CN115031633B - On-board detection system of laser scribing machine and detection method thereof - Google Patents

On-board detection system of laser scribing machine and detection method thereof Download PDF

Info

Publication number
CN115031633B
CN115031633B CN202210958831.4A CN202210958831A CN115031633B CN 115031633 B CN115031633 B CN 115031633B CN 202210958831 A CN202210958831 A CN 202210958831A CN 115031633 B CN115031633 B CN 115031633B
Authority
CN
China
Prior art keywords
image
cutting line
front image
unit
line
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210958831.4A
Other languages
Chinese (zh)
Other versions
CN115031633A (en
Inventor
邢鹏展
刘遵明
张男男
梁崑
卜煜
孙君实
王凯
杨蒙
孙铭霞
孙海波
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.)
Changchun Guanghua Micro Electronic Equipment Engineering Center Co ltd
Original Assignee
Changchun Guanghua Micro Electronic Equipment Engineering Center 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 Changchun Guanghua Micro Electronic Equipment Engineering Center Co ltd filed Critical Changchun Guanghua Micro Electronic Equipment Engineering Center Co ltd
Priority to CN202210958831.4A priority Critical patent/CN115031633B/en
Publication of CN115031633A publication Critical patent/CN115031633A/en
Application granted granted Critical
Publication of CN115031633B publication Critical patent/CN115031633B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
    • 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
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • G01B11/028—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring lateral position of a boundary of the object
    • 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
    • G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • 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
    • Y02P40/00—Technologies relating to the processing of minerals
    • Y02P40/50—Glass production, e.g. reusing waste heat during processing or shaping
    • Y02P40/57—Improving the yield, e-g- reduction of reject rates

Abstract

The invention provides an on-board detection system of a laser scribing machine and a detection method thereof, wherein the on-board detection system comprises a motion control module, a three-dimensional objective table, an illumination acquisition module and an identification module, a measurement substrate is adsorbed on the three-dimensional objective table in a vacuum adsorption manner, and the motion control module is used for controlling the three-dimensional objective table to move to a measurement position of the measurement substrate; the illumination acquisition module is used for providing a stable light source and acquiring images of the measurement substrate; the recognition module is used for recognizing the image collected by the illumination collection module through a recognition algorithm. The invention can put the measuring link on the machine to be carried out, and output the detection result, thereby improving the stability of the detection result.

Description

On-board detection system of laser scribing machine and detection method thereof
Technical Field
The invention relates to the technical field of automatic control, in particular to an on-board detection system of a laser scribing machine and a detection method thereof.
Background
The existing laser scribing machine can realize scribing on a substrate with a certain specification as manufacturing equipment, but the position accuracy of laser scribing is different due to the difference of the supplied substrate and the operation parameters. In order to ensure the manufacturing quality of the product, an operator in a manufacturing workshop needs to manually detect on professional equipment to pick out defective products; however, the detection equipment (microscope, double-side detector) is complex to operate, time-consuming, requires certain skill of the operator, causes labor cost, has certain measurement error, and results of manual measurement are not as stable as machine vision.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an on-board detection system of a laser dicing saw and a detection method thereof, which can put a measurement link on the machine for detection and output a detection result, thereby improving the stability of the detection result.
In order to achieve the purpose, the invention adopts the following specific technical scheme:
the invention provides an on-board detection system of a laser scribing machine, which comprises a motion control module, a three-dimensional objective table, an illumination acquisition module and an identification module, wherein a measurement substrate is vacuum-adsorbed on the three-dimensional objective table;
the motion control module is used for controlling the three-dimensional object stage to move to the measuring position of the measuring substrate;
the illumination acquisition module is used for providing stable light source illumination and acquiring images of the measurement substrate;
the identification module is used for identifying the image acquired by the illumination acquisition module through an identification algorithm.
Preferably, the illumination collection module comprises an upward-looking camera unit and an downward-looking camera unit;
the upward camera unit is used for collecting a back image of the measurement substrate and a cutting line of the back image;
the overlook camera unit is used for acquiring a front image of the measurement substrate and a cutting line of the front image.
Preferably, the identification module comprises a front image identification unit, a back image identification unit, a gray scale calculation unit, a binary image detection unit, a discrete point calculation unit and a cutting line calculation unit;
the front image identification unit is used for identifying the front image and determining the position of a cutting line of the front image;
the back image identification unit is used for identifying the back image and determining the position of a cutting line of the back image;
the gray level calculation unit is used for carrying out gray level calculation on the collected front image or back image so as to obtain a gray level mean value, and obtaining a binary image according to the condition that the gray level value of the front image or the back image is greater than the corresponding gray level mean value;
the binary image detection unit is used for extracting the vertical coordinate average value of black points with the gray value of 0 in the binary image to obtain the central point of a cutting line of the front image or the cutting line of the back image formed by discrete points;
the discrete point calculating unit is used for extracting discrete points and calculating a rectangular coordinate equation of the discrete points;
the cutting line calculation unit is used for calculating the line width and the center position of the cutting line of the front image or the back image and the distance between two adjacent cutting lines according to a rectangular coordinate equation.
Preferably, the illumination collection module is illuminated by an annular light source or a surface light source.
Preferably, an identification positioning hole for positioning the measurement substrate and a measurement identification light-transmitting channel for backlighting the measurement substrate are formed on the three-dimensional stage.
The invention provides an on-board detection method of a laser scribing machine, which comprises the following steps:
s1, a motion control module controls a three-dimensional object stage to move to a measurement position of a measurement substrate;
s2, the illumination acquisition module provides a stable light source and acquires images of the measurement substrate;
and S3, the identification module identifies the image acquired by the illumination acquisition module and calculates the identification result through an identification algorithm.
Preferably, the step S2 further includes the following steps:
s21, collecting a back image of the measurement substrate and a cutting line of the back image by the upward camera unit;
and S22, the overlook camera unit collects the front image of the measurement substrate and the cutting line of the front image.
Preferably, step S3 further includes the following steps:
s31, the front image identification unit identifies the front image and determines the position of a cutting line of the front image;
s32, the back image recognition unit recognizes the back image and determines the position of a cutting line of the back image;
s33, carrying out gray level calculation on the collected front image or the collected back image by the gray level calculating unit so as to obtain a gray level mean value, and obtaining a binary image according to the condition that the gray level value of the front image or the back image is greater than the corresponding gray level mean value;
s34, extracting the vertical coordinate average value of black points with the gray value of 0 in the binary image by a binary image detection unit to obtain the central line of the cutting line of the front image or the cutting line of the back image formed by discrete points;
s35, extracting and calculating a rectangular coordinate equation of the discrete points by a discrete point calculating unit;
and S36, the cutting line calculation unit calculates the line width, the center position and the spacing value of the cutting line according to a rectangular coordinate equation.
The invention can obtain the following technical effects:
1. the line width of a cutting line, the distance between scribing positions and the scribing center position can be accurately measured through an independently developed recognition algorithm.
2. The detection of the coincidence degree of the front and back scribing lines of the substrate is completed through the overlook camera and the upward camera.
Drawings
FIG. 1 is a system block diagram of an on-board inspection system of a laser dicing saw provided in accordance with an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an illumination collection module provided in an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a measurement substrate according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of a binarized image provided according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of polar coordinates provided in accordance with an embodiment of the present invention.
Figure 6 is a schematic view of a back cut line provided in accordance with an embodiment of the present invention.
FIG. 7 is a flowchart illustrating an inspection method of an on-board inspection system of a laser dicing saw according to an embodiment of the present invention.
Wherein the reference numerals include: the device comprises a motion control module 1, a three-dimensional object stage 1-1, an identification positioning hole 1-2, a measurement identification light-transmitting hole 1-3, an illumination acquisition module 2, an upward-looking camera unit 2-1, a downward-looking camera unit 2-2, an imaging lens 2-3, an identification module 3, a measurement substrate 4 and a cutting line 5.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, like modules are denoted by like reference numerals. In the case of the same reference numerals, their names and functions are also the same. Therefore, detailed description thereof will not be repeated.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention.
FIG. 1 illustrates a system framework of an on-board inspection system of a laser dicing saw provided in an embodiment of the present invention.
As shown in fig. 1, an on-machine detection system of a laser dicing saw provided in an embodiment of the present invention includes a motion control module 1, a three-dimensional stage 1-1, an illumination collection module 2, and an identification module 3, wherein a measurement substrate 4 is adsorbed on the three-dimensional stage 1-1 by a vacuum adsorption manner, and the motion control module 1 is configured to control the three-dimensional stage 1-1 to move to a measurement position of the measurement substrate 4; the illumination acquisition module 2 is used for providing a stable light source and acquiring an image of the measurement substrate 4; the recognition module 3 is used for recognizing the image collected by the illumination collection module 2 through a recognition algorithm.
The measurement contents include front and back surface detection of the measurement substrate 4: wherein the front detection comprises the width of the cutting lines 5 of the front image, the distance between the cutting lines 5 and the central position of the cutting lines 5 (front and back contact ratio detection); the back detection comprises the center position of the cutting line 5 of the back image, the width of the cutting line 5 and the distance between the cutting lines 5, and the center position of the cutting line 5 of the back image calculated by the identification module 3 and the center position of the cutting line 5 of the front image are calculated, so that the coincidence degree of the front image and the cutting line 5 of the back image is calculated.
Fig. 2 shows a structure of an illumination collection module provided by an embodiment of the present invention.
As shown in fig. 2, the illumination collection module 2 includes an upward-looking camera unit 2-1, an downward-looking camera unit 2-2; the upward camera unit 2-1 and the downward camera unit 2-2 together further comprise an imaging lens 2-3, and the upward camera unit 2-1 is used for acquiring a back image of the measurement substrate 4 and a cutting line 5 of the back image; the overlook camera unit 2-2 is used for collecting a front image of the measurement substrate 4 and a cutting line 5 of the front image; the imaging lens 2-3 is used for imaging on the photosensitive element; the recognition module 3 comprises a front image recognition unit and a back image recognition unit; the front image recognition unit is used for recognizing the front image and determining the position of a cutting line 5 of the front image; the back image recognition unit is used for recognizing the back image and determining the position of the cutting line 5 of the back image. The gray level calculation unit is used for carrying out gray level calculation on the collected front image or the collected back image so as to obtain a gray level average value, and obtaining a binary image when the gray level value is larger than the gray level average value according to whether the gray level value of the front image or the back image is larger than the gray level average value; the binary image detection unit is used for extracting the vertical coordinate average value of black points with the gray value of 0 in the binary image to obtain a central point line of a cutting line 5 consisting of discrete points; the discrete point calculating unit is used for extracting and calculating a rectangular coordinate equation of the discrete points; the cutting line calculation unit is used for calculating the line width, the center position and the spacing value of the cutting line 5 according to a rectangular coordinate equation.
And an annular light source or a surface light source is selected for illumination in the illumination acquisition module 2.
The imaging lens 2-3 selects a telecentric lens with 130 ten thousand pixels, the pixel size is 3.75 μm, and the lens magnification is 4 times, so as to ensure the measurement accuracy of ± 4 μm and simultaneously give consideration to the working conditions of the dicing saw device (visual system field of view 1.2mm × 0.9 mm), the minimum resolution = CCD pixel size/lens magnification, and 3.75/4 ≈ 0.94 μm, that is, the minimum resolution of the image recognition system is about 1 μm.
Fig. 3 shows a structure of a measurement substrate provided in an embodiment of the present invention.
As shown in FIG. 3, an identification positioning hole 1-2 and a measurement identification light-transmitting pore passage 1-3 are formed on a three-dimensional object stage 1-1. And the light-transmitting channels 1-3 are measured and identified and used for collecting the measurement substrate 4 of the specific model 00R 0.
A normal substrate, which can be illuminated by a light source of the downward-looking camera unit 2-2 and can be used for collecting images by the downward-looking camera unit 2-2 when measuring the distance between the cutting lines 5; the 00R0 measuring substrate of a special model needs to be illuminated in a backlight mode through a light source in the upward-looking camera unit 2-1, and an image is collected by the upward-looking camera unit 2-2. In this case, in the area outside the light-transmitting channels, the light-transmitting channels of the light-transmitting channels 1-3 need to be measured and identified by measurement, and the light-transmitting channels need to be illuminated by means of backlight.
FIG. 7 shows a flowchart of a method of an on-board inspection system of a laser dicing saw provided by an embodiment of the present invention.
As shown in fig. 7, the on-board detection method of the laser dicing saw provided by the embodiment of the present invention includes the following steps:
s1, a motion control module 1 controls a three-dimensional object stage 1-1 to move to a measurement position of a measurement substrate 4;
s2, the illumination acquisition module 2 provides a stable light source and acquires an image of the measurement substrate 4;
and S3, after the identification module 3 identifies the image acquired by the illumination acquisition module 2, the identification module 3 calculates the result after the identification algorithm.
The step S2 specifically includes the following steps:
step S21, collecting a back image of the measurement substrate 4 and a cutting line 5 of the back image by the upward camera unit 2-1;
step S22, overlooking the camera unit 2-2 to collect the front image of the measurement substrate 4 and the cutting line 5 of the front image;
the step S3 specifically includes the following steps:
in step S31, the front image recognition unit recognizes the front image and determines the position of the cutting line 5 of the front image.
In step S32, the back surface image recognition unit recognizes the back surface image and determines the position of the cutting line 5 of the back surface image.
And S33, carrying out gray level calculation on the collected front image or the back image by the gray level calculating unit so as to obtain a gray level average value, and obtaining a binary image according to whether the gray level value of the front image or the back image is larger than the gray level average value.
The upward-looking camera unit 2-1 performs gray level calculation on the collected back image to obtain a gray level mean value serving as a binarization threshold value. And when the gray value of the pixel point in the back image is greater than the binarization threshold, setting the gray value to be 1 to obtain the binarization image, otherwise, setting the gray value to be 0, wherein the pixel point with the median value of 0 is a black point.
A plurality of cutting lines 5 are arranged in the back image or the front image, so that search detection is carried out in a partition mode in the Y direction, and when the Y direction is detected within the range of 10-160, the upper first cutting line 5 can be detected; when the Y direction is detected within the range of 160-320, the middle cutting line 5 can be detected; when the Y direction is detected within the range of 330-460, the lower third cutting line 5 can be detected.
Step S34, the binarized image detection unit extracts the mean value of the ordinate of the black point with the gray value of 0 in the binarized image to obtain the central line of the cutting line 5 of the front image or the cutting line 5 of the back image formed by discrete points.
Fig. 4 shows a binarized image provided by an embodiment of the present invention.
And detecting the binary image, and averaging the vertical coordinates of the black points in each row of pixels found in the vertical direction to obtain a central point line of the cutting line 5.
As shown in fig. 4, the discrete black dots in the image are edge pixel points of the cutting line 5. Because the obtained dotted line is a series of discrete points similar to a horizontal line, and the dotted line has 620 discrete points, if the accuracy of the recognition algorithm cannot be ensured by simple straight line fitting, hough (Hough) transformation is adopted to detect the straight line. A straight line in the rectangular coordinate system parameter space corresponds to a point in the image. All the points of the cutting line 5 in the front image or the back image have the same slope and intercept, so that the points correspond to the same point in the rectangular coordinate system parameter space, and after each point on the edge point line of the cutting line 5 is projected to the rectangular coordinate system parameter space, the gathering points in the rectangular coordinate system parameter space correspond to the straight line connected by the central point.
And S35, extracting the discrete points and calculating a rectangular coordinate equation of the discrete points by the discrete point calculating unit.
The discrete point unit applies hough transform and is expressed by polar parameter equation rho = xcos theta + ysin theta. (ρ, θ) represents a straight line in a rectangular coordinate system.
Wherein: rho is the distance from the straight line to the original point, theta is the included angle between the perpendicular line of the straight line and the X axis, and the numeric area is [0 degrees, 180 degrees ].
Fig. 5 shows polar coordinates provided by an embodiment of the present invention.
As shown in fig. 5, in polar coordinate representation, after collinear points in the central point line of the cross are transformed to a parameter space of a polar coordinate system, all the points intersect at one point in the parameter space, and the obtained (ρ, θ) at this time is a polar coordinate parameter of the obtained straight line; under the polar coordinate expression, the point in the image is mapped to the parameter space of the polar coordinate system and is a sine line, and at the moment, a linear coordinate equation formed by the points in the image is converted into the coordinate of the intersection point.
The calculation processing method of the cutting line edge comprises the following steps: establishing a two-dimensional accumulator array (A) y [ρ 1, θ 1 ]，A y [ρ 2 ,θ 2 ]，…A y [ρ i , θ i ]…A y [ρ n , θ n ]）。
The coordinate origin may be any point on the front image or the back image.
ρ 1 、ρ 2 、……ρ i 、……ρ n All values of (1) are [0,460](ii) a Since the ordinate of the horizontal line is calculated, the determination is only made in the effective interval for quick reliability of the determination, so θ i (i =1,2, … …, n) is [85 °,95 ° c] 。
θ i The values can be taken at equal intervals or at unequal intervals. The smaller the interval, the higher the detection accuracy, theta in the present invention i At equal intervals, θ i And theta i-1 Is 0.1 deg. apart.
Proceed initialization A y [ρ i , θ i ]=0; to solve for the sine line in the polar parameter space.
And mapping points on the central point line to a polar coordinate system parameter space to obtain a corresponding sine line. Aiming at any point J on the central point line, the rectangular coordinate (x) is set j ，y j ) Substituting the formula (1) to calculate theta 1 ，θ 2 ，…θ i ，…θ n Respectively corresponding values of p, i.e. p j1 ，ρ j2 ，……，ρ ji ，ρ jn Obtaining a sine line of the central point mapped to the parameter space of the polar coordinate system;
ρ ji =xjcosθ i +yjsinθ i （1）。
figure 6 illustrates a back side cut line provided by an embodiment of the present invention.
As shown in FIG. 6, first, the coordinates (x) of the first discrete center point on the horizontal edge point line are determined 1 ，y 1 ) Substituting formula (1), calculating polar coordinate parameter (rho) corresponding to the first discrete central point 11 ，θ 1 ），（ρ 12 ，θ 2 ）……，（ρ 1i ，θ i ）……（ρ 1n ，θ n ) To obtain a first sine line A 1 (ii) a Then the coordinates (x) of the second discrete center point are calculated 2 ，y 2 ) Substituting formula (1), calculating polar coordinate parameter (rho) corresponding to the second discrete edge point 21 ，θ 1 ），（ρ 22 ，θ 2 ）……，（ρ 2i ，θ i ）……（ρ 2n ，θ n ) To obtain a second sine line A 2 (ii) a By analogy, all points on the edge point line are mapped into the parameter space of the polar coordinate system to obtain the corresponding sine line A 3 、A 4 、A 5 、A 6 、A 7 ...A N , 3<N<620。
As shown in FIG. 5, A 2 And A 1 Intersect at B 1 Point, suppose B 1 The corresponding point has a polar coordinate of (ρ) 21 ,θ 1 ) (or is (ρ) 11 ,θ 1 ），ρ 21 =ρ 11 ) Then the array element Ay [ rho ] 1 ,θ 1 ]Plus 1, due to initialization A y [ρ 1 ,θ 1 ]=0, so at this time A y [ρ 1 ,θ 1 ]=1。A 3 And A 1 、A 2 While crossing at B 1 Point, then A y [ρ 1 ,θ 1 ]Then 1, i.e. Ay [ rho ] 1 ,θ 1 ]=2；A 4 And A 1 、A 2 、A 3 Respectively intersect at B 2 、B 4 、B 6 Point, suppose B 2 、B 4 、B 6 The corresponding polar coordinates are respectively (ρ) 42 ,θ 2 ）、（ρ 43 ,θ 3 ）、（ρ 46 ,θ 6 ) Then A will be y [ρ 2 ,θ 2 ]、A y [ρ 3 ,θ 3 ]、A y [ρ 6 ,θ 6 ]Respectively adding 1. Repeating the steps until the sine line of all the discrete edge point mapping is calculated, and obtaining a voting result of the two-dimensional accumulator array; voting the result hereThe maximum array element is found, the polar coordinate parameter corresponding to the array element is the polar coordinate of the edge line of the cutting line 5, and the number of edge points on the horizontal line contained in the straight line on the corresponding image is the maximum.
As shown in FIG. 5, there are a total of 7 sinusoidal lines at θ i Crossing in the value range, and the crossing points are B 1 、B 2 、B 3 、B 4 、B 5 、B 6 And the corresponding array element A obtained finally y [ρ 1 ,θ 1 ]=2，A y [ρ 2 ,θ 2 ]=1，A y [ρ 3 ,θ 3 ]=1，A y [ρ 4 ,θ 4 ]=1，A y [ρ 5 ,θ 5 ]=1，A y [ρ 6 ,θ 6 ]=4; due to A y [ρ 6 ,θ 6 ]At maximum, so B 6 Polar coordinates of (p) 66 ,θ 6 ) I.e. the polar coordinates of the horizontal line of the edge sought.
And finally, obtaining the rectangular coordinate of the edge line according to the polar coordinate of the edge line.
And S36, the cutting line calculation unit is used for calculating the line width, the center position and the spacing value of the cutting line according to the rectangular coordinate equation. And subtracting the coordinate values of the upper and lower edge lines to obtain the line width pixel value of the cutting line.
The obtained upper and lower edge coordinates are averaged to be the central position of the cutting line, and because the upward-looking camera unit 2-1 and the downward-looking camera unit 2-2 are coaxially arranged, if the coincidence degree of the cutting line of the front image and the cutting line of the back image is required to be detected, namely the central position offset of the cutting line of the front image and the cutting line of the back image is calculated, the central position of the cutting line of the front image is separately measured, then the central position of the cutting line of the back image is measured, and the difference is made between the two, so that the coincidence degree detection of the front image and the back image is obtained.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
The above embodiments of the present invention should not be construed as limiting the scope of the present invention. Any other corresponding changes and modifications made according to the technical idea of the present invention should be included in the protection scope of the claims of the present invention.

Claims (7)

1. An on-board detection system of a laser scribing machine is characterized by comprising a motion control module (1), a three-dimensional objective table (1-1), an illumination acquisition module (2) and an identification module (3), wherein a measurement substrate (4) is adsorbed on the three-dimensional objective table (1-1) in a vacuum manner;
the motion control module (1) is used for controlling the three-dimensional object stage (1-1) to move to the measuring position of the measuring substrate (4);
the illumination acquisition module (2) is used for providing stable light source illumination and carrying out image acquisition on the measurement substrate (4);
the identification module (3) is used for identifying the image acquired by the illumination acquisition module (2) through an identification algorithm;
the illumination acquisition module (2) comprises an upward-looking camera unit (2-1) and an downward-looking camera unit (2-2);
the upward camera unit (2-1) is used for acquiring a back image of the measurement substrate (4) and a cutting line (5) of the back image;
the overlook camera unit (2-2) is used for acquiring a front image of the measurement substrate (4) and a cutting line (5) of the front image;
and respectively measuring the central positions of the cutting line (5) of the back image and the cutting line (5) of the front image through the upward camera unit (2-1) and the downward camera unit (2-2), and then calculating to obtain the coincidence ratio of the back image and the front image.
2. The on-board inspection system of a laser dicing saw according to claim 1, wherein the recognition module (3) includes a front image recognition unit, a back image recognition unit, a gradation calculation unit, a binarized image detection unit, a discrete point calculation unit, and a cut line calculation unit;
the front image recognition unit is used for recognizing the front image and determining the position of a cutting line (5) of the front image;
the back image recognition unit is used for recognizing the back image and determining the position of a cutting line (5) of the back image;
the gray level calculation unit is used for carrying out gray level calculation on the collected front image or the collected back image so as to obtain a gray level mean value, and when the gray level value of the front image or the back image is larger than the corresponding gray level mean value, a binary image is obtained;
the binarization image detection unit is used for extracting the vertical coordinate average value of black points with the gray value of 0 in the binarization image to obtain the central line of the cutting line (5) of the front image or the cutting line (5) of the back image, wherein the central line is composed of discrete points;
the discrete point calculating unit is used for extracting the discrete points and calculating a rectangular coordinate equation of the discrete points;
the cutting line calculation unit is used for calculating the line width and the center position of the cutting line (5) of the front side image or the back side image and the distance between two adjacent cutting lines (5) according to the rectangular coordinate equation.
3. The on-board inspection system of a laser dicing saw according to claim 1, wherein the illumination collection module (2) is selectively illuminated by an annular light source or a surface light source.
4. The on-machine inspection system of the laser dicing machine according to claim 1, wherein an identification positioning hole (1-2) for positioning the measurement substrate (4) and a measurement identification light-transmitting hole (1-3) for backlighting the measurement substrate (4) are formed in the three-dimensional stage (1-1).
5. An on-board inspection method of a laser dicing machine, as implemented using the on-board inspection system of the laser dicing machine of claim 2, comprising the steps of:
s1, the motion control module (1) controls the three-dimensional object stage (1-1) to move to a measurement position of a measurement substrate (4);
s2, the illumination acquisition module (2) provides stable light source illumination and acquires images of the measurement substrate (4);
and S3, the recognition module (3) recognizes the image collected by the illumination collection module (2) and calculates the recognition result through a recognition algorithm.
6. The on-board inspection method of a laser dicing saw of claim 5, wherein the S2 further includes the following steps:
s21, the upward camera unit (2-1) collects the back side image of the measurement substrate (4) and the cutting line (5) of the back side image;
s22, the overhead view camera unit (2-2) collects a front image of the measurement substrate (4) and a cutting line (5) of the front image.
7. The on-board inspection method of a laser dicing saw of claim 5, wherein the S3 further includes the following steps:
s31, the front image recognition unit recognizes the front image and determines the position of a cutting line (5) of the front image;
s32, the back image recognition unit recognizes the back image and determines the position of a cutting line (5) of the back image;
s33, the gray level calculation unit performs gray level calculation on the collected front image or the collected back image to obtain a gray level mean value, and a binary image is obtained according to the condition that the gray level value of the front image or the back image is larger than the corresponding gray level mean value;
s34, the binarized image detection unit extracts the mean value of the vertical coordinates of black points with the gray value of 0 in the binarized image to obtain the central line of the cutting line (5) of the front image or the cutting line (5) of the back image, wherein the central line is composed of discrete points;
s35, the discrete point calculating unit extracts and calculates a rectangular coordinate equation of the discrete points;
and S36, the cutting line calculation unit calculates the line width, the center position and the spacing value of the cutting line (5) according to the rectangular coordinate equation.
CN202210958831.4A 2022-08-11 2022-08-11 On-board detection system of laser scribing machine and detection method thereof Active CN115031633B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210958831.4A CN115031633B (en) 2022-08-11 2022-08-11 On-board detection system of laser scribing machine and detection method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210958831.4A CN115031633B (en) 2022-08-11 2022-08-11 On-board detection system of laser scribing machine and detection method thereof

Publications (2)

Publication Number Publication Date
CN115031633A CN115031633A (en) 2022-09-09
CN115031633B true CN115031633B (en) 2022-11-08

Family

ID=83130808

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210958831.4A Active CN115031633B (en) 2022-08-11 2022-08-11 On-board detection system of laser scribing machine and detection method thereof

Country Status (1)

Country Link
CN (1) CN115031633B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009165528A (en) * 2008-01-11 2009-07-30 Moriso:Kk Board case for game machine
CN101672623A (en) * 2009-10-16 2010-03-17 天津必利优科技发展有限公司 Detection system of overall dimension and surface appearance of thin-type small-size object
CN106097316A (en) * 2016-06-03 2016-11-09 长春光华微电子设备工程中心有限公司 The substrate position identifying processing method of laser scribing means image identification system
CN107219237A (en) * 2016-03-22 2017-09-29 Ckd株式会社 Base board checking device
CN207019633U (en) * 2017-08-14 2018-02-16 南京粤讯电子科技有限公司 Measurement apparatus and projective measuring instrument
CN110694922A (en) * 2019-09-24 2020-01-17 安吉深华视觉科技有限公司 Glass defect on-line measuring equipment
CN114155236A (en) * 2021-12-09 2022-03-08 南京奥特文智能科技有限公司 Laser stripe center line extraction method suitable for dynamic measurement environment

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105066903B (en) * 2015-09-09 2018-06-12 大族激光科技产业集团股份有限公司 A kind of 3-d laser measurement system and its measuring method
CN112798933A (en) * 2021-01-28 2021-05-14 长春光华微电子设备工程中心有限公司 Automatic wafer needle aligning device and method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009165528A (en) * 2008-01-11 2009-07-30 Moriso:Kk Board case for game machine
CN101672623A (en) * 2009-10-16 2010-03-17 天津必利优科技发展有限公司 Detection system of overall dimension and surface appearance of thin-type small-size object
CN107219237A (en) * 2016-03-22 2017-09-29 Ckd株式会社 Base board checking device
CN106097316A (en) * 2016-06-03 2016-11-09 长春光华微电子设备工程中心有限公司 The substrate position identifying processing method of laser scribing means image identification system
CN207019633U (en) * 2017-08-14 2018-02-16 南京粤讯电子科技有限公司 Measurement apparatus and projective measuring instrument
CN110694922A (en) * 2019-09-24 2020-01-17 安吉深华视觉科技有限公司 Glass defect on-line measuring equipment
CN114155236A (en) * 2021-12-09 2022-03-08 南京奥特文智能科技有限公司 Laser stripe center line extraction method suitable for dynamic measurement environment

Also Published As

Publication number Publication date
CN115031633A (en) 2022-09-09

Similar Documents

Publication Publication Date Title
CN112184711B (en) Photovoltaic module defect detection and positioning method and system
CN102095733B (en) Machine vision-based intelligent detection method for surface defect of bottle cap
CN100547351C (en) A kind of machine vision localization method
CN109900711A (en) Workpiece, defect detection method based on machine vision
CN106226157B (en) Concrete structure member crevices automatic detection device and method
WO2012073425A1 (en) Defect inspection method and defect inspection device
CN105021628A (en) Detection method for surface defects of optical fiber image inverter
CN105574845A (en) Cigarette pack lamination layer number measurement method and device by multi-camera array
CN103499303A (en) Wool fineness automatic measuring method
US20170199133A1 (en) Device and method for measuring distortion defects in a manufactured float glass strip
CN110966956A (en) Binocular vision-based three-dimensional detection device and method
CN110208269A (en) The method and system that a kind of glass surface foreign matter and internal foreign matter are distinguished
CN111856436A (en) Combined calibration device and calibration method for multi-line laser radar and infrared camera
CN107515481A (en) The detection method and device of a kind of display panel
CN105181713A (en) Detection device used for optical fiber image inverter surface defects
CN114998308A (en) Defect detection method and system based on photometric stereo
CN115629079A (en) Film surface defect detection system and method
JP2008209354A (en) Calibration method and device, and automatic detection device
CN115031633B (en) On-board detection system of laser scribing machine and detection method thereof
CN105391998B (en) Automatic detection method and apparatus for resolution of low-light night vision device
CN113160145B (en) Detection method, detection device, detection apparatus, and computer-readable storage medium
CN102999904B (en) Plane-based micro-nano object image tilt correction method
CN112837285B (en) Edge detection method and device for panel image
CN109584239A (en) A kind of bloom body surface defect detecting system and method based on reflected light
CN214097211U (en) Transparent plate glass&#39;s defect detecting device

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