber teeth 53 are evenly distributed on the lifting plate 52 and the horizontal bending end of the support frame 20. The rubber teeth 53 facilitate the lifting plate 52 and the horizontal bending end of the support frame 20 to firmly clamp the video device.

[0035] A video face recognition system 100 based on artificial intelligence also includes: an electromagnetic fixing mechanism 60. The electromagnetic fixing mechanism 60 includes: a connecting vertical plate 61, an electromagnet 62, a laser sensor switch 63 and a laser emitter 64. The connecting vertical plate 61 is vertically connected to the left side of the connecting side plate 46. An electromagnet 62 is attached to the left side of each first rack 47 and the second rack 48. The first rack 47 and the second rack 48 are both made of iron. The electromagnet 62 is fixedly connected to the connecting vertical plate 61. The laser sensor switch 63 is equidistantly installed on the connecting vertical plate 61, and the laser sensor switch 63 and the electromagnet 62 exist one by one, and the laser sensor switch 63 and the electromagnet 62 are electrically connected. The laser emitter 64 is installed on the left end surface of the face recognition body 30. Whenever the step-type electric telescopic rod 41 pushes the face recognition body 30 down to the corresponding height. The laser emitter 64 is aligned with the laser sensor switch 63 at the current position. Then the laser sensing switch 63 receives the laser to generate induction, so that the electromagnet 62 at the current position is energized to generate magnetic force, and then the electromagnet 62 generates attraction with the first rack 47 or the second rack 48 at the current position, causing the first rack 47 and the second rack 48 to be stable in a horizontal position, facilitating the horizontal rolling of the first drive gear 44 or the second drive gear 45.

[0036] A video face recognition system 100 based on artificial intelligence also includes: a reset mechanism 70. The reset mechanism 70 includes: a second electric guide rail 71, a limit horizontal plate 72 and a pressure sensing switch 73. The second electric guide rail 71 is horizontally fixedly connected to the left side of the support base 10. The connecting vertical plate 61 and the connecting side plate 46 are both slidably connected to the second electric guide rail 71. The limit horizontal plate 72 is horizontally fixedly connected to the left end of the lifting plate 52. The pressure sensing switch 73 is fixedly mounted on the limit horizontal plate 72. The pressure sensing switch 73 is electrically connected to the second electric guide rail 71 and the contraction control circuit of the stepping electric telescopic rod 41 respectively. When the stepping electric telescopic rod 41 pushes the face recognition body 30 down to the position where the limit horizontal plate 72 is located, the pressure sensing switch 73 is squeezed. Then the pressure sensing switch 73 causes the second electric guide rail 71 to drive the connecting vertical plate 61 and the connecting side plate 46 to move horizontally to the left, causing the first rack 47 and the second rack 48 to deviate from the first drive gear 44 and the second drive gear 45. At the same time, the pressure sensing switch 73 causes the step-type electric telescopic rod 41 to retract, causing the face recognition body 30 to reset.

[0037] A video face recognition system 100 based on artificial intelligence also includes: a cleaning mechanism 80. The cleaning mechanism 80 includes: an air pump 81, a boost chamber 82, an electric valve 83, an air pressure sensing switch 84 and a connecting tube 85. The air pump 81 is fixedly mounted on the upper end of the support frame 20. The connecting tube 85 is horizontally fixedly connected to the air port end of the air pump 81, and the end of the connecting tube 85 is an opening. The boost chamber 82 is arranged on the inner side of the connecting tube 85, and the boost chamber 82 is connected to the air outlet end of the air pump 81. The electric valve 83 is installed on the side of the boost chamber 82 facing the opening of the connecting tube 85. The air pressure sensing switch 84 is installed on the inner side of the boost chamber 82. The air pressure sensing switch 84 is electrically connected to the electric valve 83. When the face recognition lens 31 is reset with the face recognition body, it is aligned at the port of the connecting tube 85. If it is necessary to clean the dust on the outside of the face recognition lens 31, the air pump 81 is started, and the air pump 81 inflates the boost chamber 82 to increase the internal air pressure. When the air pressure in the boost chamber 82 rises to a logarithmic value, the air pressure sensing switch 84 generates a sense and opens the electric valve 83. At the moment the electric valve 83 opens, the high-pressure air impacts the outside, that is, the instantaneous high-pressure airflow acts on the face recognition lens 31 to disperse the attached dust.

[0038] The cleaning mechanism 80 further includes: a small vacuum cleaner 86 and a dust suction hole 87. The small vacuum cleaner 86 is installed on the outside of the connecting tube 85. The air pressure sensing switch 84 is electrically connected to the small vacuum cleaner 86. The dust suction hole 87 is opened on the end side wall of the connecting tube 85, and the dust suction hole 87 is connected to the dust suction end of the small vacuum cleaner 86 through a tube body. When the high-pressure airflow in the boost chamber 82 blows away the dust on the face recognition lens 31, the small vacuum cleaner 86 relies on the dust suction hole 87 to suck away the scattered dust.

[0039] The dust suction holes 87 are equidistantly arranged around the end side wall of the connecting tube 85 to facilitate the suction of dust in all directions.

[0040] The connecting tube 85 is cylindrical in shape so as to provide dust suction holes 87 at equal intervals.

[0041] A video face recognition method based on artificial intelligence is implemented by the above-mentioned video face recognition system based on artificial intelligence 100, and the specific steps are as follows:

[0042] The first step is to place the video playback device on the lifting plate 52. Then start the first electric guide rail 51, so that the first electric guide rail 51 drives the lifting plate 52 to rise upward, and clamp the video playback device at the horizontal bending end of the support frame 20 to achieve fixed clamping, without transmitting the video to the recognition system, and directly recognize it;

[0043] The second step is to start the step-by-step electric telescopic rod 41 and the face recognition body 30. The step-by-step electric telescopic rod 41 drives the face recognition body 30 to gradually descend in the vertical direction, and the recognition device plays the face in the video. And when the step-by-step electric telescopic rod 41 stops, the first drive gear 44 is just connected to the first rack 47, and the second drive gear 45 is in a suspended state. In this way, under the drive of the drive motor 43, the first drive gear 44 rolls forward along the first rack 47, so that the face recognition body 30 moves forward along the connecting guide rail 42, which is convenient for identifying the screen in the horizontal range of the video playback. When the first drive gear 44 moves to the end along the first rack 47, the step-by-step electric telescopic rod 41 performs the next round of movement, pushing the face recognition body 30 to continue to move downward. Since the first rack 47 is movably connected to the connecting side plate 46 through the rebound hinge, the first drive gear 44 is convenient for pushing the first rack 47 to pass to the lower position during this process. Then the second driving gear 45 is connected to the second rack 48, and the first driving gear 44 is in a suspended state. Since the first driving gear 44 and the second driving gear 45 rotate in opposite directions, the second driving gear 45 moves backward along the second rack 48, so that the face recognition body 30 can move in all directions, ensuring recognition of faces at different positions in the video screen.

[0044] Step 3: When the step-by-step electric telescopic rod 41 pushes the face recognition body 30 down to the position of the limit horizontal plate 72, the pressure sensing switch 73 is squeezed. Then the pressure sensing switch 73 causes the second electric guide rail 71 to drive the connecting vertical plate 61 and the connecting side plate 46 to move horizontally to the left, causing the first rack 47 and the second rack 48 to deviate from the first drive gear 44 and the second drive gear 45. At the same time, the pressure sensing switch 73 causes the step-by-step electric telescopic rod 41 to contract, causing the face recognition body 30 to reset;

[0045] Step 4: The recognition system in the face recognition body 30 classifies and arranges the recognized face information through the artificial intelligence system and outputs it;

[0046] Step 5: After the face recognition lens 31 is reset with the face recognition body, it is aligned at the port of the connecting tube 85. If the dust on the outside of the face recognition lens 31 needs to be cleaned, the air pump 81 is started, and the air pump 81 inflates the boost chamber 82 to increase the internal air pressure. When the air pressure in the boost chamber 82 rises to a logarithmic value, the air pressure sensing switch 84 generates a sense and opens the electric valve 83. At the moment the electric valve 83 opens, the high-pressure air impacts the outside, that is, the instantaneous high-pressure airflow acts on the face recognition lens 31, so that the attached dust is dispersed, and the dust is sucked away by a small vacuum cleaner.

[0047] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0048] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A video face recognition system based on artificial intelligence, comprising: A support base, a support frame and a face recognition body; the support frame is vertically fixedly connected to the support base; The face recognition body is connected to the support frame; The face recognition body is equipped with a face recognition lens for identifying and photographing; it is characterized in that the video face recognition system based on artificial intelligence also includes: a step-by-step vertical and horizontal motion mechanism and a clamping mechanism; the step-by-step vertical and horizontal motion mechanism includes: a step-by-step electric telescopic rod, a connecting guide rail, a driving motor, a first driving gear, a second driving gear, a connecting side plate, a first rack and a second rack; the step-by-step electric telescopic rod is connected to the support frame; the connecting guide rail is connected to the step-by-step electric telescopic rod; the face recognition body is slidably connected to the connecting guide rail; two driving motors are provided, both of which are connected to the face recognition body, and the main The shaft end is connected to the first driving gear, the main shaft end of the other driving motor is connected to the second driving gear, and the first driving gear and the second driving gear are staggered left and right; the connecting side plates are provided with two pieces, both connected to the supporting base; the first rack is connected to one of the connecting side plates through a rebound hinge, and the first rack is equidistantly distributed on the connecting side plates from top to bottom; the second rack is movably connected to the other connecting side plate through a rebound hinge, and the second rack is equidistantly distributed on the connecting side plates from top to bottom; the first rack and the second rack are staggered up and down; the clamping mechanism is connected to the supporting frame; The clamping mechanism includes: a first electric guide rail and a lifting plate; the first electric guide rail is vertically fixedly installed on the support frame; the lifting plate is horizontally slidably connected to the first electric guide rail; the upper end of the support frame is bent to a horizontal position, and the lifting plate is aligned parallel to the horizontal bent end of the support frame; when the video playback device needs to be fixedly clamped, the video device is placed on the lifting plate.

2. The video face recognition system based on artificial intelligence according to claim 1, characterized in that: The clamping mechanism further includes: rubber teeth; the rubber teeth are evenly distributed on the lifting plate and the horizontal bending ends of the support frame.

3. The video face recognition system based on artificial intelligence according to claim 2 is characterized in that: The artificial intelligence-based video face recognition system also includes: an electromagnetic fixing mechanism; the electromagnetic fixing mechanism includes: a connecting vertical plate, an electromagnet, a laser sensing switch and a laser emitter; the connecting vertical plate is vertically connected to the left side of the connecting side plate; each of the first rack and the second rack is attached with the electromagnet; the first rack and the second rack are both made of iron material; the electromagnet is fixedly connected to the connecting vertical plate; the laser sensing switch is equidistantly installed on the connecting vertical plate, and the laser sensing switch and the electromagnet exist one-to-one, and the laser sensing switch is electrically connected to the electromagnet; the laser emitter is installed on the face recognition body.

4. The video face recognition system based on artificial intelligence according to claim 3 is characterized in that: The artificial intelligence-based video face recognition system also includes: a reset mechanism; the reset mechanism includes: a second electric guide rail, a limit horizontal plate and a pressure sensing switch; the second electric guide rail is connected to the support base; the connecting vertical plate and the connecting side plate are both slidably connected to the second electric guide rail; the limit horizontal plate is horizontally fixedly connected to the lifting plate; the pressure sensing switch is installed on the limit horizontal plate; the pressure sensing switch is electrically connected to the second electric guide rail and the step-by-step electric telescopic rod.

5. The artificial intelligence-based video face recognition system according to claim 4, characterized in that: The artificial intelligence-based video face recognition system also includes: a cleaning mechanism; the cleaning mechanism includes: an air pump, a boost chamber, an electric valve, an air pressure sensing switch and a connecting tube; the air pump is fixedly installed on the support frame; the connecting tube is connected to the air pump; the boost chamber is arranged in the connecting tube, and the boost chamber is connected to the air outlet end of the air pump; the electric valve is installed in the boost chamber; the air pressure sensing switch is installed in the boost chamber; the air pressure sensing switch is electrically connected to the electric valve.

6. The artificial intelligence-based video face recognition system according to claim 5, characterized in that: The cleaning mechanism also includes: a small vacuum cleaner and a dust suction hole; the small vacuum cleaner is installed on the connecting tube; the air pressure sensing switch is electrically connected to the small vacuum cleaner; the dust suction hole is opened in the connecting tube, and the dust suction hole is connected to the dust suction end of the small vacuum cleaner.

7. The artificial intelligence-based video face recognition system according to claim 6, characterized in that: The dust suction holes are equidistantly arranged around the connecting tube.

8. The artificial intelligence-based video face recognition system according to claim 7, characterized in that: The connecting tube is in a cylindrical shape so as to facilitate the equidistant arrangement of the dust suction holes.

9. A video face recognition method based on artificial intelligence, implemented by the video face recognition system based on artificial intelligence according to claim 8, characterized in that: The specific steps are as follows: The first step is to place the video playback device on the lifting plate; then, through the first electric guide rail, the lifting plate clamps the video playback device at the horizontal bending end of the support frame to achieve fixed clamping; In the second step, the face recognition body is driven to gradually descend in the vertical direction by the step-type electric telescopic rod to recognize the face in the video played by the device; and during the longitudinal movement, the first driving gear and the first rack cooperate with each other, and the second driving gear and the first rack cooperate with each other, so that the face recognition body moves back and forth horizontally, which is convenient for recognizing the horizontal range of the video being played; thereby, the face recognition body can move in all directions horizontally and vertically, ensuring the recognition of faces at different positions in the video being played; In the third step, when the face recognition body descends to the position where the limit horizontal plate is located, the pressure sensing switch causes the second electric guide rail to drive the first rack and the second rack to deviate from each other; at the same time, the face recognition body rises and resets; In the fourth step, the recognition system in the face recognition machine classifies and arranges the recognized face information through the artificial intelligence system and outputs it; The fifth step is to start the air pump to increase the air pressure in the boost chamber; then the electric valve is opened; The high-pressure air impacts the outside, blows away the dust on the face recognition lens, and the small vacuum cleaner sucks away the blown dust.

Images