CN108507953A - A kind of band membrane module has defect inspection method and device by oneself - Google Patents
A kind of band membrane module has defect inspection method and device by oneself Download PDFInfo
- Publication number
- CN108507953A CN108507953A CN201810282997.2A CN201810282997A CN108507953A CN 108507953 A CN108507953 A CN 108507953A CN 201810282997 A CN201810282997 A CN 201810282997A CN 108507953 A CN108507953 A CN 108507953A
- Authority
- CN
- China
- Prior art keywords
- image
- membrane module
- measuring tape
- spectrum
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- 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
- G01N21/8851—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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
This application provides a kind of band membrane modules to have defect inspection method and device by oneself, wherein the method includes：Reference characteristic spectrum is obtained, the reference characteristic spectrum includes：The fisrt feature spectrum of membrane module is protected with ideal and with the second feature spectrum of dirty component；According to the fisrt feature spectrum, the first image for waiting for measuring tape membrane module is obtained；According to the second feature spectrum, the second image for waiting for measuring tape membrane module is obtained；Described first image and second image are compared, waits for that measuring tape membrane module whether there is from defective described in judgement.Detection method provided by the present application can effectively solve the problem that the low problem of existing detection method of surface flaw accuracy rate.
Description
Technical field
This application involves electronic product module defects detection fields more particularly to a kind of band membrane module to have defects detection side by oneself
Method and device.
Background technology
In electric consumers component, such as the manufacturing process of liquid crystal display, battery, sound film, camera, due to work
Skill is bad, environment cleanliness is insufficient, carries reasons, the surfaces of electronic product module such as collision will produce scuffing, stain, chipping etc.
Defect.The production and use of electric consumers are very high to the purity requirements of assembly surface, therefore, in order to ensure component table
The cleanliness factor in face, cleaning and attaching protective film are most common modes.The surface quality of electronic product module is usually in cleaning, patch
It is carried out after film, therefore, accurately detects that the surface defect with film electronic product module can effectively improve product yield and drop
Low manufacturing cost.
In general, using automatic optical detection method (Automatic Optic Inspection, AOI) to electronic product group
The surface of part carries out defects detection, and this method coordinates rational light source lighting system to electronic product module using industrial camera
Surface carries out Image Acquisition, is then handled the image collected using vision processing system, and is exported and examined by operation
Survey result.
But inventor there are problems that when being detected the surface defect of electronic product module using AOI.If upstream work
There is damage in the dirty or protective film itself that cleaning machine fails to clean assembly surface completely in skill, when using AOI detections, by
It is remaining after cleaning that dirty with component to have dirty imaging features by oneself identical；Protective film scratches and the own scuffing of assembly surface
Imaging features are identical.Therefore, it merely is difficult to be subject to component with external interference factor from defective using vision processing system
It distinguishes, the accuracy rate of detection can be substantially reduced.
Invention content
This application provides a kind of band membrane modules to have defect inspection method and device by oneself, to solve existing surface defects detection
The low problem of method accuracy rate.
The application first aspect provides a kind of own defect inspection method of band membrane module, the method includes：
Reference characteristic spectrum is obtained, the reference characteristic spectrum includes：Fisrt feature spectrum with ideal protection membrane module
With the second feature spectrum with dirty component；
According to the fisrt feature spectrum, the first image for waiting for measuring tape membrane module is obtained；
According to the second feature spectrum, the second image for waiting for measuring tape membrane module is obtained；
Described first image and second image are compared, waits for that measuring tape membrane module whether there is from defective described in judgement.
Optionally, the specific steps for obtaining reference characteristic spectrum include：
Obtain desirable component, the spectral response curve with ideal protection membrane module and with dirty component；
The spectral response curve of membrane module is protected according to the spectral response curve of the desirable component and the band ideal, really
The fixed fisrt feature spectrum for enabling ideal protective film not be imaged；
According to the spectral response curve of the spectral response curve of the desirable component and the dirty component of the band, determination enables group
The dirty second feature spectrum not being imaged of part.
Optionally, described according to the fisrt feature spectrum, acquisition waits for the first image of measuring tape membrane module and the basis
The second feature spectrum, acquisition wait for that the specific steps of the second image of measuring tape membrane module further include：
According to described first image, the grey value profile of the first image is determined；
According to second image, the grey value profile of the second image is determined.
Optionally, the comparison described first image and second image wait for whether measuring tape membrane module is deposited described in judgement
Including from defective specific steps：
According to the grey value profile of the grey value profile of described first image and second image, first figure is determined
Picture overlaps angle value with each gray areas of second image；
Judge whether the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module is not present from defective if the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module exists from defective if the coincidence angle value is more than 0, and gray areas mutually exists together
To have defect area by oneself.
Optionally, the comparison described first image and second image wait for whether measuring tape membrane module is deposited described in judgement
Including from defective specific steps：
According to the grey value profile of described first image, the sub- gray value of the first image in each same grayscale value region is extracted；
According to the grey value profile of second image, the sub- gray value of the second image in each same grayscale value region is extracted；
The sub- gray value of described first image and the sub- gray value of the second image are traversed, judges whether sub- gray value is identical；
It is if fruit gray value is identical, then described to wait for that measuring tape membrane module exists from defective, and identical sub- gray value is corresponding
Gray value region is own defect area；
It is if fruit gray value differs, then described to wait for that measuring tape membrane module is not present from defective.
Second aspect, this application provides a kind of band membrane modules to have defect detecting device by oneself, and described device includes：
Reference characteristic spectrum acquiring unit, for obtaining reference characteristic spectrum, the reference characteristic spectrum includes：Band is ideal
Protect the fisrt feature spectrum of membrane module and the second feature spectrum with dirty component；
First image acquisition unit, for according to the fisrt feature spectrum, obtaining the first image for waiting for measuring tape membrane module；
Second image acquisition unit, for according to the second feature spectrum, obtaining the second image for waiting for measuring tape membrane module；
Image comparison unit waits for measuring tape membrane module for comparing described first image and second image described in judgement
With the presence or absence of from defective.
Optionally, the reference characteristic spectrum acquiring unit includes：
Spectral response curve acquiring unit, for obtaining desirable component, with ideal protection membrane module and with dirty component
Spectral response curve；
Fisrt feature spectrum determination unit, for being protected according to the spectral response curve of the desirable component and the band ideal
The spectral response curve of cuticula component determines the fisrt feature spectrum for enabling ideal protective film not be imaged；
Second feature spectrum determination unit, for the spectral response curve and dirty group of the band according to the desirable component
The spectral response curve of part, determination enable the dirty second feature spectrum not being imaged of component.
Optionally,
Described first image acquiring unit includes：
First grey value profile determination unit, for according to described first image, determining the grey value profile of the first image；
Second image acquisition unit includes：
Second grey value profile determination unit, for according to second image, determining the grey value profile of the second image.
Optionally, described image comparison unit includes：
Angle value determination unit is overlapped, the gray scale of the grey value profile and second image according to described first image is used for
Distribution value, determine described first image and each gray areas of second image overlaps angle value；
First judging unit, for judging whether the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module is not present from defective if the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module exists from defective if the coincidence angle value is more than 0, and gray areas mutually exists together
To have defect area by oneself.
Optionally, described image comparison unit includes：
First extraction unit extracts each same grayscale value region for the grey value profile according to described first image
The sub- gray value of first image；
Second extraction unit extracts each same grayscale value region for the grey value profile according to second image
The sub- gray value of second image；
Second judgment unit judges for traversing the sub- gray value of described first image and the sub- gray value of the second image
Whether sub- gray value is identical；
It is if fruit gray value is identical, then described to wait for that measuring tape membrane module exists from defective, and identical sub- gray value is corresponding
Gray value region is own defect area；
It is if fruit gray value differs, then described to wait for that measuring tape membrane module is not present from defective.
By the above technology it is found that this application provides a kind of band membrane modules to have defect inspection method and device by oneself, wherein institute
The method of stating includes：Reference characteristic spectrum is obtained, the reference characteristic spectrum includes：Fisrt feature light with ideal protection membrane module
Spectrum and the second feature spectrum with dirty component；According to the fisrt feature spectrum, the first image for waiting for measuring tape membrane module is obtained；
According to the second feature spectrum, the second image for waiting for measuring tape membrane module is obtained；Compare described first image and second figure
Picture waits for that measuring tape membrane module whether there is from defective described in judgement.Described device includes：Reference characteristic spectrum acquiring unit is used
In acquisition reference characteristic spectrum, the reference characteristic spectrum includes：The fisrt feature spectrum of membrane module is protected with ideal and with dirty
The second feature spectrum of dirty component；First image acquisition unit, for according to the fisrt feature spectrum, acquisition to wait for measuring tape film group
First image of part；Second image acquisition unit, for according to the second feature spectrum, acquisition to wait for the second of measuring tape membrane module
Image；Whether image comparison unit waits for measuring tape membrane module for comparing described first image and second image described in judgement
In the presence of from defective.In use, before batch detection band membrane module product, first, each benchmark is determined using spectrometer analysis
Characteristic spectrum, the judgement benchmark as subsequent step.Order respectively waits for measuring tape membrane module respectively in fisrt feature spectrum and second feature
It is imaged under spectrum, and compares gained image twice, the defect that occurs of two images of judgement is component from defective.The application
The defect inspection method and device of offer can avoid membrane damage and not clean the dirty shadow for having defects detection result by oneself to component
It rings, effectively improves the accuracy in detection of assembly surface defect.
Description of the drawings
In order to illustrate more clearly of the technical solution of the application, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without having to pay creative labor,
Other drawings may also be obtained based on these drawings.
Fig. 1 is a kind of flow chart carrying defect inspection method with membrane module provided by the present application；
Fig. 2 (A) is a kind of type of first image provided by the present application；
Fig. 2 (B) is a kind of type of second image provided by the present application；
Fig. 3 is a kind of flow chart obtaining reference characteristic spectrum provided by the present application；
Fig. 4 is a kind of method flow diagram obtaining the first image and the second image provided by the present application；
Fig. 5 is that a kind of determination provided by the present application waits for measuring tape membrane module from defective method flow diagram；
Fig. 6 is that another determination provided by the present application waits for measuring tape membrane module from defective method flow diagram；
Fig. 7 is a kind of structural schematic diagram for having defect detecting device by oneself with membrane module provided by the present application；
Fig. 8 is a kind of concrete structure schematic diagram of reference characteristic spectrum acquiring unit provided by the present application；
Fig. 9 is the concrete structure signal of a kind of first image acquisition unit and the second image acquisition unit provided by the present application
Figure；
Figure 10 is a kind of concrete structure schematic diagram of image comparison unit provided by the present application；
Figure 11 is the concrete structure schematic diagram of another image comparison unit provided by the present application.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Whole description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
Referring to Fig. 1, a kind of flow chart carrying defect inspection method with membrane module.
The embodiment of the present application provides a kind of own defect inspection method of band membrane module, the method includes：
S100, reference characteristic spectrum is obtained, the reference characteristic spectrum includes：Fisrt feature with ideal protection membrane module
Spectrum and second feature spectrum with dirty component；
S200, according to the fisrt feature spectrum, obtain the first image for waiting for measuring tape membrane module；
S300, according to the second feature spectrum, obtain the second image for waiting for measuring tape membrane module；
S400, described first image and second image are compared, waits for measuring tape membrane module with the presence or absence of own described in judgement
Defect.
When being interacted due to various substances (atom, group, molecule and high-molecular compound) and optical radiation energy,
With transmitting, absorption, scattering spectrum characteristic, since the energy level of substance internal microstructure is different, the feature that each substance generates
The curve of spectrum have uniqueness, i.e., band ideal film component, on dirty component, desirable component and component from defective
All have respective unique characteristic spectrum.Therefore, discriminating can be distinguished with different characteristic spectrum curves and waits for that measuring tape membrane module is
It is no to have from defective.
In use, before batch detection band membrane module product, first, ideal protective film group is carried using spectrometer analysis
Part obtains fisrt feature spectrum, wherein ideal protective film is without damage and dirty protective film；Then spectrometer is utilized
Analysis obtains second feature spectrum with dirty component, wherein with dirty component without from defective, and stain type can
There are greasy dirt, water stain and fingerprint etc..In order to improve the accuracy of detection, stain type should be expanded as far as possible, it can be dirty by various bands
The second feature Spectrum Formation characteristic spectrum library of component, using and analyzing convenient for later.Fisrt feature spectrum and second is special
Levy judgement benchmark of the spectrum as subsequent step.Order respectively waits for measuring tape membrane module respectively in fisrt feature spectrum and second feature spectrum
Lower imaging, respectively obtains the first image and the second image.As shown in Figure 2, wherein Fig. 2 (A) is the type of the first image, respectively
Have：A, without special imaging (no grey scale change)；B, display module does not clean dirty and/or component from defective, and Fig. 2 (B) is the
The type of two images, has respectively：A, without special imaging (no grey scale change)；B, the damage of display protective film and/or component are own
Defect.Image obtained by comparison twice, if two images, there are identical image block, which is that the own of component lacks
It falls into；If any identical image block is not present in two images, this is detected component without from defective, shown figure
As that be in the damage and/or component of protective film be is clean dirty.Different remedy can be accurately taken according to judgement result
Measure had not only saved the time but also cost-effective.
Defect inspection method and device provided by the present application can avoid membrane damage and not clean dirty own to component scarce
The influence for falling into testing result, effectively improves the accuracy in detection of assembly surface defect.
Referring to Fig. 3, a kind of flow chart obtaining reference characteristic spectrum.
Optionally, the specific steps for obtaining reference characteristic spectrum include：
S101, desirable component, the spectral response curve with ideal protection membrane module and with dirty component are obtained；
S102, protect the spectral response of membrane module bent according to the spectral response curve of the desirable component and the band ideal
Line determines the fisrt feature spectrum for enabling ideal protective film not be imaged；
S103, the spectral response curve according to the spectral response curve and the dirty component of the band of the desirable component, really
Surely the dirty second feature spectrum not being imaged of component is enabled.
If the band ideal protection membrane module that spectrometer is detected and the spectrum with dirty component, directly as the first spy
Levy spectrum and second feature spectrum, then using in the obtained image for waiting for measuring tape membrane module of the two characteristic spectrums in addition to aobvious
Show necessary characteristic image, can also show the interference image such as dirty of protective film, different component, can greatly increase so follow-up
The difficulty and take that image comparison works.
Spectral response curve by comparative analysis desirable component and with ideal protection membrane module, wherein desirable component is
Without damage and dirty component, the characteristic spectrum that protective film can be enabled not to be imaged is obtained, and this characteristic spectrum is determined as the
One characteristic spectrum.Spectral response curve by comparative analysis desirable component and with dirty component, obtain capable of enabling it is each it is dirty not
The characteristic spectrum of imaging, and this characteristic spectrum is determined as second feature spectrum.In this way, waiting for that measuring tape membrane module passes through fisrt feature
The image that spectrum and second feature spectrum obtain, for without special imaging, or contain only it is necessary to characteristic image image,
In, essential feature image in the first image is the dirty of component and from defective, and the essential feature image in the second image is
The damage of protective film and component from defective, to effectively avoid protecting component in film image and the second image in the first image
The various dirty interference to subsequent image comparison process, improve accuracy and the efficiency of detection.
Referring to Fig. 4, a kind of method flow diagram obtaining the first image and the second image.
Optionally, described according to the fisrt feature spectrum, acquisition waits for the first image of measuring tape membrane module and the basis
The second feature spectrum, acquisition wait for that the specific steps of the second image of measuring tape membrane module further include：
S201, according to described first image, determine the grey value profile of the first image；
S202, according to second image, determine the grey value profile of the second image.
Various defects on band membrane module, as the damaged portion of film, component dirty can scheme from defective and component
Different gray values is presented as upper, by determining the grey value profile of the first image and the second image, can quickly, clearly divide
The characteristic image for analysing and determining each defect part provides the basis of accurate data and figure for the comparison work of subsequent image,
Effectively improve efficiency and the accuracy of whole detection process.
Referring to Fig. 5, a kind of determination waits for measuring tape membrane module from defective method flow diagram.
Optionally, the comparison described first image and second image wait for whether measuring tape membrane module is deposited described in judgement
Including from defective specific steps：
S401, the grey value profile according to the grey value profile and second image of described first image, determine described in
First image overlaps angle value with each gray areas of second image；
S402, judge whether the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module is not present from defective if S403, the coincidence angle value are 0；
It is described to wait for that measuring tape membrane module exists from defective if S404, the coincidence angle value are more than 0, and gray areas
It mutually exists together to have defect area by oneself.
According to the grey value profile of the first image and the second image, each gray scale with same grayscale value can be obviously determined
Region is compared each gray areas of two images one by one, can find the identical gray areas of boundary shape.It calculates
The coincidence angle value of the gray areas of two images weighs for example, if two images have gray areas at corresponding identical one
Right value is 1, there are if the gray areas has gray areas at two, it is 2 to overlap angle value at two, and so on；If
There is no this kind of gray areas, then it is 0 to overlap angle value.Only when component exist from it is defective when, can just occur no matter use which
The phenomenon that planting characteristic spectrum, will appear gray-value variation region.Therefore, it when there is the case where coincidence angle value is more than 0, then proves
There is the case where gray areas all same of two images under fisrt feature spectrum and second feature spectrum, that is, wait for measuring tape
Membrane module exists from defective, and gray areas mutually exists together to have defect area by oneself.Detection method provided in this embodiment can
The own defect area for quickly and accurately finding out component, avoids the interference of other factors.
Referring to Fig. 6, another kind determination waits for measuring tape membrane module from defective method flow diagram.
Optionally, the comparison described first image and second image wait for whether measuring tape membrane module is deposited described in judgement
Including from defective specific steps：
S405, the grey value profile according to described first image extract the first image ash in each same grayscale value region
Angle value；
S406, according to the grey value profile of second image, extract the second image ash in each same grayscale value region
Angle value；
Whether S407, the traversal sub- gray value of described first image and the sub- gray value of the second image, judge sub- gray value
It is identical；
S408, such as fruit gray value are identical, then described to wait for that measuring tape membrane module exists from defective, and identical sub- gray value pair
The gray value region answered is own defect area；
S409, such as fruit gray value differ, then described to wait for that measuring tape membrane module is not present from defective.
According to the grey value profile of the first image and the second image, the gray scale of each gray value same area can be accurately obtained
Value, for example, the gray value in the identical region of each gray value is respectively defined as the first image gray value A in the first image, first
The sub- gray value B of image, sub- gray value C of the first image etc.；The gray value in the identical region of each gray value is fixed respectively in second image
Justice is the sub- gray value A of the second image, the sub- gray value B of the second image, sub- gray value C of the second image etc..According to same gray scale
The region of value is necessarily the principle of same defect, can be accurately judged in two images of the same race scarce with same grayscale value
Fall into region.Only component can show gray-value variation from defective under fisrt feature spectrum and second feature spectrum
Region, therefore, in two images possessed by with same grayscale value gray areas be component own fault location.Cause
This, if two images there are identical sub- gray value, illustrate that this waits for that measuring tape membrane module exists from defective, and with identical
The region of sub- gray value is own defect area；If there is no identical sub- gray value, then wait for that measuring tape membrane module is not present certainly
It is defective.Whether detection method provided in this embodiment can be accurately judged to component with from defective, effectively avoid other
The interference of factor.
Referring to Fig. 7, a kind of structural schematic diagram for having defect detecting device by oneself with membrane module.
The embodiment of the present application also provides a kind of band membrane modules to have defect detecting device by oneself, and described device includes：
Reference characteristic spectrum acquiring unit 1, for obtaining reference characteristic spectrum, the reference characteristic spectrum includes：Band reason
Want the fisrt feature spectrum for protecting membrane module and the second feature spectrum with dirty component；
First image acquisition unit 2, for according to the fisrt feature spectrum, obtaining the first figure for waiting for measuring tape membrane module
Picture；
Second image acquisition unit 3, for according to the second feature spectrum, obtaining the second figure for waiting for measuring tape membrane module
Picture；
Image comparison unit 4 waits for measuring tape membrane module for comparing described first image and second image described in judgement
With the presence or absence of from defective.
Referring to Fig. 8, a kind of concrete structure schematic diagram of reference characteristic spectrum acquiring unit.
Optionally, the reference characteristic spectrum acquiring unit 1 includes：
Spectral response curve acquiring unit 11, for obtaining the ideal protection membrane module of desirable component, band and with dirty component
Spectral response curve；
Fisrt feature spectrum determination unit 12, for ideal according to the spectral response curve of the desirable component and the band
The spectral response curve of membrane module is protected, determines the fisrt feature spectrum for enabling ideal protective film not be imaged；
Second feature spectrum determination unit 13, for dirty according to the spectral response curve of the desirable component and the band
The spectral response curve of component, determination enable the dirty second feature spectrum not being imaged of component.
Referring to Fig. 9, a kind of concrete structure schematic diagram of first image acquisition unit and the second image acquisition unit.
Optionally,
Described first image acquiring unit 2 includes：
First grey value profile determination unit 21, for according to described first image, determining the gray value point of the first image
Cloth；
Second image acquisition unit 3 includes：
Second grey value profile determination unit 31, for according to second image, determining the gray value point of the second image
Cloth.
Referring to Figure 10, a kind of concrete structure schematic diagram of image comparison unit.
Optionally, described image comparison unit 4 includes：
Angle value determination unit 41 is overlapped, the ash of the grey value profile and second image according to described first image is used for
Angle value is distributed, and determine described first image and each gray areas of second image overlaps angle value；
First judging unit 42, for judging whether the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module is not present from defective if the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module exists from defective if the coincidence angle value is more than 0, and gray areas mutually exists together
To have defect area by oneself.
Referring to Figure 11, the concrete structure schematic diagram of another image comparison unit.
Optionally, described image comparison unit 4 includes：
First extraction unit 43 extracts each same grayscale value region for the grey value profile according to described first image
The sub- gray value of the first image；
Second extraction unit 44 extracts each same grayscale value region for the grey value profile according to second image
The sub- gray value of the second image；
Second judgment unit 45 is sentenced for traversing the sub- gray value of described first image and the sub- gray value of the second image
Whether the sub- gray value that breaks is identical；
It is if fruit gray value is identical, then described to wait for that measuring tape membrane module exists from defective, and identical sub- gray value is corresponding
Gray value region is own defect area；
It is if fruit gray value differs, then described to wait for that measuring tape membrane module is not present from defective.
By above technical scheme it is found that this application provides a kind of band membrane modules to have defect inspection method, the method by oneself
Including：Reference characteristic spectrum is obtained, the reference characteristic spectrum includes：Fisrt feature spectrum and band with ideal protection membrane module
The second feature spectrum of dirty component；According to the fisrt feature spectrum, the first image for waiting for measuring tape membrane module is obtained；According to institute
Second feature spectrum is stated, the second image for waiting for measuring tape membrane module is obtained；Described first image and second image are compared, is judged
It is described to wait for that measuring tape membrane module whether there is from defective.In use, before batch detection band membrane module product, first, utilize
Spectrometer analysis determines each reference characteristic spectrum, the judgement benchmark as subsequent step.Order respectively waits for measuring tape membrane module respectively the
It is imaged under one characteristic spectrum and second feature spectrum, and compares gained image twice, the defect that two images of judgement occur
It is component from defective.Defect inspection method and device provided by the present application can avoid membrane damage and not clean dirty to component
The influence of own defects detection result, effectively improves the accuracy in detection of assembly surface defect.
It is worth noting that, in the specific implementation, the present invention also provides a kind of computer storage medias, wherein the computer
Storage medium can have program stored therein, which may include the service providing method or use of user identity provided by the invention when executing
Step some or all of in each embodiment of family register method.The storage medium can be magnetic disc, CD, read-only storage note
Recall body (English：Read-only memory, referred to as：ROM) or random access memory is (English：random access
Memory, referred to as：RAM) etc..
It is required that those skilled in the art can be understood that the technology in the embodiment of the present invention can add by software
The mode of general hardware platform realize.Based on this understanding, the technical solution in the embodiment of the present invention substantially or
Say that the part that contributes to existing technology can be expressed in the form of software products, which can deposit
Storage is in storage medium, such as ROM/RAM, magnetic disc, CD, including some instructions are used so that computer equipment (can be with
Be personal computer, server either network equipment etc.) execute certain part institutes of each embodiment of the present invention or embodiment
The method stated.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the present invention
Its embodiment.This application is intended to cover the present invention any variations, uses, or adaptations, these modifications, purposes or
Person's adaptive change follows the general principle of the present invention and includes undocumented common knowledge in the art of the invention
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be understood that the application is not limited to the precision architecture for being described above and being shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims.
Claims (10)
1. a kind of band membrane module has defect inspection method by oneself, which is characterized in that the method includes：
Reference characteristic spectrum is obtained, the reference characteristic spectrum includes：Fisrt feature spectrum and band with ideal protection membrane module
The second feature spectrum of dirty component；
According to the fisrt feature spectrum, the first image for waiting for measuring tape membrane module is obtained；
According to the second feature spectrum, the second image for waiting for measuring tape membrane module is obtained；
Described first image and second image are compared, waits for that measuring tape membrane module whether there is from defective described in judgement.
2. band membrane module according to claim 1 has defect inspection method by oneself, which is characterized in that the acquisition reference characteristic
The specific steps of spectrum include：
Obtain desirable component, the spectral response curve with ideal protection membrane module and with dirty component；
The spectral response curve that membrane module is protected according to the spectral response curve of the desirable component and the band ideal, determines and enables
The fisrt feature spectrum that ideal protective film is not imaged；
According to the spectral response curve of the spectral response curve of the desirable component and the dirty component of the band, determination enables component dirty
The second feature spectrum that dirt is not imaged.
3. band membrane module according to claim 2 has defect inspection method by oneself, which is characterized in that described according to described first
Characteristic spectrum obtains the first image for waiting for measuring tape membrane module and described according to the second feature spectrum, and acquisition waits for measuring tape film group
The specific steps of second image of part further include：
According to described first image, the grey value profile of the first image is determined；
According to second image, the grey value profile of the second image is determined.
4. band membrane module according to claim 3 has defect inspection method by oneself, which is characterized in that the comparison described first
Image and second image, waiting for that measuring tape membrane module whether there is from defective specific steps described in judgement includes：
According to the grey value profile of the grey value profile of described first image and second image, determine described first image with
The coincidence angle value of each gray areas of second image；
Judge whether the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module is not present from defective if the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module exists from defective if the coincidence angle value is more than 0, and gray areas mutually exist together for from
Defective region.
5. band membrane module according to claim 3 has defect inspection method by oneself, which is characterized in that the comparison described first
Image and second image, waiting for that measuring tape membrane module whether there is from defective specific steps described in judgement includes：
According to the grey value profile of described first image, the sub- gray value of the first image in each same grayscale value region is extracted；
According to the grey value profile of second image, the sub- gray value of the second image in each same grayscale value region is extracted；
The sub- gray value of described first image and the sub- gray value of the second image are traversed, judges whether sub- gray value is identical；
It is if fruit gray value is identical, then described to wait for that measuring tape membrane module exists from defective, and the corresponding gray scale of identical sub- gray value
It is own defect area to be worth region；
It is if fruit gray value differs, then described to wait for that measuring tape membrane module is not present from defective.
6. a kind of band membrane module has defect detecting device by oneself, which is characterized in that described device includes：
Reference characteristic spectrum acquiring unit, for obtaining reference characteristic spectrum, the reference characteristic spectrum includes：The ideal protection of band
The fisrt feature spectrum of membrane module and second feature spectrum with dirty component；
First image acquisition unit, for according to the fisrt feature spectrum, obtaining the first image for waiting for measuring tape membrane module；
Second image acquisition unit, for according to the second feature spectrum, obtaining the second image for waiting for measuring tape membrane module；
Whether image comparison unit waits for measuring tape membrane module for comparing described first image and second image described in judgement
In the presence of from defective.
7. band membrane module according to claim 6 has defect inspection method by oneself, which is characterized in that the reference characteristic spectrum
Acquiring unit includes：
Spectral response curve acquiring unit, for obtaining desirable component, the spectrum with ideal protection membrane module and with dirty component
Response curve；
Fisrt feature spectrum determination unit is used for the spectral response curve according to the desirable component and the band ideal protective film
The spectral response curve of component determines the fisrt feature spectrum for enabling ideal protective film not be imaged；
Second feature spectrum determination unit, for according to the spectral response curve of the desirable component and the dirty component of the band
Spectral response curve, determination enable the dirty second feature spectrum not being imaged of component.
8. band membrane module according to claim 7 has defect inspection method by oneself, which is characterized in that
Described first image acquiring unit includes：
First grey value profile determination unit, for according to described first image, determining the grey value profile of the first image；
Second image acquisition unit includes：
Second grey value profile determination unit, for according to second image, determining the grey value profile of the second image.
9. band membrane module according to claim 8 has defect inspection method by oneself, which is characterized in that described image comparison unit
Including：
Angle value determination unit is overlapped, for dividing according to the grey value profile of described first image and the gray value of second image
Cloth, determine described first image and each gray areas of second image overlaps angle value；
First judging unit, for judging whether the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module is not present from defective if the coincidence angle value is 0；
It is described to wait for that measuring tape membrane module exists from defective if the coincidence angle value is more than 0, and gray areas mutually exist together for from
Defective region.
10. band membrane module according to claim 8 has defect inspection method by oneself, which is characterized in that described image comparison is single
Member includes：
First extraction unit extracts the first of each same grayscale value region for the grey value profile according to described first image
The sub- gray value of image；
Second extraction unit extracts the second of each same grayscale value region for the grey value profile according to second image
The sub- gray value of image；
Second judgment unit judges sub- ash for traversing the sub- gray value of described first image and the sub- gray value of the second image
Whether angle value is identical；
It is if fruit gray value is identical, then described to wait for that measuring tape membrane module exists from defective, and the corresponding gray scale of identical sub- gray value
It is own defect area to be worth region；
It is if fruit gray value differs, then described to wait for that measuring tape membrane module is not present from defective.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810282997.2A CN108507953B (en) | 2018-04-02 | 2018-04-02 | Method and device for detecting self-defect of membrane assembly |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810282997.2A CN108507953B (en) | 2018-04-02 | 2018-04-02 | Method and device for detecting self-defect of membrane assembly |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108507953A true CN108507953A (en) | 2018-09-07 |
| CN108507953B CN108507953B (en) | 2021-01-29 |
Family
ID=63379881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810282997.2A Active CN108507953B (en) | 2018-04-02 | 2018-04-02 | Method and device for detecting self-defect of membrane assembly |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108507953B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110899150A (en) * | 2019-12-23 | 2020-03-24 | 中国环境科学研究院 | Method for intelligently identifying physical defects on surfaces of cathodes and anodes of electrolytic zinc and manganese |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010021016A1 (en) * | 2000-03-08 | 2001-09-13 | Kazuhiro Shimoda | Apparatus, system and method for checking film for defect |
| CN101587079A (en) * | 2009-05-08 | 2009-11-25 | 清华大学 | Multispectral chromatic polarization detection method of foreign impurity in the textile raw material |
| CN105548193A (en) * | 2014-10-22 | 2016-05-04 | 东友精细化工有限公司 | System and method for defect detection |
| CN107402216A (en) * | 2017-07-07 | 2017-11-28 | 深圳市维图视技术有限公司 | Coated products detecting system and method |
| CN107576663A (en) * | 2017-08-30 | 2018-01-12 | 无锡达蒙科技有限公司 | A kind of display screen defect automatic checkout system and method |
| WO2018030603A1 (en) * | 2016-08-08 | 2018-02-15 | 동우화인켐 주식회사 | Method and device for inspecting for defects in optical film |
-
2018
- 2018-04-02 CN CN201810282997.2A patent/CN108507953B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20010021016A1 (en) * | 2000-03-08 | 2001-09-13 | Kazuhiro Shimoda | Apparatus, system and method for checking film for defect |
| CN101587079A (en) * | 2009-05-08 | 2009-11-25 | 清华大学 | Multispectral chromatic polarization detection method of foreign impurity in the textile raw material |
| CN105548193A (en) * | 2014-10-22 | 2016-05-04 | 东友精细化工有限公司 | System and method for defect detection |
| WO2018030603A1 (en) * | 2016-08-08 | 2018-02-15 | 동우화인켐 주식회사 | Method and device for inspecting for defects in optical film |
| CN107402216A (en) * | 2017-07-07 | 2017-11-28 | 深圳市维图视技术有限公司 | Coated products detecting system and method |
| CN107576663A (en) * | 2017-08-30 | 2018-01-12 | 无锡达蒙科技有限公司 | A kind of display screen defect automatic checkout system and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110899150A (en) * | 2019-12-23 | 2020-03-24 | 中国环境科学研究院 | Method for intelligently identifying physical defects on surfaces of cathodes and anodes of electrolytic zinc and manganese |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108507953B (en) | 2021-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9846930B2 (en) | Detecting defects on a wafer using defect-specific and multi-channel information | |
| US9721337B2 (en) | Detecting defects on a wafer using defect-specific information | |
| CN111815630A (en) | Defect detection method and device for LCD screen | |
| US9171364B2 (en) | Wafer inspection using free-form care areas | |
| US20150012900A1 (en) | Methods and Systems for Detecting Repeating Defects on Semiconductor Wafers Using Design Data | |
| KR101782363B1 (en) | Vision inspection method based on learning data | |
| CZ278293A3 (en) | Method of checking eye lenses and apparatus for making the same | |
| US9984454B2 (en) | System, method and computer program product for correcting a difference image generated from a comparison of target and reference dies | |
| US8914754B2 (en) | Database-driven cell-to-cell reticle inspection | |
| CN108507953A (en) | A kind of band membrane module has defect inspection method and device by oneself | |
| KR100779312B1 (en) | Defect detecting device, image sensor device, image sensor module, image precessing device, digital image quality tester, and defect detecting method | |
| CN112465780A (en) | Method and device for monitoring abnormal film thickness of insulating layer | |
| CN116908185A (en) | Method and device for detecting appearance defects of article, electronic equipment and storage medium | |
| CN113614774A (en) | Method and system for defect detection in image data of target coating | |
| KR20130039266A (en) | Optical device for inspecting foreign substance and method thereof | |
| CN110874837B (en) | Defect automatic detection method based on local feature distribution | |
| CN109100359A (en) | A kind of product defects recognition methods based on machine vision | |
| US10475178B1 (en) | System, method and computer program product for inspecting a wafer using a film thickness map generated for the wafer | |
| CN115311228A (en) | Ball indentation measuring method and system based on MATLAB image edge detection | |
| Guo et al. | Novel methods for inspection of damage on airframes | |
| KR20220065110A (en) | Automatic inspection apparatus for stain and method for inspecting stain using thereof | |
| Anchini et al. | Evaluation of the uncertainty of geometrical features extracted from images: A proposal | |
| Sacha et al. | Stemware inspection system |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100094 701, 7 floor, 7 building, 13 Cui Hunan Ring Road, Haidian District, Beijing. Applicant after: Lingyunguang Technology Co.,Ltd. Address before: 100094 701, 7 floor, 7 building, 13 Cui Hunan Ring Road, Haidian District, Beijing. Applicant before: Beijing lingyunguang Technology Group Co.,Ltd. Address after: 100094 701, 7 floor, 7 building, 13 Cui Hunan Ring Road, Haidian District, Beijing. Applicant after: Beijing lingyunguang Technology Group Co.,Ltd. Address before: 100094 701, 7 floor, 7 building, 13 Cui Hunan Ring Road, Haidian District, Beijing. Applicant before: LUSTER LIGHTTECH GROUP Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |