Chip identification device based on machine vision deep learning

Abstract

The utility model discloses a chip identification device based on machine vision deep learning, which comprises a shell, an operation panel, a picture display screen, a data display screen, a radio sound outlet hole, a controller and a processing data board, and is characterized in that a capturing device is arranged, a motor drives a round rod to rotate, and the round rod drives a supporting plate to rotate when rotating; the supporting plate rotates to drive the connecting block to rotate, the connecting block rotates to drive the fixing block to rotate, and the fixing block rotates to drive the camera to rotate, so that the camera can rotate left and right, the electric push rod drives the rack to move, the rack moves to drive the gear to rotate, and the gear rotates to drive the adjusting rod to rotate. When the adjusting rod rotates, the fixing block is driven to rotate, when the fixing block rotates, the camera is driven to rotate, the camera can rotate up and down through the arrangement, the camera can automatically rotate through the arrangement, the camera can automatically capture learning objects, manual alignment is not needed, and the recognition learning efficiency is improved.

Description

Technical Field

[0001] The utility model relates to the technical field of chip identification technology, and specifically to a chip identification device based on machine vision deep learning. Background Art

[0002] The concept of deep learning originated from the study of artificial neural networks. A multilayer perceptron with multiple hidden layers is a deep learning structure. Deep learning combines low-level features to form more abstract high-level representations of attribute categories or features to discover the distributed feature representation of data. Deep learning is a method in machine learning based on characterizing and learning data. It is a new field in machine learning research. Its motivation is to establish and simulate neural networks for analytical learning in the human brain. It imitates the mechanisms of the human brain to interpret data.

[0003] For example, the "A chip identification device based on machine vision deep learning" with publication number CN215729866U includes a device body, a handwriting screen, a wide-angle camera and a sound receiving hole. A handwriting screen is installed in the middle of the front of the device body, a wide-angle camera is arranged above the handwriting screen, a plurality of sound receiving holes are respectively provided on the left and right sides of the wide-angle camera, a plurality of sound outlet holes are respectively provided on the left and right sides of the handwriting screen, an identification plate is arranged at the lower left side of the handwriting screen, and a switch is arranged at the lower right side of the handwriting screen. By setting up a wide-angle camera and an AI module, the recognition chip can realize intelligent recognition operation process, making it more practical. By setting up a voice input unit, the recognition chip can recognize sound data and respond intelligently through the AI ​​module. In actual use, it is more suitable for the field of chip recognition technology.

[0004] Although the above recognition device has certain advantages in learning recognition, it still has certain disadvantages:

[0005] When using the above-mentioned recognition device for deep learning of machine vision, the object to be learned needs to be moved to align with the camera to ensure that the camera can capture the object. This method requires constant correction of the position of the object, which takes time and slows down the learning process, thereby affecting learning efficiency. Utility Model Content

[0006] 1. Technical issues to be resolved

[0007] In view of the deficiencies in the prior art, the utility model provides a chip identification device based on machine vision deep learning, which solves the above-mentioned problems.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the utility model is implemented through the following technical solutions: a chip recognition device based on machine vision deep learning, including a shell, an operation panel, a picture display screen, a data display screen, a sound receiving and outputting hole, a controller, a processing data board and a capture device, wherein the operation panel is installed on the front top side of the shell, the picture display screen is arranged at the front end of the shell, the data display screen is arranged on the front top side of the shell, the sound receiving and outputting hole is arranged on the front top side of the shell, the controller is installed on the inner top end of the shell, the processing data board is installed on the inner bottom end of the shell, the capture device is arranged on the front end of the shell, and the capture device includes a protective shell, a motor, a round rod, a support plate, a fixing rod, a connecting ... A connecting block, an adjusting rod, a fixing block, a camera and an adjusting mechanism, wherein the protective shell is fixed to the front end top of the shell, the motor is installed at the top end of the protective shell, the round rod is arranged inside the protective shell, and the top end of the round rod is transmission-connected to the output shaft of the motor through a coupling, the support plate is fixed to the bottom end of the round rod, the fixing rod is provided with two groups, and both are arranged at the top end of the support plate, the top end of the fixing rod is arranged at the inner top end of the protective shell, the connecting block is fixed to the bottom end of the support plate, the adjusting rod passes through the front end and the rear end of the connecting block, the fixing block is arranged on the outside of the adjusting rod, and extends downward to the bottom end of the protective shell, the camera is installed at the front end of the fixing block, and the adjusting mechanism is arranged inside the protective shell.

[0010] Preferably, the adjustment mechanism includes a fixed plate, an electric push rod, a rack and a gear, the fixed plate is fixed to the rear side of the right end of the support plate, the electric push rod is installed on the top of the fixed plate, and the front end of the electric push rod is transmission connected to the rack, the rack is arranged on the outside of the adjustment rod, and the gear is fixed to the outside of the adjustment rod.

[0011] Preferably, a groove is provided at the bottom end of the protective shell, and the groove is arranged in a ring shape, so that the fixing rod will not cause jamming when rotating.

[0012] Preferably, the top end of the fixing rod is arranged in a convex shape and fits into the inside of the bottom groove of the protective shell. Through this arrangement, the fixing rod can be fixed to the protective shell, so that the position of the support plate is fixed.

[0013] Preferably, a groove is provided at the bottom end of the connecting block, and this arrangement enables the fixing block to rotate.

[0014] Preferably, the motor, round rod, support plate and connecting block are arranged in the same vertical direction, through which the rotation of the motor drives the round rod to rotate, the rotation of the round rod drives the support plate to rotate, and the rotation of the support plate drives the connecting block to rotate.

[0015] Preferably, the rack and the gear are arranged in the same vertical position, and the bottom end of the rack and the gear are meshed with each other. Through this arrangement, the rack can drive the gear to rotate when it moves.

[0016] (III) Beneficial effects

[0017] The utility model provides a chip recognition device based on machine vision deep learning. It has the following beneficial effects: by setting a capture setting, the motor drives the round rod to rotate, the round rod rotates and drives the support plate to rotate, the support plate rotates and drives the connecting block to rotate, the connecting block rotates and drives the fixed block to rotate, the fixed block rotates and drives the camera to rotate, through this setting, the camera can be rotated left and right, the electric push rod drives the rack to move, the rack movement drives the gear to rotate, the gear rotates and drives the adjustment rod to rotate, the adjustment rod rotates and drives the fixed block to rotate, the fixed block rotates and drives the camera to rotate, through this setting, the camera can be rotated up and down, through this setting, the camera can be automatically rotated, so that the camera can automatically capture the learning objects, without manual alignment, and improve the recognition learning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the structure of the utility model;

[0019] Figure 2 It is a structural side view of the utility model;

[0020] Figure 3 It is a side view of the structure of the capture device in the utility model;

[0021] Figure 4 This is a bottom view of the capture device structure in the utility model;

[0022] Figure 5 It is a bottom view of the adjusting mechanism structure in the utility model.

[0023] In the figure: shell 1, operation panel 2, screen display 3, data display 4, sound receiving and output hole 5, controller 6, data processing board 7, capture device 8, protective shell 81, motor 82, round rod 83, support plate 84, fixing rod 85, connecting block 86, adjusting rod 87, fixing block 88, camera 89, adjusting mechanism 810, fixing plate 8101, electric push rod 8102, rack 8103, gear 8104. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the utility model to clearly and completely describe the technical solutions in the embodiments of the utility model. Obviously, the described embodiments are only part of the embodiments of the utility model, not all of the embodiments. Based on the embodiments in the utility model, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the utility model.

[0025] See also Figure 1-4 The utility model provides a technical solution of a chip recognition device based on machine vision deep learning: a chip recognition device based on machine vision deep learning, comprising a shell 1, an operation panel 2, a picture display screen 3, a data display screen 4, a sound receiving and outputting hole 5, a controller 6, a processing data board 7 and a capture device 8, wherein the operation panel 2 is mounted on the front top side of the shell 1, the picture display screen 3 is arranged at the front end of the shell 1, the data display screen 4 is arranged on the front top side of the shell 1, the sound receiving and outputting hole 5 is arranged on the front top side of the shell 1, the controller 6 is mounted on the inner top of the shell 1, and the processing data board 7 and the capture device 8 are arranged. The data board 7 is installed at the inner bottom end of the shell 1, and the capture device 8 is arranged at the front end of the shell 1. The capture device 8 includes a protective shell 81, a motor 82, a round rod 83, a support plate 84, a fixing rod 85, a connecting block 86, an adjusting rod 87, a fixing block 88, a camera 89 and an adjusting mechanism 810. The protective shell 81 is fixed to the front top of the shell 1, the motor 82 is installed at the top of the protective shell 81, the round rod 83 is arranged inside the protective shell 81, and the top of the round rod 83 is connected to the output shaft of the motor 82 through a coupling, the support plate 84 is fixed to the bottom end of the round rod 83, and the fixing rod 87 is connected to the output shaft of the motor 82 through a coupling. There are two groups of 85, and both are arranged at the top of the support plate 84. The top of the fixing rod 85 is arranged at the inner top of the protective shell 81. The connecting block 86 is fixed to the bottom end of the support plate 84. The adjusting rod 87 runs through the front and rear ends of the connecting block 86. The fixing block 88 is arranged on the outside of the adjusting rod 87 and extends downward to the bottom end of the protective shell 81. The camera 89 is installed at the front end of the fixing block 88. The adjusting mechanism 810 is arranged inside the protective shell 81. The bottom end of the protective shell 81 is provided with a groove, and the groove is arranged in an annular shape. Through this arrangement, the fixing rod 85 will not cause jamming when rotating. The top of the fixing rod 85 is arranged in a convex shape and fits into the inside of the bottom groove of the protective shell 81. Through this arrangement, the fixing rod can be fixed to the protective shell 81, so that the position of the support plate 84 is fixed. The bottom end of the connecting block 86 is provided with a groove. Through this arrangement, the fixing block 88 can be rotated. The motor 82, the round rod 83, the support plate 84 and the connecting block 86 are arranged in the same vertical direction. Through this arrangement, the motor 82 rotates to drive the round rod 83 to rotate, and when the round rod 83 rotates, it drives the support plate 84 to rotate, and when the support plate 84 rotates, it drives the connecting block 86 to rotate.

[0026] See also Figure 5The utility model provides a technical solution of a chip recognition device based on machine vision deep learning: a chip recognition device based on machine vision deep learning, including an adjustment mechanism 810 including a fixed plate 8101, an electric push rod 8102, a rack 8103 and a gear 8104, the fixed plate 8101 is fixed to the rear side of the right end of the support plate 84, the electric push rod 8102 is installed on the top of the fixed plate 8101, and the front end of the electric push rod 8102 is transmission connected with the rack 8103, the rack 8103 is arranged on the outer side of the adjustment rod 87, and the gear 8104 is fixed on the outer side of the adjustment rod 87, the rack 8103 and the gear 8104 are arranged in the same vertical direction, and the bottom end of the rack 8103 and the gear 8104 are meshed with each other, through this arrangement, the rack 8103 can drive the gear 8104 to rotate when it moves.

[0027] Here’s how it works:

[0028] First, before use, click the operation panel 2 to turn on the learning mode of the device, and place the object to be learned next to it and wait for recognition and learning;

[0029] Second, bring the object to the camera 89, calibrate it through the controller 6 according to the object picture taken by the camera 89, start the motor 82, the motor 82 drives the round rod 83 to rotate, the round rod 83 drives the support plate 84 to rotate when it rotates, the support plate 84 drives the connecting block 86 to rotate when it rotates, the connecting block 86 drives the fixing block 88 to rotate when it rotates, and the fixing block 88 drives the camera 89 to rotate when it rotates, so that the camera 89 can swing left and right to capture the object, so that the object appears completely in the picture;

[0030] Third, start the electric push rod 9102 so that the electric push rod 8102 pushes the rack 8103 to move. When the rack 8103 moves, it drives the gear 8104 to rotate. When the gear 8104 rotates, it drives the adjusting rod 87 to rotate. When the adjusting rod 87 rotates, it drives the fixed block 88 to rotate. When the fixed block 88 rotates, it drives the camera 89 to rotate, so that the camera 89 can rotate up and down to capture objects, thereby reducing the time for aligning objects and improving efficiency.

[0031] The control method of the present invention is to control by manually starting and closing the switch. The wiring diagram of the power element and the provision of power supply are common knowledge in the field, and the present invention is mainly used to protect mechanical devices, so the present invention will not explain the control method and wiring arrangement in detail.

[0032] The control method of the present invention is automatic control through a controller. The control circuit of the controller can be realized by simple programming by technicians in this field. The provision of power is also common knowledge in this field. The present invention is mainly used to protect mechanical devices, so the present invention will no longer explain the control method and circuit connection in detail.

[0033] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A chip recognition device based on machine vision deep learning, comprising a housing (1), an operation panel (2), a picture display screen (3), a data display screen (4), a sound receiving and outputting hole (5), a controller (6) and a data processing board (7), wherein the operation panel (2) is mounted on the front top side of the housing (1), the picture display screen (3) is arranged at the front end of the housing (1), the data display screen (4) is arranged on the front top side of the housing (1), the sound receiving and outputting hole (5) is arranged on the front top side of the housing (1), the controller (6) is mounted on the inner top end of the housing (1), and the data processing board (7) is mounted on the inner bottom end of the housing (1); Features: The invention also comprises a capture device (8), wherein the capture device (8) is arranged at the front end of the housing (1), and the capture device (8) comprises a protective shell (81), a motor (82), a round rod (83), a support plate (84), a fixing rod (85), a connecting block (86), an adjusting rod (87), a fixing block (88), a camera (89) and an adjusting mechanism (810), wherein the protective shell (81) is fixed to the top of the front end of the housing (1), the motor (82) is mounted on the top end of the protective shell (81), the round rod (83) is arranged inside the protective shell (81), and the top end of the round rod (83) is driven by the output shaft of the motor (82) through a coupling. The support plate (84) is fixed to the bottom end of the round rod (83), two groups of the fixing rods (85) are provided, and both are arranged at the top end of the support plate (84), the top end of the fixing rods (85) is arranged at the inner top end of the protective shell (81), the connecting block (86) is fixed to the bottom end of the support plate (84), the adjusting rod (87) passes through the front end and the rear end of the connecting block (86), the fixing block (88) is arranged on the outside of the adjusting rod (87) and extends downward to the bottom end of the protective shell (81), the camera (89) is installed at the front end of the fixing block (88), and the adjusting mechanism (810) is arranged inside the protective shell (81).

2. The chip recognition device based on machine vision deep learning according to claim 1, characterized in that: The adjustment mechanism (810) comprises a fixed plate (8101), an electric push rod (8102), a rack (8103) and a gear (8104); the fixed plate (8101) is fixed to the rear side of the right end of the support plate (84); the electric push rod (8102) is installed on the top end of the fixed plate (8101); and the front end of the electric push rod (8102) is transmission-connected to the rack (8103); the rack (8103) is arranged on the outer side of the adjustment rod (87); and the gear (8104) is fixed to the outer side of the adjustment rod (87).

3. The chip recognition device based on machine vision deep learning according to claim 1, characterized in that: The bottom end of the protective shell (81) is provided with a groove, and the groove is arranged in an annular shape.

4. The chip recognition device based on machine vision deep learning according to claim 1, characterized in that: The top end of the fixing rod (85) is arranged in a convex shape and fits in the inside of the bottom groove of the protective shell (81).

5. The chip recognition device based on machine vision deep learning according to claim 1, characterized in that: The bottom end of the connecting block (86) is provided with a groove.

6. The chip recognition device based on machine vision deep learning according to claim 1, characterized in that: The motor (82), the round rod (83), the support plate (84) and the connecting block (86) are arranged vertically in the same manner.

7. The chip recognition device based on machine vision deep learning according to claim 2, characterized in that: The rack (8103) and the gear (8104) are arranged vertically in the same manner, and the bottom end of the rack (8103) and the gear (8104) are meshed with each other.

Images