CN110487821A - A kind of clear sheet defect detecting device and its detection method based on machine vision - Google Patents
A kind of clear sheet defect detecting device and its detection method based on machine vision Download PDFInfo
- Publication number
- CN110487821A CN110487821A CN201910818712.7A CN201910818712A CN110487821A CN 110487821 A CN110487821 A CN 110487821A CN 201910818712 A CN201910818712 A CN 201910818712A CN 110487821 A CN110487821 A CN 110487821A
- Authority
- CN
- China
- Prior art keywords
- industrial
- clear sheet
- camera
- detecting device
- ball
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 51
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 239000000463 material Substances 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 230000003287 optical effect Effects 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims 1
- 239000012780 transparent material Substances 0.000 abstract description 9
- 238000000034 method Methods 0.000 abstract description 6
- 238000007689 inspection Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 abstract 1
- RZVAJINKPMORJF-UHFFFAOYSA-N Acetaminophen Chemical compound CC(=O)NC1=CC=C(O)C=C1 RZVAJINKPMORJF-UHFFFAOYSA-N 0.000 description 6
- 238000005498 polishing Methods 0.000 description 6
- 239000005297 pyrex Substances 0.000 description 6
- 239000011521 glass Substances 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 229910017435 S2 In Inorganic materials 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000009738 saturating Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/958—Inspecting transparent materials or objects, e.g. windscreens
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
A kind of clear sheet defect detecting device and its detection method based on machine vision belongs to the defect intelligent testing technology field of transparent material, solves detection clear sheet internal flaw and surface defects detection erroneous detection, missing inspection and low efficiency technical problem.Solution are as follows: the present apparatus includes the detection system of industrial camera, industrial lens, industrial light source and stepper motor composition, detection system is placed in camera bellows, light source is mounted on conveyer belt and measured material side, and industrial camera is mounted on measured material upper vertical position and is shot.Detection system using computer and industrial camera realizes ethernet communication to obtain image, and using " first binaryzation noise reduction, then gaussian filtering, after again binaryzation enhance " method image is handled, obtain profile information.In such a way that shooting graduated scale is compared, flaw size information and defect area are calculated.The present invention can save manually, reduce cost, improve Detection accuracy, and size detection error range is 0.5-5.0%.
Description
Technical field
The invention belongs to the defect intelligent testing technology fields of transparent material, and what is involved is a kind of based on the saturating of machine vision
Isotropic disk material defect detecting device and its detection method, and in particular to a kind of based on machine vision, polishing technology and image procossing
Transparent glass material defect inspection method.
Background technique
At this stage, the plate transparent material based on glass has obtained more and more extensive application as raw material.In order to
So that transparent material is more suitable for various working environments, material manufacturing enterprise turn to produce a variety of different colours, different light transmittances with
And the plate of configuration of surface, the probability of fault in material generation is thus considerably increased, common defect has surface scratch, inside to split
Line, gravel and bubble.The defect generated during producing transparent material plate only rely on human eye be difficult to defect size into
The judgement of row accurately and quickly is easy to produce more erroneous detections, missing inspection and inefficient phenomenon using traditional artificial detection method.
It is particularly important to design a kind of efficient automatic defect detection method.
Summary of the invention
In order to overcome the shortcomings in the prior art, solve detection clear sheet internal flaw and surface defects detection erroneous detection,
Missing inspection and low efficiency technical problem, the present invention provide a kind of clear sheet defect detecting device based on machine vision and its detection
Method is used for machine vision on-line detecting system.Realize that real-time detection plate is transparent by Image Acquisition and image processing techniques
The internal flaw and surface defect of material, and will test result information and be supplied to master controller, for production management system provide according to
According to.The common deficiency of transparent material mainly has: surface scratch, underbead crack, gravel and bubble, and material production division is according to different
Defect standard judge product qualification rate, to meet different use demands.
The present invention is achieved by the following technical programs.
A kind of clear sheet defect detecting device based on machine vision, it includes industrial camera, industrial lens, industrial light
Source, stepper motor and camera bellows, in which:
The bottom of the camera bellows is respectively arranged with inlet port and outlet port according to the conveying direction of conveyer belt, and conveyer belt runs through camera bellows
Inlet port and outlet port extend to the outside of camera bellows, clear sheet to be measured is placed on conveyer belt；
In the camera bellows:
Door shape hanger is provided with above conveyer belt, the industry light source is set to the root of door shape hanger column,
Industrial light source is set as linear light source, and beam direction is parallel with the surface of clear sheet to be measured, and light beam is from the side of clear sheet to be measured
Face is injected；
One end on hanger positioned at crossbeam, which is provided with, moves horizontally ball-screw slide unit, is provided with and moves horizontally ball on crossbeam
The horizontal screw lead that screw slide matches is provided on horizontal screw lead and vertically moves ball-screw slid platform base, moves horizontally rolling
Be provided on ballscrew slide unit for drive horizontal screw lead rotate move horizontally stepper motor, move horizontally stepper motor and pass through
It moves horizontally ball-screw slide unit and horizontal screw lead driving vertically moves ball-screw slid platform base and moves back and forth along horizontal screw lead；
It vertically moves to be equipped in ball-screw slid platform base and vertically moves ball-screw slide unit, vertically move and set on ball-screw slide unit
It is equipped with and vertically moves stepper motor, the upper end of down-feed screw, which is installed on, to be vertically moved on ball-screw slide unit, under down-feed screw
End is fixedly installed with industrial camera, and industrial lens are set to the lower section of industrial camera, vertically moves stepper motor by vertically moving
Dynamic ball-screw slide unit and down-feed screw driving industrial camera move back and forth along the vertical direction.
Further, the material of the camera bellows is black POM plastic, and the inner surface frosted of camera bellows is handled.
Further, the industrial light source is set as linear light source, and the illumination width of industrial light source is greater than clear sheet to be measured
Thickness.
Further, the optical signal of acquisition is converted to electric signal by the industrial camera, and industrial camera will by signal wire
Electric signal inputs in computer, and computer controls stepper motor, conveyer belt and industrial camera work by control cabinet or stops.
Further, the industrial camera selects black and white camera, and pixel coverage is 5,000,000-2,000 ten thousand；Industrial lens focal length
Range is 9mm-25mm.
Further, the object distance range of the industrial camera is 100mm-1000mm, and field range is 20-1700mm, is exposed
Light time range 3ms-5ms.
Further, the conveyer belt is black.
A kind of detection method of the clear sheet defect detecting device based on machine vision, comprising the following steps:
S1, after installing the present apparatus, pass through the position for moving horizontally stepper motor with vertically moving stepper motor adjustment industrial camera
It sets, industrial camera is made to be located at the top of conveyer belt；The focal length of debugging and industrial lens keeps conveyer belt clear in industrial lens
Clear imaging；
S2, clear sheet to be measured are placed on the conveyor belt, are delivered in camera bellows by the feed inlet of camera bellows, are opened industrial light source, are made
The light beam of industrial light source is injected from the side of clear sheet to be measured, occur when meeting the microdefect in clear sheet to be measured refraction or
Reflection, reflects upwards or the optical information of reflection is received by industrial camera, reflects downwards or the light of reflection is absorbed by conveyer belt；
Digitized image is transmitted to by computer by gigabit Ethernet after S3, industrial camera capture, computer is by gained image
Image procossing and output test result are carried out, wherein flaw size measurement is using the shooting graduated scale in same field of view and and defect
The mode that image compares.
Further, microdefect is surface scratch, underbead crack, gravel and bubble, the step in the step S2
In S3 the step of image procossing are as follows: first binaryzation noise reduction, then gaussian filtering, then binaryzation enhancing.
Further, binaryzation noise reduction threshold value range of choice is 48, and low-pass Gaussian filter selects 15 × 15 filter
Template, it is 50 that binaryzation, which enhances threshold value range of choice,.
Compared with prior art the invention has the benefit that
Currently, most effective most common transparent material defect inspection method is irradiated using material bottom straight line fluorescent tube, manually
The method observed and made marks above, there is false detection rate, omission factor is higher, detection is inaccurate, and labor intensity of workers is big etc.
Problem.The present invention can save manually, reduce cost, improve Detection accuracy, guarantee product quality, improve efficiency, produce
Good economic benefit and social benefit.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the clear sheet defect detecting device based on machine vision；
Fig. 2 is polishing schematic diagram in side of the present invention；
Fig. 3 be acquired after the polishing of side in embodiment 1 there are the images of surface scratch defect；
Fig. 4 is that there are the images of surface scratch defect for transparent Pyrex plate after image procossing by Fig. 3；
Fig. 5 be acquired after the polishing of side in embodiment 1 there are the images of underbead crack defect；
Fig. 6 is that there are the images of underbead crack defect for transparent Pyrex plate after image procossing by Fig. 5；
Fig. 7 be acquired after the polishing of side in embodiment 2 there are the images of gravel defect；
Fig. 8 is that there are the images of gravel defect for clear PE O plastic plate after image procossing by Fig. 7；
Fig. 9 be acquired after the polishing of side in embodiment 3 there are the images of air blister defect；
Figure 10 is that there are the images of air blister defect for transparent PYREX glass plate after image procossing by Fig. 9.
In figure, 1. industrial cameras, 2. industrial strip sources, the fixation bracket of 3. industrial cameras and strip source, 4. is horizontal
Mobile stepper motor, 5. vertically move stepper motor, and 6. move horizontally ball-screw slide unit, and 7., which vertically move ball-screw, slides
Platform, 8. computers, 9. control cabinets, 10. black conveyer belts, 11. transparent materials to be detected, 12. camera bellows, 13. industrial lens.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.
Embodiment 1
A kind of clear sheet defect detecting device based on machine vision as depicted in figs. 1 and 2, it includes industrial camera 1, work
Industry camera lens 13, industrial light source 2, stepper motor and camera bellows 12, in which:
The bottom of the camera bellows 12 is respectively arranged with inlet port and outlet port according to the conveying direction of conveyer belt 10, and conveyer belt 10 passes through
The inlet port and outlet port for wearing camera bellows 12 extend to the outside of camera bellows 12, and clear sheet 11 to be measured is placed on conveyer belt 10；
In the camera bellows 12:
The top of conveyer belt 10 is provided with door shape hanger 3, the industry light source 2 is set to 3 column of door shape hanger
Root, industrial light source 2 are set as linear light source, and beam direction is parallel with the surface of clear sheet 11 to be measured, and light beam is to be measured transparent
The side of plate 11 is injected；
One end on hanger 3 positioned at crossbeam, which is provided with, moves horizontally ball-screw slide unit 6, is provided with and moves horizontally rolling on crossbeam
The horizontal screw lead that ballscrew slide unit 6 matches is provided on horizontal screw lead and vertically moves ball-screw slid platform base, moves horizontally
Be provided on ball-screw slide unit 6 for drive horizontal screw lead rotate move horizontally stepper motor 4, move horizontally stepper motor
4 by moving horizontally ball-screw slide unit 6 and horizontal screw lead driving, to vertically move ball-screw slid platform base past along horizontal screw lead
Multiple movement；It vertically moves to be equipped in ball-screw slid platform base and vertically moves ball-screw slide unit 7, vertically move ball-screw
It is provided on slide unit 7 and vertically moves stepper motor 5, the upper end of down-feed screw, which is installed on, to be vertically moved on ball-screw slide unit 5, is hung down
The lower end of raw silk rings thick stick is fixedly installed with industrial camera 1, and industrial lens 13 are set to the lower section of industrial camera 1, vertically move stepping
Motor 5 drives industrial camera 1 to move back and forth along the vertical direction by vertically moving ball-screw slide unit 7 and down-feed screw.
Further, the material of the camera bellows 12 is black POM plastic, and the inner surface of camera bellows 12 prevents anti-through frosted processing
It penetrates and generates light interference, camera bellows can shield extraneous natural light interference.
Further, the industrial light source 2 is set as linear light source, and the illumination width of industrial light source 2 is greater than transparent panel to be measured
The thickness of material 11.
Further, the optical signal of acquisition is converted to electric signal by the industrial camera 1, and industrial camera 1 passes through signal wire
By electric signal input computer 8 in, computer 8 by control cabinet 9 control stepper motor, conveyer belt and industrial camera work or
Stop.Anaconda software is installed on computer 8, supports Python programming, can realize and communicate with industrial camera 1,
The image and carry out image procossing that industrial camera 1 transmits are obtained, realizes the detection to 11 defect of clear sheet to be measured.
Further, the industrial camera 1 selects black and white camera, and pixel coverage is 5,000,000-2,000 ten thousand；Industrial lens 13
Focal range is 9mm-25mm.
Further, the object distance range of the industrial camera 1 is 100mm-1000mm, and field range is 20-1700mm, is exposed
Light time range 3ms-5ms.
Further, the conveyer belt 10 is black.
A kind of detection method of the clear sheet defect detecting device based on machine vision, comprising the following steps:
S1, after installing the present apparatus, industrial camera 1 is adjusted by moving horizontally stepper motor 4 and vertically moving stepper motor 5
Position makes industrial camera 1 be located at the top of conveyer belt 10；The focal length of debugging and industrial lens 13, enables conveyer belt 10 in work
Blur-free imaging in industry camera lens 13；
S2, clear sheet to be measured 11 are placed on conveyer belt 10, are delivered in camera bellows 12 by the feed inlet of camera bellows 12, and industry is opened
Light source 2 injects the light beam of industrial light source 2 from the side of clear sheet 11 to be measured, meets microcosmic scarce in clear sheet 11 to be measured
Refraction or reflection occur when falling into, scratch, underbead crack, gravel, the air blister defect in glass plate prevent the directional light from side
Line is directed through transparent material plate, cause reach Defect Edge at light to other directions reflect or reflect, upwards refraction or
The optical information of reflection is received by industrial camera 1, reflects downwards or the light of reflection is absorbed by conveyer belt 10, to avoid to upward
Normal optical signal generate interference so that Defect Edge image is with regard to relatively sharp, defect profile is more highlighted；
Digitized image is transmitted to by computer 8 by gigabit Ethernet after S3,1 capture of industrial camera, computer 8 schemes gained
As carrying out image procossing and output test result, wherein flaw size measurement using shot in same field of view graduated scale and with lack
The mode that sunken image compares.
Further, microdefect is surface scratch, underbead crack, gravel and bubble, the step in the step S2
In S3 the step of image procossing are as follows: first binaryzation noise reduction, then gaussian filtering, then binaryzation enhancing, make to show tested measures and monitor the growth of standing timber
Profile information of the material defect profile information closest to original image.
Further, binaryzation noise reduction threshold value range of choice is 48, and low-pass Gaussian filter selects 15 × 15 filter
Template, it is 50 that binaryzation, which enhances threshold value range of choice,.
In the present embodiment 1, device provided by the invention and detection method are applied to the thick transparent Pyrex plate table of 3mm
Face scratch, underbead crack, gravel and bubble detection, using the black and white industrial camera of 8,900,000 pixels, selecting focal length is 12.5mm's
The image resolution ratio of industrial lens, object distance 167.74mm, visual field 189.63mm × 100mm, time for exposure 4.4ms, acquisition is
4096×2160.Binaryzation noise reduction threshold value range of choice is 48, the filter template of low-pass Gaussian filter selection 15 × 15, two
It is 50 that value, which enhances threshold value range of choice,.
Measure Pyrex surface scratch width 5.0mm, relative error 3.9%；Scratch length 35.5mm, relative error
3.2%；Bubble width 3.0mm, relative error 4.1%；Bubble height 2.5mm, relative error 3.0%；Underbead crack width 1.7mm,
Relative error 2.1%；Underbead crack length 25.1mm, relative error 2.6%；Gravel width 5.0mm, relative error 0.9%；Gravel
Height 4.9mm, relative error 1.1%.
Embodiment 2
A kind of clear sheet defect detecting device structure based on machine vision is same as Example 1 in the present embodiment 2, herein not
It repeats.
In the present embodiment 2, device provided by the invention and detection method are applied to 4mm thickness clear PE O plastic plate table
Face scratch, underbead crack, gravel and bubble detection, using the black and white industrial camera of 8,900,000 pixels, selecting focal length is the work of 9mm
Industry camera lens, object distance 241.55mm, visual field 379.27mm*200mm, time for exposure 4.6ms, the image resolution ratio of acquisition is 4096 ×
2160。
Binaryzation noise reduction threshold value range of choice is 46, and low-pass Gaussian filter selects 15 × 15 filter template, two-value
Changing enhancing threshold value range of choice is 49.
Measure scratch width 6.5mm, relative error 3.2%；Scratch length 42.7mm, relative error 4.1%；Bubble width
3.5mm, relative error 3.3%；Bubble height 2.8mm, relative error 3.1%；Underbead crack width 1.5mm, relative error 3.1%；
Underbead crack length 34.7mm, relative error 1.6%；Gravel width 5.5mm, relative error 0.7%；Gravel height 4.8mm, relatively
Error 0.8%.
Embodiment 3
A kind of clear sheet defect detecting device structure based on machine vision is same as Example 1 in the present embodiment 3, herein not
It repeats.
In the present embodiment 3, device provided by the invention and detection method are applied to the thick transparent PYREX glass plate of 1mm
The detection of stomata, surface scratch, underbead crack, gravel and bubble selects focal length using the black and white industrial camera of 8,900,000 pixels
For the industrial lens of 25mm, object distance 268.38mm, visual field 151.7mm*80mm, time for exposure 4.2ms, the image resolution ratio of acquisition
It is 4096 × 2160.Binaryzation noise reduction threshold value range of choice is 47, and low-pass Gaussian filter selects 15 × 15 filter template,
It is 51 that binaryzation, which enhances threshold value range of choice,.
Measure stomatal width 6.0mm, relative error 2.4%；Scratch length 22.3mm, relative error 1.2%；Bubble width
4.00mm, relative error 2.1%；Bubble height 3.2mm, relative error 3.3%；Underbead crack width 1.0mm, relative error
3.1%；Underbead crack length 30.7mm, relative error 3.9%；Gravel width 4.1mm, relative error 2.9%；Gravel height
4.4mm, relative error 2.2%.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
It is familiar with those skilled in the art in the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of, should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of clear sheet defect detecting device based on machine vision, it include industrial camera (1), industrial lens (13),
Industrial light source (2), stepper motor and camera bellows (12), it is characterised in that:
The bottom of the camera bellows (12) is respectively arranged with inlet port and outlet port, conveyer belt according to the conveying direction of conveyer belt (10)
(10) inlet port and outlet port through camera bellows (12) extend to the outside of camera bellows (12), and clear sheet (11) to be measured is placed in defeated
It send on band (10)；
In the camera bellows (12):
It is provided with above conveyer belt (10) door shape hanger (3), the industry light source (2) is set to door shape hanger
(3) root of column, industrial light source (2) are set as linear light source, and beam direction is parallel with the surface of clear sheet to be measured (11), light
Beam is injected from the side of clear sheet to be measured (11)；
One end on hanger (3) positioned at crossbeam, which is provided with, to be moved horizontally ball-screw slide unit (6), is provided on crossbeam and is moved with horizontal
The horizontal screw lead that ball-screw slide unit (6) match is moved, is provided on horizontal screw lead and vertically moves ball-screw slid platform base, water
It translates and is provided on dynamic ball-screw slide unit (6) for driving moving horizontally stepper motor (4) for horizontal screw lead rotation, level is moved
Dynamic stepper motor (4) vertically move ball-screw slide unit bottom by moving horizontally ball-screw slide unit (6) and horizontal screw lead driving
Seat is moved back and forth along horizontal screw lead；It vertically moves to be equipped in ball-screw slid platform base and vertically moves ball-screw slide unit (7),
It vertically moves to be provided on ball-screw slide unit (7) and vertically moves stepper motor (5), the upper end of down-feed screw is installed on vertical shifting
On dynamic ball-screw slide unit (5), the lower end of down-feed screw is fixedly installed with industrial camera (1), and industrial lens (13) are set to work
The lower section of industry camera (1) vertically moves stepper motor (5) and is driven by vertically moving ball-screw slide unit (7) and down-feed screw
Industrial camera (1) moves back and forth along the vertical direction.
2. a kind of clear sheet defect detecting device based on machine vision according to claim 1, it is characterised in that: institute
The material for stating camera bellows (12) is black POM plastic, and the inner surface frosted of camera bellows (12) is handled.
3. a kind of clear sheet defect detecting device based on machine vision according to claim 1, it is characterised in that: institute
It states industrial light source (2) and is set as linear light source, the illumination width of industrial light source (2) is greater than the thickness of clear sheet to be measured (11).
4. a kind of clear sheet defect detecting device based on machine vision according to claim 1, it is characterised in that: institute
It states industrial camera (1) and the optical signal of acquisition is converted into electric signal, electric signal is inputted by signal wire and calculated by industrial camera (1)
In machine.
5. a kind of clear sheet defect detecting device based on machine vision according to claim 1, it is characterised in that: institute
It states industrial camera (1) and selects black and white camera, pixel coverage is 5,000,000-2,000 ten thousand；Industrial lens (13) focal range is 9mm-
25mm。
6. a kind of clear sheet defect detecting device based on machine vision according to claim 5, it is characterised in that: institute
The object distance range for stating industrial camera (1) is 100mm-1000mm, and field range is 20-1700mm, exposure time range 3ms-
5ms。
7. a kind of clear sheet defect detecting device based on machine vision according to claim 1, it is characterised in that: institute
Stating conveyer belt (10) is black.
8. a kind of detection method of the clear sheet defect detecting device based on machine vision as described in claim 1, special
Sign be the following steps are included:
S1, after installing the present apparatus, industrial phase is adjusted by moving horizontally stepper motor (4) and vertically moving stepper motor (5)
The position of machine (1) makes industrial camera (1) be located at the top of conveyer belt (10)；The focal length of debugging and industrial lens (13), makes to convey
Band (10) can in industrial lens (13) blur-free imaging；
S2, clear sheet to be measured (11) are placed on conveyer belt (10), are delivered in camera bellows (12) by the feed inlet of camera bellows (12),
Industrial light source ((2)) is opened, injects the light beam of industrial light source (2) from the side of clear sheet to be measured (11), is met to be measured transparent
Refraction or reflection occur when microdefect in plate (11), reflects upwards or the optical information of reflection is received by industrial camera (1),
It reflects downwards or the light of reflection is absorbed by conveyer belt (10)；
Digitized image is transmitted to computer (8) by gigabit Ethernet after S3, industrial camera (1) capture, computer (8) will
Gained image carries out image procossing and output test result, and wherein flaw size measurement is used shoots graduated scale in same field of view
And the mode compared with defect image.
9. a kind of detection method of clear sheet defect detecting device based on machine vision according to claim 8,
Be characterized in that: microdefect is surface scratch, underbead crack, gravel and bubble, image in the step S3 in the step S2
The step of processing are as follows: first binaryzation noise reduction, then gaussian filtering, then binaryzation enhancing.
10. a kind of detection method of clear sheet defect detecting device based on machine vision according to claim 9,
Be characterized in that: binaryzation noise reduction threshold value range of choice is 48, and low-pass Gaussian filter selects 15 × 15 filter template, two-value
Changing enhancing threshold value range of choice is 50.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910818712.7A CN110487821A (en) | 2019-08-30 | 2019-08-30 | A kind of clear sheet defect detecting device and its detection method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910818712.7A CN110487821A (en) | 2019-08-30 | 2019-08-30 | A kind of clear sheet defect detecting device and its detection method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110487821A true CN110487821A (en) | 2019-11-22 |
Family
ID=68555870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910818712.7A Pending CN110487821A (en) | 2019-08-30 | 2019-08-30 | A kind of clear sheet defect detecting device and its detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110487821A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110967349A (en) * | 2020-01-04 | 2020-04-07 | 盛广济 | Active monitoring method for curtain wall glass burst |
| CN111060521A (en) * | 2019-12-31 | 2020-04-24 | 中国水利水电第十四工程局有限公司 | Method for detecting quantity and area of bubbles on surface of precast concrete T beam |
| CN111239163A (en) * | 2020-03-13 | 2020-06-05 | 苏州鑫睿益荣信息技术有限公司 | Windshield scratch connection detection device and detection method based on machine vision |
| CN111272231A (en) * | 2020-04-07 | 2020-06-12 | 深圳回收宝科技有限公司 | Detection device of electronic equipment |
| CN111289536A (en) * | 2020-04-07 | 2020-06-16 | 深圳回收宝科技有限公司 | Defect detection device of electronic equipment screen |
| CN111307824A (en) * | 2020-04-08 | 2020-06-19 | 山东交通学院 | Pit defect detection device on surface of wooden board |
| CN112285127A (en) * | 2020-09-23 | 2021-01-29 | 苏州新佰利智能科技有限公司 | Visual detection device based on mechanical arm |
| CN112726174A (en) * | 2020-12-22 | 2021-04-30 | 杭州聚森科技有限公司 | Cloth surface defect automatic detection device and cloth surface defect detection method |
| WO2021212548A1 (en) * | 2020-04-23 | 2021-10-28 | 苏州必为智能控制科技有限公司 | 3d visual inspection apparatus |
| CN113686887A (en) * | 2021-08-20 | 2021-11-23 | 信维通信（江苏）有限公司 | Nanocrystalline strip detection device |
| CN113777268A (en) * | 2021-09-17 | 2021-12-10 | 奥瑞视（北京）科技有限公司 | Automatic flaw detection system for medium plate and control method thereof |
| CN114236885A (en) * | 2021-11-10 | 2022-03-25 | 云南电网有限责任公司 | Visual detection system and method for electric energy meter liquid crystal display machine |
| CN114324387A (en) * | 2021-12-14 | 2022-04-12 | 北京玖瑞科技有限公司 | Plate defect detection device and method |
| CN114354633A (en) * | 2022-01-14 | 2022-04-15 | 广东猛犸象智能机器人制造有限公司 | Ceramic bathroom appearance quality detection system and detection method |
| CN115847625A (en) * | 2022-12-16 | 2023-03-28 | 江苏迪丞光电材料有限公司 | Automatic ceramic forming production line |
| CN117191807A (en) * | 2023-11-06 | 2023-12-08 | 常州讯磊电子科技有限公司 | Product on-line defect detection device based on industrial camera |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1908638A (en) * | 2006-08-24 | 2007-02-07 | 上海交通大学 | Optical detecting instrument of defects in glass |
| CN205484096U (en) * | 2016-01-28 | 2016-08-17 | 浙江工业大学 | Stitch slope defect detecting device based on machine vision |
| CN108548825A (en) * | 2018-03-16 | 2018-09-18 | 天津大学 | A kind of transparent plate defect detecting device and method based on two-dimentional illumination |
| CN108709890A (en) * | 2018-06-26 | 2018-10-26 | 华南理工大学 | Bend glass defect detecting device based on machine vision and method |
| CN211122594U (en) * | 2019-08-30 | 2020-07-28 | 太原科技大学 | Transparent plate defect detection device based on machine vision |
-
2019
- 2019-08-30 CN CN201910818712.7A patent/CN110487821A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1908638A (en) * | 2006-08-24 | 2007-02-07 | 上海交通大学 | Optical detecting instrument of defects in glass |
| CN205484096U (en) * | 2016-01-28 | 2016-08-17 | 浙江工业大学 | Stitch slope defect detecting device based on machine vision |
| CN108548825A (en) * | 2018-03-16 | 2018-09-18 | 天津大学 | A kind of transparent plate defect detecting device and method based on two-dimentional illumination |
| CN108709890A (en) * | 2018-06-26 | 2018-10-26 | 华南理工大学 | Bend glass defect detecting device based on machine vision and method |
| CN211122594U (en) * | 2019-08-30 | 2020-07-28 | 太原科技大学 | Transparent plate defect detection device based on machine vision |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111060521A (en) * | 2019-12-31 | 2020-04-24 | 中国水利水电第十四工程局有限公司 | Method for detecting quantity and area of bubbles on surface of precast concrete T beam |
| CN111060521B (en) * | 2019-12-31 | 2024-01-02 | 中国水利水电第十四工程局有限公司 | Method for detecting quantity and area of air bubbles on surface of precast concrete T beam |
| CN110967349A (en) * | 2020-01-04 | 2020-04-07 | 盛广济 | Active monitoring method for curtain wall glass burst |
| CN111239163A (en) * | 2020-03-13 | 2020-06-05 | 苏州鑫睿益荣信息技术有限公司 | Windshield scratch connection detection device and detection method based on machine vision |
| CN111289536B (en) * | 2020-04-07 | 2021-10-26 | 深圳回收宝科技有限公司 | Defect detection device of electronic equipment screen |
| CN111272231A (en) * | 2020-04-07 | 2020-06-12 | 深圳回收宝科技有限公司 | Detection device of electronic equipment |
| CN111289536A (en) * | 2020-04-07 | 2020-06-16 | 深圳回收宝科技有限公司 | Defect detection device of electronic equipment screen |
| CN111272231B (en) * | 2020-04-07 | 2022-04-26 | 深圳回收宝科技有限公司 | Detection device of electronic equipment |
| CN111307824A (en) * | 2020-04-08 | 2020-06-19 | 山东交通学院 | Pit defect detection device on surface of wooden board |
| WO2021212548A1 (en) * | 2020-04-23 | 2021-10-28 | 苏州必为智能控制科技有限公司 | 3d visual inspection apparatus |
| CN112285127A (en) * | 2020-09-23 | 2021-01-29 | 苏州新佰利智能科技有限公司 | Visual detection device based on mechanical arm |
| CN112726174A (en) * | 2020-12-22 | 2021-04-30 | 杭州聚森科技有限公司 | Cloth surface defect automatic detection device and cloth surface defect detection method |
| CN113686887A (en) * | 2021-08-20 | 2021-11-23 | 信维通信（江苏）有限公司 | Nanocrystalline strip detection device |
| CN113777268A (en) * | 2021-09-17 | 2021-12-10 | 奥瑞视（北京）科技有限公司 | Automatic flaw detection system for medium plate and control method thereof |
| CN114236885A (en) * | 2021-11-10 | 2022-03-25 | 云南电网有限责任公司 | Visual detection system and method for electric energy meter liquid crystal display machine |
| CN114236885B (en) * | 2021-11-10 | 2023-09-12 | 云南电网有限责任公司 | Electric energy meter liquid crystal display machine vision detection system and method |
| CN114324387A (en) * | 2021-12-14 | 2022-04-12 | 北京玖瑞科技有限公司 | Plate defect detection device and method |
| CN114354633A (en) * | 2022-01-14 | 2022-04-15 | 广东猛犸象智能机器人制造有限公司 | Ceramic bathroom appearance quality detection system and detection method |
| CN114354633B (en) * | 2022-01-14 | 2024-04-12 | 广东猛犸象智能机器人制造有限公司 | Ceramic bathroom appearance quality detection system and detection method |
| CN115847625A (en) * | 2022-12-16 | 2023-03-28 | 江苏迪丞光电材料有限公司 | Automatic ceramic forming production line |
| CN115847625B (en) * | 2022-12-16 | 2023-08-29 | 江苏迪丞光电材料有限公司 | Ceramic automatic molding production line |
| CN117191807A (en) * | 2023-11-06 | 2023-12-08 | 常州讯磊电子科技有限公司 | Product on-line defect detection device based on industrial camera |
| CN117191807B (en) * | 2023-11-06 | 2024-01-30 | 常州讯磊电子科技有限公司 | Product on-line defect detection device based on industrial camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110487821A (en) | A kind of clear sheet defect detecting device and its detection method based on machine vision | |
| CN211122594U (en) | Transparent plate defect detection device based on machine vision | |
| CN104597058B (en) | The white wine foreign matter in bottles automatic detection device and method of a kind of view-based access control model | |
| CN104101608B (en) | Intelligent detecting device for detecting defects of multi-type irregularly shaped product | |
| CN110261390B (en) | Optical detection system and method for surface defects of diffuse reflection structured light | |
| CN204085844U (en) | A kind of eyeglass detects and automatic sorting device | |
| CN104198157A (en) | Automatic sorting device with lens detection function | |
| CN203824934U (en) | Optical system for mirror appearance inspection of trademark | |
| CN101539529A (en) | Light source system for online detection of minitype fruits based on LED | |
| CN102621156A (en) | Image-processing-based automatic micro part sorting system | |
| CN208505916U (en) | A kind of glass detection machine | |
| CN110146516A (en) | Fruit sorter based on orthogonal binocular machine vision | |
| CN203178210U (en) | Online inspection machine for glass-bottle bodies | |
| CN211122578U (en) | Glass surface flaw detection device | |
| CN106000903B (en) | A kind of non-contact detection system and method for being used to detect loom cloth gripper edge gap | |
| CN207336384U (en) | A kind of LED appearance delection devices | |
| CN110044926A (en) | A kind of lens defect detection device | |
| CN205940471U (en) | Measure device of glass thickness and refracting index | |
| CN209311359U (en) | A kind of screen appearance quality detection device | |
| CN105057229A (en) | Spraying surface defect detector | |
| CN109596633A (en) | Light guide plate defect detection equipment and detection method | |
| CN207689390U (en) | A kind of bottleneck inner wall defect on-line measuring device | |
| CN208350678U (en) | Transparent vessel oral area crackle on-line measuring device | |
| CN117760969A (en) | Photovoltaic module surface detection system and photovoltaic module surface detection method | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe 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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xue Bin Inventor after: Liu Cuirong Inventor after: Li Yajie Inventor after: Wu Zhisheng Inventor after: Meng Qingsen Inventor after: Liu Dong Inventor after: Chi Wen Qing Inventor before: Xue Bin Inventor before: Li Yajie Inventor before: Wu Zhisheng Inventor before: Meng Qingsen Inventor before: Liu Dong Inventor before: Chi Wen Qing |
|
| CB03 | Change of inventor or designer information |