CN110361395A - A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision - Google Patents
A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision Download PDFInfo
- Publication number
- CN110361395A CN110361395A CN201910721539.9A CN201910721539A CN110361395A CN 110361395 A CN110361395 A CN 110361395A CN 201910721539 A CN201910721539 A CN 201910721539A CN 110361395 A CN110361395 A CN 110361395A
- Authority
- CN
- China
- Prior art keywords
- light source
- detected
- film
- picture
- camera
- 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 50
- 239000012528 membrane Substances 0.000 title claims abstract description 41
- 238000010998 test method Methods 0.000 title claims abstract description 20
- 239000000463 material Substances 0.000 claims abstract description 50
- 238000012360 testing method Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000003475 lamination Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 17
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 claims description 9
- 239000005304 optical glass Substances 0.000 claims description 9
- 238000001179 sorption measurement Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000010521 absorption reaction Methods 0.000 claims description 5
- 230000000740 bleeding effect Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004141 dimensional analysis Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011521 glass Substances 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 230000006378 damage Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005086 pumping Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000001508 eye Anatomy 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention provides a kind of waterproof ventilated membrane defect test method and apparatus based on machine vision, including step 1: film to be detected is placed between light source and camera, and wherein light source is located at below film to be detected, and camera is located above film to be detected；Step 2: according to the lamination and assembling structure of different films to be detected, the incident angle of light source and film to be detected is adjusted, so that light source is cooperated with product structure；Step 3: camera shoots material picture to film to be detected, completes flatness defect test, full-scale test and the open defect test of film to be detected.Waterproof ventilated membrane defect test method and apparatus of the present invention based on machine vision is cooperated by light source and test process, completes low-cost and high-precision testing flatness, the quality of product turnout is effectively ensured.
Description
Technical field
The invention belongs to be die cut testing field, more particularly, to a kind of waterproof ventilated membrane defect test based on machine vision
Method and apparatus.
Background technique
With the development of science and technology consumption electronic product protective is continuously improved in brand manufacturers, special waterproofness is in weight
The problem of weight, waterproof ventilated membrane raw material are relatively soft while thin due to characteristic itself, are easy to appear damage, is generating
With foreign matter is easy to appear in process, damage, the problems such as burr, prevent final products shipment from being protected.Current is anti-
The relatively common die cutting product of water ventilated membrane price, added value is higher, and the absolute mass of customer requirement is higher, allows bad space very
It is low.
The equipment of present market, have can only test size, other defect cannot be tested；Some energy test defects, still
Precision is unable to monitor waterproof ventilated membrane in 0.1mm or so, can not also feed back the state of waterproof ventilated membrane.Such urgent need
A kind of equipment of the high-precision detection waterproof ventilated membrane of energy, puts into full inspection to waterproof ventilated membrane 100%, while having to microscopic conditions
Adequately understand, the big data detected is analyzed and judged, selects to conceptual design and material, and manufacturing process provides ginseng
It examines.The waterproofness of waterproof ventilated membrane is characteristic of the most important thing waterproof ventilated membrane raw material due to itself, is compared while thin
It is soft, the problems such as generating with corrugation is easy to appear in process, final products is made flatness problem occur.Average flatness exists
10 microns, the best tolerances of the sensors such as 3D camera in the market is at 10 microns, and the error of Keyemce is at 100 microns, nothing
Method meets waterproof ventilated membrane testing flatness requirement.Conventional method cost is very high simultaneously, inexpensive can not survey to project
Examination.Flatness problem can the very serious acoustic efficiency for influencing waterproof ventilated membrane, using section there is an urgent need for a kind of low cost,
The method of high precision measurement flatness.
Summary of the invention
In view of this, the present invention is directed to propose a kind of waterproof ventilated membrane defect test method based on machine vision, to mention
For a kind of low cost, high-precision, the waterproof ventilated membrane defect test method of effective guarantee product quality.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of waterproof ventilated membrane defect test method based on machine vision, including step 1: film to be detected is placed on light
Between source and camera, wherein light source is located at below film to be detected, and camera is located above film to be detected；
Step 2: according to the lamination and assembling structure of different films to be detected, the incidence angle of light source and film to be detected is adjusted
Degree, so that light source is cooperated with product structure；
Step 3: camera shoots material picture to film to be detected, completes the flatness defect test, full-scale of film to be detected
Test and open defect test.
Further, the flatness defect test of film to be detected method particularly includes:
Step 11: after camera shoots material picture, the controller of camera carries out Blob processing to picture；
Step 12: controller is matched according to the template position of inner setting and the placement location of existing film to be detected,
It to judge whether the placement location of film to be detected is correct, and is shown by screen, when being improperly situated, can manually be adjusted
It is whole, until film location to be detected is correct (i.e. product orientation)；
Step 13: controller carries out figure dividing processing to picture, and treated, and figure carries out Fourier transformation again, real
Transformation of the existing image data time domain to frequency domain；
Step 14: controller carries out Gauss processing to the frequency domain of picture described in step 13；
Step 15: controller carries out Fourier inversion to picture in step 14；
Step 16: controller compares the picture in step 15 with original image, obtains out-of-flatness region；
Step 17: controller carries out time domain linear Gauss processing to the out-of-flatness region in step 16, for filtering interference
Factor；
Step 18: output determines result and figure.
Further, the full-scale test of film to be detected method particularly includes:
Step 21: after camera shoots material picture, the controller of camera carries out Blob processing to picture；
Step 22: controller is matched according to the template position of inner setting and the placement location of existing film to be detected,
It to judge whether the placement location of film to be detected is correct, and is shown by screen, when being improperly situated, can manually be adjusted
It is whole, until film location to be detected is correct；
Step 23: the controller of camera determines the Luminance edge of picture；
Step 24: controller carries out picture element interpolation algorithm to the picture in step 23, so that accurate Drawing goes out boundary line；
Step 25: controller carries out two secondary pixel interpolation algorithms to the picture in step 24, thus more accurate drafting
The boundary line of picture；
Step 26: controller carries out two-dimensional analysis geometric manipulations to the picture in step 25, and will treated data with
The standard value of its storage inside compares judgement；
Step 27: controller obtains size conclusion and exports conclusion.
Further, open defect is tested method particularly includes:
Step 31: camera shoots material picture；
Step 32: the picture in step 31 is filtered by the controller of camera；
Step 33: controller compares the picture in step 32 with the picture in step 31, finds bad order
Position；
Step 34: controller carries out feature extraction to the undesirable position of appearance；
Step 35: the negative characteristics in step 34 are compared by controller with the normal data of its storage inside, output
Conclusion；
Step 36: camera output state of appearance summarizes.
Compared with the existing technology, the waterproof ventilated membrane defect test method of the present invention based on machine vision have with
Lower advantage:
(1) the waterproof ventilated membrane defect test method of the present invention based on machine vision by light source and was tested
Cheng Peihe completes low-cost and high-precision testing flatness, and the quality of product turnout is effectively ensured.
(2) the waterproof ventilated membrane defect test method of the present invention based on machine vision, it is special according to different products
Property, it is versatile using different light source and combination of light sources.
(3) the waterproof ventilated membrane defect test method of the present invention based on machine vision, the angle of scattering of side light source
No more than 5 °, the uniform illumination degree in product scope is effectively ensured.
Another object of the present invention is to propose a kind of waterproof ventilated membrane defect test equipment based on machine vision, with one
Kind low cost, high-precision, the waterproof ventilated membrane defect test equipment of effective guarantee product quality.
In order to achieve the above objectives, the technical scheme of the present invention is realized as follows:
A kind of waterproof ventilated membrane defect test equipment based on machine vision, including detection device and host computer, detection dress
Bottom set portion is equipped with pedestal, and support frame is installed in pedestal side, and camera is installed above support frame, and the top of pedestal is pacified by jig
Light source is filled, light source is located at the lower section of camera lens, and the space for placing film to be detected, camera are equipped between light source and the camera lens of camera
Controller signals be connected to host computer.
Further, light source is the combination of side light source and backlight, and jig upper surface is equipped with sheet material positioning area, and sheet material is fixed
The lower section in position area is equipped with optical glass slot, and the two sides of optical glass slot are equipped with several absorption apertures, each absorption aperture respectively with
The vacuum pumping opening of jig side setting, the direct adsorption sheet bleeding point of jig upper surface setting are connected to, optical glass slot
Backlight is installed in lower section, installs a side light source respectively above the side of sheet material positioning area.
Further, side light source is bar shaped side light source or annular side light source.
Further, feed device is installed in the side of jig, and material collecting device, feed device and material collecting device are installed in the other side
It is conveyer belt or transmission wheel or transmission track, the feeding motor signal in feed device is connected to host computer, in material collecting device
Rewinding motor signal be connected to host computer.
Further, host computer is computer, and computer is connected separately to keyboard and mouse, detection device, host computer, key
Disk and mouse are respectively mounted on the table, and working cabined is equipped with below workbench, is equipped with shell structure, shell knot outside detection device
Structure is equipped with feeding port, rewinding mouth and observation panel, and feeding port is correspondingly arranged with feed device, and rewinding mouth and material collecting device correspondence are set
It sets.
Compared with the existing technology, the waterproof ventilated membrane defect test equipment of the present invention based on machine vision have with
Lower advantage:
(1) the waterproof ventilated membrane defect test equipment of the present invention based on machine vision, the XY linear guide of setting
Mould group is finely tuned with camera, so as to adjust the position of light source, film to be detected and camera, so that detection device practicability is stronger.
(2) the waterproof ventilated membrane defect test equipment of the present invention based on machine vision, the robot arm of setting,
Feed device and material collecting device, high degree of automation provide the detection efficiency of product to be detected significantly.
Detailed description of the invention
The attached drawing for constituting a part of the invention is used to provide further understanding of the present invention, schematic reality of the invention
It applies example and its explanation is used to explain the present invention, do not constitute improper limitations of the present invention.In the accompanying drawings:
The step of Fig. 1 is the flatness defect test of film to be detected described in the embodiment of the present invention；
The step of Fig. 2 is the full-scale test of film to be detected described in the embodiment of the present invention；
The step of Fig. 3 is the test of open defect described in the embodiment of the present invention；
Fig. 4 is the structural schematic diagram of semiautomatic equipment described in the embodiment of the present invention；
Fig. 5 is the structural schematic diagram of fully-automatic equipment described in the embodiment of the present invention；
Fig. 6 is the structural schematic diagram of detection device described in the embodiment of the present invention；
Fig. 7 is the structural schematic diagram of bar shaped side light source described in the embodiment of the present invention and backlight cooperation；
Fig. 8 is the structural schematic diagram of annular side light source described in the embodiment of the present invention and backlight cooperation；
Fig. 9 is the top view of jig described in the embodiment of the present invention；
Figure 10 is the side view of jig described in the embodiment of the present invention.
Description of symbols:
1- detection device；2- host computer；3- keyboard；4- mouse；5- workbench；6- working cabined；7- camera finely tunes mould group；8-
Camera；9- light source；10- sheet material positioning area；11- jig；12-XY linear guide；13- support frame；14- pedestal；15- feeding dress
It sets；16- material collecting device；17- adsorbs aperture；18- optical glass slot；The side 19- light source；20- backlight；The direct suction sheet of 21-
Material bleeding point；22- vacuum pumping opening；23- positioning column.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In addition, term " first ", " second " etc. are used for description purposes only, it is not understood to indicate or imply phase
To importance or implicitly indicate the quantity of indicated technical characteristic.The feature for defining " first ", " second " etc. as a result, can
To explicitly or implicitly include one or more of the features.In the description of the present invention, unless otherwise indicated, " multiple "
It is meant that two or more.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can
To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood by concrete condition
Concrete meaning in the present invention.
The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
Explanation of nouns:
Blob processing: being exactly to carry out connected domain extraction and label to the bianry image after foreground/background separation.
A kind of waterproof ventilated membrane defect test method based on machine vision, as shown in Figure 1 to Figure 3, including
Step 1: film to be detected is placed between light source and camera, and wherein light source is located at below film to be detected, and camera is located at
Above film to be detected；
Step 2: according to the lamination and assembling structure of different films to be detected, the incident angle of light source is adjusted, so that light source
Cooperated with product structure；
Step 3: camera shoots material picture to film to be detected, completes the flatness defect test, full-scale of film to be detected
Test and open defect test.
Camera is CMOS industrial camera, and pixel resolution changes, the pixel model of camera according to the typesetting size of product
It encloses for 200~30,000,000 pixels.
Light source is that backlight, frontlighting light source, side light source or above-mentioned various light sources use simultaneously.
For the product of size and conventional appearance problem, backlight and frontlighting light source are used.Frontlighting light source packet
Include dome light, axis light, ring light etc..Backlight is suitable for the uncomplicated mechanical structure of structure or product to required precision height
Field.Backlight and frontlighting light source can also be configured simultaneously, is suitable for test request complexity, and single light source is unable to satisfy
Product scope.
When side light source is mainly used for product and has the defect test of the Z-directions such as fold, light source incidence angle angle is from -10 degree to 50
Spend angle.Main function is the case where low cost substitution 3D camera system or 3D system are unable to test.
The angle of scattering of side light source is no more than 5 °, and the uniform illumination degree in product scope is effectively ensured.
The color of side light source is blue-light source or green light source.
Side light source is annular side light source or bar shaped side light source or oval side light source.
The flatness defect test of film to be detected method particularly includes:
Step 11: after camera shoots material picture, the controller of camera carries out Blob processing to picture；
Step 12: controller is matched according to the template position of inner setting and the placement location of existing film to be detected,
It to judge whether the placement location of film to be detected is correct, and is shown by screen, when being improperly situated, can manually be adjusted
It is whole, until film location to be detected is correct (i.e. product orientation)；
Step 13: controller carries out figure dividing processing to picture, and treated, and figure carries out Fourier transformation again, real
Transformation of the existing image data time domain to frequency domain；
Step 14: controller carries out Gauss processing to the frequency domain of picture described in step 13；
Step 15: controller carries out Fourier inversion to picture in step 14；
Step 16: controller compares the picture in step 15 with original image, obtains out-of-flatness region；
Step 17: controller carries out time domain linear Gauss processing to the out-of-flatness region in step 16, for filtering interference
Factor；
Step 18: output determines result and figure.
The full-scale test of film to be detected method particularly includes:
Step 21: after camera shoots material picture, the controller of camera carries out Blob processing to picture；
Step 22: controller is matched according to the template position of inner setting and the placement location of existing film to be detected,
It to judge whether the placement location of film to be detected is correct, and is shown by screen, when being improperly situated, can manually be adjusted
It is whole, until film location to be detected is correct (i.e. product orientation)；
Step 23: the controller of camera determines the Luminance edge of picture；
Step 24: controller carries out picture element interpolation algorithm (also known as slide calliper rule interpolation algorithm) to the picture in step 23, from
And accurate Drawing goes out boundary line；
Step 25: controller carries out two secondary pixel interpolation algorithms to the picture in step 24, thus more accurate drafting
The boundary line of picture；
Step 26: controller carries out two-dimensional analysis geometric manipulations to the picture in step 25, and will treated data with
The standard value of its storage inside compares judgement；
Step 27: controller obtains size conclusion and exports conclusion.
Open defect test method particularly includes:
Step 31: camera shoots material picture；
Step 32: the picture in step 31 is filtered by the controller of camera；
Step 33: controller compares the picture in step 32 with the picture in step 31, finds bad order
Position；
Step 34: controller carries out feature extraction to the undesirable position of appearance；
Step 35: the negative characteristics in step 34 are compared by controller with the normal data of its storage inside, output
Conclusion；
Step 36: camera output state of appearance summarizes.
A kind of waterproof ventilated membrane defect test equipment based on machine vision, as shown in Figure 7 to 10, including detection device
1 and host computer 2, detection device 1 includes that camera finely tunes mould group 7, camera 8, light source 9, jig 11, XY linear guide 12, support rib
Support frame 13 is installed in frame 13, pedestal 14,14 side of pedestal, and installation camera finely tunes mould group 7, camera fine tuning above support frame 13
Camera 8 is installed, the top of pedestal 14 is installed XY linear guide 12, installed above XY linear guide 12 by jig 11 in mould group 7
Light source 9, light source 9 are located at the lower section of 8 camera lens of camera, and the space for placing film to be detected is equipped between light source 9 and the camera lens of camera 8,
The controller of camera 8, the X of XY linear guide 12 are connected to host computer 2 to motor and the equal signal of Y-direction motor.According to the actual situation
XY linear guide 12 is adjusted, so as to adjust the position of light source 9 and film to be detected, so that detection device practicability is stronger.
Camera fine tuning mould group 7 is that line sweeps camera adjustments mould group, can be according to different films to be detected come the angle to camera 8
It is finely adjusted, it is more adaptable.
Light source 9 is that backlight, frontlighting light source, side light source or above-mentioned various light sources use simultaneously.
Light source 9 is the combination of side light source 19 and backlight 20, and jig 11 is rectangular configuration, and upper surface is fixed equipped with sheet material
Position area 10, the lower section of sheet material positioning area 10 are equipped with optical glass slot 18, and the two sides of optical glass slot 18 are equipped with absorption aperture 17, inhale
Direct adsorption sheet of the attached aperture 17 respectively with the vacuum pumping opening 22 of 11 side of jig setting, the setting of 11 upper surface of jig is evacuated
21 connection composition sorption channels of mouth, direct 21 external connection adsorption machine of adsorption sheet bleeding point, adsorption machine signal is connected to upper
Machine 2 for adsorbing film to be detected, while preventing sheet material deformation from influencing test effect, and backlight is installed in the lower section of optical glass slot 18
A side light source 19 is installed in the side top in source 20, sheet material positioning area 10 respectively, for illuminating to film to be detected.
The edge of sheet material positioning area 10 is equipped with positioning column 23, so that between having between positioning column 23 and product to be detected centainly
Gap reduces influence of the positioning column to light source
Side light source 19 is bar shaped side light source or annular side light source.
One bar shaped side light source is installed respectively above any three sides of sheet material positioning area 10.
Host computer 2 is computer, and computer is connected separately to keyboard 3 and mouse 4, facilitates operation.
Feed device 15 is installed in the side of jig 11, and material collecting device 16 is installed in the other side, and one end mounting robot arm is sent
Material device 15 and material collecting device 16 are conveyer belt or transmission wheel or transmission track, and the feeding motor signal in feed device 15 connects
It is connected to host computer 2, the equal signal of rewinding motor and robot arm in material collecting device 16 is connected to host computer 2, so that equipment is
Automation equipment greatly improves work efficiency.Film to be detected is transmitted to 11 top of jig by feed device 15, and is passed through
Host computer 2 controls robot arm and is placed on sheet material positioning area 10, and after detection, host computer 2 controls robot arm will
Detection film is placed on material collecting device 16, is greatly improved work efficiency.
Detection device 1, host computer 2, keyboard 3 and mouse 4 are installed on workbench 5, and working cabined is equipped with below workbench 5
6, shell structure is equipped with outside detection device 1, the injection of light in limiting light source 9 prevents the eye of injury operation and maintenance personnel
Eyeball, shell structure are equipped with feeding port, rewinding mouth and observation panel, and feeding port is correspondingly arranged with feed device 15, rewinding mouth and receipts
Material device 16 is correspondingly arranged, and observation panel is for observing shell structure inner case.Detection device 1, host computer 2, keyboard 3, mouse
4, the motor of XY linear guide 12, feed device 15 and material collecting device 16 is connected to external power supply.
It is semiautomatic equipment, feeding and rewinding are required to manually when equipment does not have feeding device 15 and material collecting device 16
Processing is fully-automatic equipment when equipment installs feeding device 15 and material collecting device 16, for semiautomatic equipment, is carried out
Illustrate, specific as follows:
A kind of course of work of the equipment of the waterproof ventilated membrane defect test method based on machine vision are as follows:
For staff according to the structure and level of film to be detected, the camera 8 for selecting resolution ratio different selects corresponding side
Film to be detected is placed on sheet material positioning area 10, opens equipment master switch by light source 9, and light source 9 is powered simultaneously, and camera 8 is to be detected
Film is taken pictures, and camera 8 is matched according to the template position of inner setting and the placement location of existing film to be detected, to sentence
Break film to be detected placement location it is whether correct, and shown by screen, while show by the display screen of computer, when placement position
It when setting incorrect, can manually adjust, until film location to be detected is correct (i.e. product orientation), film covering to be detected is directly inhaled at this time
Tag material bleeding point 21, when film location to be detected is correct, the controller of camera 8 can send signal to computer, and computer control is inhaled
For random by sorption channel, then camera 8 analyzes the pictorial information of film to be detected, and takes different surveys according to actual needs
Method for testing is tested, and result is finally transported to computer, is shown or is exported by computer screen, and computer output is final
As a result after, film to be detected is taken away.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of waterproof ventilated membrane defect test method based on machine vision, it is characterised in that: including
Step 1: film to be detected is placed between light source and camera, and wherein light source is located at below film to be detected, and camera is located to be checked
It surveys above film；
Step 2: according to the lamination and assembling structure of different films to be detected, the incident angle of light source and film to be detected is adjusted, is made
Light source is obtained to be cooperated with product structure；
Step 3: camera shoots material picture to film to be detected, completes the flatness defect test of film to be detected, full-scale test
It is tested with open defect.
2. a kind of waterproof ventilated membrane defect test method based on machine vision according to claim 1, it is characterised in that:
The flatness defect test of film to be detected method particularly includes:
Step 11: after camera shoots material picture, the controller of camera carries out Blob processing to picture；
Step 12: controller is matched according to the template position of inner setting and the placement location of existing film to be detected, thus
Judge whether the placement location of film to be detected is correct, and shown by screen, when being improperly situated, can be manually adjusted,
Until film location to be detected is correct (i.e. product orientation)；
Step 13: controller carries out figure dividing processing to picture, and treated, and figure carries out Fourier transformation again, realizes figure
As the transformation of data time domain to frequency domain；
Step 14: controller carries out Gauss processing to the frequency domain of picture described in step 13；
Step 15: controller carries out Fourier inversion to picture in step 14；
Step 16: controller compares the picture in step 15 with original image, obtains out-of-flatness region；
Step 17: controller carries out time domain linear Gauss processing to the out-of-flatness region in step 16, for filtering disturbing factor；
Step 18: output determines result and figure.
3. a kind of waterproof ventilated membrane defect test method based on machine vision according to claim 1, it is characterised in that:
The full-scale test of film to be detected method particularly includes:
Step 21: after camera shoots material picture, the controller of camera carries out Blob processing to picture；
Step 22: controller is matched according to the template position of inner setting and the placement location of existing film to be detected, thus
Judge whether the placement location of film to be detected is correct, and shown by screen, when being improperly situated, can be manually adjusted,
Until film location to be detected is correct；
Step 23: the controller of camera determines the Luminance edge of picture；
Step 24: controller carries out picture element interpolation algorithm to the picture in step 23, so that accurate Drawing goes out boundary line；
Step 25: controller carries out two secondary pixel interpolation algorithms to the picture in step 24, thus more accurate drafting picture
Boundary line；
Step 26: controller carries out two-dimensional analysis geometric manipulations to the picture in step 25, and will be in treated data and its
The standard value of portion's storage compares judgement；
Step 27: controller obtains size conclusion and exports conclusion.
4. a kind of waterproof ventilated membrane defect test method based on machine vision according to claim 1, it is characterised in that:
Open defect test method particularly includes:
Step 31: camera shoots material picture；
Step 32: the picture in step 31 is filtered by the controller of camera；
Step 33: controller compares the picture in step 32 with the picture in step 31, finds the position of bad order；
Step 34: controller carries out feature extraction to the undesirable position of appearance；
Step 35: the negative characteristics in step 34 are compared by controller with the normal data of its storage inside, output knot
By；
Step 36: camera output state of appearance summarizes.
5. a kind of waterproof ventilated membrane defect test method based on machine vision according to claim 1, it is characterised in that:
Light source is that backlight, frontlighting light source, side light source or above-mentioned various light sources use simultaneously.
6. a kind of waterproof ventilated membrane defect test equipment based on machine vision, it is characterised in that: including detection device and upper
Machine, detection device bottom are equipped with pedestal, and pedestal side installs support frame, installs camera, the top of pedestal above support frame
Light source is installed by jig, light source is located at the lower section of camera lens, is equipped between light source and the camera lens of camera and places film to be detected
Space, controller, the signal of camera be connected to host computer.
7. a kind of waterproof ventilated membrane defect test equipment based on machine vision according to claim 6, it is characterised in that:
Light source is the combination of side light source and backlight, and jig upper surface is equipped with sheet material positioning area, and the lower section of sheet material positioning area is equipped with light
Glass guide channel is learned, the two sides of optical glass slot are equipped with several absorption apertures, and each absorption aperture is true with the setting of jig side respectively
Backlight, piece are installed in the direct adsorption sheet bleeding point connection that empty pump port, jig upper surface are arranged, the lower section of optical glass slot
One side light source is installed respectively above the side of material positioning area.
8. a kind of waterproof ventilated membrane defect test equipment based on machine vision according to claim 7, it is characterised in that:
Side light source is bar shaped side light source or annular side light source.
9. a kind of waterproof ventilated membrane defect test equipment based on machine vision according to claim 6, it is characterised in that:
Feed device is installed in the side of jig, and material collecting device is installed in the other side, and feed device and material collecting device are conveyer belt or transmission
Wheel or transmission track, the feeding motor signal in feed device are connected to host computer, and the rewinding motor signal in material collecting device connects
It is connected to host computer.
10. a kind of waterproof ventilated membrane defect test equipment based on machine vision according to claim 9, feature exist
In: host computer is computer, and computer is connected separately to keyboard and mouse, and detection device, host computer, keyboard and mouse are respectively mounted
On the table, it is equipped with working cabined below workbench, shell structure is equipped with outside detection device, shell structure is equipped with feeding
Mouth, rewinding mouth and observation panel, feeding port are correspondingly arranged with feed device, and rewinding mouth and material collecting device are correspondingly arranged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910721539.9A CN110361395A (en) | 2019-08-06 | 2019-08-06 | A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910721539.9A CN110361395A (en) | 2019-08-06 | 2019-08-06 | A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110361395A true CN110361395A (en) | 2019-10-22 |
Family
ID=68223463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910721539.9A Pending CN110361395A (en) | 2019-08-06 | 2019-08-06 | A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110361395A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111220620A (en) * | 2020-03-09 | 2020-06-02 | 广东荣旭智能技术有限公司 | Machine visual appearance flaw detection device and flaw detection method thereof |
| CN111595849A (en) * | 2020-04-26 | 2020-08-28 | 深圳市联得自动化装备股份有限公司 | Defect detecting device |
| CN111912759A (en) * | 2020-07-15 | 2020-11-10 | 天津日博工业技术有限公司 | Method for testing air permeability of waterproof breathable film |
| CN112255244A (en) * | 2020-12-08 | 2021-01-22 | 荣旗工业科技(苏州)股份有限公司 | Patch detection device integrated in femto-camera and detection method |
| CN112945988A (en) * | 2021-02-04 | 2021-06-11 | 宁波舜宇仪器有限公司 | Lens defect detection system and detection method |
| CN113091657A (en) * | 2021-04-07 | 2021-07-09 | 广东九联科技股份有限公司 | Flatness tester |
| CN113310988A (en) * | 2021-04-19 | 2021-08-27 | 上海汇扬智能科技有限公司 | Optical film surface defect detection equipment and detection method based on machine vision |
| CN114113110A (en) * | 2021-11-26 | 2022-03-01 | 博迈科海洋工程股份有限公司 | Natural gas pipeline insulation layer defect detection method based on machine vision |
| CN114184616A (en) * | 2021-11-25 | 2022-03-15 | 安徽布拉特智能科技有限公司 | Detection device for blue film for lithium battery and control method thereof |
| CN114235818A (en) * | 2021-12-20 | 2022-03-25 | 南京大学 | Online detection device and detection method for membrane electrode defects |
| CN116721074A (en) * | 2023-06-07 | 2023-09-08 | 昊泽吉顺新材料(深圳)有限公司 | Mobile phone protection film production quality detection system based on image analysis |
| CN117213411A (en) * | 2023-11-08 | 2023-12-12 | 天津欧派集成家居有限公司 | Intelligent decorative plate flatness detection device and detection method based on machine vision |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1690698A (en) * | 2004-04-23 | 2005-11-02 | 大日本网目版制造株式会社 | Optical type appearance testing method and optical type appearance testing device |
| CN1825099A (en) * | 2005-02-24 | 2006-08-30 | 大日本网目版制造株式会社 | General view test device and general view test method |
| CN203838069U (en) * | 2014-04-29 | 2014-09-17 | 重庆云天化纽米科技有限公司 | Film imaging detection device |
| CN106053348A (en) * | 2016-08-16 | 2016-10-26 | 苏州恒铭达电子科技有限公司 | Hiding-type adjustable film detection mechanism |
| CN206258399U (en) * | 2016-12-16 | 2017-06-16 | 重庆云天化纽米科技股份有限公司 | Film is imaged luminescence detection device |
| CN107478657A (en) * | 2017-06-20 | 2017-12-15 | 广东工业大学 | Stainless steel surfaces defect inspection method based on machine vision |
| CN211318237U (en) * | 2019-08-06 | 2020-08-21 | 天津日博工业技术有限公司 | Waterproof ventilated membrane defect test equipment based on machine vision |
-
2019
- 2019-08-06 CN CN201910721539.9A patent/CN110361395A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1690698A (en) * | 2004-04-23 | 2005-11-02 | 大日本网目版制造株式会社 | Optical type appearance testing method and optical type appearance testing device |
| CN1825099A (en) * | 2005-02-24 | 2006-08-30 | 大日本网目版制造株式会社 | General view test device and general view test method |
| CN203838069U (en) * | 2014-04-29 | 2014-09-17 | 重庆云天化纽米科技有限公司 | Film imaging detection device |
| CN106053348A (en) * | 2016-08-16 | 2016-10-26 | 苏州恒铭达电子科技有限公司 | Hiding-type adjustable film detection mechanism |
| CN206258399U (en) * | 2016-12-16 | 2017-06-16 | 重庆云天化纽米科技股份有限公司 | Film is imaged luminescence detection device |
| CN107478657A (en) * | 2017-06-20 | 2017-12-15 | 广东工业大学 | Stainless steel surfaces defect inspection method based on machine vision |
| CN211318237U (en) * | 2019-08-06 | 2020-08-21 | 天津日博工业技术有限公司 | Waterproof ventilated membrane defect test equipment based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| 吴韶波 等: "数字音视频技术及应用", 31 March 2016, 哈尔滨工业大学出版社, pages: 241 * |
| 董耀华: "物联网技术与应用", 31 December 2011, 上海科学技术出版社, pages: 96 - 102 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111220620A (en) * | 2020-03-09 | 2020-06-02 | 广东荣旭智能技术有限公司 | Machine visual appearance flaw detection device and flaw detection method thereof |
| CN111595849A (en) * | 2020-04-26 | 2020-08-28 | 深圳市联得自动化装备股份有限公司 | Defect detecting device |
| CN111912759A (en) * | 2020-07-15 | 2020-11-10 | 天津日博工业技术有限公司 | Method for testing air permeability of waterproof breathable film |
| CN112255244A (en) * | 2020-12-08 | 2021-01-22 | 荣旗工业科技(苏州)股份有限公司 | Patch detection device integrated in femto-camera and detection method |
| CN112945988A (en) * | 2021-02-04 | 2021-06-11 | 宁波舜宇仪器有限公司 | Lens defect detection system and detection method |
| CN112945988B (en) * | 2021-02-04 | 2023-11-07 | 宁波舜宇仪器有限公司 | Lens defect detection system and detection method |
| CN113091657A (en) * | 2021-04-07 | 2021-07-09 | 广东九联科技股份有限公司 | Flatness tester |
| CN113310988B (en) * | 2021-04-19 | 2022-10-28 | 上海汇扬智能科技有限公司 | Optical film surface defect detection equipment and detection method based on machine vision |
| CN113310988A (en) * | 2021-04-19 | 2021-08-27 | 上海汇扬智能科技有限公司 | Optical film surface defect detection equipment and detection method based on machine vision |
| CN114184616A (en) * | 2021-11-25 | 2022-03-15 | 安徽布拉特智能科技有限公司 | Detection device for blue film for lithium battery and control method thereof |
| CN114113110B (en) * | 2021-11-26 | 2023-10-13 | 博迈科海洋工程股份有限公司 | Natural gas pipeline insulation layer defect detection method based on machine vision |
| CN114113110A (en) * | 2021-11-26 | 2022-03-01 | 博迈科海洋工程股份有限公司 | Natural gas pipeline insulation layer defect detection method based on machine vision |
| CN114235818A (en) * | 2021-12-20 | 2022-03-25 | 南京大学 | Online detection device and detection method for membrane electrode defects |
| CN116721074A (en) * | 2023-06-07 | 2023-09-08 | 昊泽吉顺新材料(深圳)有限公司 | Mobile phone protection film production quality detection system based on image analysis |
| CN116721074B (en) * | 2023-06-07 | 2024-02-13 | 昊泽吉顺新材料(深圳)有限公司 | Mobile phone protection film production quality detection system based on image analysis |
| CN117213411A (en) * | 2023-11-08 | 2023-12-12 | 天津欧派集成家居有限公司 | Intelligent decorative plate flatness detection device and detection method based on machine vision |
| CN117213411B (en) * | 2023-11-08 | 2024-01-05 | 天津欧派集成家居有限公司 | Intelligent decorative plate flatness detection device and detection method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110361395A (en) | A kind of waterproof ventilated membrane defect test method and apparatus based on machine vision | |
| CN105032788A (en) | Product appearance defect detection equipment | |
| CN106323600B (en) | Cascade distributed AOI defect detection system and detection method thereof | |
| CN208580039U (en) | A kind of vision imaging detection device | |
| CN205377994U (en) | Multistation cell -phone camera module detects machine | |
| CN103017026A (en) | LED shadowless lamp system with failure detection and repair functions | |
| CN104527193A (en) | Image system laminator | |
| US20200264459A1 (en) | Detecting device and detecting method and detecting equipment therefor | |
| CN109975318A (en) | A kind of plastic bottle open defect detection method and equipment | |
| CN110942059A (en) | Equipment data real-time reading method and device based on machine vision recognition | |
| CN105352969A (en) | Edible oil product color and luster, transparency and impurity detecting device | |
| CN211318237U (en) | Waterproof ventilated membrane defect test equipment based on machine vision | |
| CN116008294B (en) | Key cap surface particle defect detection method based on machine vision | |
| CN208066784U (en) | A kind of external diameter detection device for auto parts and components | |
| CN217688600U (en) | Detection device | |
| CN105203554A (en) | Vacuum multilayer graphene stain detection device | |
| CN102068238A (en) | Automatic stereoscopic vision and colour vision examination instrument | |
| CN210401907U (en) | Optical detection system of liquid crystal display screen | |
| CN108393276A (en) | A kind of external diameter detection device for auto parts and components | |
| US20150146005A1 (en) | Mounting and inspection data creation device and mounting and inspection data creation method | |
| CN210513014U (en) | Online TV backplate vision inspection machine | |
| CN108956628B (en) | Plastic cover plate defect imaging detection system | |
| KR102117652B1 (en) | Apparatus for testing of display panel | |
| CN207965413U (en) | A kind of quick flexible liquid crystal optical monitoring device of detection | |
| CN204638580U (en) | Tank body tank switching checkout gear |
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 |