CN106097316A - The substrate position identifying processing method of laser scribing means image identification system - Google Patents

The substrate position identifying processing method of laser scribing means image identification system Download PDF

Info

Publication number
CN106097316A
CN106097316A CN201610388780.0A CN201610388780A CN106097316A CN 106097316 A CN106097316 A CN 106097316A CN 201610388780 A CN201610388780 A CN 201610388780A CN 106097316 A CN106097316 A CN 106097316A
Authority
CN
China
Prior art keywords
line
point
image
spider
pixel
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
CN201610388780.0A
Other languages
Chinese (zh)
Other versions
CN106097316B (en
Inventor
邢鹏展
王忠生
钱雨松
刘遵明
吴梦晗
郑福志
徐丽萍
梁崑
王星
郭尧
杨蒙
赵锋锋
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.)
Guangjingtuo intelligent equipment (Suzhou) Co.,Ltd.
Original Assignee
CHANGCHUN GUANGHUA MICRO-ELECTRONICS EGUIPMENT 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-ELECTRONICS EGUIPMENT ENGINEERING CENTER Co Ltd filed Critical CHANGCHUN GUANGHUA MICRO-ELECTRONICS EGUIPMENT ENGINEERING CENTER Co Ltd
Priority to CN201610388780.0A priority Critical patent/CN106097316B/en
Publication of CN106097316A publication Critical patent/CN106097316A/en
Application granted granted Critical
Publication of CN106097316B publication Critical patent/CN106097316B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • G06T7/0006Industrial image inspection using a design-rule based approach
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image

Landscapes

  • Engineering & Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The present invention relates to a kind of substrate position identifying processing method of laser scribing means image identification system, the method comprises the steps: that the entire image to gathering carries out binary conversion treatment;Image Mark point is done rim detection, obtains the level of spider, vertical centre dotted line;Mark dot center line is detected, central point on the dotted line of spider center is transformed into the sinusoidal line of rectangular coordinate system parameter space, by straight line ask for be converted into asking for of intersection point pole coordinate parameter between sinusoidal line, obtain the pole coordinate parameter of spider horizontal line and vertical line;Pole coordinate parameter according to spider horizontal line and spider vertical line obtains the polar coordinate of spider intersection point.Accuracy of identification of the present invention is high, good reliability, and being applicable to laser scribing (line) machine or laser cutting machine etc. needs the equipment of image recognition processing.

Description

The substrate position identifying processing method of laser scribing means image identification system
Technical field
The invention belongs to technical field of image processing, the substrate position relating to a kind of laser scribing means image identification system is known Other processing method.
Background technology
In order to improve workpiece quality, reducing process time, reduce processing cost, laser technology produces therewith and is subject to extensively Pay close attention to, be progressively applied to the fields such as manufacture, surface process and materials processing.Laser scribing means is that passive device resistance substrate is made In special equipment.The image identification system of this equipment, for automatically determining the position of dicing substrate, makes exit positions and substrate Position is fully aligned.Due to equipment scribing positional precision the most a height of ± 3 μm, less demanding in ± 2 μ to the accuracy of identification of Mark point , due to multiformity and the unstability of scribing process, often there are multiple noise spot and the feelings of two Mark points in visual field in m Condition, therefore the recognition methods of traditional template matching can not meet the scribing requirement of reality.
Summary of the invention
The technical problem to be solved in the present invention is to provide the substrate position identification of a kind of laser scribing means image identification system Processing method, the method accuracy of identification is high, identification certainty is good.
In order to solve above-mentioned technical problem, the substrate position identifying processing of the laser scribing means image identification system of the present invention Method comprises the steps:
Step one, image binaryzation process:
The view picture figure gathered is done gray count, obtains its gray average and using this gray average as binary-state threshold; When the gray value of pixel is more than this binary-state threshold in image, it is set as 1, is otherwise 0, obtains binary image;Two-value Change in image be 0 pixel be " stain ";
Step 2, image Mark point is done rim detection:
Described Mark point is spider graph;In selected image-region, respectively both horizontally and vertically from surrounding Carrying out gray value detection to field of view center, the vertical coordinate of " stain " in the often row pixel finding above-below direction is averaged, Obtain the horizontal centre dotted line of spider;The abscissa of " stain " in each column pixel finding left and right directions is averaged, Obtain the vertical centre dotted line of spider;
Step 3: Mark dot center line detection:
1) for spider horizontal centre dotted line, any point is taken on image as the initial point of rectangular coordinate system;Set up one Two dimension accumulator array (Ay [ρ11], Ay [ρ22] ... Ay [ρii]…Ay[ρnn]);θiIn the angular range set Value;
2) Ay [ρ is initializedii]=0;Point on the dotted line of center is mapped in polar coordinate system parameter space, obtains correspondence Sinusoidal line;
For any point J on the dotted line of center, by its rectangular coordinate (xj, yj) substitute into formula (1), calculate θ1, θ2... θi... θnThe most corresponding ρ value, i.e. ρj1, ρj2..., ρji, ρjn, obtain this central point and be mapped in polar coordinate system parameter space Sinusoidal line;
ρji=xjcosθi+yjsinθi (1)
Often obtain a central point and be mapped to sinusoidal line in polar coordinate system parameter space, it is judged that this sinusoidal line with obtain before Sinusoidal line whether have intersection point;For any point J, if sinusoidal line corresponding to this point has intersection points B with the sinusoidal line obtained before0joo), then by the array element Ay [ρ in corresponding two-dimentional accumulator arrayoo] add 1;The like, until obtaining center The sinusoidal line being mapped to a little on dotted line in polar coordinate system parameter space and the intersection point of these sinusoidal line, finally give two dimension tired Add device array (Ay [ρ11], Ay [ρ22] ... Ay [ρii]…Ay[ρnn]) voting result;In two dimension accumulator array Finding the array element of maximum in voting result, the intersection point that this array element is corresponding is central point horizontal polar coordinate ginseng Number;
Use the method as calculating central point horizontal line pole coordinate parameter, obtain the polar coordinate ginseng of central point vertical line Number;
Step 4, pole coordinate parameter according to spider horizontal line and spider vertical line obtain the pole of spider intersection point and sit Mark.
In described step 2, after entire image edge is removed 20 pixels, take mid portion as selected image Region.
In described step 3, θiThe angular range set is as [85 °, 95 °].Can need between set angle according to available accuracy Every, take equiangularly spaced or the most equiangularly spaced.In two dimension accumulator array of the present invention, take equiangularly spaced, adjacent Array element θiAngle interval take 0.1 °.
Further, present invention additionally comprises the step gathering spectral discrimination, this step is as follows:
If the discrete pixel that the binary image intermediate value that step one obtains is 0 and the value of surrounding pixel point is 1 is for " to make an uproar Point ";Judge in binary image, whether " noise " number exceedes the noise amount threshold of setting, be to judge current image date Mistake, does not identifies;Otherwise carry out step 2;The noise amount threshold wherein set is more than or equal to 1% and less than or equal to 3%.
Further, present invention additionally comprises identification point coordinate determination step;This step is as follows:
The spider intersection point obtained for step 3, in about 30 × 30 pixel coverages, if binary image Intermediate value is that the pixel quantity of 1 is more than the 20% of total pixel quantity, then it is assumed that be wrong identification image, otherwise it is assumed that step 3 In the rectangular coordinate of spider intersection point that obtains correct.
Beneficial effects of the present invention:
When image Mark point is done rim detection by the present invention, in selected image-region, carry out gray value detection, thus The horizontal centre dotted line obtained and vertical centre dotted line, it is possible to rejection image marginal interference, improve spider identification accuracy;? In the line detection of Mark dot center, the central point on the dotted line of spider center is transformed into the sine of rectangular coordinate system parameter space Line, by straight line ask for be converted into asking for of intersection point pole coordinate parameter between sinusoidal line, accuracy of identification is high, good reliability;For Image has the situation of bigger noise jamming, by the ratio shared by " noise " as judgment basis, it is possible to effectively judge side by side Except error image, it is ensured that without the problem of misrecognition.Present invention can be suitably applied to laser scribing (line) needs such as machine or laser cutting machine The equipment of image recognition processing.
Accompanying drawing explanation
With detailed description of the invention, the present invention is described in further detail below in conjunction with the accompanying drawings.
Fig. 1 is image identification system hardware block diagram.
Fig. 2 is the substrate position identifying processing method flow diagram of the laser scribing means image identification system of the present invention.
Fig. 3 is the process image to be identified containing Mark point that CCD camera Real-time Collection arrives.
Fig. 4 is finely to detect through edge, the pixel coordinate distribution situation figure drawn.
Fig. 5 is the parameter list diagram of rectangular coordinate system parameter space straight line in hough conversion.
Fig. 6 is the expression figure that in hough conversion, center dotted line is mapped to polar coordinate system parameter space.
Fig. 7 be identified after, the center position coordinates of Mark point is done the image judged.
Detailed description of the invention
The image identification system of the present invention is as follows:
As it is shown in figure 1, industrial computer 1 controls slide holder 4 moves the position making substrate motion to CCD camera 3, and make on substrate Mark point enter CCD camera 3 visual field in;Industrial computer 1 obtains the signal that puts in place from linear electric motors XY platform, industry control simultaneously Machine 1 triggers CCD camera 3 and gathers piece image, as shown in Figure 3.Via image pick-up card 2, view data is transferred to industrial computer 1 In, it is handled as follows after obtaining view data by industrial computer 1, as shown in Figure 2:
Step one, collection spectral discrimination:
Image owing to gathering is formed by cutting ceramic by laser substrate, by technique and environmental effect in cutting process, Cause fraction substrate to have dust to be attached on substrate and Mark point, image recognition is produced noise jamming, therefore is identifying image Before " noise " number in image is judged.In piece image, view picture figure is done gray count, obtain its gray scale equal Value, as binary-state threshold.When the gray value at image midpoint is more than this binary-state threshold, it is set as 1, is otherwise 0, obtains two Value image, its intermediate value be the pixel of 0 be " stain "." noise " is in binary image, and value is 0 and surrounding pixel point Value is discrete " stain " of 1.
When " noise " number exceedes the noise amount threshold of setting in piece image, then judge that current image date is wrong By mistake, do not identify.The noise amount threshold set is as 1%, 2% or 3%.
Determine view data correct after, it is handled as follows:
Step 2, image Mark point is done rim detection:
Mark dot image owing to gathering is affected by light-source brightness, substrate scribing process, for the reliability identified, is dividing Taking middle 620 × 460 pixels in the range of 640 × 480 pixels of resolution, rejection image marginal interference is identified. Mark point is spider graph.The binary image obtaining step one detects, the often row pixel finding above-below direction In the vertical coordinate of " stain " average, the abscissa of " stain " in each column pixel finding left and right directions is averaged Value, obtains the center dotted line of spider.As shown in Figure 4, discrete in image stain is " noise " and spider detected Edge pixel point, the middle dotted line in spider edge pixel point is the spider center dotted line obtained.
Step 3, the line detection of Mark dot center:
1) the spider center dotted line owing to obtaining in step 2 is a series of level of approximation line and the discrete point of vertical line, So extracting the key that rectilinear coordinates equation is the present invention from these discrete points accurately.Horizontal line has 620 discrete points, Vertical line has 460 discrete points, if cannot ensure the precision of recognizer with simple fitting a straight line, therefore takes hough to become Change and straight line is detected.The principle of this conversion is: through step 2) each some correspondence in the spider center dotted line that obtains The straight line in rectangular coordinate system parameter space, as it is shown in figure 5, the straight line of rectangular coordinate system parameter space is corresponding A point in image.In original image straight a little, their slope and intercept are identical, so they are directly Angle coordinate system parameter space corresponds to same point.So each spot projection on the dotted line of spider center to rectangular coordinate system is joined After under number space, the accumulation point under rectangular coordinate system parameter space is just corresponding straight line that central point is linked to be.Due to horizontal line ten The equation of word fork is x=c, and the slope of straight line is infinitely great.The equation of y=kx+b form cannot represent.So in the present invention In the hough conversion of application, parametric polar equation ρ=xcos θ+ysin θ is used to represent.(ρ, θ) represents under rectangular coordinate system Straight line.Wherein ρ is this straight line distance to initial point, and θ is the vertical line angle with X-axis of this straight line, and span is [0°,180°].As shown in Figure 6.Under polar coordinate representation, in the dotted line of spider center, the point transformation of conllinear is to polar coordinate system parameter Behind space, all intersecting at a bit at parameter space, (ρ, the θ) that now obtain is the pole coordinate parameter of required straight line.Sit in pole Under mark represents, it is sinusoidal line that the point in image is mapped to polar coordinate system parameter space.Now, the straight line side that image midpoint forms is asked Journey translates into the coordinate found intersection.
2) in the present invention, the horizontal computation processing method of spider is: set up a two-dimentional accumulator array (Ay [ρ1, θ1], Ay [ρ22] ... Ay [ρii]…Ay[ρnn]).Zero can take any point on image (with in level in Fig. 4 A little as initial point bottom heart dotted line).ρ1、ρ2、……ρi、……ρnSpan be [0,460];Due to calculate it is Horizontal vertical coordinate, for the fast reliability judged, only judges at valid interval, therefore θi(i=1,2 ..., n) Span be [85 °, 95 °], as shown in Figure 4.θiCan value or unequal interval value at equal intervals.It is spaced the least detection essence Spend the highest, θ in the present inventioniValue at equal intervals, θiWith θi-1Angle be spaced apart 0.1 °.
3) Ay [ρ is initializedii]=0.Point on the dotted line of center is mapped in polar coordinate system parameter space, obtains correspondence Sinusoidal line.For any point J on the dotted line of center, by its rectangular coordinate (xj, yj) substitute into formula (1), calculate θ1, θ2... θi... θnThe most corresponding ρ value, i.e. ρj1, ρj2..., ρji, ρjn, obtain this central point and be mapped in polar coordinate system parameter space Sinusoidal line;
ρji=xjcosθi+yjsinθi (1)
Specific as follows:
As shown in Figure 6, first by the coordinate (x of first discrete central point on horizontal centre dotted line1, y1) substitute into formula (1) first pole coordinate parameter (ρ corresponding to discrete central point, is calculated11, θ1), (ρ12, θ2) ..., (ρ1i, θi)……(ρ1n, θn), obtain Article 1 sinusoidal line A1;Again by the coordinate (x of second discrete central point2, y2) substitute into formula (1), calculate second Pole coordinate parameter (the ρ that individual discrete central point is corresponding21, θ1), (ρ22, θ2) ..., (ρ2i, θi)……(ρ2n, θn), obtain second Sinusoidal line A2;By that analogy, by being mapped to a little in polar coordinate system parameter space on the dotted line of center, the sine of correspondence is obtained Line A3, A4, A5, A6...AN, 3 < N < 620.As shown in Figure 6, A2 Yu A1 intersects at B1 point, it is assumed that the polar coordinate that B1 point is corresponding are (ρ211) (or (ρ111), ρ2111), then by array element Ay [ρ11] add 1, Ay [ρ during owing to initializing11]= 0, so now Ay [ρ11]=1.A3 Yu A1, A2 intersect at B1 point simultaneously, then by Ay [ρ11] add 1 again, i.e. Ay [ρ11]= 2;A4 Yu A1, A2, A3 intersect at B2, B4, B6 point respectively, it is assumed that the polar coordinate that B2, B4, B6 are corresponding are respectively (ρ422)、(ρ43, θ3)、(ρ466), then by Ay [ρ22]、Ay[ρ33]、Ay[ρ66] add 1 respectively.By that analogy, until all discrete in The sinusoidal line that heart point maps calculates and terminates, and obtains two dimension accumulator array voting result;Maximum is found in this voting result Array element, the pole coordinate parameter that this array element is corresponding, it is the horizontal polar coordinate of central point, straight in its correspondence image Central point quantity on the horizontal line that line comprises is most.As a example by shown in Fig. 6, totally 7 sinusoidal line are at θiIn span respectively Intersecting, intersection point is respectively B1, B2, B3...B6, the corresponding array element Ay [ρ finally obtained11]=2, Ay [ρ22]=1, Ay[ρ33]=1, Ay [ρ44]=1, Ay [ρ55]=1, Ay [ρ66]=4;Due to Ay [ρ66] maximum, so the pole of B6 Coordinate (ρ666) it is the horizontal polar coordinate of required spider.In like manner, the polar coordinate of spider vertical line, wherein θ i can be obtained Span can be [-5 °, 5 °].Spider is obtained finally according to the horizontal polar coordinate of spider vertical line and spider The rectangular coordinate of intersection point.
4) identification point coordinate judges: owing to the substrate of laser scribing machine equipment cutting is relatively costly, the image recognition of mistake Directly affect the positional precision of cutting, cause the substrate of cutting can not meet required precision and scrap, thus the most right The coordinate of identification point judges.As it is shown in fig. 7, the width of usual spider center dotted line is 20 pixel values, therefore at cross Do gray scale in 30 pixel value range in fork XY direction, center to judge.Ideally, the some two-value in gray scale judges district Change process after, value be the some number of 0 be 800 pixel values, be that the some number of 1 is 100 pixel values, it is contemplated that the shadow of " noise " Ring, if after binary conversion treatment value be 1 pixel be more than total pixel number 20%, be wrong identification image.When being judged to During the image of error in data and wrong identification, industrial computer sends the process instruction being judged to error image, and the motion of slide glass platform will Reject bin put into by substrate, otherwise carries out scribing work.

Claims (5)

1. the substrate position identifying processing method of a laser scribing means image identification system, it is characterised in that include walking as follows Rapid:
Step one, image binaryzation process:
The view picture figure gathered is done gray count, obtains its gray average and using this gray average as binary-state threshold;Work as figure When the gray value of pixel is more than this binary-state threshold in Xiang, it is set as 1, is otherwise 0, obtains binary image;Binary picture In Xiang be 0 pixel be " stain ";
Step 2, image Mark point is done rim detection:
Described Mark point is spider graph;In selected image-region, both horizontally and vertically regarding from four circumferences respectively Center, field carries out gray value detection, and the vertical coordinate of " stain " in the often row pixel finding above-below direction is averaged, and obtains The horizontal centre dotted line of spider;The abscissa of " stain " in each column pixel finding left and right directions is averaged, and obtains The vertical centre dotted line of spider;
Step 3: Mark dot center line detection:
1) for spider horizontal centre dotted line, any point is taken on image as the initial point of rectangular coordinate system;Set up a two dimension Accumulator array (Ay [ρ11], Ay [ρ22] ... Ay [ρii]…Ay[ρnn]);θiValue in the angular range set;
2) Ay [ρ is initializedii]=0;Point on the dotted line of center is mapped in polar coordinate system parameter space, is just obtaining correspondence The string of a musical instrument;
For any point J on the dotted line of center, by its rectangular coordinate (xj, yj) substitute into formula (1), calculate θ1, θ2... θi... θn The most corresponding ρ value, i.e. ρj1, ρj2..., ρji, ρjn, obtain the sine that this central point is mapped in polar coordinate system parameter space Line;
ρji=xjcosθi+yjsinθi (1)
Often obtain a central point and be mapped to sinusoidal line in polar coordinate system parameter space, it is judged that this sinusoidal line with just obtain before Whether the string of a musical instrument has intersection point;For any point J, if sinusoidal line corresponding to this point has intersection points B 0 (ρ with the sinusoidal line obtained beforejo, θo), then by the array element Ay [ρ in corresponding two-dimentional accumulator arrayoo] add 1;The like, until obtaining center dotted line The upper sinusoidal line being mapped to a little in polar coordinate system parameter space and the intersection point of these sinusoidal line, finally give two dimension accumulator Array (Ay [ρ11], Ay [ρ22] ... Ay [ρii]…Ay[ρnn]) voting result;In two dimension accumulator array voting Finding the array element of maximum in result, the intersection point that this array element is corresponding is the horizontal pole coordinate parameter of central point;
Use the method as calculating central point horizontal line pole coordinate parameter, obtain the pole coordinate parameter of central point vertical line;
Step 4, pole coordinate parameter according to spider horizontal line and spider vertical line obtain the polar coordinate of spider intersection point.
The substrate position identifying processing method of laser scribing means image identification system the most according to claim 1, its feature It is in described step 2, after entire image edge is removed 20 pixels, takes mid portion as selected image-region.
The substrate position identifying processing method of laser scribing means image identification system the most according to claim 1 and 2, it is special Levy and be in described step 3, θiThe angular range set is as [85 °, 95 °].
The substrate position identifying processing method of laser scribing means image identification system the most according to claim 1, its feature Being the step also including gathering spectral discrimination, this step is as follows:
If the discrete pixel that the binary image intermediate value that step one obtains is 0 and the value of surrounding pixel point is 1 is " noise "; Judge in binary image, whether " noise " number exceedes the noise amount threshold of setting, be then to judge that current image date is wrong By mistake, do not identify;Otherwise carry out step 2;The noise amount threshold wherein set is more than or equal to 1% and less than or equal to 3%.
5., according to the substrate position identifying processing method of the laser scribing means image identification system described in claim 1 or 4, it is special Levy and be also to include identification point coordinate determination step;This step is as follows:
The spider intersection point obtained for step 3, in about 30 × 30 pixel coverages, if binary image intermediate value Be 1 pixel quantity more than the 20% of total pixel quantity, then it is assumed that be wrong identification image, otherwise it is assumed that in step 3 The rectangular coordinate of the spider intersection point arrived is correct.
CN201610388780.0A 2016-06-03 2016-06-03 The substrate position identifying processing method of laser scribing means image identification system Active CN106097316B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610388780.0A CN106097316B (en) 2016-06-03 2016-06-03 The substrate position identifying processing method of laser scribing means image identification system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610388780.0A CN106097316B (en) 2016-06-03 2016-06-03 The substrate position identifying processing method of laser scribing means image identification system

Publications (2)

Publication Number Publication Date
CN106097316A true CN106097316A (en) 2016-11-09
CN106097316B CN106097316B (en) 2018-07-13

Family

ID=57447994

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610388780.0A Active CN106097316B (en) 2016-06-03 2016-06-03 The substrate position identifying processing method of laser scribing means image identification system

Country Status (1)

Country Link
CN (1) CN106097316B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108398946A (en) * 2018-01-25 2018-08-14 成都图灵智控科技有限公司 Intelligent tracking accurate positioning device and method
CN109345550A (en) * 2018-08-07 2019-02-15 信利光电股份有限公司 The grasping means of hot spot angle point, device and the readable storage medium storing program for executing of structure light image
CN109961067A (en) * 2019-03-19 2019-07-02 上海望友信息科技有限公司 Choosing method, system, computer storage medium and the equipment of optical reference point
CN112505055A (en) * 2021-02-03 2021-03-16 苏州维嘉科技股份有限公司 Method and device for detecting copper leakage of circuit board
CN112614094A (en) * 2020-12-15 2021-04-06 郑州金惠计算机***工程有限公司 Insulator string abnormity positioning and identifying method based on sequence state coding
CN114627141A (en) * 2022-05-16 2022-06-14 沈阳和研科技有限公司 Cutting path center detection method and system
CN115031633A (en) * 2022-08-11 2022-09-09 长春光华微电子设备工程中心有限公司 On-board detection system of laser scribing machine and detection method thereof

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09318352A (en) * 1996-05-29 1997-12-12 Maeda Corp Apparatus and method for measuring hollow displacement in tunnel
CN101555961A (en) * 2009-05-11 2009-10-14 中天建设集团浙江安装工程有限公司 Construction method of arch pipeline support and hanger laser positioning

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH09318352A (en) * 1996-05-29 1997-12-12 Maeda Corp Apparatus and method for measuring hollow displacement in tunnel
CN101555961A (en) * 2009-05-11 2009-10-14 中天建设集团浙江安装工程有限公司 Construction method of arch pipeline support and hanger laser positioning

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JINGJIANG HE等: "Laser surface modification with powder feeding for vertical surfaces", 《PHOTONICS ASIA 2004;OPTICS AND LASERS》 *
侯廉平等: "射频CO2激光陶瓷基板划片机光路设计及分析", 《光学精密工程》 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108398946A (en) * 2018-01-25 2018-08-14 成都图灵智控科技有限公司 Intelligent tracking accurate positioning device and method
CN108398946B (en) * 2018-01-25 2021-12-21 成都图灵时代科技有限公司 Intelligent tracking accurate positioning device and method
CN109345550A (en) * 2018-08-07 2019-02-15 信利光电股份有限公司 The grasping means of hot spot angle point, device and the readable storage medium storing program for executing of structure light image
CN109961067A (en) * 2019-03-19 2019-07-02 上海望友信息科技有限公司 Choosing method, system, computer storage medium and the equipment of optical reference point
CN112614094A (en) * 2020-12-15 2021-04-06 郑州金惠计算机***工程有限公司 Insulator string abnormity positioning and identifying method based on sequence state coding
CN112614094B (en) * 2020-12-15 2023-04-18 郑州金惠计算机***工程有限公司 Insulator string abnormity positioning and identifying method based on sequence state coding
CN112505055A (en) * 2021-02-03 2021-03-16 苏州维嘉科技股份有限公司 Method and device for detecting copper leakage of circuit board
CN114627141A (en) * 2022-05-16 2022-06-14 沈阳和研科技有限公司 Cutting path center detection method and system
CN114627141B (en) * 2022-05-16 2022-07-22 沈阳和研科技有限公司 Cutting path center detection method and system
CN115031633A (en) * 2022-08-11 2022-09-09 长春光华微电子设备工程中心有限公司 On-board detection system of laser scribing machine and detection method thereof
CN115031633B (en) * 2022-08-11 2022-11-08 长春光华微电子设备工程中心有限公司 On-board detection system of laser scribing machine and detection method thereof

Also Published As

Publication number Publication date
CN106097316B (en) 2018-07-13

Similar Documents

Publication Publication Date Title
CN106097316A (en) The substrate position identifying processing method of laser scribing means image identification system
CN104990926B (en) A kind of TR elements positioning of view-based access control model and defect inspection method
CN105563481B (en) A kind of robot vision bootstrap technique for peg-in-hole assembly
CN106251353A (en) Weak texture workpiece and the recognition detection method and system of three-dimensional pose thereof
CN107218927B (en) A kind of cargo pallet detection system and method based on TOF camera
CN103292701A (en) Machine-vision-based online dimensional measurement method of precise instrument
CN105913093A (en) Template matching method for character recognizing and processing
CN103345755A (en) Chessboard angular point sub-pixel extraction method based on Harris operator
CN112037159B (en) Cross-camera road space fusion and vehicle target detection tracking method and system
CN106934813A (en) A kind of industrial robot workpiece grabbing implementation method of view-based access control model positioning
CN109284718B (en) Inspection robot-oriented variable-view-angle multi-instrument simultaneous identification method
CN107392929B (en) Intelligent target detection and size measurement method based on human eye vision model
CN104200188B (en) Method and system for rapidly positioning position detection patterns of QR code
CN105930795A (en) Walking state identification method based on space vector between human body skeleton joints
CN105574161B (en) A kind of brand logo key element recognition methods, device and system
CN102799867A (en) Meter pointer angle identification method based on image processing
CN106407924A (en) Binocular road identifying and detecting method based on pavement characteristics
CN103295239A (en) Laser-point cloud data automatic registration method based on plane base images
CN112614188B (en) Dot-matrix calibration board based on cross ratio invariance and identification method thereof
CN103400373A (en) Method for automatically identifying and positioning coordinates of image point of artificial mark in camera calibration control field
CN110108712A (en) Multifunctional visual sense defect detecting system
CN113724193A (en) PCBA part size and clearance high-precision visual measurement method
CN109359537A (en) Human face posture angle detecting method neural network based and system
CN109870106A (en) A kind of building volume measurement method based on unmanned plane picture
CN106529548A (en) Sub-pixel level multi-scale Harris corner detection algorithm

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20210107

Address after: No.10 workshop, no.515, Xincheng South Road, Yushan Town, Kunshan City, Suzhou City, Jiangsu Province

Patentee after: Guangjingtuo intelligent equipment (Suzhou) Co.,Ltd.

Address before: 130033 block B, 77 Yingkou Road, Jingkai District, Changchun City, Jilin Province

Patentee before: CHANGCHUN GUANGHUA MICRO-ELECTRONIC EQUIPMENT ENGINEERING CENTER Co.,Ltd.

TR01 Transfer of patent right