CN108918543A - A kind of device for dynamically detecting and method of mirror surfaces scuffing - Google Patents
A kind of device for dynamically detecting and method of mirror surfaces scuffing Download PDFInfo
- Publication number
- CN108918543A CN108918543A CN201810455914.5A CN201810455914A CN108918543A CN 108918543 A CN108918543 A CN 108918543A CN 201810455914 A CN201810455914 A CN 201810455914A CN 108918543 A CN108918543 A CN 108918543A
- Authority
- CN
- China
- Prior art keywords
- object plate
- ccd camera
- camera
- scanning
- conveyer belt
- 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
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
- G01N21/896—Optical defects in or on transparent materials, e.g. distortion, surface flaws in conveyed flat sheet or rod
Abstract
The invention belongs to machine vision defect detecting technique fields, the device for dynamically detecting and method scratched more particularly to a kind of mirror surfaces, the device is that with camera bellows, motion scan light source, symmetrically arranged high-speed array CCD camera and can realize the gray level image to object plate in the case of quickly, precisely, repeatedly acquiring different location, different reflection angles, different highlight regions to isostructural intelligent, the automatic detection platform of object plate multistation transformation;Simultaneously using the image vision algorithm of Gassian low-pass filter algorithm, Laplace operator, binaryzation and the Hough transformation successively carried out, quickly, it precisely, steadily extracts and is scratched to object plate, it is particularly suitable for extracting the atomic weak scuffing of mirror surfaces, greatly improve detection efficiency and detection quality, save the cost;And the present invention device for dynamically detecting and method are easy to implement, meet the production model of on-line checking, and reliable and stable, it is easy to promote and utilize.
Description
Technical field
The invention belongs to machine vision defect detecting technique fields, and in particular to a kind of dynamic detection that mirror surfaces scratch
Device and method.
Background technique
With the continuous development of glass industry, demand is continuously increased, and the quality requirement to glass product is also more next
It is higher.Due to being influenced by the factors such as manufacturing process, artificial, glass raw sheet is likely to generate in the either phase of production process
Defect, at this time glass quality detection play the role of very important.According to the regulation of glass current standard, glass is common to be lacked
It falls into and mainly includes:Bubble, scratches, is mingled with viscous tin.
Traditional mirror mass detection method is artificial detection method, but with the requirement and market competition of user's high quality
Aggravation, the requirement to mirror mass is higher and higher, as automobile rearview mirror requires must not have deformation, fuzzy, striped, gas on mirror surface
Bubble, scar, crackle, the defects of being mingled with, and some radius of curvature of the flatness or even mirror edge to mirror surface also have strictly
It is required that at this point, traditional artificial detection method is unable to satisfy high quality, efficient production needs.
Now, in mirror commercial process, the surface defects of products problems such as scuffing, and these problems pair are frequently encountered
Challenge is rich in artificial detection and Machine Vision Detection.The detection difficulty that mirror surfaces scratch is:Scratch it is in irregular shape,
Depth contrast is low, mirror surfaces light reflection interference detection process and result.Therefore, mirror surfaces scratch detection process
In, to correct polishing, camera resolution, the relative position for being detected component and industrial camera, complicated machine vision algorithm etc.
There is very high requirement.
Summary of the invention
In view of the deficiencies of the prior art, it is an object of the present invention to provide a kind of mirror surfaces scratch device for dynamically detecting,
The device provides the dark field environment of Image Acquisition, repeats acquisition different location, different reflection angles, different highlight regions feelings
Lens image to be checked under condition reduces the probability of missing inspection and erroneous detection, improves the precision and accuracy for scratching detection;The device can be real
Existing intelligent automatic control, while improving detection quality and detection efficiency, save the cost.
The present invention also provides the dynamic testing method that a kind of mirror surfaces scratch, this method acquires ash under dark field environment
Image is spent, and uses the noise reduction and algorithm for image enhancement of unique gray level image, the accuracy of raising machine vision algorithm extraction,
Accuracy and stability simplify machine vision algorithm, realize that eyeglass scratches the intelligent automation control of detection, meet eyeglass scuffing
High quality, the high efficiency demand of detection.
The technical scheme is that:The device for dynamically detecting that a kind of mirror surfaces scratch, including camera bellows, for transmit to
The first conveyer belt and the second conveyer belt of object plate, the first conveyer belt and the setting of the second conveyer belt parallel interval, lift bar setting
First camera fixed link, second camera fixed link, scanning are additionally provided between the first conveyer belt and the second conveyer belt, in camera bellows
Fluorescent tube dynamic sliding rail and scanning fluorescent tube, first camera fixed link and the setting of second camera fixed link are being lifted above bar, the first phase
It is fixed with the first CCD camera in machine fixed link, the second CCD camera is fixed in second camera fixed link;Positioned at lift bar just on
The scanning fluorescent tube setting of side can move back and forth in scanning fluorescent tube dynamic sliding rail along scanning fluorescent tube dynamic sliding rail;The two of camera bellows
Be respectively arranged with feeding inlet and discharge port on side, the first conveyer belt and the setting of the second conveyer belt feeding inlet and discharge port it
Between;
Bar, the first CCD camera, the second CCD camera and scanning fluorescent tube are lifted in PLC system control;First CCD camera and second
CCD camera connects image pick-up card, and the lens image to be checked of acquisition is transmitted to the image analysis on computer by image pick-up card
Software;
On material transmission direction from feeding inlet to discharge port, it is placed in the first conveyer belt and the simultaneously with a piece of eyeglass to be checked
On two conveyer belts, the first conveyer belt of lower synchronous loopy moving and the second conveyer belt is driven to transmit jointly by stepper motor;
Lifting bar is hollow tube, lifts and is fixed with Universal vacuum chuck at the top of bar;Lifting bar will be to by negative-pressure adsorption
Object plate is horizontally fixed on Universal vacuum chuck, will be held up straight up to object plate, and can drive and tilt to object plate
Movement;In unadsorbed fixation when object plate, the sucker face of Universal vacuum chuck keep it is horizontal and with the first conveyer belt and second
The transmission plane positioned at upper end of conveyer belt flushes;
First CCD camera and the second CCD camera be respectively arranged at scanning fluorescent tube move back and forth direction two sides, and be located to
On the center line of object plate;Bar is being lifted by level fixation after object plate is held up straight up, the camera lens of the first CCD camera
It is respectively facing with the camera lens of the second CCD camera to object plate, and forms angle with camera lens to be checked respectively;Lifting ten thousand at the top of bar
It is driven when object plate makees banking motion to vacuum chuck, it is any in the camera lens of the camera lens of the first CCD camera and the second CCD camera
One can be perpendicular to object plate.
Bar is being lifted by level fixation after object plate is held up straight up, the camera lens of the first CCD camera and the 2nd CCD
The camera lens of camera intersects at the center to object plate, and forms angle with camera lens to be checked respectively;It is universal true at the top of bar lifting
Suction disk drives any one in the camera lens of the camera lens of the first CCD camera and the second CCD camera when object plate makees banking motion
It can be perpendicular to the center to object plate.
Bar is being lifted by level fixation after object plate is held up straight up, the camera lens of the first CCD camera and the 2nd CCD
The camera lens of camera forms 45 degree of angles with to object plate respectively.
Scanning fluorescent tube reciprocating movement direction is parallel with material transmission direction, and the first CCD camera and the second CCD camera are symmetrically divided
Cloth is on the center line to object plate.Further, the first CCD camera and the second CCD camera are symmetrically distributed in object plate
On the center line parallel with material transmission direction.
The surface for lifting bar is arranged in scanning fluorescent tube dynamic sliding rail, lifts bar and scans the center pair of fluorescent tube dynamic sliding rail
It answers;Scanning fluorescent tube dynamic sliding rail includes the first elliptical ring and the second elliptical ring, and the first elliptical ring and the second elliptical ring are respectively along object
Material direction of transfer is fixed on vertically on the top surface inner wall of camera bellows, the first elliptical ring and the second elliptical ring horizontal interval and end face is neat
It is flat;The both ends of scanning fluorescent tube are separately fixed in the first elliptical ring and the second elliptical ring, along the first elliptical ring and the second elliptical ring
It reciprocatingly slides.
Interval of the bar between the first conveyer belt and the second conveyer belt is lifted, and is set between two parties on material transmission direction
It sets;It is corresponding with the center fixed thereon to object plate to lift Universal vacuum chuck fixed at the top of bar.
Scanning light source uses LED strip light source, and the back of scanning light source is equipped with barn door.
The method that device for dynamically detecting carries out dynamic detection is scratched using mirror surfaces of the present invention, step includes:
I. spaced two conveyer belts synchronous loopy moving under stepper motor drive on material transmission direction, simultaneously
Be placed on two conveyer belts when object plate is moved to the top for lifting bar with two conveyer belts, the feeding inlet of camera bellows and go out
Material mouth is closed, and PLC system control lifts bar, scanning light source, the first CCD camera and the second CCD camera and starts simultaneously at work;
Under the control of II.PLC system, lifts bar and held up what its top level was fixed straight up to object plate, scan light
Source starting shines and moves back and forth scanning along the whole process of scanning fluorescent tube dynamic sliding rail, when the luminous scanning light source of starting distinguishes position
When scanning the both ends of fluorescent tube dynamic sliding rail, respectively make a banking motion to object plate, tilts to object plate and scanning light
End where source be located at the first ipsilateral CCD camera camera lens or the second CCD camera camera lens it is perpendicular, and by with to microscopy
The first perpendicular CCD camera of piece or the second CCD camera acquisition different location, different reflection angles, different highlight regions feelings
Lens image to be checked under condition, and it is transmitted to through image pick-up card the image analysis software on computer;
When scanning light source moves back and forth in scanning process along the whole process of scanning fluorescent tube dynamic sliding rail, to object plate holding water
Placing flat state;Be respectively arranged at scanning light source move back and forth direction two sides, and be located to object plate center line and with it is to be checked
Eyeglass acquires different location, different reflection angles, different height in the first CCD camera of angle and the second CCD camera difference in real time
Lens image to be checked in the case of bright area, and it is sent to through image pick-up card the image analysis software on computer;
III. image analysis software successively uses Gassian low-pass filter algorithm, Laplace operator, binaryzation and Hough to become
The vision algorithm changed carries out noise reduction, filtering, binaryzation and Hough transformation processing, quickly, precisely, steadily extracts to object plate
Scuffing;
When object plate has scuffing, it is distributed to object plate to one of the first conveyer belt and the second conveyer belt
On, it is spread out of by discharge port;When object plate is without scratching, it is distributed to object plate another to the first conveyer belt and the second conveyer belt
On one, spread out of by discharge port.
In step II, when the luminous scanning light source of starting is located at the both ends of scanning fluorescent tube dynamic sliding rail, and sweep
Retouch end where light source be located at the first ipsilateral CCD camera camera lens or the second CCD camera camera lens perpendicular to inclination after
Center to object plate;
When scanning light source along scanning fluorescent tube dynamic sliding rail whole process move back and forth in scanning process, the first CCD camera
Camera lens and the camera lens of the second CCD camera intersect at the center to object plate, and form angle with to object plate respectively.
In step II, when scanning light source along scanning fluorescent tube dynamic sliding rail whole process move back and forth in scanning process, first
CCD camera and the second CCD camera form 45 degree of angles with to object plate respectively.
In step II, scanning light source reciprocating movement scanning direction is parallel with material transmission direction, the first CCD camera and second
CCD camera is symmetrically distributed on the center line to object plate.Further, the first CCD camera and the second CCD camera are symmetrical
On the center line parallel with material transmission direction to object plate.
In step II, under PLC system control, lifts bar and will be horizontally fixed on to object plate by negative-pressure adsorption and lift bar top
On the Universal vacuum chuck at end.Under PLC system control, when being moved to object plate, to lift bar corresponding with the center to object plate
When, it will be horizontally fixed on to object plate on the Universal vacuum chuck for lifting bar top by negative-pressure adsorption.
In step II, scanning light source starting is located at the end of scan lamp pipe dynamic sliding rail, under PLC system control, scanning
Light source starting shines and moves back and forth scanning along starting point to the clearing end of scanning fluorescent tube dynamic sliding rail.When scanning light source is located at
When along starting point and the clearing end of scanning fluorescent tube dynamic sliding rail, respectively make a banking motion to object plate.
Compared with the existing technology, beneficial effects of the present invention are:
The device for dynamically detecting and detection method that mirror surfaces of the present invention scratch provide a kind of with camera bellows, motion scan
Light source, symmetrically arranged high speed display CCD camera and can realize to the isostructural intelligent, automation of object plate multistation transformation
Detection platform, quickly, precisely, repeatedly acquire in the case of different location, different reflection angle, different highlight regions to microscopy
The gray level image of piece realizes the highly effective gathering of lens surface gray level image to be checked;Simultaneously using the Gaussian low pass successively carried out
Wave algorithm, Laplace operator, binaryzation and Hough transformation image vision algorithm, rationally, it is easy while, quickly, precisely,
It steadily extracts and is scratched to object plate, be particularly suitable for extracting the atomic weak scuffing detection of mirror surfaces, greatly improve detection effect
Rate and detection quality, save the cost.
Relative to existing artificial detection and common scuffing detection platform, the dynamic detection of mirror surfaces scuffing of the present invention
Platform and method, intelligent and high-efficiency, speed is fast, and accuracy is high, easy to implement, meets the production model of on-line checking, and stabilization can
It leans on, it is easy to promote and utilize.
Detailed description of the invention
Fig. 1 is the volume rendering schematic diagram that mirror surfaces of the present invention scratch device for dynamically detecting.
Fig. 2 is that mirror surfaces of the present invention scratch the lens image comparison diagram to be checked of dynamic testing method before and after the processing.In figure,
A is that mirror surfaces of the present invention scratch the lens image to be checked before dynamic testing method processing, and B is that mirror surfaces of the present invention scuffing is dynamic
State detection method treated lens image to be checked.
Wherein, 1- camera bellows, 11- feeding inlet, 12- discharge port, the first conveyer belt of 2-, the second conveyer belt of 3-, 4- lift bar, 5-
First camera fixed link, the first CCD camera of 51-, 6- second camera fixed link, the second CCD camera of 61-, 7- scan fluorescent tube dynamic
Sliding rail, the first elliptical ring of 71-, the second elliptical ring of 72-, 8- scan fluorescent tube, and 9- waits for object plate.
Specific embodiment
The embodiment of the invention will now be described in detail with reference to the accompanying drawings.
Mirror surfaces as depicted in figs. 1 and 2 scratch dynamic detection platform, including camera bellows 1, for transmitting to object plate 9
The first conveyer belt 2 and the second conveyer belt 3, lift bar 4 be arranged between the first conveyer belt 2 and the second conveyer belt 3, in camera bellows 1
It is additionally provided with first camera fixed link 5, second camera fixed link 6, scanning fluorescent tube dynamic sliding rail 7 and scanning fluorescent tube 8, first camera
Fixed link 5 and the setting of second camera fixed link 6 are being lifted above bar 4, and the first CCD camera is fixed in first camera fixed link 5
51, the second CCD camera 61 is fixed in second camera fixed link 6, and the first CCD camera 51 and the second CCD camera 61 also are located at support
Lift the top of bar 4;It, can be along scan lamp positioned at the setting of scanning fluorescent tube 8 lifted right above bar 4 in scanning fluorescent tube dynamic sliding rail 7
Pipe dynamic sliding rail 7 moves back and forth;Feeding inlet 11 and discharge port 12, the first conveyer belt 2 are respectively arranged on the two sides of camera bellows 1
And second conveyer belt 3 be arranged between feeding inlet 11 and discharge port 12.
First conveyer belt 2 and the second conveyer belt 3 are located inside camera bellows 1, the both ends of the first conveyer belt 2 and the second conveyer belt 3
Portion is respectively close to feeding inlet 11 and discharge port 12;Alternatively, the first conveyer belt 2 and the second conveyer belt 3 can also be respectively from feeding inlets 11
Camera bellows 1 is passed through with discharge port 12.
Camera bellows 1 completely cuts off natural light outside, and after object plate 9 enters camera bellows 1, feeding inlet 11 and discharge port 12 can be closed,
Dark field environment is formed inside camera bellows 1.On from feeding inlet 11 to the material transmission direction of discharge port 12, it is same to object plate simultaneously
It is placed on the first conveyer belt 2 and the second conveyer belt 3, is driven down by stepper motor and make mobile 2 He of the first conveyer belt of synchronous circulating
Second transmission jointly of conveyer belt 3, the first conveyer belt 2 and the second conveyer belt 3 are alternatively arranged.
Lifting bar 4 can hold up what is transmitted jointly by the first conveyer belt 2 and the second conveyer belt 3 straight up to object plate 9,
For the imaging of taking pictures under follow up scan light source.It lifts between bar 4, the first CCD camera 51, the second CCD camera 61 and scanning fluorescent tube 8
It cooperates, for the image checking to object plate.
Interval of the bar 4 between the first conveyer belt 2 and the second conveyer belt 3 is lifted, and from feeding inlet 11 to discharging
It is centrally located on the material transmission direction of mouth 12.Lifting bar 4 is hollow tube, and the top for lifting bar 4 is fixed with Universal vacuum chuck.
It lifts bar 4 to vacuumize down in negative pressure state, 4 top of bar will be lifted to horizontal be firmly adsorbed on of object plate 9 by negative-pressure adsorption
On the Universal vacuum chuck of setting, Universal vacuum chuck drives under micro machine control makees banking motion to object plate 9.
When the unadsorbed fixation in the top for lifting bar is when object plate, that lifts 4 top Universal vacuum chuck of bar is in level
The sucker face of state is flushed with the transmission plane positioned at upper end of the first conveyer belt 2 and the second conveyer belt 3;When the top for lifting bar is inhaled
When object plate, the Universal vacuum chuck for lifting the top of bar 4 is absorbed and fixed at center to object plate 9 for attached fixation, lifts
Bar 4 can hold up straight up 100mm to object plate 9 for fixed thereon.
The surface for lifting bar 4 is provided with scanning fluorescent tube dynamic sliding rail 7, lifts in bar 4 and scanning fluorescent tube dynamic sliding rail 7
The heart is corresponding.Scanning fluorescent tube dynamic sliding rail 7 includes the first elliptical ring 71 and the second elliptical ring 72;First elliptical ring 71 and second is oval
Along the top surface inner wall that material transmission direction of the edge from feeding inlet 11 to discharge port 12 is fixed on camera bellows 1 vertically respectively of ring 72, first
Elliptical ring 71 and 72 horizontal interval of the second elliptical ring and end face.
The both ends of scanning fluorescent tube 8 are separately fixed in the first elliptical ring 71 and the second elliptical ring 72, and along the first elliptical ring
71 and second elliptical ring 72 move back and forth.Scan reciprocating movement direction and material transmission of the fluorescent tube 8 along scanning fluorescent tube dynamic sliding rail 7
Direction is parallel.
The back of scanning fluorescent tube 8 is provided with barn door, such as c-type barn door, will scan the back seal of fluorescent tube 8, not light leakage;
It scans fluorescent tube 8 and uses LED strip light source.
First camera fixed link 5 and second camera fixed link 6 are fixed on vertically respectively on the top surface inner wall of camera bellows 1, and right
Claim the both ends along material transmission direction for being distributed in scanning fluorescent tube dynamic sliding rail 7;It is fixed with when lifting the absorption of bar top to microscopy
When piece, the second CCD camera fixed in fixed the first CCD camera 51 and second camera fixed link 6 in first camera fixed link 5
61 are symmetrically distributed on the center line parallel with material transmission direction to object plate 9.
When fixed when object plate but when not yet holding up straight up, the camera lens of the first CCD camera 51 of lifting the absorption of bar top
Center and the optical center of the second CCD camera 61 are arrived respectively lifts the fixation of 4 top level of bar to the vertical of 9 place plane of object plate
Height is 350mm, and the optical center of the optical center of the first CCD camera 51 and the second CCD camera 61 is arrived respectively lifts bar 4
The horizontal distance of vertical centerline is 250mm.
When lift bar drive its top level it is fixed when object plate 9 holds up 100mm straight up, as shown in Figure 1, the
The camera lens of one CCD camera 51 and the camera lens of the second CCD camera 61 intersect at the center to object plate 9, the mirror of the first CCD camera 51
What head and level were fixed is 45 degree to the angle β between object plate 9;The camera lens of second CCD camera 61 is with horizontal fixation to microscopy
Angle α between piece 9 is 45 degree.
First CCD camera 51 and the second CCD camera 61 connect image pick-up card, and image pick-up card is by the first CCD camera 51
It is transmitted to the image analysis software on computer with the lens image to be checked of the second CCD camera 61 acquisition, is carried out to object plate figure
Noise reduction, filtering, binaryzation and the Hough transformation image information vision algorithm of picture are precisely extracted to the scuffing on object plate.
Scratching dynamic detection platform progress mirror surface detection using mirror surfaces of the present invention, detailed process is as follows:
(1) first conveyer belt 2 synchronous loopy moving under stepper motor drive with the second conveyer belt 3, will from feeding inlet 11
It is placed on the first conveyer belt 2 and the second conveyer belt 3 simultaneously to object plate 9, to object plate 9 preferably in the first conveyer belt 2 and the
It is placed centrally on two conveyer belts 3;When to object plate 9 with the first conveyer belt 2 and 3 synchronizing moving of the second conveyer belt to lifting bar 4
When top, the feeding inlet 11 and discharge port 12 of camera bellows 1 are closed, and completely cut off the natural light outside camera bellows 1;Bar is lifted in PLC system control
4, scanning light source 8, the first CCD camera 51 and the second CCD camera 61 start simultaneously at work, realize the intelligence of lens image to be checked
Automatic collection.
(2) it under PLC system control, lifts bar 4 and fixed thereon move to object plate 9 is driven to detect required station,
The starting of scanning light source 8 that starting is located at 7 one end of scan lamp pipe dynamic sliding rail shines and motion scan, the first CCD camera 51 and the
Two CCD cameras 61 simultaneously in real time in the case of crawl different location, different reflection angles, different highlight regions to object plate figure
Picture, and it is transmitted to the image analysis software on computer through image pick-up card, image analysis software passes sequentially through Gaussian low pass
Wave algorithm, Laplace operator, binaryzation and Hough transformation quickly, precisely, steadily extract the scuffing to object plate.Specifically
It is as follows:
S1:The starting of scanning light source 8 that starting is located at 7 one end of scan lamp pipe dynamic sliding rail shines;Bar 4 is lifted to inhale by negative pressure
It is attached to be horizontally fixed on the Universal vacuum chuck for lifting bar 4 to object plate 9, Universal vacuum chuck and the center to object plate 9
It is corresponding, and 100mm will be held up straight up to object plate 9;Afterwards under micro machine control, Universal vacuum chuck is driven to object plate
9 make 45 degree of banking motions, tilt to vertical positioned at the ipsilateral camera lens of the first CCD camera 51 with 8 place starting point of scanning light source
In the center to object plate 9;At this point, the first CCD camera 51 grabs the image to object plate 9, and it is sent to through image pick-up card
Image analysis software on computer;
S2:After the crawl of the first CCD camera 51 after the image of object plate 9, level is returned to from heeling condition to object plate 9
Placement status, scanning light source 8 are moved from the starting point of scanning fluorescent tube dynamic sliding rail 7 to clearing end along the direction parallel with material transmission
It is dynamic, in the process, the first CCD camera 51 and the second CCD camera 61 simultaneously in real time crawl different location, different reflection angles,
Image in the case of different highlight regions to object plate 9, and it is sent to through image pick-up card the image analysis software on computer;
S3:Stop movement after scanning light source 8 is moved to the clearing end of scanning fluorescent tube dynamic sliding rail 7, is controlled in micro machine
Under, Universal vacuum chuck, which drives, makees 45 degree of banking motions to object plate 9, tilts to and is located at together with 8 place clearing end of scanning light source
The camera lens of second CCD camera 61 of side is perpendicular to the center to object plate 9;At this point, the crawl of the second CCD camera 61 is to object plate 9
Image, and be sent to through image pick-up card the image analysis software on computer;
S4:After the second CCD camera 61 has grabbed image, it is returned to horizontal positioned state from heeling condition to object plate 9,
Scanning light source 8 moves from the clearing end of scanning fluorescent tube dynamic sliding rail 7 along the direction parallel with material transmission and is returned to starting point, complete
At reset, in the process, the first CCD camera 51 and the second CCD camera 61 grab different location, different angles of reflection in real time simultaneously
Image in the case of degree, different highlight regions to object plate 9, and it is soft through image pick-up card to be sent to the image analysis on computer
Part;
During S1 to S4, the position of the first CCD camera 51 and the second CCD camera 61, angle are fixed, only to object plate
9 make banking motion;First CCD camera 51 and the second CCD camera 61 are symmetrically distributed in the flat with material transmission direction of object plate 9
On capable center line, and the two sides along material transmission direction of scanning fluorescent tube dynamic sliding rail 7 are distributed in, vertical to object plate 9
After holding up upwards, the first CCD camera 51 and the second CCD camera 61 intersect at the center to object plate 9, and respectively and to object plate
9 shapes are in angle of 45 degrees.
It is moved back and forth in scanning process in scanning light source 8, the first CCD of direction two sides is moved back and forth positioned at scanning light source 8
It is to be checked in the case of camera 51 and the repeatable acquisition different location of the second CCD camera 61, different reflection angles, different highlight regions
Lens image, repeated acquisition method reduce the probability of missing inspection and erroneous detection, improve the detection accuracy and accuracy of scuffing.
It is moved back and forth in scanning process in scanning light source 8, lens surface to be checked generates different highlight regions, to object plate
There are luminance difference (i.e. biggish gray value gradients) with remaining region for the highlight regions on surface, if having scuffing or scratch position at this time
In the penumbra of highlight regions and remaining region, the feature of scuffing is just it is obvious that be easier to detect.
(3) image analysis software passes sequentially through Gassian low-pass filter algorithm, Laplace operator, binaryzation and Hough and becomes
It changes, realizes quick, accurate, the stable extraction scratched to object plate.
If to have scuffing on object plate 9, to object plate 9 be distributed to the first conveyer belt 2 and the second conveyer belt 3 wherein it
On one, spread out of by discharge port 12;If to, without scuffing, be distributed to object plate 9 to the first conveyer belt 2 and second and pass on object plate 9
It send on another of band 3, is spread out of by discharge port 12.
Image analysis software passes sequentially through Gassian low-pass filter algorithm, Laplace operator, binaryzation and Hough transformation essence
It is as follows really to extract the step of scratching to object plate:
Step I. carries out noise reduction using mirror surfaces gray level image of the Gassian low-pass filter algorithm to acquisition.Because image is dark
It is acquired in room, deficiency in light quantity, leads on image that there are many noises.These noises have certain interference to the detection of scuffing,
Therefore Gassian low-pass filter algorithm (Gaussian Low Pass Filter) is used, using Gaussian kernel, to whole picture gray level image
Carry out sliding convolution, by gray level image low frequency energy (such as noise) filter off, keep image more smooth, obtain it is more visible,
The small image of noise.
The image after noise reduction is filtered using Laplace operator (Laplace Operator), Laplce
Operator is a kind of simplest differential operator, and programming is not difficult and calculation amount is little, but because of its rotational invariance, to isolated point
Perhaps especially suitable for the isolated point or isolated line (as scratched) in prominent image the features such as the sensibility of endpoint, image is allowed
Boundary information become apparent so that scratch boundary information it is more prominent in the picture.It is only carried on the back on image after filtering
Two kinds of ingredients of scape and scuffing, the gray value difference of two kinds of ingredients is larger, and subsequent Hough transformation can be improved to the accurate of scuffing detection
Rate.
The noise in image can equally be enhanced because of Laplace operator, thus with Laplce carry out image enhancement it
Between, noise reduction smoothing processing first is carried out to image with Gassian low-pass filter algorithm, while scuffing in prominent image, and reduces and makes an uproar
The disturbing factors such as sound improve the accuracy of image zooming-out.
Step II. carries out binaryzation to the image after noise reduction and filtering processing.Binaryzation makes image become simply, to reduce number
According to amount, the profile of target (scuffing) is highlighted.Because the scuffing of mirror surfaces is to collide with or scratch the linear or camber line left mostly
The scratch of class, in order to more accurately detect to scratch, we first carry out local binarization to the image after the completion of step I pretreatment
It handles, the scuffing of different zones, sets different threshold values on unified image, and it is high that background black, scratch are obtained after binary conversion treatment
Bright binary image.Laplace's operation is highlighted in image and is scratched, and is carried out binaryzation after Laplace's operation, is facilitated difference
The threshold value setting for scratching region, obtains more accurate binary image.
Step III. uses the scuffing of Hough transformation (Hough Transform) extraction step II binary conversion treatment image.
Hough transformation directly extracts the image without binary conversion treatment, if Hough transformation size is tuned up, filtering is largely interfered same
When, but lose some shorter lighter scuffings;It, but can be by some noises while scratch delicate if Hough transformation size is turned down
Miscellaneous background is mistakenly considered to scratch;It can not accurately extract scratch in image.Black and pure white is only existed in image after binaryzation
Two kinds of features, background is pure, there's almost no interference, and subsequent Hough variation can get optimal scuffing testing result, binaryzation
It is more efficient accurate that processing extracts Hough transformation.
The concrete operations of Hough transformation are:Firstly, one block buffer of initialization, corresponds to parameter plane, by its all number
According to being set to 0.For foreground point each on binary image, the source pixel point data on image space, Hough transformation algorithm are obtained
Start, each pixel coordinate point P (x, y) is switched to above the curve point of (r, theta), and be added to corresponding grid number
Strong point finds out the correspondence straight line in parameter plane, and the frequency of occurrence of all the points on the straight line is counted, and it is flat to find parameter
The most point position of frequency of occurrence, this position are exactly the parameter of straight line on original image on face.Finally, maximum Hough value is found,
Threshold value is set, corresponding straight line contravariant will be scratched on parameter space and changes to image space.
The lens image comparing result such as Fig. 2 to be checked of dynamic testing method before and after the processing is scratched using mirror surfaces of the present invention
Shown, A is that mirror surfaces of the present invention scratch the lens image to be checked before dynamic testing method processing, and B is mirror surfaces of the present invention
Scratch dynamic testing method treated lens image to be checked;In A and B, white coil, which encloses in position, has white oblique line to scratch.
By A and B comparison it is found that through mirror surfaces of the present invention scratch dynamic testing method treated lens surface scratch more clearly plus
It is strong prominent, illustrate that mirror surfaces of the present invention scratch device for dynamically detecting and method extraction lens surface scuffing to be checked is more precisely and steady
It is fixed, it is particularly suitable for the detection of the atomic weak scuffing of mirror surfaces.
Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that these
It is only the explanation of embodiment, without departing from the principle and essence of the present invention, these embodiments can be made
Various changes or modifications, therefore, protection scope of the present invention are defined by the appended claims.
Claims (10)
1. the device for dynamically detecting that a kind of mirror surfaces scratch, which is characterized in that including camera bellows (1), for transmitting to object plate
(9) the first conveyer belt (2) and the second conveyer belt (3), the first conveyer belt (2) and the setting of the second conveyer belt (3) parallel interval, support
It lifts bar (4) to be arranged between the first conveyer belt (2) and the second conveyer belt (3), is additionally provided with first camera fixed link in camera bellows (1)
(5), second camera fixed link (6), scanning fluorescent tube dynamic sliding rail (7) and fluorescent tube (8) are scanned, first camera fixed link (5) and the
The setting of two camera fixed links (6) is being lifted above bar (4), is fixed with the first CCD camera (51) in first camera fixed link (5),
The second CCD camera (61) are fixed in second camera fixed link (6);Positioned at scanning fluorescent tube (8) setting lifted right above bar (4)
In scanning fluorescent tube dynamic sliding rail (7), it can be moved back and forth along scanning fluorescent tube dynamic sliding rail (7);Divide on the two sides of camera bellows (1)
Be not provided with feeding inlet (11) and discharge port (12), the first conveyer belt (2) and the second conveyer belt (3) setting in feeding inlet (11) and
Between discharge port (12);
Bar (4), the first CCD camera (5), the second CCD camera (6) and scanning fluorescent tube (8) are lifted in PLC system control;First CCD phase
Machine (51) and the second CCD camera (61) connect image pick-up card, and the lens image to be checked of acquisition is transmitted to meter by image pick-up card
Image analysis software on calculation machine;
On from feeding inlet (11) to the material transmission direction of discharge port (12), it is placed in the first conveyer belt simultaneously with a piece of eyeglass to be checked
(2) it and on the second conveyer belt (3), is driven down by stepper motor and makees mobile the first conveyer belt (2) of synchronous circulating and the second transmission
Band (3) transmits jointly;
Lifting bar (4) is hollow tube, lifts and is fixed with Universal vacuum chuck at the top of bar (4);It lifts bar (4) and passes through negative-pressure adsorption
It will be horizontally fixed on Universal vacuum chuck, will be held up straight up to object plate (9), and can drive to be checked to object plate (9)
Eyeglass (9) makees banking motion;In unadsorbed fixation when object plate, the sucker face of Universal vacuum chuck keeps horizontal and with first
The transmission plane positioned at upper end of conveyer belt (2) and the second conveyer belt (3) flushes;
First CCD camera (51) and the second CCD camera (61) are respectively arranged at the two sides that scanning fluorescent tube (8) moves back and forth direction,
And it is located on the center line to object plate (9);Bar (4) is being lifted by level fixation after object plate (9) is held up straight up,
The camera lens of first CCD camera (51) and the camera lens of the second CCD camera (61) are respectively facing to object plate (9), and respectively with it is to be checked
Camera lens (9) forms angle;It is driven when object plate (9) makees banking motion lifting the Universal vacuum chuck at the top of bar (4), first
Any one in the camera lens of CCD camera (51) and the camera lens of the second CCD camera (61) can be perpendicular to object plate (9).
2. device for dynamically detecting according to claim 1, which is characterized in that lifting bar (4) for the to be checked of level fixation
After eyeglass (9) is held up straight up, the camera lens of the first CCD camera (51) and the camera lens of the second CCD camera (61) intersect to be checked
The center of eyeglass (9), and angle is formed with camera lens to be checked (9) respectively;Lift Universal vacuum chuck at the top of bar (4) drive to
When object plate (9) makees banking motion, any one in the camera lens of the first CCD camera (51) and the camera lens of the second CCD camera (61)
It can be perpendicular to the center to object plate (9).
3. device for dynamically detecting according to claim 2, which is characterized in that lifting bar (4) for the to be checked of level fixation
After eyeglass (9) is held up straight up, the camera lens of the camera lens of the first CCD camera (51) and the second CCD camera (61) respectively with it is to be checked
Eyeglass (9) shape is in angle of 45 degrees.
4. device for dynamically detecting according to claim 1, which is characterized in that scanning fluorescent tube (8) moves back and forth direction and object
Expect that direction of transfer is parallel, the first CCD camera (51) and the second CCD camera (61) are symmetrically distributed in the center line to object plate (9)
On.
5. device for dynamically detecting according to claim 1, which is characterized in that scanning fluorescent tube dynamic sliding rail (7) setting is being held in the palm
The surface of bar (4) is lifted, scanning fluorescent tube dynamic sliding rail (7) includes the first elliptical ring (71) and the second elliptical ring (72), and first is ellipse
Annulus (71) and the second elliptical ring (72) are respectively along the top surface inner wall that material transmission direction is fixed on camera bellows (1) vertically, and first
Elliptical ring (71) and the second elliptical ring (72) horizontal interval and end face;The both ends of scanning fluorescent tube (8) are separately fixed at first
In elliptical ring (71) and the second elliptical ring (72), reciprocatingly slide along the first elliptical ring (71) and the second elliptical ring (72).
6. a kind of dynamic testing method for any one of the claim 1-5 device for dynamically detecting, which is characterized in that step
Including:
I. spaced two conveyer belts synchronous loopy moving under stepper motor drive on material transmission direction, is placed simultaneously
On two conveyer belts when object plate (9) is moved to the top for lifting bar (4) with two conveyer belts, the pan feeding of camera bellows (1)
Mouth (11) and discharge port (12) are closed, and bar (4), scanning light source (8), the first CCD camera (51) and second are lifted in PLC system control
CCD camera (61) starts simultaneously at work;
Under the control of II.PLC system, lifts bar (4) and held up what its top level was fixed straight up to object plate (9), scanned
Light source (8) starting shines and moves back and forth scanning along the whole process of scanning fluorescent tube dynamic sliding rail (7), when the luminous scanning light of starting
When source (8) is located at the both ends of scanning fluorescent tube dynamic sliding rail (7), respectively makees a banking motion to object plate (9), tilt to
It is located at the camera lens or the 2nd CCD phase of ipsilateral the first CCD camera (51) with end where scanning light source (8) to object plate (9)
The camera lens of machine (61) is perpendicular, and by with first CCD camera (51) or second CCD camera perpendicular to object plate (9)
(61) lens image to be checked in the case of different location, different reflection angles, different highlight regions is acquired, and through image pick-up card
The image analysis software being transmitted on computer;
When scanning light source (8) move back and forth in scanning process along the whole process of scanning fluorescent tube dynamic sliding rail (7), to object plate (9)
Keep horizontal positioned state;It is respectively arranged at scanning light source (8) and moves back and forth direction two sides, and be located in object plate (9)
Heart line simultaneously acquires different positions in the first CCD camera (51) and the second CCD camera (61) of angle to object plate (9) in real time respectively
It sets, the lens image to be checked in the case of different reflection angles, different highlight regions, and is sent on computer through image pick-up card
Image analysis software;
III. image analysis software successively uses Gassian low-pass filter algorithm, Laplace operator, binaryzation and Hough transformation
Vision algorithm carries out noise reduction, filtering, binaryzation and Hough transformation processing, quickly, precisely, steadily extracts to object plate (9)
It scratches;
When object plate has scuffing, it is distributed to the first conveyer belt (2) and the second conveyer belt (3) wherein to object plate (9)
One of on, by discharge port (12) spread out of;When object plate is without scratching, be distributed to object plate (9) to the first conveyer belt (2) and
On another of second conveyer belt (3), spread out of by discharge port (12).
7. dynamic testing method according to claim 6, which is characterized in that in step II, when the luminous scanning light of starting
When source (8) is located at the both ends of scanning fluorescent tube dynamic sliding rail (7), end where with scanning light source (8) is located at ipsilateral the
The camera lens of one CCD camera (51) or the camera lens of the second CCD camera (61) are perpendicular to the center to object plate (9) after inclination;
When scanning light source (8) along scanning fluorescent tube dynamic sliding rail (7) whole process move back and forth in scanning process, the first CCD camera (51)
Camera lens and the camera lens of the second CCD camera (61) intersect at the center to object plate (9), and formed respectively and to object plate (9)
Angle.
8. dynamic testing method according to claim 6 or 7, which is characterized in that in step II, when scanning light source (8) edge
The whole process of scanning fluorescent tube dynamic sliding rail (7) moves back and forth in scanning process, the first CCD camera (51) and the second CCD camera
(61) respectively with to object plate (9) shape in angle of 45 degrees.
9. dynamic testing method according to claim 6, which is characterized in that in step II, under PLC system control, lift
Bar (4) will be horizontally fixed on the Universal vacuum chuck for lifting bar (4) top by negative-pressure adsorption to object plate (9).
10. dynamic testing method according to claim 6, which is characterized in that in step II, scanning light source (8) start bit
In the end of scanning fluorescent tube dynamic sliding rail (7), under PLC system control, scanning light source (8) starting is luminous and dynamic along scanning fluorescent tube
Starting point to the clearing end of state sliding rail (7) moves back and forth scanning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810455914.5A CN108918543B (en) | 2018-05-14 | 2018-05-14 | Dynamic detection device and method for mirror surface scratch |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810455914.5A CN108918543B (en) | 2018-05-14 | 2018-05-14 | Dynamic detection device and method for mirror surface scratch |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108918543A true CN108918543A (en) | 2018-11-30 |
CN108918543B CN108918543B (en) | 2021-03-23 |
Family
ID=64402448
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810455914.5A Active CN108918543B (en) | 2018-05-14 | 2018-05-14 | Dynamic detection device and method for mirror surface scratch |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108918543B (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110044919A (en) * | 2019-04-23 | 2019-07-23 | 上海工程技术大学 | A kind of detection device and its detection method for mirror surfaces scratch |
CN110177268A (en) * | 2019-05-31 | 2019-08-27 | 苏州五方光电材料有限公司 | A kind of camera eyeglass characterization processes |
CN110779920A (en) * | 2019-10-30 | 2020-02-11 | 中国计量大学 | Pearl detection device |
CN110779474A (en) * | 2019-10-16 | 2020-02-11 | 徐州市铜山区嘉量计量检测创新中心 | Workpiece abrasion detection multipoint control positioning closed type light beam detection equipment |
KR102147470B1 (en) * | 2020-02-20 | 2020-08-24 | 정규성 | Vision inspection device |
CN111650212A (en) * | 2020-07-03 | 2020-09-11 | 东北大学 | Metal surface normal direction three-dimensional information acquisition method based on linear array camera three-dimensional vision |
CN112093477A (en) * | 2020-06-16 | 2020-12-18 | 丹阳市精通眼镜技术创新服务中心有限公司 | Automatic feeding device for optical lenses |
WO2020252879A1 (en) * | 2019-06-19 | 2020-12-24 | 罗博特科智能科技股份有限公司 | Mobile phone screen defect detection system based on ultrasonic spray |
CN112258448A (en) * | 2020-09-15 | 2021-01-22 | 郑州金惠计算机系统工程有限公司 | Fine scratch detection method, fine scratch detection device, electronic equipment and computer-readable storage medium |
CN112557400A (en) * | 2020-11-30 | 2021-03-26 | 电子科技大学 | System and method for detecting surface defect contour of lens of satellite telescope |
CN113125449A (en) * | 2021-04-20 | 2021-07-16 | 江苏善果缘智能科技有限公司 | Scanning device for detecting surface of integrated product and assembling method thereof |
CN114055764A (en) * | 2022-01-17 | 2022-02-18 | 深圳市利和兴股份有限公司 | Pre-detection equipment for OLED flexible screen laminating |
CN114113131A (en) * | 2021-12-03 | 2022-03-01 | 中科计算技术西部研究院 | Device and method for detecting scratch defects of reflective lens |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004294088A (en) * | 2003-03-25 | 2004-10-21 | Dainippon Screen Mfg Co Ltd | Image acquiring device and image acquisition method |
CN202735263U (en) * | 2012-08-23 | 2013-02-13 | 深圳市纳研科技有限公司 | Device for detecting minor defects of array graphs by machine vision |
CN204924983U (en) * | 2015-07-20 | 2015-12-30 | 丹阳市精通眼镜技术创新服务中心有限公司 | Lens defect automatic checkout device of grating modulation |
CN205844213U (en) * | 2016-06-28 | 2016-12-28 | 华南理工大学 | A kind of curved surface automatic defect detecting device |
CN106353336A (en) * | 2016-10-27 | 2017-01-25 | 哈尔滨理工大学 | Lens coating automatic detection system |
CN207280968U (en) * | 2017-08-02 | 2018-04-27 | 深圳市迪姆自动化有限公司 | Full-automatic glass surface blemish detection machine |
-
2018
- 2018-05-14 CN CN201810455914.5A patent/CN108918543B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004294088A (en) * | 2003-03-25 | 2004-10-21 | Dainippon Screen Mfg Co Ltd | Image acquiring device and image acquisition method |
CN202735263U (en) * | 2012-08-23 | 2013-02-13 | 深圳市纳研科技有限公司 | Device for detecting minor defects of array graphs by machine vision |
CN204924983U (en) * | 2015-07-20 | 2015-12-30 | 丹阳市精通眼镜技术创新服务中心有限公司 | Lens defect automatic checkout device of grating modulation |
CN205844213U (en) * | 2016-06-28 | 2016-12-28 | 华南理工大学 | A kind of curved surface automatic defect detecting device |
CN106353336A (en) * | 2016-10-27 | 2017-01-25 | 哈尔滨理工大学 | Lens coating automatic detection system |
CN207280968U (en) * | 2017-08-02 | 2018-04-27 | 深圳市迪姆自动化有限公司 | Full-automatic glass surface blemish detection machine |
Non-Patent Citations (2)
Title |
---|
李青 等: "机器视觉技术在玻璃基板缺陷检测设备中的应用", 《玻璃与搪瓷》 * |
杨杰 等: "机器视觉在钢化玻璃缺陷检测中的应用研究", 《计算机技术与发展》 * |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110044919A (en) * | 2019-04-23 | 2019-07-23 | 上海工程技术大学 | A kind of detection device and its detection method for mirror surfaces scratch |
CN110177268A (en) * | 2019-05-31 | 2019-08-27 | 苏州五方光电材料有限公司 | A kind of camera eyeglass characterization processes |
WO2020252879A1 (en) * | 2019-06-19 | 2020-12-24 | 罗博特科智能科技股份有限公司 | Mobile phone screen defect detection system based on ultrasonic spray |
CN110779474B (en) * | 2019-10-16 | 2021-06-01 | 徐州市铜山区嘉量计量检测创新中心 | Workpiece abrasion detection multipoint control positioning closed type light beam detection equipment |
CN110779474A (en) * | 2019-10-16 | 2020-02-11 | 徐州市铜山区嘉量计量检测创新中心 | Workpiece abrasion detection multipoint control positioning closed type light beam detection equipment |
CN110779920A (en) * | 2019-10-30 | 2020-02-11 | 中国计量大学 | Pearl detection device |
KR102147470B1 (en) * | 2020-02-20 | 2020-08-24 | 정규성 | Vision inspection device |
CN112093477A (en) * | 2020-06-16 | 2020-12-18 | 丹阳市精通眼镜技术创新服务中心有限公司 | Automatic feeding device for optical lenses |
CN111650212A (en) * | 2020-07-03 | 2020-09-11 | 东北大学 | Metal surface normal direction three-dimensional information acquisition method based on linear array camera three-dimensional vision |
CN112258448A (en) * | 2020-09-15 | 2021-01-22 | 郑州金惠计算机系统工程有限公司 | Fine scratch detection method, fine scratch detection device, electronic equipment and computer-readable storage medium |
CN112557400A (en) * | 2020-11-30 | 2021-03-26 | 电子科技大学 | System and method for detecting surface defect contour of lens of satellite telescope |
CN113125449A (en) * | 2021-04-20 | 2021-07-16 | 江苏善果缘智能科技有限公司 | Scanning device for detecting surface of integrated product and assembling method thereof |
CN114113131A (en) * | 2021-12-03 | 2022-03-01 | 中科计算技术西部研究院 | Device and method for detecting scratch defects of reflective lens |
CN114113131B (en) * | 2021-12-03 | 2024-04-30 | 中科计算技术西部研究院 | Device and method for detecting scratch defects of reflecting lens |
CN114055764A (en) * | 2022-01-17 | 2022-02-18 | 深圳市利和兴股份有限公司 | Pre-detection equipment for OLED flexible screen laminating |
CN114055764B (en) * | 2022-01-17 | 2022-04-29 | 深圳市利和兴股份有限公司 | Pre-detection equipment for OLED flexible screen laminating |
Also Published As
Publication number | Publication date |
---|---|
CN108918543B (en) | 2021-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108918543A (en) | A kind of device for dynamically detecting and method of mirror surfaces scuffing | |
CN106251352B (en) | A kind of cover defect inspection method based on image procossing | |
CN105044114B (en) | A kind of electrolytic capacitor appearance packaging defect image detecting system and method | |
CN108765416A (en) | PCB surface defect inspection method and device based on fast geometric alignment | |
CN105784722B (en) | On a kind of assembly line in medicinal liquid bottle visible foreign matters detection method and system | |
CN202277385U (en) | Automatic identifying and counting system of surgical instrument | |
CN107101598B (en) | Automatic detection method and device for concentricity quality of piezoelectric ceramic silver sheet | |
CN208679851U (en) | A kind of articles sorting device based on bar code identification | |
CN107290347B (en) | Automatic honeycomb carrier defect detection method | |
CN207675660U (en) | A kind of magnet ring surface defect detection apparatus | |
CN208207914U (en) | PCB surface defect detecting device based on fast geometric alignment | |
CN109342373A (en) | A kind of eyeglass detection device for assembly line | |
CN110108712A (en) | Multifunctional visual sense defect detecting system | |
Yang et al. | An automatic aperture detection system for LED cup based on machine vision | |
CN112304954A (en) | Part surface defect detection method based on line laser scanning and machine vision | |
CN105835507A (en) | Method for attaching mobile phone cover lens to liquid crystal display | |
CN102141379A (en) | Novel glass bottle and jar detection device | |
CN109949362A (en) | A kind of material visible detection method | |
CN114820475B (en) | Edge identification method and system, wafer processing device and method for determining concentric state of wafer and processing table | |
CN111222445A (en) | Straw detection system and method thereof | |
CN204422435U (en) | Camera module optical filter gluing pick-up unit | |
CN107891012B (en) | Pearl size and circularity sorting device based on equivalent algorithm | |
CN109827974A (en) | A kind of resin optical filter film splits detection device and detection method | |
CN106000903B (en) | A kind of non-contact detection system and method for being used to detect loom cloth gripper edge gap | |
CN108838099A (en) | Safety pin badge Defect Detection system and method based on machine vision |
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 |