CN107068589B - Crystal grain selection system and method based on image recognition - Google Patents

Crystal grain selection system and method based on image recognition Download PDF

Info

Publication number
CN107068589B
CN107068589B CN201611197539.6A CN201611197539A CN107068589B CN 107068589 B CN107068589 B CN 107068589B CN 201611197539 A CN201611197539 A CN 201611197539A CN 107068589 B CN107068589 B CN 107068589B
Authority
CN
China
Prior art keywords
blue film
optical lens
image
crystal grains
image recognition
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
CN201611197539.6A
Other languages
Chinese (zh)
Other versions
CN107068589A (en
Inventor
刘水旺
吴文彬
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.)
Xiamen Sanan Integrated Circuit Co Ltd
Original Assignee
Xiamen Sanan Integrated Circuit 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 Xiamen Sanan Integrated Circuit Co Ltd filed Critical Xiamen Sanan Integrated Circuit Co Ltd
Priority to CN201611197539.6A priority Critical patent/CN107068589B/en
Publication of CN107068589A publication Critical patent/CN107068589A/en
Application granted granted Critical
Publication of CN107068589B publication Critical patent/CN107068589B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H01ELECTRIC ELEMENTS
    • H01LSEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
    • H01L21/00Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
    • H01L21/67Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
    • H01L21/67005Apparatus not specifically provided for elsewhere
    • H01L21/67242Apparatus for monitoring, sorting or marking
    • H01L21/67271Sorting devices

Abstract

The invention discloses a crystal grain selecting system and method based on image recognition, wherein the system comprises: the device comprises a worktable, a plurality of crystal grains to be selected, a plurality of crystal grains, a plurality of groups of crystal grains and a plurality of groups of crystal grains, wherein the worktable is provided with a blue film; an image recognition device that creates a pixelet with at least one standard die: decomposing the image of the standard crystal grain into N pixel points, and recording the gray scale standard value of each pixel point; the manipulator is used for selecting out required crystal grains; the image recognition device is connected with an optical lens for acquiring images of all directions of the surface of the blue film, and the optical lens is arranged above the workbench; the image recognition device compares the gray-scale value of each pixel point of the image acquired by the optical lens each time with the corresponding standard crystal grain pixel set one by one, and judges that the object under the current visual field of the optical lens is the required crystal grain when the comparison result is greater than a preset value. The invention has the characteristics of high working efficiency, material mixing avoidance and the like.

Description

Crystal grain selection system and method based on image recognition
Technical Field
The present invention relates to a die sorting system, and more particularly, to a die sorting system based on image recognition.
Background
At present, in order to save cost, some IC factories will cut a plurality of dies with different sizes and types on the same wafer, and the object selected by the existing die selecting equipment must be the dies with the same size and type, and the operation cannot be performed on the dies with different types placed on the same blue film. Therefore, the crystal grains of the same type are mostly selected by adopting a manual selection method at present, and the manual selection method has the defects of low selection efficiency, easy error, easy pollution, easy crystal grain scratching and the like.
Disclosure of Invention
The invention provides a crystal grain selecting system based on image recognition, which is used for overcoming the defects in the background technology.
The technical scheme adopted by the invention for solving the technical problems is as follows: a crystal grain selecting system based on image recognition comprises: the method comprises the following steps:
the device comprises a worktable, a plurality of crystal grains to be selected, a plurality of crystal grains, a plurality of groups of crystal grains and a plurality of groups of crystal grains, wherein the worktable is provided with a blue film;
an image recognition device that creates a pixelet with at least one standard die: decomposing the image of the standard crystal grain into N pixel points, and recording the gray scale standard value of each pixel point;
the manipulator is used for selecting out crystal grains required on the blue film;
the image recognition device is connected with an optical lens for acquiring images of all directions of the surface of the blue film, and the optical lens is arranged above the workbench; the image recognition device compares the gray-scale value of each pixel point of the image acquired by the optical lens each time with the corresponding standard crystal grain pixel set one by one, and when the comparison result is greater than a preset value, the object under the image coordinate is judged to be the required crystal grain.
Further, the optical lens is fixed, the workstation is moving platform, and it is connected with the movement control mechanism, and control workstation moves and predetermines the displacement at every preset time, makes optical lens acquire an image, and the removal order of workstation is: and moving the blue film in sequence along the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, moving the blue film in sequence along the reverse direction of the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, and repeating the steps until the optical lens acquires the images of all directions of the blue film surface.
Furthermore, the workbench is also connected with an angle adjusting mechanism for adjusting the angle of the workbench.
Further, a suction nozzle for sucking up the crystal grains is mounted at the tail of the manipulator, and the manipulator sucks and discharges materials through rotation; the workbench is driven by the movement control mechanism to convey the required crystal grains to a material suction position of the manipulator, a thimble positioned below the blue film is arranged at the material suction position, and the workbench enables the thimble to jack up the required crystal grains by moving along the z-axis direction.
The mechanical arm is used for placing the selected crystal grains on the discharging blue film in order.
Further, the image recognition device comprises a display and an image recognition host connected with the display, and the image recognition host is connected with the optical lens.
Further, the preset value is a positioning score set to a certain value, and the positioning score is a ratio of all coincident pixel points in an image acquired by the optical lens each time to a total pixel point of the image.
Further, the preset displacement is the length of one pixel point or the sum of the lengths of a plurality of pixel points.
A crystal grain selecting method based on image identification is characterized in that a blue film with a plurality of crystal grains to be selected arranged at intervals is placed on a workbench; establishing a pixel set of at least one standard grain: decomposing the image of the standard crystal grain into N pixel points, and recording the gray scale standard value of each pixel point; acquiring images of all directions of the surface of the blue film by using an optical lens, comparing the gray scale value of each pixel point of the image acquired by the optical lens each time with the corresponding standard crystal grain pixel set one by one, and if the comparison result is greater than a preset value, judging that an object under the image coordinate is a required crystal grain; and selecting the required crystal grains by a mechanical arm.
Further, the optical lens is fixed, the workbench moves a preset distance every preset time to enable the optical lens to acquire an image, and the moving sequence of the workbench is as follows: and moving the blue film in sequence along the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, moving the blue film in sequence along the reverse direction of the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, and repeating the steps until the optical lens acquires the images of all directions of the blue film surface.
And further, memorizing coordinates of the images with the results larger than the preset value by comparison, acquiring images of all directions of the surface of the blue film by the optical lens, and selecting crystal grains under the memorized coordinates of all the images by using a manipulator after the comparison of all the images is completed.
Compared with the prior art, the invention has the following beneficial effects:
1. the automatic crystal grain selecting system comprises the workbench, the image recognition device and the mechanical arm, can replace manual work to select the same type of crystal grains one by one from various different types of crystal grains placed on the blue film, greatly improves the working efficiency and the selecting accuracy, reduces the material mixing, and can greatly reduce pollution and scratch to the crystal grains caused by manual work.
2. The workbench is a mobile platform and is connected with the mobile control mechanism, so that the invention completes image scanning on each direction of the blue film surface by the movement of the workbench in cooperation with the optical lens, and can avoid the situation that the optical lens moves to cause image shaking and cannot acquire accurate images.
3. The method of completing the scanning and comparison of each image and selecting the required crystal grains one by one is adopted, so that the working efficiency is greatly improved.
The invention is further explained in detail with the accompanying drawings and the embodiments; however, the die-picking system based on image recognition of the present invention is not limited to the embodiment.
Drawings
FIG. 1 is a schematic diagram of a die pick system according to the present invention;
FIG. 2 is a schematic diagram of the creation of a standard die pixelet according to the present invention;
FIG. 3 is a schematic view of an image scan of the present invention;
FIG. 4 is a schematic diagram of a pick flow of the present invention;
FIG. 5 is a schematic drawing of discharging a blue film on the discharging table of the present invention.
Detailed Description
In an embodiment, referring to fig. 1-4, a die-picking system based on image recognition according to the present invention includes:
a workbench 1, on which a blue film 2 is placed, and a plurality of crystal grains 3 to be selected are arranged on the blue film 2 at intervals;
the image recognition device is established with a pixel set of a plurality of standard crystal grains: decomposing the images of various standard crystal grains into N pixel points, and recording the gray scale standard value of each pixel point, as shown in FIG. 2, wherein the standard Die in the graph represents the standard crystal grains;
the manipulator 7 is used for selecting out the crystal grains required on the workbench 1;
the image recognition device is connected with an optical lens 5 for acquiring images of all directions on the surface of the blue film 2, and the optical lens 5 is arranged above the workbench 1; the image recognition device compares the gray scale value of each pixel point of the image acquired by the optical lens 5 each time with the pixel set of the selected standard crystal grain (i.e. the gray scale standard value of each pixel point corresponding to the image of the standard crystal grain), and when the comparison result is greater than a preset value, determines that the object in the current view of the optical lens 5 is the required crystal grain.
In this embodiment, the optical lens 5 is fixed, the workbench 1 is a mobile platform, and is connected to a mobile control mechanism (not shown in the figure), which controls the workbench 1 to move for a preset displacement every preset time (the preset time may be, for example, 1-2s), so that the optical lens obtains an image. The moving sequence of the workbench is as follows: and moving the blue film 2 to the limit position along the preset direction of the x axis in sequence, moving the preset displacement along the preset direction of the y axis in sequence, moving the blue film 2 to the limit position along the reverse direction of the preset direction of the x axis in sequence, moving the preset displacement along the preset direction of the y axis in sequence, and repeating the steps in a circulating manner until the optical lens 5 finishes the scanning process of the images of all directions on the surface of the blue film 2. The image scanning process of the present invention is illustrated by way of example in fig. 3: the dotted line square in the figure represents the lens visual field, and the length and the width of the lens visual field correspond to the length and the width of the standard crystal grains; the optical lens 5 firstly acquires an image 51 of the upper left corner of the blue film 2, and then the workbench 1 translates along the negative direction of the x axis for preset displacement, so that the optical lens 5 acquires images of the upper and lower directions of the blue film 2, and so on until the optical lens 5 acquires an image of the upper right corner of the blue film 2; then, the workbench 1 translates in the positive direction of the y axis by a preset displacement, so that the optical lens 5 acquires an image 52 of the blue film 2 at the upper and lower directions, and the image 52 and the image acquired last time are different by the distance of the preset displacement in the y axis direction; then, the workbench 1 translates in the positive direction of the x axis for preset displacement, so that the optical lens 5 acquires images of the blue film 2 in the next upper direction and the next lower direction, and so on until the optical lens 5 acquires the image of the blue film 2 in the corresponding left direction; thereafter, the table 1 is translated by a preset displacement in the positive direction of the y-axis. The workbench 1 reciprocates circularly according to the movement mode until the optical lens 5 sequentially acquires images of all directions on the blue film 2. The movement control mechanism comprises an x-axis linear sliding rail module, a y-axis linear sliding rail module, a z-axis linear sliding rail module, a guide screw rod module (y axis, x axis and z axis are respectively provided with a guide screw rod for driving the workbench to move along the x axis, the y axis and the z axis), a motor system and a movement control system host, and the working principle is as follows: the control system host receives the movement signal command, converts the movement signal command into a control command and sends the control command to the motor system, the motor drives the lead screw to move remotely, and the lead screw drives the linear slide rail to move in the x, y or z directions. The xyz-three dimensional coordinates are referenced to the ground. The preset displacement is the length of one pixel point or the sum of the lengths of a plurality of pixel points. The work platform can focus the optical lens by moving in the z direction.
In this embodiment, the worktable 1 is further connected with an angle adjusting mechanism for adjusting the angle of the worktable 1, so that the required die can be searched through the rotation angle in the present invention, which is particularly suitable for the case that the die on the blue film 2 is placed obliquely.
In this embodiment, a suction nozzle 71 for sucking up the die is installed at the tail of the manipulator 7, and the suction nozzle 71 is connected to a vacuum-pumping device. The manipulator 7 realizes material suction and discharge through rotation; after the optical lens 5 acquires images of all directions of the surface of the blue film and comparison work of all the images is completed, the workbench 1 drives the movement along the x-axis direction and the y-axis direction through the movement control mechanism to convey required crystal grains to a material suction position of the manipulator 7, a thimble 11 positioned below the blue film is arranged at the material suction position, and the workbench enables the thimble 11 to jack up the required crystal grains through movement along the z-axis direction. The manipulator 7, the movement control mechanism of the workbench 1 and the image recognition device are controlled by the same control assembly in a unified way, so that the three can act in a coordinated way.
In this embodiment, the device further includes a material placing table 8, a material placing blue film 9 is laid on the material placing table 8, and the manipulator 7 places the selected crystal grains on the material placing blue film 9 in order, as shown in fig. 4. The discharging platform 8 and the working platform 1 are respectively arranged on the system platform 10.
In this embodiment, the image recognition apparatus includes a display 6 and an image recognition host 4 connected to the display 6. The system also comprises an operation panel which is used for starting and stopping the system and selecting which pixel set of standard crystal grains is adopted as a comparison standard of a new round of selection work, namely, after one type of crystal grains are selected, a worker can select the pixel set of another type of standard crystal grains to carry out the next round of selection work, and then selects the other type of crystal grains one by one, and the operation is circulated until all types of crystal grains are selected.
In this embodiment, the preset value is a positioning score set to a certain numerical value (in this embodiment, the numerical value is 90), and the positioning score is a ratio of all coincident pixel points in an image acquired by the optical lens 5 each time to a total pixel point of the image. The preset value can be adjusted according to the complexity of the actual crystal grain.
The work flow of the crystal grain selecting system based on image recognition can be simply illustrated by using fig. 4, namely, a pixel set of standard crystal grains is established → scanning and comparison → the required crystal grains are selected. The selected various types of crystal grains can be placed on the same discharge blue film 9 (as shown in fig. 5) or different discharge blue films. And the image recognition device memorizes the coordinates of the image with the result larger than the preset value in a comparison manner, acquires the images of all directions on the surface of the blue film from the optical lens, and selects the crystal grains under the memorized coordinates of all the images one by using a manipulator matched with a workbench and an ejector pin after the comparison of all the images is completed.
The invention discloses a crystal grain selection method based on image recognition, which comprises the following steps: placing a blue film on a workbench, wherein a plurality of crystal grains to be selected are arranged at intervals; establishing a pixel set of at least one standard grain: decomposing the image of the standard crystal grain into N pixel points, and recording the gray scale standard value of each pixel point; acquiring images of all directions of the surface of the blue film by using an optical lens, comparing the gray scale value of each pixel point of the image acquired by the optical lens each time with the corresponding standard crystal grain pixel set one by one, and if the comparison result is greater than a preset value, judging that an object under the image coordinate is a required crystal grain; and selecting the required crystal grains by a mechanical arm.
In this embodiment, the optical lens is fixed, the workbench moves a preset distance every preset time to enable the optical lens to acquire an image, and the moving sequence of the workbench is as follows: and moving the blue film in sequence along the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, moving the blue film in sequence along the reverse direction of the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, and repeating the steps until the optical lens acquires the images of all directions of the blue film surface.
In this embodiment, the coordinates of the image whose result is greater than the preset value are memorized by comparison, the images of all directions on the surface of the blue film are obtained by the optical lens, and after the comparison of all the images is completed, the crystal grains under the memorized coordinates of all the images are selected by the manipulator.
In this embodiment, a suction nozzle for sucking up the die is installed at the tail of the manipulator, and the suction nozzle is connected to a vacuum pumping device. The manipulator realizes material suction and material discharge through rotation; after the optical lens acquires images of all directions of the surface of the blue film and comparison of all the images is completed, the workbench conveys required crystal grains to a material suction position of a manipulator by moving in the x-axis direction and the y-axis direction, a thimble positioned below the blue film is arranged at the material suction position, and the workbench enables the thimble to jack up the required crystal grains by moving in the z-axis direction so that the suction nozzle can suck the required crystal grains.
In this embodiment, the preset value is a positioning score set to a certain numerical value (in this embodiment, the numerical value is 90), and the positioning score is a ratio of all matched pixel points in an image acquired by the optical lens each time to a total pixel point of the image. The preset value can be adjusted according to the complexity of the actual crystal grain.
Compared with the prior art which adopts a manual selection mode, the crystal grain selection system and the method based on the image recognition have the following advantages: the working efficiency is greatly improved; mixing is reduced, and the selected crystal grains can be integrally placed; the crystal grain pollution and scratch caused by manpower can be greatly reduced; the selected various types of crystal grains can be placed on the same discharge blue film in order or on different discharge blue films.
The above embodiments are only used to further illustrate the die-picking system and method based on image recognition, but the present invention is not limited to the embodiments, and any simple modifications, equivalent changes and modifications made to the above embodiments according to the technical spirit of the present invention fall within the scope of the technical solution of the present invention.

Claims (9)

1. A die selection system based on image recognition is characterized by comprising:
the device comprises a worktable, a plurality of crystal grains to be selected, a plurality of crystal grains, a plurality of groups of crystal grains and a plurality of groups of crystal grains, wherein the worktable is provided with a blue film;
an image recognition device that creates a pixelet with several different types of standard dies: decomposing the image of the standard crystal grain into N pixel points, and recording the gray scale standard value of each pixel point;
the manipulator is used for selecting out crystal grains required on the blue film;
the image recognition device is connected with an optical lens for acquiring images of all directions of the surface of the blue film, and the optical lens is arranged above the workbench; the image recognition device compares the gray-scale value of each pixel point of the image acquired by the optical lens each time with the corresponding standard crystal grain pixel set one by one, and when the comparison result is greater than a preset value, the object under the image coordinate is judged to be the required crystal grain; and the image recognition device memorizes the coordinates of the image with the result larger than the preset value in a comparison manner, acquires the image of each position on the surface of the blue film from the optical lens, and selects the crystal grains under the memorized coordinates of each image by the manipulator after the comparison of each image is completed.
2. The image recognition-based die pick system of claim 1, wherein: the optical lens is fixed, the workstation is moving platform, and it is connected with the movement control mechanism, and the displacement is predetermine in the movement of control workstation interval preset time, makes optical lens acquire an image, and the removal order of workstation is: and moving the blue film in sequence along the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, moving the blue film in sequence along the reverse direction of the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, and repeating the steps until the optical lens acquires the images of all directions of the blue film surface.
3. The image recognition-based die pick system of claim 1, wherein: the workbench is also connected with an angle adjusting mechanism for adjusting the angle of the workbench.
4. The image recognition-based die pick system of claim 2, wherein: a suction nozzle for sucking up the crystal grains is arranged at the tail of the manipulator, and the manipulator realizes material sucking and discharging through rotation; the workbench is driven by the movement control mechanism to convey the required crystal grains to a material suction position of the manipulator, a thimble positioned below the blue film is arranged at the material suction position, and the workbench enables the thimble to jack up the required crystal grains by moving along the z-axis direction.
5. The image recognition-based die pick system of claim 1, wherein: the automatic crystal grain sorting machine is characterized by further comprising a discharging platform, wherein a discharging blue film is laid on the discharging platform, and the mechanical arm is used for placing the selected crystal grains on the discharging blue film in order.
6. The image recognition-based die pick system of claim 1, wherein: the image recognition device comprises a display and an image recognition host connected with the display, and the image recognition host is connected with the optical lens; and/or the preset value is a positioning score set to a certain numerical value, and the positioning score is the ratio of all the consistent pixel points in the image acquired by the optical lens every time to the total pixel points of the image.
7. The image recognition-based die pick system of claim 2, wherein: the preset displacement is the length of one pixel point or the sum of the lengths of a plurality of pixel points.
8. A crystal grain selection method based on image recognition is characterized in that: placing a blue film on a workbench, wherein a plurality of crystal grains to be selected are arranged at intervals; several different types of standard grain pixelets are created: decomposing the image of the standard crystal grain into N pixel points, and recording the gray scale standard value of each pixel point; acquiring images of all directions of the surface of the blue film by using an optical lens, comparing the gray scale value of each pixel point of the image acquired by the optical lens each time with the corresponding standard crystal grain pixel set one by one, and if the comparison result is greater than a preset value, judging that an object under the image coordinate is a required crystal grain; selecting out the required crystal grains by a mechanical arm; and memorizing the coordinates of the images with the results larger than the preset value, acquiring the images of all directions on the surface of the blue film by the optical lens, and selecting the crystal grains under the memorized coordinates of all the images by using the mechanical arm after finishing the comparison work of all the images.
9. The method for selecting crystal grains based on image recognition according to claim 8, wherein: the optical lens is fixed, the workbench moves for a preset distance at preset intervals to enable the optical lens to acquire an image, and the moving sequence of the workbench is as follows: and moving the blue film in sequence along the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, moving the blue film in sequence along the reverse direction of the preset direction of the x axis until the blue film moves to the limit position, moving the preset displacement along the preset direction of the y axis, and repeating the steps until the optical lens acquires the images of all directions of the blue film surface.
CN201611197539.6A 2016-12-22 2016-12-22 Crystal grain selection system and method based on image recognition Active CN107068589B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611197539.6A CN107068589B (en) 2016-12-22 2016-12-22 Crystal grain selection system and method based on image recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611197539.6A CN107068589B (en) 2016-12-22 2016-12-22 Crystal grain selection system and method based on image recognition

Publications (2)

Publication Number Publication Date
CN107068589A CN107068589A (en) 2017-08-18
CN107068589B true CN107068589B (en) 2020-03-20

Family

ID=59618821

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611197539.6A Active CN107068589B (en) 2016-12-22 2016-12-22 Crystal grain selection system and method based on image recognition

Country Status (1)

Country Link
CN (1) CN107068589B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108872028A (en) * 2018-08-27 2018-11-23 武汉古奥基因科技有限公司 A kind of soybean beans Phenotypic examination device and method
CN114042641A (en) * 2021-07-20 2022-02-15 重庆康佳光电技术研究院有限公司 LED crystal grain screening device and method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4030560B2 (en) * 2005-12-14 2008-01-09 三菱電機株式会社 Image processing apparatus and image display apparatus
CN104637833B (en) * 2013-11-12 2017-07-21 旺矽科技股份有限公司 Crystal grain selection method and bad crystal map generation method
CN105424190A (en) * 2015-09-30 2016-03-23 广州超音速自动化科技股份有限公司 Grayscale detection method of product appearance
CN106024666A (en) * 2016-07-14 2016-10-12 无锡宏纳科技有限公司 Method of picking out unqualified dies through camera

Also Published As

Publication number Publication date
CN107068589A (en) 2017-08-18

Similar Documents

Publication Publication Date Title
CN205650478U (en) Switch outward appearance check out test set and system
CN104483106A (en) Online flip LED chip detection device
CN108890144A (en) A kind of laser cutting machine
CN107068589B (en) Crystal grain selection system and method based on image recognition
CN104551865A (en) Image measuring system and method
CN109724987A (en) Automated detection system and detection method based on machine vision
CN105607651A (en) Rapid aligning system and method via visual guiding
CN107655897B (en) Product appearance automatic checkout device
CN218180709U (en) Appearance detection equipment for semiconductor chip
CN211085127U (en) Single polycrystalline silicon rod automatic checkout device
CN107796336B (en) Automatic optical detector
CN111735397A (en) Single polycrystalline silicon rod automatic checkout device
CN117092114B (en) Appearance detection system based on AI
CN110488261A (en) A kind of shelf locating hole checking device and method based on LiDAR
CN210863574U (en) Detection marking equipment for internal flaws of solar crystal column
CN116030449B (en) Automatic sorting method and automatic sorting system for laser cutting pieces
CN108801942B (en) Linear array laser imaging method for rice tillering counting
CN110646436B (en) Detection marking equipment and detection method for defects in solar crystal column
CN210664334U (en) Sealing strip size detection equipment based on visual identification
CN113900270A (en) Precision positioning equipment and automatic optical axis precision positioning method
CN218481432U (en) High-precision detection device for surface defects of optical element
CN111422587A (en) Method for accurately positioning materials in feeding process of conveyor belt
CN110030929A (en) A kind of 3D measuring system and its measurement method based on five axis
JPH02137339A (en) Pellet bonding device
CN113446941B (en) Intelligent production line for motor belt pulley

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant