CN219519638U - Automatic recognition machine - Google Patents

Automatic recognition machine Download PDF

Info

Publication number
CN219519638U
CN219519638U CN202320059499.8U CN202320059499U CN219519638U CN 219519638 U CN219519638 U CN 219519638U CN 202320059499 U CN202320059499 U CN 202320059499U CN 219519638 U CN219519638 U CN 219519638U
Authority
CN
China
Prior art keywords
product
module
detected
identified
analysis module
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202320059499.8U
Other languages
Chinese (zh)
Inventor
温天雨
龚兵
段建红
向佳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Xinhao Photoelectric Technology Co ltd
Original Assignee
Shenzhen Xinhao Photoelectric Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Xinhao Photoelectric Technology Co ltd filed Critical Shenzhen Xinhao Photoelectric Technology Co ltd
Priority to CN202320059499.8U priority Critical patent/CN219519638U/en
Application granted granted Critical
Publication of CN219519638U publication Critical patent/CN219519638U/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Image Processing (AREA)

Abstract

The utility model provides an automatic identification machine, which relates to the technical field of automatic identification and comprises a transmission module, a detection module, an analysis module and a control module, wherein the transmission module is used for transmitting standard products and products to be detected; the detection module is used for collecting the image information of the standard product and the product to be detected and transmitting the image information to the analysis module for analysis; the analysis module sets the center position of the product to be detected according to the outline dimensions of the standard product and the product to be detected in the image information, establishes a coordinate system, and identifies the positioning line, the character mark, the IR hole and the date code of the product to be detected; the control module is connected with the analysis module and is used for eliminating the product identified as bad according to the identification result of the analysis module.

Description

Automatic recognition machine
Technical Field
The utility model relates to the technical field of automatic identification, in particular to an automatic identification machine.
Background
Along with the approach of the design concept of each mobile phone manufacturer, the mobile phone shape, display area and size structure of each manufacturer are basically similar. Because the mobile phone manufacturer attaches the display screen to the same mobile phone by sending different module manufacturers, and different module factories can print own models to the rear of the glass cover plate in a printing mode, the models are distinguished as character marks, the method is a common method for the module manufacturers to distinguish the models of materials by themselves, and in the same situation, the sizes are the same, only the character marks are different, so that a great test is brought to the process of producing the mobile phone protective screen for preventing mixing materials; in addition, the silk-screen optical sensing function hole (i.e. IR hole) is used for a mobile phone light sensing sensor, is a functional component of a mobile phone, and is easy to generate the printing leakage because the IR hole is printed independently; the alignment auxiliary line (i.e. the positioning line) of the screen printing paste display module is a main functional component for alignment of the paste display module, and the screen is easy to block after printing for a certain time due to the narrow line width of the printed positioning line. The following procedures can not be performed if the following procedures flow to the client, and the following procedures can not be performed, so that the following procedures are wasted, and a poor sheet can be caused, so that the following procedures can be performed together to discard a set of materials.
However, the above defects are serious errors for manufacturers, and defective products must be removed to prevent the defective products from flowing to the next process. At present, the most original method is that personnel are arranged to fully check character marks and print shape structures, then the full check size is arranged, the situation that the same character mark materials are misused with white piece glass, the full check IR holes are in missing printing, and the full check positioning lines are missing is prevented. The prior inspection error mixing before shipment generally prevents the white chips from being used by mistake through the full inspection size of a machine, and then the manual inspection is performed to select the character mark mixing and IR hole missing printing and select the missing positioning line. The manual inspection is low in efficiency, high in personnel cost, easy to fatigue and easy to misjudge, and the personnel can inspect for a long time. In addition, because the distribution of the positioning line structure basically covers the whole back, and the structural design is mainly intermittent, besides the single line, the positioning line structure also has different structures such as punctiform, triangular, square, LOGO and the like, through manual inspection, the defect of the positioning line on the back can not be completely detected, and 100% of the positioning line structure is not mixed.
Disclosure of Invention
In order to overcome the defects in the prior art, the utility model provides an automatic identification machine.
The technical scheme adopted for solving the technical problems is as follows: in an automatic identification machine, the improvement comprising: the device comprises a transmission module, a detection module, an analysis module and a control module, wherein the transmission module is used for transmitting standard products and products to be tested; the detection module is used for collecting the image information of the standard product and the product to be detected and transmitting the image information to the analysis module for analysis; the analysis module sets the center position of the product to be detected according to the outline dimensions of the standard product and the product to be detected in the image information, establishes a coordinate system, and identifies the positioning line, the character mark, the IR hole and the date code of the product to be detected; the control module is connected with the analysis module and is used for eliminating the product identified as bad according to the identification result of the analysis module.
In the structure, the device further comprises an induction module, wherein the induction module is connected with the analysis module and is used for counting the products which are identified as good after the products to be detected are identified.
In the above structure, the device further comprises a manipulator connected with the control module, and the manipulator is used for sucking away the product identified as bad according to the instruction of the control module.
In the structure, the transmission module comprises a motor and a conveyor belt, and the motor drives the conveyor belt to enable a product to be tested to be transmitted to the sensing module from the starting point of the conveyor belt;
the control module is connected with the motor and is used for reducing the transmission speed of the motor after the product is identified as bad, so that the mechanical arm sucks away the product identified as bad.
In the above structure, the analysis module identifies the positioning line, the mark, the IR hole and the date code of the product to be detected by the following method:
the positioning line is taken as an image, the image is identified according to the existence of the positioning line, if the positioning line exists, the image is identified as good, and if the positioning line does not exist, the image is identified as bad;
taking the mark as a number, detecting the number on the product, analyzing specific data, if the number on the product to be detected is the same as the number on the standard product, identifying the product as good, and if the number is different, identifying the product as bad;
the IR hole position is taken as an image, and is identified according to the presence or absence of IR ink, if the IR ink is not present, the color of the conveyor belt is the missing print, the IR hole position is identified as bad, if the IR ink is present, the color of the IR hole position is inconsistent with the color of the conveyor belt, the IR hole position is identified as not missing print, and if the IR ink is present, the IR hole position is identified as good;
and taking the date code as a number, detecting whether the number is in the data range of the standard product, if so, identifying the number as good, and if not, identifying the number as bad.
The beneficial effects of the utility model are as follows: the image recognition and the information recognition are carried out on the images of the standard products, then the standard program is set, the mass recognition and detection are carried out on the products to be detected, the bad products are automatically removed, the outflow probability of the bad products is reduced, the machine replaces people, and the manpower input is reduced.
Drawings
Fig. 1 is a schematic structural diagram of an automatic recognition machine according to the present utility model.
Detailed Description
The utility model will be further described with reference to the drawings and examples.
The conception, specific structure, and technical effects produced by the present utility model will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, features, and effects of the present utility model. It is apparent that the described embodiments are only some embodiments of the present utility model, but not all embodiments, and that other embodiments obtained by those skilled in the art without inventive effort are within the scope of the present utility model based on the embodiments of the present utility model. In addition, all the coupling/connection relationships referred to in the patent are not direct connection of the single-finger members, but rather, it means that a better coupling structure can be formed by adding or subtracting coupling aids depending on the specific implementation. The technical features in the utility model can be interactively combined on the premise of no contradiction and conflict.
Referring to fig. 1, an automatic recognition machine comprises a transmission module, a detection module, an analysis module, a control module, an induction module and a manipulator, wherein the transmission module comprises a motor and a conveyor belt, and the motor drives the conveyor belt to enable a product to be detected to be transmitted from a starting point of the conveyor belt to the induction module;
the detection module is used for collecting the image information of the standard product and the product to be detected and transmitting the image information to the analysis module for analysis;
the analysis module sets the center position of the product to be detected according to the outline dimensions of the standard product and the product to be detected in the image information, establishes a coordinate system, and identifies the positioning line, the character mark, the IR hole and the date code of the product to be detected;
the control module is connected with the analysis module and is used for eliminating the product identified as bad according to the identification result of the analysis module; further, the manipulator is connected with the control module, and the manipulator sucks away the product identified as bad according to the instruction of the control module; further, the control module is connected with the motor, and after the product is identified as bad, the transmission speed of the motor is reduced, so that the mechanical arm can conveniently suck the product identified as bad on the conveyor belt;
the sensing module is connected with the analysis module and is used for counting the products which are identified as good after the products to be detected are identified.
Firstly, placing a standard product with the back face upwards on a conveyor belt, picking an image of the standard product through a detection module, and inputting the image to an analysis module; analyzing the standard product image acquired by the analysis module, setting the center position of the product through the outline dimension of the product, and establishing a coordinate system; according to a similar method, the detection module picks up images of the product to be detected, and transmits the images to the analysis module for analysis and identification, and the positioning line, the character mark, the IR hole and the date code to be detected on the product to be detected are all on the fixed area coordinates of the product coordinate system;
the analysis module identifies the positioning line, the character mark, the IR hole and the date code of the product to be detected, and the method is as follows:
the positioning lines are recognized as images, such as silk screen printing lines, angle lines, circles, LOGO and the like, according to the presence or absence of the positioning lines, if the positioning lines are good, if the positioning lines are bad, the positioning lines are bad;
the mark is used as a number, for example, the number 12345678 on a standard product, the number on the product to be detected is detected, specific data is analyzed, if the number on the product to be detected is the same as the number on the standard product, the mark is identified as good, and if the mark is different, the mark is identified as bad;
the IR hole position is taken as an image, and is identified according to the presence or absence of IR ink, if the IR ink is not present, the color of the conveyor belt is the missing print, the IR hole position is identified as bad, if the IR ink is present, the color of the IR hole position is inconsistent with the color of the conveyor belt, the IR hole position is identified as not missing print, and if the IR ink is present, the IR hole position is identified as good; the IR holes are kept away by the main ink, then the IR ink is printed independently, the size is small, but the IR holes are not printed, namely, the IR holes are transparent, and the bottom is the color of the conveyor belt;
the date code is taken as a number, for example, the number 220101 to 221230 on the standard product, whether the number on the product to be detected is within the data range of the standard product is detected, if so, the number is identified as good, and if not, the number is identified as bad.
The above positioning lines, the mark marks, the IR holes, and the date codes are all judged to be acceptable, and the product to be measured is identified as being good, and when at least one item is judged to be unacceptable, the product to be measured is identified as being bad.
The sensor module senses the amount of product flowing on the conveyor belt and reports the amount to the analysis module. The number of products sensed by the sensing module is necessarily consistent with the number collected by the analysis module from the detection module. When the analysis module makes identification judgment on products, when the analysis module identifies and judges that 1 piece of products are good, the sensing module senses 1 piece of good products, when the analysis module identifies and judges that 1 piece of products are bad, a piece of products are also produced, the sensing module senses the bad products and just overlaps with the number of the products identified and judged as bad by the analysis module, the analysis module sends out instructions to the control module, the control module sends out instructions to the motor again, the motor slows down, the control module sends out instructions to the manipulator, and the manipulator sucks bad products from the conveyor belt.
According to the automatic identification machine, the image identification and the information identification are carried out on the image of the standard product, then the standard program is set, the batch identification detection is carried out on the products to be detected, the bad products are automatically removed, the outflow probability of the bad products is reduced, the machine replaces people, and the labor input is reduced.
While the preferred embodiment of the present utility model has been described in detail, the present utility model is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present utility model, and the equivalent modifications or substitutions are included in the scope of the present utility model as defined in the appended claims.

Claims (4)

1. An automatic recognition machine, characterized in that: comprises a transmission module, a detection module, an analysis module and a control module,
the transmission module is used for transmitting the standard product and the product to be tested;
the detection module is used for collecting the image information of the standard product and the product to be detected and transmitting the image information to the analysis module for analysis;
the analysis module sets the center position of the product to be detected according to the outline dimensions of the standard product and the product to be detected in the image information, establishes a coordinate system, and identifies the positioning line, the character mark, the IR hole and the date code of the product to be detected;
the control module is connected with the analysis module and is used for eliminating the product identified as bad according to the identification result of the analysis module.
2. An automatic identification appliance as in claim 1 wherein: the system also comprises an induction module, wherein the induction module is connected with the analysis module and is used for counting the products which are identified as good after the products to be detected are identified.
3. An automatic identification equipment as claimed in claim 2 wherein: the device also comprises a manipulator connected with the control module and used for sucking away the product identified as bad according to the instruction of the control module.
4. An automatic identification appliance as claimed in claim 3 wherein: the transmission module comprises a motor and a conveyor belt, and the motor drives the conveyor belt to enable a product to be tested to be transmitted to the sensing module from the starting point of the conveyor belt;
the control module is connected with the motor and is used for reducing the transmission speed of the motor after the product is identified as bad, so that the mechanical arm sucks away the product identified as bad.
CN202320059499.8U 2023-01-06 2023-01-06 Automatic recognition machine Active CN219519638U (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202320059499.8U CN219519638U (en) 2023-01-06 2023-01-06 Automatic recognition machine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202320059499.8U CN219519638U (en) 2023-01-06 2023-01-06 Automatic recognition machine

Publications (1)

Publication Number Publication Date
CN219519638U true CN219519638U (en) 2023-08-15

Family

ID=87631174

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202320059499.8U Active CN219519638U (en) 2023-01-06 2023-01-06 Automatic recognition machine

Country Status (1)

Country Link
CN (1) CN219519638U (en)

Similar Documents

Publication Publication Date Title
CN108465648A (en) A kind of magnetic core Automated Sorting System based on machine vision
TWI585398B (en) Projection-type printed circuit board re-inspection system and methods, and marking the location of the defect
CN201218723Y (en) Optoelectronic non-contact type image detection apparatus
CN111289538B (en) PCB element detection system and detection method based on machine vision
CN106970318A (en) Measuring instrument circuit board intelligent test system and intelligent test method
CN110567976B (en) Mobile phone cover plate silk-screen defect detection device and detection method based on machine vision
CN107672325A (en) It is automatically positioned the Laser Jet method of product
CN204165907U (en) A kind of electronic product LOGO detector
CN110678003A (en) PCB solder mask detection and repair integrated machine and process method
CN101187684B (en) Main board light-emitting diode detection device and method
CN106971390A (en) A kind of detection method for labelling quality
CN107571636A (en) Laser Jet mark detecting system can be positioned
CN206649125U (en) Measuring instrument circuit board intelligent test system
CN108593673A (en) A kind of gold stamping product defects vision testing machine of full-automatic rotating printing
CN109596631A (en) A kind of cigarette packet seal mistake board detection device and method based on machine vision technique
CN219519638U (en) Automatic recognition machine
CN111766255A (en) Flexible circuit board flaw detection method and device
CN115165925A (en) PCB detection device with marking function, marking method, equipment and medium
CN113589772B (en) Intelligent operation regulation and control management system for packaging bag image-text printing production line
CN111060518A (en) Stamping part defect identification method based on instance segmentation
CN105136818B (en) The image detection method of printed base plate
US20220284699A1 (en) System and method of object detection using ai deep learning models
CN208013055U (en) Faulty materials indication device
CN207223202U (en) Laser Jet mark vision-based detection all-in-one machine
TWI755953B (en) Automatic detection system and operation method thereof

Legal Events

Date Code Title Description
GR01 Patent grant
GR01 Patent grant