CN114311572A - SMD LED injection molding support online detection device and detection method thereof - Google Patents
SMD LED injection molding support online detection device and detection method thereof Download PDFInfo
- Publication number
- CN114311572A CN114311572A CN202111656356.7A CN202111656356A CN114311572A CN 114311572 A CN114311572 A CN 114311572A CN 202111656356 A CN202111656356 A CN 202111656356A CN 114311572 A CN114311572 A CN 114311572A
- Authority
- CN
- China
- Prior art keywords
- camera
- led
- injection molding
- coordinate
- bad
- 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.)
- Pending
Links
- 238000001746 injection moulding Methods 0.000 title claims abstract description 74
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 50
- 230000008569 process Effects 0.000 claims abstract description 43
- 230000002950 deficient Effects 0.000 claims abstract description 20
- 238000012423 maintenance Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 238000005520 cutting process Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 7
- 230000010287 polarization Effects 0.000 claims description 6
- 238000002347 injection Methods 0.000 claims description 4
- 239000007924 injection Substances 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 230000001360 synchronised effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000010008 shearing Methods 0.000 description 6
- 230000008439 repair process Effects 0.000 description 5
- 238000005530 etching Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
The invention discloses an SMD LED injection molding support online detection device and a detection method thereof, wherein the online detection device comprises a transmission belt, an injection molding station, a first camera, a maintenance station, a second camera, a laser and a controller, the first camera is used for shooting the LED injection molding support after injection molding is finished during detection, and the controller is used for processing the pictures and searching the coordinate position of a bad LED; if no bad LED exists, the LED injection molding support is continuously transmitted to the next station after passing through the maintenance station; if the LED is defective, the LED injection molding support is conveyed to a maintenance station, a second camera is used for photographing the LED injection molding support and detecting the result of laser operation, and the controller processes the photograph and searches the coordinate position of the defective LED; the laser cuts the bad LED according to the coordinate position of the bad LED; the invention realizes on-line continuous detection, improves the detection speed, can be synchronous with the injection molding beat, and greatly improves the production efficiency.
Description
Technical Field
The invention relates to SMD LED production equipment, in particular to an SMD LED injection molding support online detection device and a detection method thereof.
Background
SMD LEDs are what is meant by surface mount light emitting diodes. The production of the current SMD LED injection molding support product is realized by a production line consisting of a plurality of devices, and the devices cannot be continuously connected to form a complete production line. Generally, an SMD LED injection molded support is formed into a continuous strip-shaped product by an injection molding machine, and the product is first rolled into a semi-finished roll and then punched into individual products by a punching device. And finally, checking by personnel, finding the position of poor injection molding in the bracket product, and repairing the poor position (manually shearing the poor position and then manually repairing an LED bracket colloidal particle at the position of the notch).
The above process has several disadvantages: 1. the time span from injection molding production to inspection and discovery of the bracket is long when the bracket is subjected to poor repair. If continuous bad products occur in the injection molding process, a large number of defective products are generated in the process. 2. The manual detection mode has higher requirement on detection personnel, low detection efficiency and can not avoid the conditions of missing detection and error detection. 3. The manual repair mode can not ensure the shearing precision, and the repair quality can not be ensured.
Therefore, how to design an online detection device and a detection method thereof, which can detect the defective SMD LED on the production line online and repair the defective SMD LED in time, is an urgent technical problem to be solved in the industry.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an SMD LED injection molding support online detection device and a detection method thereof.
The technical scheme adopted by the invention is to design an SMD LED injection molding support online detection device, which comprises a transmission belt, an injection molding station, a first camera, a maintenance station, a second camera, a laser and a controller, wherein the transmission belt is used for transmitting the LED injection molding support; a light source and a first camera are erected on the injection molding station; the first camera shoots the LED injection molding support after injection molding is completed, the controller processes the pictures, and the coordinate position of a bad LED is searched; the second camera is arranged above the maintenance station and used for taking a picture of the LED injection molding support, the controller is used for processing the picture, searching the coordinate position of the poor LED and detecting the result of the laser operation; the laser is arranged above the maintenance station in an erected mode, and the bad LEDs are cut according to the coordinate positions of the bad LEDs.
The two sides of the injection molding station are respectively provided with a polarized light source, the two polarized light sources have the same polarization angle, and a polarizer is added on the first camera to form 90 degrees with the polarization angle of the light source.
The invention also designs a detection method of the SMD LED injection molding support online detection device, wherein the detection device adopts the SMD LED injection molding support online detection device, and the detection method comprises the following steps: the LED injection molding support after injection molding is photographed by a first camera, the controller processes the photograph, and the coordinate position of a bad LED is searched; if no bad LED exists, the LED injection molding support is continuously transmitted to the next station after passing through the maintenance station; if the LED is defective, the LED injection molding support is conveyed to a maintenance station, a second camera is used for photographing the LED injection molding support and detecting the result of laser operation, and the controller processes the photograph and searches the coordinate position of the defective LED; and cutting the bad LED by the laser according to the coordinate position of the bad LED.
The LEDs in the photo are arranged into a matrix with multiple rows and multiple columns, the middle position of each row of LEDs is a process round hole, and the process round holes are correspondingly arranged up and down into a column; the step of searching the coordinate position of the bad LED specifically comprises the following steps:
step 1, carrying out Gaussian blur processing on the picture, and reducing the influence of noise points on identification;
step 3, shifting L = k n to the left and right respectively in each row from a coordinate value Xz as a central point coordinate, wherein L is a shift amount, k is a distance between the centers of two adjacent LEDs, n is a positive integer ranging from 1 to m/2, and m is the number of LEDs in a row to obtain the central point coordinate of each LED;
step 4, corroding the picture, and then performing binarization processing;
step 5, carrying out corrosion treatment and noise reduction treatment on the picture;
step 6, performing non-operation on the picture pixels, then performing vertical expansion, and removing background interference information after threshold binarization to obtain a black strip-shaped graph;
step 7, performing a template matching algorithm by using a template picture prepared in advance, and if the black strip-shaped picture has a vacant part, measuring the central coordinate of the vacant part;
and 8, comparing the central coordinate of the vacant part with the central coordinate of the LED, and if the comparison is successful, obtaining the coordinate positions of the bad LEDs in several rows and columns.
And (3) searching the central point of the process round hole in the middle column of the photo in the step (2), wherein the outline and the central point of the process round hole are searched by Hough transformation.
In the step 2, the coordinate value Xz of the central position of the middle row of the whole picture on the X axis is calculated according to the central point of the process round holes, the central point of each row of the process round holes is calculated in sequence, and then the coordinate value Xz is obtained by averaging the coordinates of the central point of each process round hole on the X axis.
The step 8 of comparing the coordinates of the center of the vacant part with the coordinates of the center of the LED comprises: calculating the linear distance between the central coordinate of the vacant part and the central coordinate of the LED, and comparing the coordinate difference value of the vacant part and the central coordinate of the LED with a comparison threshold value; if the coordinate difference is greater than or equal to the comparison threshold, the comparison is unsuccessful; if the coordinate difference is smaller than the comparison threshold, the comparison is successful.
The technical scheme provided by the invention has the beneficial effects that:
the invention realizes on-line continuous defective product detection and on-line defective product shearing, and effectively solves a plurality of defects in the traditional method; the product is molded by an injection molding machine and is separated from the mold, defective products can be found, and when the defective products continuously appear, an injection molding station gives an alarm and is switched and adjusted by an injection molding technician; the machine vision is used for online detection, so that the detection speed is improved, the detection speed can be synchronous with the injection molding beat, and meanwhile, the detection accuracy is greatly improved; when a product is dragged and discharged from an outlet of the injection molding equipment, the special shearing equipment performs accurate shearing action on the position given by machine vision detection and positioning; the detection speed is improved, the detection can be synchronous with the injection molding beat, and the detection accuracy is greatly improved; the problems of defective products, detection efficiency and accuracy and repair shearing accuracy are solved.
Drawings
The invention is described in detail below with reference to examples and figures, in which:
FIG. 1 is a schematic view of an on-line detection device;
FIG. 2 is an overall workflow diagram;
FIG. 3 is a photograph artwork;
FIG. 4 is a schematic diagram of each LED labeled with center point coordinates;
FIG. 5 is a schematic diagram of the photo after etching and binarization processing;
FIG. 6 is a schematic illustration of a photograph after etching and denoising;
FIG. 7 is a black bar graph obtained after vertical expansion and threshold binarization of a picture;
FIG. 8 is a black and white bar graph obtained by non-operating on a black bar graph;
FIG. 9 is a schematic view of a stencil picture;
fig. 10 is a schematic diagram of the position of a defective LED obtained by comparing a black-and-white bar chart with a template picture.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention discloses an SMD LED injection molding support online detection device, which refers to an online detection device structure schematic diagram shown in figure 1 and comprises a transmission belt, an injection molding station, a first camera, a maintenance station, a second camera, a laser and a controller, wherein the transmission belt is used for transmitting the LED injection molding support; a light source and a first camera are erected on the injection molding station; the first camera shoots the LED injection molding support after injection molding is completed, the shot picture is a product which is just molded in the mold cavity, and the controller processes the picture and searches the coordinate position of a bad LED; the second camera is arranged above the maintenance station and used for taking a picture of the LED injection molding support, the controller is used for processing the picture, searching the coordinate position of the poor LED and detecting the result of the laser operation; the laser is arranged above the maintenance station in an erected mode, and the bad LEDs are cut according to the coordinate positions of the bad LEDs.
The content shot by the camera is a product just molded in the mold cavity, and the lower molding die is used as a shooting background. Referring to the overall work flow diagram shown in fig. 2, the metal braid is first transported; then, an SMD LED is injection-molded on the metal braid; shooting the LED injection molding bracket transferred out of the injection molding machine, and visually detecting the injection molding result; if all the LEDs are good products in the detection result, the LED injection molding support is transmitted to the next station; and if the LED defective products exist in the detection result, cutting the defective LED products by using laser, carrying out visual detection on the cutting result after the cutting is finished, continuing to cut the non-cut products, and conveying the cut products to the next station.
In a preferred embodiment, two sides of the injection molding station are respectively provided with a polarized light source, the two polarized light sources have the same polarization angle, and a polarizer is added on the first camera to form an angle of 90 degrees with the polarization angle of the light sources.
The invention also discloses a detection method of the SMD LED injection molding support online detection device, the detection device adopts the SMD LED injection molding support online detection device, and the detection method comprises the following steps: the LED injection molding support after injection molding is photographed by a first camera, the controller processes the photograph, and the coordinate position of a bad LED is searched; if no bad LED exists, the LED injection molding support is continuously transmitted to the next station after passing through the maintenance station (whether the bad LED exists or not, the product is continuously transmitted to the maintenance station, the bad LED is maintained, and the good LED directly passes through the maintenance station); if the LED is defective, the LED injection molding support is conveyed to a maintenance station, a second camera is used for photographing the LED injection molding support and detecting the result of laser operation, and the controller processes the photograph and searches the coordinate position of the defective LED; and cutting the bad LED by the laser according to the coordinate position of the bad LED.
Referring to the original picture shown in fig. 3, the LEDs (1) in the picture are arranged in a matrix with multiple rows and multiple columns, a process round hole (2) is arranged in the middle of each row of LEDs, and the process round holes are correspondingly arranged in a row up and down; the holes at the edges of the photos are moved by mechanical driving in the conveying belt, so that the accurate positioning of the processing position is ensured.
The step of searching the coordinate position of the bad LED specifically comprises the following steps:
step 1, carrying out Gaussian blur processing on the picture, and reducing the influence of noise points on identification; fingerprints, dust and the like may be left on the LED injection molding support, so that the pictures need to be subjected to Gaussian blur processing, and the influence of noise on identification is reduced.
step 3, shifting L = k n to the left and right respectively in each row from a coordinate value Xz as a central point coordinate, wherein L is a shift amount, k is a distance between the centers of two adjacent LEDs, n is a positive integer ranging from 1 to m/2, and m is the number of LEDs in a row to obtain the central point coordinate of each LED; the technical formula for the offset L is shown visually in fig. 3, where there are 13 LEDs to the left and right of the process round hole, in this case m is 26. A schematic diagram of the LED with the center point marked is shown in fig. 4.
Step 4, corroding the picture, and then performing binarization processing; in this step, etching with correspondingly sized nuclei (Kernel) is required, and in the preferred embodiment, nuclei (Kernel) 3 high and 1 wide are used. The processed graph is shown in fig. 5, and it can be seen that the information in the middle of the dead pixel has been filtered out.
Step 5, carrying out corrosion treatment and noise reduction treatment on the picture; in this step, it is observed that the horizontal thick line characteristics of the head and foot portions of the bad LED and the normal LED are disconnected and not disconnected, respectively, so as to determine whether the LED is good. The broken part is characterized as a defective product. In this step, a Kernel (Kernel) with a height of 2 and a width of 1 can be used for etching and some detail shape transformation (mainly for noise reduction) can be performed, and as can be seen in fig. 6, bad elements are completely filtered out.
Step 6, performing non-operation on the picture pixels, then performing vertical expansion (as shown in fig. 7), and removing background interference information after threshold binarization to obtain a black strip-shaped graph as shown in fig. 8;
step 7, performing a template matching algorithm by using a template picture (shown in figure 9) prepared in advance, and measuring the central coordinates of the vacant part if the black strip-shaped graph has the vacant part;
and 8, comparing the central coordinate of the vacant part with the central coordinate of the LED, and if the comparison is successful, obtaining the coordinate positions of the bad LEDs in several rows and columns. The final result indicia is shown in fig. 10, where the bad LEDs are outlined.
In a preferred embodiment, the center point of the process circular hole in the middle column of the photo searched in step 2 is obtained by searching the contour and the center point of the process circular hole by using Hough transform.
In a preferred embodiment, the step 2 of calculating the coordinate value Xz of the central position of the middle row of the whole picture on the X axis according to the central points of the process round holes calculates the central point of each row of the process round holes in sequence, and then averages the coordinates of the central point of each process round hole on the X axis to obtain the coordinate value Xz.
In a preferred embodiment, the comparing the coordinates of the center of the vacant part with the coordinates of the center of the LED in step 8 includes: calculating the linear distance between the central coordinate of the vacant part and the central coordinate of the LED, and comparing the coordinate difference value of the vacant part and the central coordinate of the LED with a comparison threshold value; if the coordinate difference is greater than or equal to the comparison threshold, the comparison is unsuccessful; if the coordinate difference is smaller than the comparison threshold, the comparison is successful. The alignment threshold may be set to the width pixel of the LED.
The foregoing examples are illustrative only and are not intended to be limiting. Any equivalent modifications or variations without departing from the spirit and scope of the present application should be included in the claims of the present application.
Claims (7)
1. The SMD LED injection molding support on-line detection device is characterized by comprising a transmission belt, an injection molding station, a first camera, a maintenance station, a second camera, a laser and a controller, wherein the controller is used for controlling the transmission belt to rotate, and the SMD LED injection molding support on-line detection device comprises a first camera, a second camera, a third camera, a fourth camera, a fifth camera, a sixth camera, a fourth camera, a fifth camera, a sixth camera, a fifth camera, a sixth camera, a fifth camera, a sixth camera, a fourth camera, a fifth camera, a sixth camera, a fourth camera, a fifth camera, a sixth camera, a fifth camera, a sixth camera, a fourth camera, a sixth camera, a fifth camera, a sixth camera, a fourth camera, a sixth camera, a fifth, a sixth camera, a fifth, a sixth camera, a fourth camera, a sixth, a fifth, a sixth, a
The transmission belt is used for transmitting the LED injection molding bracket;
a light source and a first camera are erected on the injection molding station;
the first camera shoots the LED injection molding support after injection molding is completed, the controller processes the pictures, and the coordinate position of a bad LED is searched;
the second camera is arranged above the maintenance station and used for taking a picture of the LED injection molding support, the controller is used for processing the picture, searching the coordinate position of the poor LED and detecting the result of the laser operation;
the laser is arranged above the maintenance station in an erected mode, and the bad LEDs are cut according to the coordinate positions of the bad LEDs.
2. The on-line detection device for the SMD LED injection molding bracket of claim 1, wherein two polarized light sources are respectively arranged at two sides of the injection molding station, the two polarized light sources have the same polarization angle, and a polarizer is added on the first camera to form an angle of 90 degrees with the polarization angle of the light sources.
3. An inspection method of an SMD LED injection molded holder on-line inspection device, wherein the inspection device employs the SMD LED injection molded holder on-line inspection device of any one of claims 1 to 2, the inspection method comprising: the LED injection molding support after injection molding is photographed by a first camera, the controller processes the photograph, and the coordinate position of a bad LED is searched; if no bad LED exists, the LED injection molding support is continuously transmitted to the next station after passing through the maintenance station; if the LED is defective, the LED injection molding support is conveyed to a maintenance station, a second camera is used for photographing the LED injection molding support and detecting the result of laser operation, and the controller processes the photograph and searches the coordinate position of the defective LED; and cutting the bad LED by the laser according to the coordinate position of the bad LED.
4. The method for detecting the SMD LED injection molding support on-line detection device according to claim 3, wherein the LEDs (1) in the photo are arranged in a matrix with a plurality of rows and a plurality of columns, the middle position of each row of LEDs is a process round hole (2), and the process round holes are correspondingly arranged in a column up and down; the step of searching the coordinate position of the bad LED specifically comprises the following steps:
step 1, carrying out Gaussian blur processing on the picture, and reducing the influence of noise points on identification;
step 2, searching the central point of a process round hole in the middle column of the photo, calculating a coordinate value Xz of the central position of the middle column of the whole photo on an X axis according to the central point of the process round hole, respectively offsetting the coordinates of half diameter of the process round hole to the left and the right on the basis of the coordinate value Xz, cutting out the range of the middle column, and binarizing the gray threshold value of the middle column to obtain a round shape with 0 gray level in the middle column and a white background with 255 gray levels;
step 3, shifting L = k n to the left and right respectively in each row from a coordinate value Xz as a central point coordinate, wherein L is a shift amount, k is a distance between the centers of two adjacent LEDs, n is a positive integer ranging from 1 to m/2, and m is the number of LEDs in a row to obtain the central point coordinate of each LED;
step 4, corroding the picture, and then performing binarization processing;
step 5, carrying out corrosion treatment and noise reduction treatment on the picture;
step 6, performing non-operation on the picture pixels, then performing vertical expansion, and removing background interference information after threshold binarization to obtain a black strip-shaped graph;
step 7, performing a template matching algorithm by using a template picture prepared in advance, and if the black strip-shaped picture has a vacant part, measuring the central coordinate of the vacant part;
and 8, comparing the central coordinate of the vacant part with the central coordinate of the LED, and if the comparison is successful, obtaining the coordinate positions of the bad LEDs in several rows and columns.
5. The method as claimed in claim 4, wherein the step 2 of finding the center point of the process circular hole in the middle row of the photo is to find the contour and the center point of the process circular hole by Hough transform.
6. The method as claimed in claim 5, wherein the step 2 of calculating the coordinate value Xz of the center position of the middle row of the whole picture on the X axis according to the center points of the process round holes comprises calculating the center point of each row of the process round holes in sequence, and then averaging the coordinates of the center point of each process round hole on the X axis to obtain the coordinate value Xz.
7. The method for inspecting an on-line inspection device of an SMD LED injection molded holder of claim 4 wherein the comparing of the center coordinates of the vacant part with the center coordinates of the LED in the step 8 includes: calculating the linear distance between the central coordinate of the vacant part and the central coordinate of the LED, and comparing the coordinate difference value of the vacant part and the central coordinate of the LED with a comparison threshold value; if the coordinate difference is greater than or equal to the comparison threshold, the comparison is unsuccessful; if the coordinate difference is smaller than the comparison threshold, the comparison is successful.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656356.7A CN114311572A (en) | 2021-12-31 | 2021-12-31 | SMD LED injection molding support online detection device and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656356.7A CN114311572A (en) | 2021-12-31 | 2021-12-31 | SMD LED injection molding support online detection device and detection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114311572A true CN114311572A (en) | 2022-04-12 |
Family
ID=81018377
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111656356.7A Pending CN114311572A (en) | 2021-12-31 | 2021-12-31 | SMD LED injection molding support online detection device and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114311572A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116835079A (en) * | 2023-08-31 | 2023-10-03 | 福建鼎珂光电科技有限公司 | Automatic full-inspection packaging equipment and packaging technology for LED support belt |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006170635A (en) * | 2004-12-13 | 2006-06-29 | Hitachi Engineering & Services Co Ltd | Detector of flaw by image processing and flaw detecting method using it |
| CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
| WO2018068600A1 (en) * | 2016-10-10 | 2018-04-19 | 深圳市瀚海基因生物科技有限公司 | Image processing method and system |
| CN208118317U (en) * | 2018-03-20 | 2018-11-20 | 广州市日昇光电科技有限公司 | A kind of LED patch support injection molding grain testing apparatus |
| CN110349125A (en) * | 2019-06-17 | 2019-10-18 | 武汉大学 | A kind of LED chip open defect detection method and system based on machine vision |
| CN110681601A (en) * | 2019-10-31 | 2020-01-14 | 博罗承创精密工业有限公司 | LED support material belt online detection punching system |
| CN111487250A (en) * | 2020-04-02 | 2020-08-04 | 苏州奥创智能科技有限公司 | Intelligent visual detection method and system applied to injection molding defective product detection |
| CN111539927A (en) * | 2020-04-20 | 2020-08-14 | 南通大学 | Detection process and algorithm of automobile plastic assembly fastening buckle lack-assembly detection device |
| WO2020252920A1 (en) * | 2019-06-18 | 2020-12-24 | 平安科技（深圳）有限公司 | Picture correction method and apparatus, computer device and computer-readable storage medium |
-
2021
- 2021-12-31 CN CN202111656356.7A patent/CN114311572A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006170635A (en) * | 2004-12-13 | 2006-06-29 | Hitachi Engineering & Services Co Ltd | Detector of flaw by image processing and flaw detecting method using it |
| CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
| WO2018068600A1 (en) * | 2016-10-10 | 2018-04-19 | 深圳市瀚海基因生物科技有限公司 | Image processing method and system |
| CN208118317U (en) * | 2018-03-20 | 2018-11-20 | 广州市日昇光电科技有限公司 | A kind of LED patch support injection molding grain testing apparatus |
| CN110349125A (en) * | 2019-06-17 | 2019-10-18 | 武汉大学 | A kind of LED chip open defect detection method and system based on machine vision |
| WO2020252920A1 (en) * | 2019-06-18 | 2020-12-24 | 平安科技（深圳）有限公司 | Picture correction method and apparatus, computer device and computer-readable storage medium |
| CN110681601A (en) * | 2019-10-31 | 2020-01-14 | 博罗承创精密工业有限公司 | LED support material belt online detection punching system |
| CN111487250A (en) * | 2020-04-02 | 2020-08-04 | 苏州奥创智能科技有限公司 | Intelligent visual detection method and system applied to injection molding defective product detection |
| CN111539927A (en) * | 2020-04-20 | 2020-08-14 | 南通大学 | Detection process and algorithm of automobile plastic assembly fastening buckle lack-assembly detection device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116835079A (en) * | 2023-08-31 | 2023-10-03 | 福建鼎珂光电科技有限公司 | Automatic full-inspection packaging equipment and packaging technology for LED support belt |
| CN116835079B (en) * | 2023-08-31 | 2023-11-21 | 福建鼎珂光电科技有限公司 | Automatic full-inspection packaging equipment and packaging technology for LED support belt |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109767445B (en) | High-precision PCB defect intelligent detection method | |
| CN104992449B (en) | Information identification and surface defect online test method based on machine vision | |
| CN109839385B (en) | Self-adaptive PCB defect visual positioning detection and classification system | |
| CN108510476B (en) | Mobile phone screen circuit detection method based on machine vision | |
| CN111537517A (en) | Unmanned intelligent stamping defect identification method | |
| CN111768363A (en) | Deep learning-based circuit board surface defect detection method and detection system | |
| CN109709102A (en) | Die-cutting machine lithium battery pole slice physical imperfection detection system, method and device | |
| CN111681222B (en) | Automatic detection and judgment method for edge breakage of cutter mark and dicing saw applied by same | |
| CN109934808B (en) | PCB defect classification method based on image multi-shape normal gradient difference | |
| WO2023109557A1 (en) | Connector inspection method, electronic device and storage medium | |
| CN114311572A (en) | SMD LED injection molding support online detection device and detection method thereof | |
| CN115283835B (en) | Defect marking method and device for PCB | |
| WO2017071406A1 (en) | Method and system for detecting pin of gold needle element | |
| CN115144399B (en) | Assembly quality detection method and device based on machine vision | |
| CN110967851B (en) | Line extraction method and system for array image of liquid crystal panel | |
| CN112200776A (en) | Chip packaging defect detection method and detection device | |
| CN115493843B (en) | Quality monitoring method and equipment based on bearing retainer | |
| CN105023018A (en) | Jet code detection method and system | |
| CN115239626A (en) | Defect detection method, optical detection device, electronic device, and storage medium | |
| CN105404900A (en) | Positioning method of paralleled diodes and device | |
| CN112419274B (en) | Solder paste detection method, system, electronic equipment and medium | |
| CN113706455B (en) | Rapid detection method for damage of 330kV cable porcelain insulator sleeve | |
| CN112634259A (en) | Automatic modeling and positioning method for keyboard keycaps | |
| CN115035118B (en) | PCB production line defect detection method and system based on recognition model | |
| CN113192061A (en) | LED package appearance detection image extraction method and device, electronic equipment and storage medium |
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 |