CN116051563A - Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology - Google Patents

Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology Download PDF

Info

Publication number
CN116051563A
CN116051563A CN202310336570.7A CN202310336570A CN116051563A CN 116051563 A CN116051563 A CN 116051563A CN 202310336570 A CN202310336570 A CN 202310336570A CN 116051563 A CN116051563 A CN 116051563A
Authority
CN
China
Prior art keywords
lamp panel
sealing process
angle
surface sealing
gob
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.)
Granted
Application number
CN202310336570.7A
Other languages
Chinese (zh)
Other versions
CN116051563B (en
Inventor
汪雄杰
程丽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Meiyad Optoelectronics Co ltd
Original Assignee
Shenzhen Meiyad Optoelectronics Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Meiyad Optoelectronics Co ltd filed Critical Shenzhen Meiyad Optoelectronics Co ltd
Priority to CN202310336570.7A priority Critical patent/CN116051563B/en
Publication of CN116051563A publication Critical patent/CN116051563A/en
Application granted granted Critical
Publication of CN116051563B publication Critical patent/CN116051563B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
    • G01B11/306—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces for measuring evenness
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • 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)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Robotics (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention belongs to the field of detection, and discloses a detection device for detecting the surface flatness of a lamp panel of a GOB surface sealing process, which comprises an angle detection module; the angle detection module comprises a shooting unit and an image operation unit; the shooting unit is used for acquiring an angle image of the GOB surface sealing process lamp panel on the conveyor belt; the image operation unit obtains an extracted image based on the angle image, and obtains the position relation between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt based on the variation coefficient statistical value of the extracted image. Because the calculation of the neural network model is not needed, the calculation efficiency is greatly improved under the same hardware condition, so that the efficiency of adjusting the angle relation between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt is improved, and the efficiency of detecting the flatness of the surface of the GOB surface sealing process lamp panel is further improved.

Description

Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology
Technical Field
The invention relates to the field of detection, in particular to a detection device for detecting the surface flatness of a lamp panel of a GOB surface sealing process.
Background
The quality inspection is required before the GOB surface sealing process lamp panel leaves the factory, and the quality inspection is one of the contents of the quality inspection for detecting the surface flatness of the GOB surface sealing process lamp panel. In the prior art, the flatness of the GOB surface sealing process lamp panel is often detected by adopting a line laser mode, namely, the line laser is emitted to different positions of the GOB surface sealing process lamp panel, then the reflected light of the line laser on the GOB surface sealing process lamp panel is shot to obtain a detection image, and then the flatness is measured based on the detection image.
In the prior art, a GOB surface sealing process lamp panel is generally placed on a conveyor belt, the conveyor belt carries the GOB surface sealing process lamp panel to pass through a flatness detection device, and then a detection image of the GOB surface sealing process lamp panel is obtained.
When the long side of the GOB surface sealing process lamp panel on the conveyor belt is not in parallel relation with the advancing direction of the conveyor belt, the distance swept by the line laser on the GOB surface sealing process lamp panel is larger than the width of the GOB surface sealing process lamp panel, and the number of obtained detection images is excessive, so that the detection efficiency is affected.
In order to improve the detection efficiency, the long side of the GOB surface sealing process lamp panel needs to be adjusted to be approximately perpendicular to the advancing direction of the conveyor belt before shooting, in the prior art, an image for position judgment is generally input into a neural network model for operation to obtain the angle relation between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt, however, the image processing mode needs to be participated in by the neural network model, so that the calculation efficiency is relatively low under the same hardware condition, the efficiency of adjusting the angle relation between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt is affected, and the efficiency of detecting the flatness of the surface of the GOB surface sealing process lamp panel is further affected.
Disclosure of Invention
The invention aims to disclose a detection device for detecting the surface flatness of a GOB surface sealing process lamp panel, which solves the problem of how to improve the efficiency of judging the angle relation between the long side of the GOB surface sealing process lamp panel and the advancing direction of a conveyor belt in an image recognition mode under the same hardware condition.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a detection device for detecting the surface flatness of a lamp panel of a GOB surface sealing process comprises an angle detection module;
the angle detection module comprises a shooting unit and an image operation unit;
the shooting unit is used for shooting the GOB surface sealing process lamp panel on the conveyor belt vertically above the conveyor belt and acquiring an angle image of the GOB surface sealing process lamp panel on the conveyor belt;
the image operation unit is used for operating the angle image to obtain the position relationship between the long edge of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt;
calculating the angle image to obtain the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt, wherein the method comprises the following steps:
performing binarization processing on the angle image to obtain a binarized image;
performing image multiplication operation on a preset extraction template image and a binarization image to obtain an extraction image;
respectively acquiring the change coefficient of each column of pixel points with gray values different from 0 in the extracted image;
if the statistical value of the change coefficient is larger than the set statistical value threshold, the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt is approximately vertical;
if the statistical value of the change coefficient is smaller than or equal to the set statistical value threshold value, the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt is not approximately vertical.
Preferably, the resolution of the extracted template image is the same as the resolution of the angle image;
extracting gray values of pixel points in the template image, wherein the gray values comprise 0 and 1;
extracting the gray value of the pixel points of each column of the template image to be the same;
the extraction template image sets a column of pixel points with gray values of 1 every Q columns, and the gray values of the rest columns are 0 except for the columns with gray values of 1.
Preferably, the coefficient of variation is calculated using the following function:
Figure SMS_1
wherein (1)>
Figure SMS_2
A coefficient of variation for the pixel point of the ith column,/>
Figure SMS_3
Representing the total number of pixel points of the ith column,/->
Figure SMS_4
And
Figure SMS_5
the gradation values of the pixel points in the j-th row and the j+1-th row in the i-th column are respectively represented.
Preferably, the calculation method of the statistical value of the change coefficient includes:
screening the change coefficients to obtain an effective set of change coefficients
Figure SMS_6
；
The statistical value of the coefficient of variation is calculated using the following function:
Figure SMS_7
in the function of->
Figure SMS_8
Statistical value representing coefficient of variation,/->
Figure SMS_9
Is->
Figure SMS_10
The number of columns contained in>
Figure SMS_11
For the total number of columns of angle images。
Preferably, the detection device for detecting the surface flatness of the lamp panel of the GOB surface sealing process further comprises an angle adjustment module;
and the angle adjusting module is used for adjusting the position of the GOB surface sealing process lamp panel on the conveyor belt when the position relation is not approximately vertical, and adjusting the long side of the GOB surface sealing process lamp panel to be vertical to the advancing direction of the conveyor belt.
Preferably, the angle adjustment module comprises an adjustment angle calculation unit and an adjustment unit;
the adjusting angle calculating unit is used for calculating a first angle between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt based on the angle image, and acquiring a second angle for angle adjustment based on the first angle;
the adjusting unit is used for carrying out angle adjustment on the GOB surface sealing process lamp panel based on the second angle, so that the long side of the GOB surface sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt.
Preferably, the adjusting unit includes a robot arm body and a robot arm driving device;
the mechanical arm driving device is used for calculating a moving path of the mechanical arm body based on the second angle and controlling the mechanical arm body to move along the moving path, so that the GOB surface glue sealing process lamp panel is pushed to move, and the long side of the GOB surface glue sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt.
Preferably, the detection device for detecting the surface flatness of the lamp panel of the GOB surface sealing process further comprises an accuracy detection module;
the precision detection module is used for emitting line laser from the GOB surface sealing process lamp panel on the conveying belt and obtaining a flatness detection result based on the line laser.
According to the invention, the binarized image is calculated by extracting the template image to obtain the extracted image, and then the position relation between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt is judged based on the statistic value of the change coefficient of the column pixels in the extracted image.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a first detecting device for detecting the surface flatness of a lamp panel in a GOB surface sealing process according to the present invention.
Fig. 2 is a second schematic diagram of a device for detecting the surface flatness of a lamp panel in a GOB surface sealing process according to the present invention.
Fig. 3 is a third schematic diagram of a detecting device for detecting the surface flatness of a lamp panel in a GOB surface sealing process according to the present invention.
Fig. 4 is a schematic diagram of an angle detection module according to the present invention.
Fig. 5 is a schematic diagram of the angle adjusting module of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made more apparent and fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the invention, fall within the scope of protection of the invention.
In the following, the technical solution of the present invention will be clearly and completely described with reference to the accompanying drawings, referring to an embodiment shown in fig. 1, and it is apparent that the described embodiment is only a part of embodiments of the present invention, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the invention, fall within the scope of protection of the invention.
As shown in fig. 1, the invention provides a detection device for detecting the surface flatness of a GOB surface sealing process lamp panel, which comprises an angle detection module 101;
as shown in fig. 4, the angle detection module 101 includes a photographing unit 111 and an image operation unit 112.
The shooting unit 111 is used for vertically shooting the GOB surface sealing process lamp panel on the conveyor belt 401 above the conveyor belt 401, and acquiring an angle image of the GOB surface sealing process lamp panel on the conveyor belt 401.
In the implementation process, whether the GOB surface sealing process lamp panel enters the shooting range or not can be judged by an image difference mode or whether the GOB surface sealing process lamp panel enters the shooting range or not is judged by sensors such as an infrared sensor and the like,
when the GOB surface sealing process lamp panel is detected to enter the shooting range, the shooting unit 111 shoots the GOB surface sealing process lamp panel, and an angle image is obtained.
The image operation unit 112 is configured to operate the angle image to obtain a positional relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt 401.
Preferably, the calculating the angular image to obtain the positional relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt 401 includes:
performing binarization processing on the angle image to obtain a binarized image;
performing image multiplication operation on a preset extraction template image and a binarization image to obtain an extraction image;
respectively acquiring the change coefficient of each column of pixel points with gray values different from 0 in the extracted image;
if the statistical value of the change coefficient is greater than the set statistical value threshold, the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt 401 is approximately vertical;
if the statistical value of the variation coefficient is smaller than or equal to the set statistical value threshold, the positional relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt 401 is not approximately vertical.
In the process of acquiring the position relationship, in order to improve the operation result, the invention does not adopt an image recognition mode to acquire the long side of the GOB surface sealing process lamp panel, because the time consumption is high, and the performance requirement on hardware is high. The invention adopts the template image and the binarization image to multiply to obtain the extraction image, wherein only partial pixel points in the extraction image have gray values, and the gray values of the rest pixel points are all 0; in this way, by calculating the change coefficient of the gray value of each column of pixel points and then obtaining the corresponding statistic value based on the change coefficient, whether the pixel points are approximately vertical or not can be judged according to the statistic value class. In the present invention, approximately vertical means that there may be an angle slightly smaller than 90 degrees, for example 89 degrees, out of all angles formed between the long side of the GOB surface sealing process lamp panel and the foreground direction of the conveyor belt 401. Because of this angular difference, it can be considered that the number of detected images produced is very small compared to the total vertical. This way of properly setting the error range improves the applicability of the present invention.
The arrow in fig. 1-3 indicates the direction of advance of the conveyor belt 401.
In the present invention, the long side is a rectangle, and the long side is a longer side of the rectangle.
In the process of detecting the flatness of the GOB surface sealing process lamp panel, the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt 401 is judged, and then the GOB surface sealing process lamp panel is adjusted based on the judging result, so that the long side of the GOB surface sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt 401, and the quantity of detection images for calculating the flatness can be reduced when the flatness of the single GOB surface sealing process lamp panel is calculated, thereby improving the detection efficiency.
Preferably, the resolution of the extracted template image is the same as the resolution of the angle image;
extracting gray values of pixel points in the template image, wherein the gray values comprise 0 and 1;
extracting the gray value of the pixel points of each column of the template image to be the same;
the extraction template image sets a column of pixel points with gray values of 1 every Q columns, and the gray values of the rest columns are 0 except for the columns with gray values of 1.
Specifically, after the columns with the gray value of 0 are multiplied by the columns in the binarized image, the gray value of the corresponding columns in the obtained extracted image becomes 0, so that the number of pixels required to calculate the change coefficient is reduced, and the calculation speed of the statistical value of the change coefficient is improved.
In practice, Q may be set to 1, where the columns with gray values 1 are periodically distributed with the columns with gray values 0.
Preferably, the coefficient of variation is calculated using the following function:
Figure SMS_12
wherein (1)>
Figure SMS_13
A coefficient of variation for the pixel point of the ith column,/>
Figure SMS_14
Representing the total number of pixel points of the ith column,/->
Figure SMS_15
And
Figure SMS_16
the gradation values of the pixel points in the j-th row and the j+1-th row in the i-th column are respectively represented.
The change coefficient is mainly used for representing the total number of changes of gray values of the pixel points of the row, and when the long side of the GOB surface sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt 401, the total number of rows belonging to the region of the GOB surface sealing process lamp panel in the extracted image is larger; and the proportion of the total number of such columns in the total number of columns of the entire angle image is also relatively large, thereby recognizing whether or not the angle between the long side and the advancing direction of the conveyor belt 401 is approximately the angle at which it is vertical.
Preferably, the calculation method of the statistical value of the change coefficient includes:
screening the change coefficients to obtain an effective set of change coefficients
Figure SMS_17
；
The statistical value of the coefficient of variation is calculated using the following function:
Figure SMS_24
in the function of the method,
Figure SMS_22
statistical value representing coefficient of variation,/->
Figure SMS_27
Is->
Figure SMS_19
The number of columns contained in>
Figure SMS_31
For the total number of columns of the angle image, +.>
Figure SMS_30
The maximum value of the ordinate of all the pixel points in the column h satisfying the judgment condition is:
Figure SMS_33
wherein->
Figure SMS_20
And->
Figure SMS_26
Respectively the +.>
Figure SMS_18
Line and->
Figure SMS_29
Pixel values of pixels of a row, < >>
Figure SMS_23
，/>
Figure SMS_32
Is the number of pixels in column h, < >>
Figure SMS_25
For a preset comparison constant, +.>
Figure SMS_28
、/>
Figure SMS_21
Is the weight.
In the template image, columns with gray values not being 0 may exist in columns not belonging to the GOB surface sealing process lamp panel, so that screening is performed first, and the accuracy of the obtained statistical values is improved. The statistics are on the one hand from
Figure SMS_34
Another aspect is to consider the variance of the ordinate of the pixel points meeting the determination condition, the larger the duty ratio is, the smaller the variance is, the larger the number of columns meeting the requirement is, and the smaller the difference of the maximum values of the coordinate values meeting the determination condition is, namely the larger the probability that the GOB surface sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt 401 is, in the columns meeting the requirement, so as to accurately determine whether the GOB surface sealing process lamp panel is approximately perpendicular to the advancing direction of the conveyor belt 401.
Preferably, the coefficients of variation are filtered to obtain an effective set of coefficients of variation
Figure SMS_35
Comprising:
judging whether the change coefficient is equal to a preset change value
Figure SMS_36
If not, discarding the change coefficient; if yes, save the judgment change coefficient to the set +.>
Figure SMS_37
；
Acquisition of
Figure SMS_38
Of columns corresponding to the change coefficients of the extracted image, +.>
Figure SMS_39
；
For a pair of
Figure SMS_40
The column corresponding to the coefficient of variation in (c) is calculated as follows:
according to a left-to-right manner
Figure SMS_41
The columns corresponding to the coefficients of variation in (a) are numbered and d is denoted by +.>
Figure SMS_42
Is the number of (2);
when the column number is greater than d, then the following screen is performed:
the first step: right screening:
s1, will
Figure SMS_43
The column numbered d in (b) serves as the initial comparative column;
s2, calculating
Figure SMS_44
If the distance is smaller than the set distance threshold, S3 is entered, and if the distance is equal to or greater than the set distance threshold, the change coefficient of the column with the number greater than the current comparison column is determined from the set->
Figure SMS_45
Middle deletion, ending right screening;
s3, will
Figure SMS_46
A column with the middle number 1 larger than the comparison column is used as a new comparison column, and S2 is entered; />
And a second step of: left screening:
s11, will
Figure SMS_47
The column numbered d in (b) serves as the initial comparative column;
s12, calculating
Figure SMS_48
If the distance is smaller than the set distance threshold, the process proceeds to S3, and if the distance is equal to or greater than the set distance threshold, the change coefficient of the column with the number smaller than the current comparison column is determined from the set->
Figure SMS_49
The middle deletion ends the left screening;
s13, will
Figure SMS_50
The column with the middle number 1 larger than the comparison column is used as a new comparison column, and the process proceeds to S12.
During screening, the screening is started from the value of the change coefficient, because the quantity of the change coefficient is generally the same except that the GOB surface sealing process lamp panel is provided with two long sides, and when the two long sides intersect with the row with the pixel value which is not 0 in the extraction template, the formed intersection point is generally two. Then, in order to eliminate columns meeting the requirements in the non-GOB surface sealing process lamp panel area, at this time, the right screening and the left screening are used for screening, and the influence of the columns meeting the requirements in the non-GOB surface sealing process lamp panel area is eliminated through the distance, so that the accuracy of the statistical value of the change coefficient is improved.
In particular, in the course of implementation,
Figure SMS_51
the value of (2) may be 4.
In one embodiment, as shown in fig. 2, the detecting device for detecting the flatness of the surface of the lamp panel of the GOB surface sealing process further includes an angle adjusting module 201;
the angle adjustment module 201 is configured to adjust the position of the GOB surface sealing process lamp panel on the conveyor 401 to be perpendicular to the advancing direction of the conveyor 401 when the positional relationship is not approximately perpendicular.
Preferably, as shown in fig. 5, the angle adjustment module 201 includes an adjustment angle calculation unit 211 and an adjustment unit 212;
the adjustment angle calculating unit 211 is configured to calculate a first angle between a long side of the GOB surface sealing process lamp panel and a forward direction of the conveyor belt 401 based on the angle image, and obtain a second angle for performing angle adjustment based on the first angle;
the adjusting unit 212 is configured to perform angle adjustment on the GOB surface sealing process lamp panel based on the second angle, so that a long side of the GOB surface sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt 401.
Preferably, calculating the first angle between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt 401 based on the angle image includes:
performing image recognition on the angle image to obtain the long side of the GOB surface glue sealing process lamp panel;
acquiring a first linear expression of the long side of the GOB surface glue sealing process lamp panel in an angle image;
acquiring a second linear expression of the advancing direction of the conveyor belt 401 in the angle image;
the first angle is obtained from the first linear expression and the second linear expression.
Wherein the first angle is an acute angle.
Specifically, the angle formed when two straight lines intersect can be obtained from the slope of the straight line.
Preferably, obtaining the second angle for performing the angle adjustment based on the first angle includes:
the second angle is obtained using the following function:
Figure SMS_52
wherein (1)>
Figure SMS_53
A second angle is indicated and is indicated as such,
Figure SMS_54
representing a first angle.
Preferably, the adjustment unit 212 includes a robot body and a robot driving device;
the mechanical arm driving device is used for calculating a moving path of the mechanical arm body based on the second angle and controlling the mechanical arm body to move along the moving path, so that the GOB surface sealing process lamp panel is pushed to move, and the long side of the GOB surface sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt 401.
In one embodiment, as shown in fig. 3, the detecting device for detecting the flatness of the surface of the lamp panel in the GOB surface sealing process further includes a precision detecting module 301;
the precision detection module 301 is configured to emit line laser to a GOB surface sealing process lamp panel on the conveyor 401, and obtain a flatness detection result based on the line laser.
Preferably, the precision detection module 301 includes a line laser emitting unit, a camera unit, and an arithmetic unit;
the line laser emission unit is used for emitting line laser to the GOB surface glue sealing process lamp panel;
the camera unit is used for shooting the GOB surface sealing process lamp panel to obtain a detection image containing line laser;
the operation unit is used for carrying out operation on all detection images corresponding to the GOB surface sealing process lamp panel to obtain a flatness detection result.
Specifically, by driving the conveyor belt 401, the line laser can continuously sweep different positions of the GOB surface sealing process lamp panel, so as to obtain a plurality of detection images. When no lamp panel passes, the straight line projected by the line laser on the conveyor belt is perpendicular to the advancing direction of the conveyor belt.
Preferably, the line laser has the same width in the detection image as the single pixel point in the detection image.
Preferably, the calculating of all the detection images corresponding to the GOB surface sealing process lamp panel is performed to obtain a flatness detection result, including:
the following calculation is performed for each detected image:
acquiring a set of pixel points belonging to line laser in a detection image
Figure SMS_55
；
Judging
Figure SMS_56
If not, setting the flatness parameter of the detected image to be 0, and if so, setting the flatness parameter of the detected image to be 1;
flatness was calculated using the following formula:
Figure SMS_57
wherein (1)>
Figure SMS_58
Represents flatness +.>
Figure SMS_59
Indicating the total number of all detection images corresponding to the GOB surface sealing process lamp panel, and the +.>
Figure SMS_60
Indicating the set of all detection images corresponding to the GOB surface sealing technology lamp panel, and the +.>
Figure SMS_61
For detecting the flatness parameter of the image u.
Specifically, if the GOB surface sealing process lamp panel is uneven, in the detection image formed by reflecting the laser on the GOB surface sealing process lamp panel, the pixel points of the laser are not on a straight line, so that after all the detection images are judged, the flatness is obtained through the function calculation, and the higher the flatness is, the more the GOB surface sealing process lamp panel is flat.
In one embodiment, the GOB surface sealing process lamp panel is placed on the conveyor 401 with the front side facing horizontally upwards, and then passes through the angle detection module 101, the angle adjustment module 201, and the accuracy detection module 301 sequentially on the conveyor 401.
The above embodiments are merely illustrative of the preferred embodiments of the present invention, and not intended to limit the scope of the present invention, and various modifications and improvements made by those skilled in the art to the technical solution of the present invention should fall within the protection scope of the present invention without departing from the design spirit of the present invention.

Claims (8)

1. The detection device for detecting the surface flatness of the lamp panel of the GOB surface sealing process is characterized by comprising an angle detection module;
the angle detection module comprises a shooting unit and an image operation unit;
the shooting unit is used for shooting the GOB surface sealing process lamp panel on the conveyor belt vertically above the conveyor belt and acquiring an angle image of the GOB surface sealing process lamp panel on the conveyor belt;
the image operation unit is used for operating the angle image to obtain the position relationship between the long edge of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt;
calculating the angle image to obtain the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt, wherein the method comprises the following steps:
performing binarization processing on the angle image to obtain a binarized image;
performing image multiplication operation on a preset extraction template image and a binarization image to obtain an extraction image;
respectively acquiring the change coefficient of each column of pixel points with gray values different from 0 in the extracted image;
if the statistical value of the change coefficient is larger than the set statistical value threshold, the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt is approximately vertical;
if the statistical value of the change coefficient is smaller than or equal to the set statistical value threshold value, the position relationship between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt is not approximately vertical.
2. The detection device for detecting the surface flatness of a GOB surface sealing process lamp panel according to claim 1, wherein the resolution of the extracted template image is the same as the resolution of the angle image;
extracting gray values of pixel points in the template image, wherein the gray values comprise 0 and 1;
extracting the gray value of the pixel points of each column of the template image to be the same;
the extraction template image sets a column of pixel points with gray values of 1 every Q columns, and the gray values of the rest columns are 0 except for the columns with gray values of 1.
3. The detection device for detecting the surface flatness of a GOB surface sealing process lamp panel according to claim 2, wherein the change coefficient is calculated by adopting the following function:
Figure QLYQS_1
wherein (1)>
Figure QLYQS_2
A coefficient of variation for the pixel point of the ith column,/>
Figure QLYQS_3
Representing the total number of pixel points of the ith column,/->
Figure QLYQS_4
And->
Figure QLYQS_5
The gradation values of the pixel points in the j-th row and the j+1-th row in the i-th column are respectively represented.
4. A device for detecting the surface flatness of a GOB surface sealing process lamp panel according to claim 3, wherein the calculation mode of the statistical value of the variation coefficient includes:
to change the coefficientScreening to obtain effective change coefficient set
Figure QLYQS_6
；
The statistical value of the coefficient of variation is calculated using the following function:
Figure QLYQS_7
in the function of->
Figure QLYQS_8
Statistical value representing coefficient of variation,/->
Figure QLYQS_9
Is->
Figure QLYQS_10
The number of columns contained in>
Figure QLYQS_11
Is the total number of columns of the angle image.
5. The detection device for detecting the surface flatness of the lamp panel of the GOB surface sealing process according to claim 1, further comprising an angle adjusting module;
and the angle adjusting module is used for adjusting the position of the GOB surface sealing process lamp panel on the conveyor belt when the position relation is not approximately vertical, and adjusting the long side of the GOB surface sealing process lamp panel to be vertical to the advancing direction of the conveyor belt.
6. The detection device for detecting the surface flatness of the lamp panel of the GOB surface sealing process according to claim 5, wherein the angle adjusting module comprises an adjusting angle calculating unit and an adjusting unit;
the adjusting angle calculating unit is used for calculating a first angle between the long side of the GOB surface sealing process lamp panel and the advancing direction of the conveyor belt based on the angle image, and acquiring a second angle for angle adjustment based on the first angle;
the adjusting unit is used for carrying out angle adjustment on the GOB surface sealing process lamp panel based on the second angle, so that the long side of the GOB surface sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt.
7. The detecting device for detecting the surface flatness of a GOB surface sealing process lamp panel as claimed in claim 6, wherein,
the adjusting unit comprises a mechanical arm body and a mechanical arm driving device;
the mechanical arm driving device is used for calculating a moving path of the mechanical arm body based on the second angle and controlling the mechanical arm body to move along the moving path, so that the GOB surface glue sealing process lamp panel is pushed to move, and the long side of the GOB surface glue sealing process lamp panel is perpendicular to the advancing direction of the conveyor belt.
8. The detection device for detecting the surface flatness of the lamp panel of the GOB surface sealing process of claim 5, further comprising an accuracy detection module;
the precision detection module is used for emitting line laser from the GOB surface sealing process lamp panel on the conveying belt and obtaining a flatness detection result based on the line laser.
CN202310336570.7A 2023-03-31 2023-03-31 Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology Active CN116051563B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310336570.7A CN116051563B (en) 2023-03-31 2023-03-31 Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310336570.7A CN116051563B (en) 2023-03-31 2023-03-31 Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology

Publications (2)

Publication Number Publication Date
CN116051563A true CN116051563A (en) 2023-05-02
CN116051563B CN116051563B (en) 2023-06-16

Family

ID=86122160

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310336570.7A Active CN116051563B (en) 2023-03-31 2023-03-31 Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology

Country Status (1)

Country Link
CN (1) CN116051563B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117015121A (en) * 2023-10-07 2023-11-07 南通医疗器械有限公司 Fault alarm management method and system for shadowless lamp

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010117322A (en) * 2008-11-14 2010-05-27 Nippon Steel Corp Surface flaw inspection device, method and program for surface flaw inspection
CN107945152A (en) * 2017-10-27 2018-04-20 深圳市创科自动化控制技术有限公司 The defects of industrial camera detecting and controlling system and method
CN112819772A (en) * 2021-01-28 2021-05-18 南京挥戈智能科技有限公司 High-precision rapid pattern detection and identification method
CN112859189A (en) * 2020-12-31 2021-05-28 广东美的白色家电技术创新中心有限公司 Workpiece detection device, detection method, and computer-readable storage medium
CN113487606A (en) * 2021-09-06 2021-10-08 常州奥智高分子新材料有限公司 Image detection system and method, and television backlight diffusion plate detection system and method
CN113532332A (en) * 2021-06-08 2021-10-22 宁波帅特龙集团有限公司 Method and device for detecting workpiece installation angle
CN115311270A (en) * 2022-10-11 2022-11-08 南通至顺聚氨酯材料有限公司 Plastic product surface defect detection method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010117322A (en) * 2008-11-14 2010-05-27 Nippon Steel Corp Surface flaw inspection device, method and program for surface flaw inspection
CN107945152A (en) * 2017-10-27 2018-04-20 深圳市创科自动化控制技术有限公司 The defects of industrial camera detecting and controlling system and method
CN112859189A (en) * 2020-12-31 2021-05-28 广东美的白色家电技术创新中心有限公司 Workpiece detection device, detection method, and computer-readable storage medium
CN112819772A (en) * 2021-01-28 2021-05-18 南京挥戈智能科技有限公司 High-precision rapid pattern detection and identification method
CN113532332A (en) * 2021-06-08 2021-10-22 宁波帅特龙集团有限公司 Method and device for detecting workpiece installation angle
CN113487606A (en) * 2021-09-06 2021-10-08 常州奥智高分子新材料有限公司 Image detection system and method, and television backlight diffusion plate detection system and method
CN115311270A (en) * 2022-10-11 2022-11-08 南通至顺聚氨酯材料有限公司 Plastic product surface defect detection method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YAN LIU等: "Edge Detection for Conveyor Belt Based on the Deep Convolutional Network", 《PROCEEDINGS OF 2018 CHINESE INTELLIGENT SYSTEMS CONFERENCE》, pages 275 *
许维维: "H公司物流包装纸箱外观智能检测系统设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 11, pages 138 - 146 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117015121A (en) * 2023-10-07 2023-11-07 南通医疗器械有限公司 Fault alarm management method and system for shadowless lamp
CN117015121B (en) * 2023-10-07 2023-12-15 南通医疗器械有限公司 Fault alarm management method and system for shadowless lamp

Also Published As

Publication number Publication date
CN116051563B (en) 2023-06-16

Similar Documents

Publication Publication Date Title
CN109871938B (en) Component code spraying detection method based on convolutional neural network
US11227405B2 (en) Determining positions and orientations of objects
CN116051563B (en) Detection device for detecting surface flatness of lamp panel of GOB surface sealing technology
WO2017032308A1 (en) Pcb board detection method and apparatus
CN108896550B (en) Facial mask printing quality detection method and system
CN112084964A (en) Product identification apparatus, method and storage medium
CN109978908B (en) Single-target rapid tracking and positioning method suitable for large-scale deformation
CN108257188A (en) A kind of moving target detecting method
CN113095445B (en) Target identification method and device
CN105988596A (en) Optical navigation device and related automatic magnification adjusting method
CN113298787A (en) Plate edge sealing defect detection method, controller and computer readable storage medium
CN110516725A (en) The detection method of plank fringe spacing and color based on machine vision
CN116739986A (en) Optical acoustic combination method for detecting typical defects of AUV in water conveyance tunnel
JP2003185419A (en) Method and apparatus for measuring warpage shape
CN116433584A (en) Surface defect detection method, system and storage medium for strip-shaped polishing template
CN113793293B (en) Contour detection method, apparatus, system and computer readable storage medium
TWI533950B (en) Method for checking a terminal of a metal plate and a rolling method using the same
KR20230009360A (en) Systems and methods for 3D scanning of moving objects that are longer than the field of view
CN103873786A (en) Image adjustment method and optical navigator using same
CN113192061A (en) LED package appearance detection image extraction method and device, electronic equipment and storage medium
CN110823134B (en) Target line calculation and industrial sensor installation detection method
JP2021063780A (en) Object detection system and program for objection detection system
CN117078666B (en) Two-dimensional and three-dimensional combined defect detection method, device, medium and equipment
CN113448082B (en) Lens defogging method, device and system
CN115356355B (en) Automatic detection blanking conveying line and detection method for vacuum laminated glass

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