CN114723758B - Production quality detection method for full-automatic connection of MiniLED thin plate - Google Patents
Production quality detection method for full-automatic connection of MiniLED thin plate Download PDFInfo
- Publication number
- CN114723758B CN114723758B CN202210649474.3A CN202210649474A CN114723758B CN 114723758 B CN114723758 B CN 114723758B CN 202210649474 A CN202210649474 A CN 202210649474A CN 114723758 B CN114723758 B CN 114723758B
- Authority
- CN
- China
- Prior art keywords
- welding
- image
- miniled
- straight line
- circle
- 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
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 41
- 238000001514 detection method Methods 0.000 title claims abstract description 23
- 238000003466 welding Methods 0.000 claims abstract description 130
- 238000000034 method Methods 0.000 claims abstract description 27
- 239000011324 bead Substances 0.000 claims abstract description 25
- 238000013441 quality evaluation Methods 0.000 claims abstract description 17
- 230000008859 change Effects 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 description 19
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 229910000679 solder Inorganic materials 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000010409 thin film Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000005493 welding type Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the field of image processing, in particular to a production quality detection method for full-automatic connection of a MiniLED sheet, which comprises the steps of collecting an unwelded gray image, a welding wire gray image and a welding spot gray image in real time; obtaining the matching degree of each circle in the unwelded gray level image and the standard circle; determining a corresponding welding area according to the circle center and the radius of each circle and the welding rule; determining a welding line in a corresponding welding area image in the welding line gray level image, and calculating a welding line quality evaluation index; meanwhile, calculating similar indexes of each welding spot image and a standard welding spot template image and obtaining the change degree of the lamp beads; and weighting and summing the matching degree, the welding wire quality evaluation index, the similar index and the change degree to obtain a comprehensive production quality index, and judging whether the MiniLED sheet is qualified. The scheme of the invention can monitor the quality of the process flow of the whole production line, thereby realizing the quality detection of the MiniLED sheet.
Description
Technical Field
The invention relates to the field of image processing, in particular to a production quality detection method for full-automatic connection of MiniLED sheets.
Background
Currently, mini LEDs are one of the important technical trends in the display industry, and have the advantages of thin film, miniaturization, array, high brightness and low cost as a display technology for LED to Micro LEDs transition. The conventional Mini LED production line in China at present is in the technical discussion and research and development stage, a matched detection equipment manufacturer is not moved in a large scale, and the applied Mini LED detection equipment part is imported equipment, so that the manufacturing cost is high, and the detection cost is high.
Therefore, it is particularly important to provide a quality inspection of the MiniLED sheet during the production process.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a production quality detection method for full-automatic connection of MiniLED sheets, and the adopted technical scheme is as follows:
the technical scheme of the production quality detection method for the full-automatic connection of the MiniLED thin plate provided by the invention comprises the following steps of:
acquiring an unwelded gray level image, a welding line gray level image and a welding point gray level image in real time;
performing edge detection on the unwelded gray level image to obtain edge pixel points, and performing Hough circle detection on the edge pixel points to obtain the circle centers and corresponding radiuses of a plurality of circles; calculating the difference between the radius of each circle and the radius of the standard circle, and determining the matching degree of each circle and the standard circle according to the difference; meanwhile, determining a corresponding welding area according to the circle center and the radius of each circle and the welding rule;
the welding areas correspond to the welding line gray level images one by one, the corresponding welding area images in the welding line gray level images are determined, edge pixel points of the welding area images are extracted, hough line detection is carried out on the edge pixel points, and corresponding K lines are obtained; classifying all the straight lines to obtain straight line groups of different categories; calculating the difference between one pixel point and the adjacent pixel point on the straight line; taking the mean value of the differences of all the pixel points as the confidence coefficient of the corresponding straight line, and when the confidence coefficient is greater than a set threshold value, all the straight lines in the corresponding straight line group are bonding lines; calculating a welding wire quality evaluation index according to the number of welding wires in each straight line group and the width of the welding wire area;
extracting welding spot images in the welding spot gray level images, calculating the similarity between each welding spot image and a standard welding spot template image, and obtaining the similarity index of the welding spot gray level images; electrifying the welded MiniLED sheet to obtain the change degree of the lamp beads;
and weighting and summing the matching degree, the welding wire quality evaluation index, the similar index and the change degree to obtain a comprehensive production quality index, and when the comprehensive production quality index is greater than a set threshold value, determining that the MiniLED sheet is qualified.
Further, the surface images of the MiniLED sheet in different processes in the production process are collected in real time, the surface images which are not welded, the surface images of the welding wires and the surface images of the welding points are obtained, and the surface images are subjected to gray processing to obtain corresponding gray images.
Further, the difference obtaining method comprises the following steps: acquiring the length and the angle of each straight line; classifying all the straight lines based on the lengths and the angles to obtain straight line groups of different classes; determining the LBP value of each pixel point according to the number of the pixel points of each straight line in each straight line group and the corresponding gray value; obtaining the hue value of the pixel point of each straight line; and calculating the difference between one pixel point and the adjacent pixel point on the straight line based on the LBP value and the hue value of the pixel point.
Further, the wire bonding quality evaluation index is as follows:
wherein, U represents the width of the welding area,
representing the average distance between all bonding wires, F is the number of bonding wires in the straight line group,
is as followsfStrip bonding wire and the firstf+1 distance between adjacent bonding wires.
Further, the method also comprises the step of correcting the confidence coefficient:
arbitrarily taking a certain line in the category
Adjacent straight lines thereof are
，
；
Obtaining straight lines
On pixel point S respectively reaches adjacent straight lines
、
Of (2) is
，
；
Calculating the difference between the two distances, and determining the confidence level according to the difference between the two distances
Adjusting to obtain a new confidence:
wherein,
is a firstkConfidence of the line.
Further, the degree of change is:
wherein,
is in a position before power-on
The gray value of the lamp bead of (1),
is at a position after being electrified
The gray value of the rear lamp bead is,
is the number of lines of the lamp beads,
the number of the rows of the lamp beads.
The invention has the beneficial effects that:
according to the scheme of the invention, the gray level image of the non-welding part, the gray level image of the welding wire and the gray level image of the welding spot are collected in real time; obtaining the matching degree of each circle in the unwelded gray level image and the standard circle; determining a corresponding welding area according to the circle center and the radius of each circle and the welding rule; determining the welding lines in the corresponding welding area image in the welding line gray level image, and calculating a welding line quality evaluation index; meanwhile, calculating similar indexes of each welding spot image and a standard welding spot template image and obtaining the change degree of the lamp beads; carrying out weighted summation on the matching degree, the welding wire quality evaluation index, the similar index and the change degree to obtain a comprehensive production quality index, and judging whether the MiniLED sheet is qualified or not; the scheme of the invention can monitor the quality of the process flow of the whole production line, thereby realizing the quality detection of the MiniLED sheet.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a method flowchart of the full-automatic online production quality detection method for MiniLED thin plates.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, characteristics and effects thereof according to the present invention will be made with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention aims at the following scenes: detecting the production quality of the MiniLED sheet produced on the factory production line; the brightness, contrast and color gamut of the display and the viewing experience of the user are influenced by the quality of the MiniLED sheet; therefore, the invention collects the thin plate images on each flow in the production process in real time through the image processing technology, thereby completing the detection of the final production quality.
Specifically, the method for detecting the production quality of the MiniLED sheet by full-automatic wire connection provided by the present invention is described with reference to fig. 1, and includes the following steps:
step 1, acquiring an unwelded gray image, a welding line gray image and a welding point gray image in real time.
In the embodiment, the surface image of the MiniLED sheet in the production process is acquired in the form of a fixed light source by a high-resolution camera, the acquired image is often an RGB image, and a weighted graying method is adopted to perform graying processing on the RGB image to obtain a corresponding grayscale image.
It should be noted that the acquired images are images corresponding to various process flows in a full-automatic production line, such as a surface image of a sheet before welding, a welding line image after automatic wiring, and a gray scale image after welding of a welded electronic component.
Step 2, performing edge detection on the unwelded gray image to obtain edge pixel points, and performing Hough circle detection on the edge pixel points to obtain the circle centers and corresponding radiuses of a plurality of circles; calculating the difference between the radius of each circle and the radius of the standard circle, and determining the matching degree of each circle and the standard circle according to the difference; and meanwhile, determining a corresponding welding area according to the circle center and the radius of each circle and the welding rule.
In the embodiment, firstly, extracting edge pixel points of each welding area is to perform canny operator detection on images which are not welded, and detect edge information; secondly, hough circle detection is carried out on the edge pixel points, and N records are assumed to exist for each obtained circle center (A), (B)
，
，
) The sheet meeting the specification should have the center of M welding areas and the coordinate is (
，
) The circle radius is R.
Then, matching the detected N circle centers, wherein the circle centers are matched according to the distance, namely the detected circle center (W) is matched with the circle center (W) with the minimum Euclidean distance to the circle center on the standard template (c)
) And (3) performing correlation, and calculating the similarity C between the detected circle center radius and the correlated circle center radius:
wherein, R is the radius of the standard circle,
for the m-th circle center detected, m =1,2,3, \8230, N.
In this embodiment, a specific method for determining the corresponding welding area is as follows:
and connecting each detected circle center (assumed to be the circle center W at this time) with the circle center adjacent in the horizontal and vertical directions (the projection length in the horizontal or vertical direction with the circle center W is minimum) to obtain a line segment L, selecting a line segment center E point, selecting a point with the length of d/2 from the E point along the W point direction as a point B if the distance between welding areas in production requirements is d, and obtaining a line segment EB. Each circle center can obtain 4 line segments, and the area formed by the 4 line segments is the welding area of the circle center.
It should be noted that, in the above, the position information of each welding area is obtained, and the overall abnormal degree of the welding area in production is detected, and the greater the similarity C is, the better the quality is; thus, positional information of each welding area is obtained.
Step 3, enabling the welding areas to correspond to the welding line gray level images one by one, determining the corresponding welding area images in the welding line gray level images, extracting edge pixel points of the welding area images, and performing Hough line detection on the edge pixel points to obtain K corresponding lines; classifying all the straight lines to obtain straight line groups of different categories; calculating the difference between one pixel point and the adjacent pixel point on the straight line; taking the mean value of the differences of all the pixel points as the confidence coefficient of the corresponding straight line, and when the confidence coefficient is greater than a set threshold value, all the straight lines in the corresponding straight line group are bonding lines; and calculating the quality evaluation index of the welding wires according to the number of the welding wires in each straight line group and the width of the welding wire area.
In this embodiment, the welding area image in the welding line grayscale image corresponds to the welding area obtained in step 2 one to one, and the difference is that the welding area image includes the welding line that has been automatically wired, and the welding area is an area that is not wired.
The method comprises the following steps of analyzing each welding area image, namely detecting the welding area image by using a canny operator again to obtain edge pixel points, detecting Hough straight line of the edge pixel points to detect straight lines in the welding area image, judging whether the detected straight lines are welding lines or not due to the fact that interference straight lines exist inside the welding area image, and the specific process is as follows:
assuming that K straight lines are detected by hough line detection, the length L and angle of each straight line are obtained as y = ax + b
(clockwise from horizontal).
First according to the angle
And calculating the similarity xs between the straight lines and the L, and performing primary clustering.
I in the formula represents the ith straight line, j represents the jth straight line, i =1,2,3 \ 8230, K, j =1,2,3 \ 8230, K, however
. And setting a threshold value T, judging xs, and if xs is greater than the threshold value T, indicating that the ith straight line and the jth straight line belong to the same straight line, otherwise, indicating that the ith straight line and the jth straight line belong to different straight lines.
Calculating confidence of each straight line
：
Firstly, counting the number of pixels on a straight line as Z and the gray value of the pixels;
secondly, calculating the LBP value of each pixel point according to the gray value A of each pixel point;
the LBP value in the above is a value that has been converted into a decimal, and since LBP (local binary pattern) is a well-known technique, the acquisition process is not described in detail.
Then, performing HSV space transformation on the welding line gray image to obtain the hue value H of each pixel point;
and finally, calculating the difference between a certain pixel point and the adjacent pixel point on the straight line so as to represent the confidence coefficient Y of the pixel point as the bonding wire pixel point:
wherein,
for the LBP value of the z-th pixel,
the LBP value of the z +1 th pixel point,
for the LBP value of the z-1 th pixel,
is the tone value of the z-th pixel,
the tone value of the z +1 th pixel point,
the hue value of the Z +1 th pixel point, wherein Z =1,2,3, \ 8230;, Z. Recalculating confidence of linear integral
：
Wherein,
the confidence of the z-th pixel point on the straight line.
Further, in order to ensure that the accuracy is improved, the method further comprises the step of correcting the confidence coefficient of the whole acquired straight line, and the method comprises the following steps:
1) Arbitrarily taking a certain line in the category
Adjacent straight lines thereof are
，
；
2) Obtaining straight lines
The upper pixel point, assumed to be the S point: (
，
) And calculating the distance D:
then can obtain
，
Respectively representing the distance from the point S to two adjacent straight lines;
3) Calculating distance difference, wherein the smaller the difference, the greater the confidence should be, based on which, the relative confidence
And (6) adjusting.
For is to
Performing normalization processing, and setting threshold
Confidence of the line
Is greater than
If so, the straight line can be considered as a bonding line, otherwise, the straight line is not a bonding line.
Based on the bonding wire determined in the above, the specific process of the quality evaluation index of the bonding wire in this embodiment for the bonding wire is as follows:
obtaining the width U of each welding line area image on the thin plate, evaluating the production quality of the welding lines in the welding line area images, and obtaining the number of the same type of welding lines in each straight line group as F, wherein F is less than or equal to K; calculating the distance D between any two adjacent bonding wires, if F bonding wires exist, namely F-1D values exist, then the bonding wire quality evaluation PG of the bonding wire area image is as follows:
in the formula U represents the width of the strip,
representing the average distance of all bond wires. The larger PG, the better the quality of the weld area.
The quality evaluation index of the medium bonding wire is calculated on the premise of judging whether the medium bonding wire is a bonding wire, so that the quality of the bonding wire under the process can be accurately evaluated, and the influence of other factors is avoided.
Step 4, extracting welding spot images in the welding spot gray level images, calculating the similarity between each welding spot image and the standard welding spot template image, and obtaining the similarity index of the welding spot gray level images; and electrifying the welded MiniLED sheet to obtain the change degree of the lamp beads.
The welding spot gray level image in this embodiment is an image after welding is completed, wherein the welding spot gray level image includes a lamp bead and a welding spot.
In this embodiment, detecting the welding spot in the welding spot gray image specifically includes: and (3) carrying out median filtering processing on the welded welding spot gray level image to reduce noise interference, then segmenting the welding spots by an otsu Dajin threshold value method, and processing each welding spot image on the assumption that P welding spots are obtained.
Carrying out template matching on the welding spot image and a standard welding spot template image to calculate similarity V; p welding points obtain P V, and the overall similarity is calculated
：
Wherein,
is as followspThe similarity of individual solder joints. Wherein the greater the similarity, the better the quality of the weld spot and the better the quality of the weld area.
The process of obtaining the change degree of the lamp bead is as follows:
and electrifying the welded thin plate to obtain the gray images of the surface of the thin plate before and after electrifying, differentiating the images, and when the images are differentiated, proving that the LED in the welding area is in normal operation, otherwise, indicating that the quality of the welding area does not meet the standard.
For the area where the lamp beads normally run, before and after the lamp beads are electrified, the image gray level changes greatly due to the fact that the lamp beads are lightened, and the change degree of the image gray level changes greatly as a production quality evaluation index py:
wherein,
is in a position before power-on
The gray value of the lamp bead of (1),
is at a position after being electrified
The gray value of the rear lamp bead,
is the number of lines of the lamp beads,
the number of the rows of the lamp beads.
And 5, carrying out weighted summation on the matching degree, the welding wire quality evaluation index, the similar index and the change degree to obtain a comprehensive production quality index, and when the comprehensive production quality index is greater than a set threshold value, determining that the MiniLED sheet is qualified.
The comprehensive production quality indexes in the embodiment are as follows:
wherein in the formula
，
，
，
Is a weight, wherein
The normalized average similarity of the nth weld area on the board to the standard weld area is characterized,
a normalized quality assessment average of the bond wires within the bond area is characterized,
the normalized quality assessment of the solder joint is characterized,
the normalized quality condition of the welded lamp beads is represented.
In the invention is provided with
，
，
，
=0.1, which can be modified according to specific requirements.
Four indexes are obtained for N welding areas
，
,
，
The four indexes are normalized, and the welding region py =0 which cannot normally operate has been described.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (6)
1. A production quality detection method for full-automatic connection of MiniLED sheets is characterized by comprising the following steps:
acquiring an unwelded gray level image, a welding line gray level image and a welding point gray level image in real time;
performing edge detection on the unwelded gray image to obtain edge pixel points, and performing Hough circle detection on the edge pixel points to obtain the circle centers and corresponding radiuses of a plurality of circles; calculating the difference between the radius of each circle and the radius of the standard circle, and determining the matching degree of each circle and the standard circle according to the difference; meanwhile, determining a corresponding welding area according to the circle center and the radius of each circle and the welding rule;
the welding areas correspond to the welding line gray level images one by one, the corresponding welding area images in the welding line gray level images are determined, edge pixel points of the welding area images are extracted, hough line detection is carried out on the edge pixel points, and corresponding K lines are obtained; classifying all the straight lines to obtain straight line groups of different categories; calculating the difference between one pixel point and the adjacent pixel point on each straight line; taking the mean value of the differences of all the pixel points as the confidence coefficient of the corresponding straight line, and when the confidence coefficient is greater than a set threshold value, all the straight lines in the corresponding straight line group are bonding lines; calculating a welding wire quality evaluation index according to the number of welding wires in each straight line group and the width of the welding wire area;
extracting welding spot images in the welding spot gray level images, calculating the similarity between each welding spot image and the standard welding spot template image, and obtaining the similarity index of the welding spot gray level images; electrifying the welded MiniLED sheet to obtain the change degree of the lamp beads;
respectively carrying out normalization processing on the matching degree, the welding wire quality evaluation index, the similar index and the change degree, carrying out weighted summation on the normalized matching degree, the welding wire quality evaluation index, the similar index and the change degree to obtain a comprehensive production quality index, and when the comprehensive production quality index is greater than a set threshold value, determining that the MiniLED sheet is qualified;
the comprehensive production quality indexes are as follows:
wherein u in the formula 1 ，u 2 ，u 3 ，u 4 Is a weight, C n ' normalized matching degree of nth welding area and standard welding area, PG n ' is a normalized wire quality assessment indicator of the wire bond within the bond area,
and py' is a similar index of the normalized welding spot, and is the normalized change degree of the welded lamp bead.
2. The method for detecting the production quality of the MiniLED sheet in the full-automatic connection mode according to claim 1, wherein the surface images of the MiniLED sheet in different processes in the production process are collected in real time to obtain the surface images which are not welded, the surface images of the welding wires and the surface images of the welding points, and the surface images are subjected to gray processing to obtain corresponding gray images.
3. The method for detecting the production quality of the MiniLED sheet in the full-automatic line connection manner according to claim 1, wherein the difference obtaining method comprises the following steps: acquiring the length and the angle of each straight line; classifying all the straight lines based on the lengths and the angles to obtain straight line groups of different classes; determining the LBP value of each pixel point according to the number of the pixel points of each straight line in each straight line group and the corresponding gray value; obtaining the hue value of the pixel point of each straight line; and calculating the difference between one pixel point and the adjacent pixel point on the straight line based on the LBP value and the hue value of the pixel point.
4. The method for detecting the production quality of the full-automatic MiniLED sheet connection line of claim 1, wherein the wire bonding quality evaluation indexes are as follows:
wherein U represents the width of the welding zone,
representing the average distance between all bonding wires, F being the number of bonding wires in the straight line group, D f The distance between the f-th bonding wire and the f + 1-th adjacent bonding wire.
5. The method for detecting the production quality of the MiniLED thin plate in the full-automatic connection mode according to claim 1, further comprising the step of correcting the confidence coefficient:
arbitrarily take a certain line y in the category k ＝a k x+b k Adjacent straight lines thereof are y k+1 ＝a k+1 x+b k+1 ，
y k-1 ＝a k-1 x+b k-1 ；
Obtaining a straight line y k To adjacent straight lines y respectively k+1 、y k-1 Distance D of k+1 ，D k-1 ；
Calculating the difference between the two distances, and determining the confidence level according to the difference between the two distances
Adjusting to obtain a new confidence:
wherein,
the confidence of the k-th line.
6. The method for detecting the production quality of the MiniLED thin plate full-automatic connection line of claim 1, wherein the variation degree is as follows:
wherein A is 1(i′，j′) Is the gray value A of the lamp bead with the position (i ', j') before electrification 2(i′，j′) The gray value of the lamp bead at the position (i ', j') after the lamp bead is electrified, M 'is the row number of the lamp bead, and N' is the column number of the lamp bead.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210649474.3A CN114723758B (en) | 2022-06-10 | 2022-06-10 | Production quality detection method for full-automatic connection of MiniLED thin plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210649474.3A CN114723758B (en) | 2022-06-10 | 2022-06-10 | Production quality detection method for full-automatic connection of MiniLED thin plate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114723758A CN114723758A (en) | 2022-07-08 |
| CN114723758B true CN114723758B (en) | 2022-11-15 |
Family
ID=82232806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210649474.3A Active CN114723758B (en) | 2022-06-10 | 2022-06-10 | Production quality detection method for full-automatic connection of MiniLED thin plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114723758B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115018833B (en) * | 2022-08-05 | 2022-11-04 | 山东鲁芯之光半导体制造有限公司 | Processing defect detection method of semiconductor device |
| CN115049653B (en) * | 2022-08-15 | 2022-12-06 | 凤芯微电子科技(聊城)有限公司 | Integrated circuit board quality detection system based on computer vision |
| CN115082508B (en) * | 2022-08-18 | 2022-11-22 | 山东省蓝睿科技开发有限公司 | Ocean buoy production quality detection method |
| CN115165899B (en) * | 2022-09-02 | 2022-12-09 | 扬州中科半导体照明有限公司 | LED chip welding quality detection method adopting optical means |
| CN115792473B (en) * | 2023-01-29 | 2023-05-30 | 惠州威尔高电子有限公司 | Quality detection method for MiniLED sheet production process |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2911093A2 (en) * | 2014-02-22 | 2015-08-26 | Xiaomi Inc. | Method and device for detecting straight line |
| WO2021213223A1 (en) * | 2020-04-20 | 2021-10-28 | 广东利元亨智能装备股份有限公司 | Weld quality inspection method, apparatus and system, and electronic device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109064440B (en) * | 2018-06-19 | 2022-02-22 | 广东工业大学 | Loudspeaker voice coil bonding wire identification method based on machine vision |
| CN114423558B (en) * | 2019-10-04 | 2024-03-01 | 日本制铁株式会社 | Welded joint and automobile part |
| CN110930376A (en) * | 2019-11-13 | 2020-03-27 | 上海交通大学 | Method and system for detecting welding spot burrs based on machine vision |
| CN114549530B (en) * | 2022-04-26 | 2022-06-24 | 海门裕隆光电科技有限公司 | PCB welding quality evaluation method based on image processing |
-
2022
- 2022-06-10 CN CN202210649474.3A patent/CN114723758B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2911093A2 (en) * | 2014-02-22 | 2015-08-26 | Xiaomi Inc. | Method and device for detecting straight line |
| WO2021213223A1 (en) * | 2020-04-20 | 2021-10-28 | 广东利元亨智能装备股份有限公司 | Weld quality inspection method, apparatus and system, and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114723758A (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114723758B (en) | Production quality detection method for full-automatic connection of MiniLED thin plate | |
| US9582872B2 (en) | Optical film defect detection method and system thereof | |
| CN107945184B (en) | Surface-mounted component detection method based on color image segmentation and gradient projection positioning | |
| CN113724216B (en) | Method and system for detecting wave crest welding spot defects | |
| CN115049653A (en) | Integrated circuit board quality detection system based on computer vision | |
| CN115082466B (en) | PCB surface welding spot defect detection method and system | |
| JPH11344450A (en) | Instruction data forming method and defect classifying method and apparatus thereof | |
| CN106501272B (en) | Machine vision soldering tin positioning detection system | |
| JP4516253B2 (en) | Defect classification device | |
| CN115184380B (en) | Method for detecting abnormity of welding spots of printed circuit board based on machine vision | |
| JP7393313B2 (en) | Defect classification device, defect classification method and program | |
| CN116523923B (en) | Battery case defect identification method | |
| CN115861307B (en) | Fascia gun power supply driving plate welding fault detection method based on artificial intelligence | |
| TWI822968B (en) | Color filter inspection device, inspection device, color filter inspection method, and inspection method | |
| CN116503316A (en) | Chip defect measurement method and system based on image processing | |
| CN115937517A (en) | Photovoltaic fault automatic detection method based on multispectral fusion | |
| CN115239727A (en) | PCB surface defect detection method | |
| CN115082444A (en) | Copper pipe weld defect detection method and system based on image processing | |
| JP2008281580A (en) | Defect classification system | |
| CN117495852B (en) | Digital printing quality detection method based on image analysis | |
| CN116843615B (en) | Lead frame intelligent total inspection method based on flexible light path | |
| CN116152234B (en) | Template end face defect identification method based on image processing | |
| CN117710873A (en) | Novel turning plate state detection method based on binocular vision | |
| CN114742832B (en) | Welding defect detection method for MiniLED thin plate | |
| JP2840347B2 (en) | Board mounting inspection equipment |
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 |