CN107796825A - Device inspection method - Google Patents
Device inspection method Download PDFInfo
- Publication number
- CN107796825A CN107796825A CN201610807384.7A CN201610807384A CN107796825A CN 107796825 A CN107796825 A CN 107796825A CN 201610807384 A CN201610807384 A CN 201610807384A CN 107796825 A CN107796825 A CN 107796825A
- Authority
- CN
- China
- Prior art keywords
- light source
- image
- shadow
- inspection method
- detection
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000007689 inspection Methods 0.000 title claims abstract description 26
- 230000007547 defect Effects 0.000 claims abstract description 46
- 230000009182 swimming Effects 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 7
- 238000004026 adhesive bonding Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 90
- 230000010354 integration Effects 0.000 abstract description 2
- 230000004807 localization Effects 0.000 abstract description 2
- 239000003292 glue Substances 0.000 description 25
- 239000002245 particle Substances 0.000 description 23
- 238000012360 testing method Methods 0.000 description 15
- 230000011218 segmentation Effects 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 5
- 238000000149 argon plasma sintering Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000428 dust Substances 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000005498 polishing Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- -1 cut etc. Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 235000012431 wafers Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
-
- 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
- G01N2021/9511—Optical elements other than lenses, e.g. mirrors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N2021/95638—Inspecting patterns on the surface of objects for PCB's
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a kind of device inspection method, including：With the first light source irradiation measured device surface, and measured device is taken pictures under the irradiation of the first light source, obtain the first image；Measured device is positioned according to the first image；With secondary light source irradiation measured device surface, and measured device is taken pictures under the irradiation of secondary light source, obtain the second image；Second image is analyzed, determines whether measured device is qualified.The present invention can carry out detection and localization and defects detection to device, both it ensure that the position of device was accurate, it is capable of detecting when whether device is good devices simultaneously, so as to help that the subsequent operations such as alignment, assembling are performed to device, effectively increases the quality of product.To be performed in addition, The invention also achieves the integration of positioning and defects detection, device can be avoided to be transmitted in detection between different station, so as to improve detection efficiency.
Description
Technical field
The present invention relates to units test field, and especially, it is related to a kind of device inspection method.
Background technology
In the exploitation of active alignment (Active Alignment, referred to as AA) equipment, it is necessary to FPC (letter
Referred to as FPC) component carries out picture glue, and need to (lens assembly includes lens and motor, the motor with lens assembly by FPC components
Can be voice coil motor (VCM), therefore lens assembly can be described as VCM components) position to pre- clear position, AA can be carried out
Action.
During being aligned, the position of FPC components and VCM components in tool has deviation, if without
Positioning compensation, AA operations will be caused exactly can not to be directed at FPC with VCM.It is the U's of CN 205067834 in Authorization Notice No.
In utility model patent, the camera lens adsorption jig for carrying out active alignment is disclosed.The tool can adsorb camera lens, additionally it is possible to
Operating personnel are allowed to adjust the relative position of camera lens and motor, so as to be aligned.Although the program can allow wiring board and camera lens
Alignment, but can not detector lens and the defects of motor.
In actual production, in the front procedure of Dutch treatment journey and component, FPC and VCM surface are likely to appearance
Grain, cut, it is dirty the defects of, if being carried out AA operations without detection, can there will be the FPC of defect and VCM to be assembled,
So as to influence the product quality of camera module.
For above-mentioned technical problem, effective solution is not yet proposed at present.
The content of the invention
The problem of in correlation technique, the present invention propose a kind of device inspection method, device effectively can be examined
Look into, solve the ropy problem of completed knocked down products.
A kind of according to an aspect of the invention, there is provided device inspection method.
Included according to the device inspection method of the present invention：With the first light source irradiation measured device surface, and in the first light source
Irradiation under measured device is taken pictures by image capture device, obtain the first image；According to the first image to being tested device
Part is positioned；With secondary light source irradiation measured device surface, and pass through image capture device pair under the irradiation of secondary light source
Measured device is taken pictures, and obtains the second image；Second image is analyzed, determines whether measured device is qualified.
Wherein, carrying out positioning to measured device according to the first image includes：Binary conversion treatment is carried out to the first image；To two
The first image after value processing is analyzed, and determines the region of measured device；Entered according to the region of measured device
Row form fit, determine center and/or the current angular of measured device.
In addition, carrying out analysis to the second image includes：The second image is compensated according to predetermined offset, and to mending
The second image after repaying carries out binary conversion treatment；Run- Length Coding is carried out to the pixel of the second image after binary conversion treatment, and
Analyzed based on coding result, determine the size of defect area；According to the size in region the defects of determination and pre-set
The defects of dimension threshold, determine whether wiring board qualified；
Wherein, predetermined offset determines in the following manner：Shoot and referred under the irradiation of secondary light source in advance
Image, mean filter is carried out to reference picture, based on the difference between the reference picture after mean filter and former reference picture, really
Fixed predetermined offset.
Specifically, it is determined that defect area size when, connected region, Zhi Hougen are determined according to the result of Run- Length Coding
The size of defect area is determined according to the connected region of determination；Wherein, the determination of connected region is completed by multiple determination process, often
Distance of swimming node of the individual determination process corresponding to adjacent rows pixel determines connectedness, also, it is determined that when connective, passes through
Determination of the OpenGL mode to connected region carries out parallel processing.
In addition, in the case where measured device is wiring board, the first light source is coaxial light source, and secondary light source is shadow-free light
Source, coaxial light source are disposed adjacent with shadow-free light source, and coaxial light source is arranged between shadow-free light source and image capture device.
Further, may further include according to the device inspection method of the present invention：
It is determined that wiring board is qualified and in the case that wiring board has completed gluing, pass through under the irradiation in shadow-free light source
Surface after image capture device glues to wiring board is taken pictures, and obtains the 3rd image；3rd image is carried out at binaryzation
Reason, and extract tree lace from the image after binary conversion treatment；Closure padding is carried out to the tree lace of extraction；If closure filling
Operating successful execution, then the tree lace after being filled to closure is analyzed, and determines the area and/or width of tree lace, and by tree lace
Area and/or width judge whether tree lace is qualified compared with the area threshold and/or width threshold value that pre-set；If
Because the tree lace of extraction does not form enclosed region and can not successful execution closure padding, then judge that tree lace is unqualified.
Alternatively, above-mentioned coaxial light source includes luminescent device and speculum, wherein, speculum is located at going out for luminescent device
Penetrate in light path, and be in 45 degree of angles with the bearing of trend of emitting light path, the luminescent device is used to send infrared waves or white light.It is above-mentioned
Luminescent device in shadow-free light source is set for annular, for sending no shadow blue light.
In addition, when taking pictures to obtain the second image, taken pictures by way of dark-ground illumination, and by shadow-free light source with
The control of the distance between wiring board is in 5mm between 15mm.
In the case where measured device is lens assembly, the first light source is backlight, and secondary light source is shadow-free light source.Its
In, the backlight is used to send white light, and the shadow-free light source be dome light source, image capture device setting neighbouring with shadow-free light source and
Positioned at the side in shadow-free light source, backlight is located at the opposite side in shadow-free light source, and leaves space between backlight and shadow-free light source.
The present invention can realize following technique effect：
(1) present invention can carry out detection and localization and defects detection to device, both ensure that the position of device was accurate,
It is capable of detecting when whether device is good devices simultaneously, so as to help that the subsequent operations such as alignment, assembling are performed to device, effectively
Improve the quality of product；
(2) present invention realizes positioning and the integration execution of defects detection, is shot using same image capture device
The image of measured device (lens assembly or wiring board), it can be photographed in same station under different light source irradiations for fixed
Position and the image of defects detection, can effectively improve detection efficiency, and can reduce the volume of detection device, reduce detection and set
Standby complexity, contributes to control cost；Device can also be avoided to be transmitted in detection between different station simultaneously, so as to carry
High detection efficiency；
(3) present invention compensates to image beforehand through offset when carrying out defects detection, carries out two-value again afterwards
Change is handled, and can effectively reduce the noise in image, avoids interference (e.g., including signal interference, camera pixel fluctuation etc.) shadow
Testing result is rung, ensure that the degree of accuracy of detection；
(4) by using OpenGL, process progress that can be to defects detection is hardware-accelerated, so as to improve detection efficiency；
(5) when being detected to wiring board, the present invention detects tree lace by using the mode of closure filling, can be effective
The defects of detecting disconnected glue whether there is, and the present invention can also determine the width and/or area of tree lace, be further ensured that gluing
Quality, effectively device is avoided to occur hidden danger of quality after assembling；
(6) present invention positions, energy by using Infrared irradiation wiring board (and chip on wiring board) to it
Light is enough allowed to pass through the silk-screen of chip, so as to make positioning more accurate and effective；
(7) when carrying out defects detection, taken pictures by using the mode of dark-ground illumination using shadow-free light source, Neng Gourang
The transition of the defects of stain of measured device, cut, particle exposes, and is effectively mutually distinguished with background, so as to improve the accurate of detection
Degree, avoids judging by accident.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 is the method flow diagram that device inspection method according to embodiments of the present invention is detected to FPC and VCM；
Fig. 2 is the flow chart positioned according to embodiments of the present invention to FPC components；
Fig. 3 is the flow chart positioned according to embodiments of the present invention to VCM components；
Fig. 4 is the flow chart according to embodiments of the present invention for carrying out defects detection；
Fig. 5 carries out the flow chart of Run- Length Coding when being detection FPC surfaces according to embodiments of the present invention；
Fig. 6 realizes the flow chart that blob judges when being detection FPC surfaces according to embodiments of the present invention；
Fig. 7 is the flow chart for carrying out tree lace detection to FPC according to embodiments of the present invention；
Fig. 8 is the structure chart of the detection device of wiring board according to embodiments of the present invention；
Fig. 9 is the structure chart of VCM according to embodiments of the present invention detection device.
Embodiment
The description of this illustrated embodiment should be combined with corresponding accompanying drawing, and accompanying drawing should be used as the one of complete specification
Part.In the accompanying drawings, the shape of embodiment or thickness can expand, and to simplify or conveniently indicate.Furthermore respectively tied in accompanying drawing
The part of structure will be to describe to illustrate respectively, it is notable that the member not illustrated not shown in figure or by word
Part, it is the form known to a person of ordinary skill in the art in art.
The description of embodiments herein, any reference about direction and orientation, is for only for ease of description, and can not manage
Solve as any restrictions to the scope of the present invention.Relational language, as " lower ", " higher ", " horizontal ", " vertical ", "
On ", " under ", " on ", " under ", " top " and " | bottom " and its derivative (such as " flatly ", " down ", " up "
Etc.) all should be interpreted described in explanation or discussed orientation is shown in accompanying drawing.These relational languages are just to side
Just describe, and be not considered as the explanation to instrument and equipment or the concrete operations in particular orientation.Term, it is such as " attached
Upper ... " a kind of relation of (attached), " being fixed on ... ", " connected " and " being connected with each other " reference, wherein tying
Another structure is fixed or be attached to structure, unless there are clear and definite description, the structure bag by directly or indirectly through insert structure
Include moveable or fixed or associated.In addition, the features and advantages of the invention are by referring to preferred reality
The scheme of applying illustrates.It is therefore preferable that embodiment illustrates the combination of possible infinite feature, these features may be independent
In the presence of or combination exist, the present invention be not defined in preferred embodiment especially.The scope of the present invention is by claim
Book is defined.
According to an embodiment of the invention, there is provided a kind of device inspection method.
This method can be used for detection wiring board (for example, FPC and the IR chips installed thereon), simultaneously can be used for detecting
Lens assembly, this method can be both used alone, and some device is detected, can also be to needing to carry out AA techniques, assembling
Multiple device parallels perform, so as to ensure that the device for participating in assembling is aligned with each other, and there is no defect.Wherein, institute herein
The lens assembly stated includes lens and motor, and alternatively, the motor in lens assembly can be voice coil motor (VCM), now,
Lens assembly can be described as VCM components.
Device inspection method according to embodiments of the present invention includes：
Step S101, with the first light source irradiation measured device surface, and pass through IMAQ under the irradiation of the first light source
Equipment is taken pictures to measured device, obtains the first image；
Step S102, measured device is positioned according to the first image；
Step S103, with secondary light source irradiation measured device surface, and pass through IMAQ under the irradiation of secondary light source
Equipment is taken pictures to measured device, obtains the second image；
Step S104, the second image is analyzed, determine whether measured device is qualified.
In actual applications, the order of above-mentioned steps can overturn, i.e. can first shoot the second image, detect tested device
Whether part is qualified, shoots the first image afterwards, measured device is positioned.
In the case where measured device is wiring board, mirror-reflection is presented in the surface of wiring board；And it is mirror in measured device
In the case of head assembly, lens assembly (for example, it may be VCM components) has light transparent member (that is, light hole).In an implementation
In example, when being positioned according to the first image to measured device, specifically it may comprise steps of：
Binary conversion treatment is carried out to the first image；
The first image after binary conversion treatment is analyzed, determines the region of measured device；
Form fit (for example, it may be rectangle fitting) is carried out according to the region of measured device, determines measured device
Center and/or current angular.
In addition, in the case of the surface smoother of measured device, mirror-reflection will be presented in measured device, and when tested
When device surface has the defects of particle (Particle), diffusing reflection can be produced thereon.In one embodiment, in order to examine
Measured device whether there is the defects of particle, when analyzing the second image, specifically may comprise steps of：
The second image is compensated according to predetermined offset, and the second image after compensation is carried out at binaryzation
Reason；
Run- Length Coding is carried out to the pixel of the second image after binary conversion treatment, and analyzed based on coding result,
Determine the size of defect area (for example, for stain, it may be determined that its area；For cut, it may be determined that its length, depth
And/or area；For particle, it may be determined that its diameter, volume and/or projected area etc.)；
The defects of according to the size in region the defects of determination and pre-setting dimension threshold is (for example, the area of stain is
It is no to exceed area threshold；Whether length, depth and/or the area of cut exceed corresponding threshold value；The diameter of particle, volume and/
Or whether projected area etc. exceedes corresponding threshold value), determine whether wiring board is qualified；
Wherein, predetermined offset determines in the following manner：Shoot and referred under the irradiation of secondary light source in advance
Image, mean filter is carried out to reference picture, based on the difference between the reference picture after mean filter and former reference picture, really
Fixed predetermined offset.In actual applications, above-mentioned reference picture can be detected under secondary light source irradiation to first
Measured device shoot obtained image, it is determined that after offset, the offset can be used for the device of subsequent detection
First compensate corresponding image；Or when can also be detected to each measured device, all redefine offset.
The testing image of measured device is compensated by using offset, carries out binary conversion treatment again afterwards, can
The noise in image is effectively reduced, avoids interference (e.g., including signal interference, camera pixel fluctuation etc.) from influenceing testing result,
It ensure that the degree of accuracy of detection.In one embodiment, offset can be less than or equal to mean filter after reference picture with
Difference between former reference picture, and the fluctuation range of image capture device can be more than.
Alternatively, in one embodiment, it is determined that defect area area when, can be true according to the result of Run- Length Coding
Determine connected region, determine the area of defect area according to the connected region of determination afterwards；Wherein, the determination of connected region passes through more
Individual determination process is completed, and distance of swimming node determination of each determination process corresponding to adjacent rows pixel is connective, also,
It is determined that when connective, the determination by way of OpenGL to connected region carries out parallel processing.In such manner, it is possible to defects detection
Process carry out it is hardware-accelerated, so as to improve detection efficiency.
In one embodiment, measured device is wiring board.Now, mirror-reflection is presented in the surface of measured device, in order to
Detected, above-mentioned first light source is coaxial light source, and secondary light source is shadow-free light source, and coaxial light source is adjacent with shadow-free light source to be set
Put, and coaxial light source is arranged between shadow-free light source and the image capture device for being taken pictures to measured device.
In one embodiment, according to the present invention detection method can be to wiring board gluing situation detect, glue
Line will present obvious raised on device.Specifically, following steps can be performed to complete the detection of tree lace：
It is determined that wiring board is qualified and in the case that wiring board has completed gluing, pass through under the irradiation in shadow-free light source
Surface after image capture device glues to wiring board is taken pictures, and obtains the 3rd image；
Binary conversion treatment is carried out to the 3rd image, and tree lace is extracted from the image after binary conversion treatment；
Closure padding is carried out to the tree lace of extraction；
If closing padding successful execution, the tree lace after being filled to closure is analyzed, and determines the area of tree lace
And/or width, and the area of tree lace and/or width are sentenced compared with the area threshold and/or width threshold value that pre-set
Whether disconnected tree lace is qualified；
If as the tree lace of extraction do not form enclosed region and can not successful execution closure padding, then judge glue
Line is unqualified.
By using closure filling mode detect tree lace, can effective detection break glue the defects of whether there is, and this
Invention can also determine the width and/or area of tree lace, be further ensured that gluing quality, effectively avoid device from occurring after assembling
Hidden danger of quality.
Moreover, wiring board is shot by using same image capture device, can be in same station different
Photographed under light source irradiation for positioning, the image of defects detection, tree lace detection, detection efficiency can not only be effectively improved, and
And the volume of detection device can also be reduced, the complexity of detection device is reduced, contributes to control cost.
Alternatively, when being detected to wiring board, above-mentioned coaxial light source includes luminescent device and speculum, wherein,
Speculum is located on the emitting light path of luminescent device, and is in 45 degree of angles with the bearing of trend of emitting light path.In order to which light can be worn
The silk-screen of circuit chip on board is crossed, above-mentioned luminescent device can be used for sending infrared waves, more efficient, accurate so as to detect.
In one embodiment, when being detected to wiring board, the luminescent device in above-mentioned shadow-free light source is set for annular, uses
In sending no shadow blue light.When taking pictures to obtain the second image, taken pictures by way of dark-ground illumination.Shone by using details in a play not acted out on stage, but told through dialogues
Bright mode, the transition the defects of stain of measured device, cut, particle can be allowed to expose, effectively mutually distinguished with background, so as to carry
The high degree of accuracy of detection, avoids judging by accident.In addition, in order to improve the effect of shooting, can be by between shadow-free light source and wiring board
Distance controlling in 5mm between 15mm.
In addition, in the case where measured device is lens assembly, light transparent member (that is, light hole) on lens assembly be present,
Above-mentioned first light source is backlight, and above-mentioned secondary light source is shadow-free light source.
Now, backlight is used to send white light, and shadow-free light source is dome light source, for the figure taken pictures to measured device
As the neighbouring side for setting and being located at shadow-free light source of collecting device and shadow-free light source, backlight is located at the opposite side in shadow-free light source,
And space is left between backlight and shadow-free light source, to place tested lens assembly.Wherein, due to the lower end of lens assembly
Face generally has certain radian, so dome light source can effectively adapt to this radian, the defects of by lens assembly lower surface
Accurately reflect out in the image for taking pictures to obtain, effectively increase the accuracy of detection.
Example
The detection method according to the present invention will be described by taking AA equipment as an example below.In this example, will be according to of the invention real
The detection method for applying example is performed parallel, and FPC components and VCM components are positioned and detected respectively.
As shown in figure 1, the process detected according to the pre-detection method of the present invention to FPC components and VCM components is as follows.
For FPC components, following detecting step can be performed：
(1) in FPC component detections, camera, the position of light source and parameter can be adjusted first (including when aperture, exposure
Between, light-source brightness etc.), specifically include：The position of camera vertical direction is adjusted, the chip of FPC components is in focal position, and
Time for exposure and the gain of camera are adjusted, makes the chip imaging clearlies of FPC components, adjusts coaxial light source and shadow-free light source respectively
Position makes light source uniformly be radiated on the chip of FPC components；
(2) after, vision system parameter can be demarcated, specifically, pixel chi can be calculated by scaling board calibration for cameras
The very little and proportionate relationship of actual size, preserved as systematic parameter.
(3), can be under coaxial light source, to the chip positioning center of FPC components and the figure of angle for FPC component detections
As carrying out device parameter, processing parameter setting；Here, it is necessary to which tested FPC is delivered into measurement position, adjustment camera and FPC it
Between relative position；
(4) next, under shadow-free light source, the IR faces dust detection to FPC components and the detection of FPC components tree lace respectively
Image carry out device parameter, processing parameter setting.Here set parameter is mainly including the area threshold of stain, cut
Length threshold, the depth threshold of cut, the volume threshold of particle, the diameter threshold of particle, the area threshold of tree lace, the width of tree lace
Degree threshold value, tree lace gap width threshold value (when detect tree lace gap occur and gap width be less than the width threshold value when, it is believed that
There is not disconnected glue) etc..
After system start-up, allow camera to run to test position, start to detect.For FPC, following three items can be detected
Mesh：
Project 1：Under being opened in coaxial light source, camera, which is taken pictures and (obtains FPC the first image) and carries out visual pattern, to be divided
Analysis, to the chip positioning center of FPC components and angle；
Project 2：After the chip positioning for completing FPC components, coaxial light source is closed, opens shadow-free light source, camera, which is taken pictures, (to be obtained
FPC the second image) and visual pattern analysis is carried out, detect FPC component IR faces particle, cut, stain etc.；If there is
Grain, cut, stain etc., and its size exceedes the threshold value that sets before, then carries out alarm, and terminate under this test starts
One module test；
Project 3：If without particle, cut etc., glue applying mechanism carries out picture glue to FPC components, after the completion of open without shadow
Light source carries out tree lace detection, and camera is taken pictures and (obtains FPC the 3rd image) and carries out visual pattern analysis, detects tree lace integrality
It is wide with glue；If it find that disconnected glue or glue are wide unqualified, alarm is carried out, and terminates this test and starts next module survey
Examination.If tree lace is normal, the FPC components wait for AA techniques, and start the test of next FPC components by test.
Similarly, (length of the area threshold of stain, cut is included for VCM components, the same setting for completing above-mentioned parameter
Threshold value, the depth threshold of cut, the volume threshold of particle, the diameter threshold of particle, the area threshold of tree lace, for VCM components
The parameter threshold about tree lace can not be set) and detecting step：
(1) for VCM component detections, camera, the position of light source and parameter (including aperture, exposure are equally adjusted first
Time, light-source brightness etc.), and it also requires the parameter of demarcation vision system, concrete mode in FPC component detection steps with being adopted
Mode is similar, is not repeated herein；
(2) after, VCM component camera lens positional parameters can be set under backlight irradiation；
(3) the face lower surface particle test parameters of VCM components Lens 02 are set under dome light source；
(4) it is then possible to allow camera to run to test position, the detection of following two projects is carried out to VCM components：
Project 1：Under backlight unlatching, camera, which is taken pictures and (obtains the first image of VCM components) and carries out visual pattern, to be divided
Analysis, to the VCM components centre of location and angle.
Project 2：After completing the positioning of VCM components camera lens, backlight is closed, opens dome light source, camera, which is taken pictures, (obtains VCM
Second image of component) and visual pattern analysis is carried out, detect particle, cut of VCM component Lens02 faces lower surface etc.；If
Particle, cut etc. be present, carry out alarm, and terminate this test and start next module test；If without particle, draw
Trace etc., then VCM components by test, and with FPC components carry out AA techniques.
Method shown in Fig. 1 can apply to AA equipment, right before FPC components are aligned and assembled with VCM components
FPC components are detected respectively with VCM components, so as to effectively improve the mould of Dutch treatment journey composition yield.
FPC assembly positioning methods
As shown in Fig. 2 being based on the first image, the positioning to FPC components can be realized by following steps：
First, a two field picture is obtained；
Afterwards, image is split based on binary-state threshold；
By way of Blob analyses, the chip region of FPC components is determined；
By way of fitted rectangle, FPC device wafers center and angle are positioned.
VCM assembly positioning methods
As shown in figure 3, being based on the first image, the positioning to VCM components can be realized by following steps：
First, a two field picture is obtained；
Afterwards, image is split based on binary-state threshold；
By way of Blob analyses, light hole (Lens) region of VCM components is determined；
By way of being fitted circle, the light hole center of VCM components is positioned, is fitted angle afterwards.
Defect inspection method
As shown in figure 4, for FPC components or VCM components, when according to the second image detection defect, can perform following
Step：
First, a two field picture is obtained；
Afterwards, mean filter is carried out with smoothed image；
Next, dynamic threshold segmentation is carried out, extraction defect area (for example, it may be stain, cut etc.)；
Then, Blob analyses are carried out, calculate the area of each stain, by the area compared with technological parameter, the work
Skill parameter can be predetermined blemished area threshold value, if meeting the requirement of technological parameter, then it is assumed that be qualified products, otherwise recognize
To be substandard product.
It will be described in detail and detected according to the defects of present invention by taking FPC component IR upper surfaces particle, scratch detection as an example below
Method.Detected for the defects of VCM components, can equally use similar approach, and similar beneficial effect can be reached.
Detection to the IR upper surfaces of FPC components can be carried out in the environment of dark-ground illumination.
Under dark-ground illumination, the dirty point such as particle, cut is brighter than IR surface a lot, white bright spot shape, is carrying out table
When face checks, dynamic threshold segmentation can be described as：If the image after mean filter is g_mean (x, y), original image g_
Origin (x, y), if detection zone meets g_origin (x, y)-g_mean (x, y)>=offset, then it is assumed that existing defects,
Wherein offset is fixed compensation value, to avoid the fluctuation (noise) because of camera pixel from causing to judge by accident, in this example, can be incited somebody to action
Offset sets a value more than camera pixel fluctuation range.
The image of the measured device of lower shooting is irradiated for shadow-free light source, can be compensated first with offset, it
After carry out binarization segmentation, now, because the image of binarization segmentation is through overcompensation, so dynamic equivalent to employing
Binarization segmentation threshold value.
After image binaryzation is realized according to dynamic threshold, quick two-value can be realized by the way of by Run- Length Coding
The Blob of image judges.The Run- Length Coding of image is by a pixel point value and a count value, to represent a series of heavy
Multiple pixel point value, specific algorithm flow are as shown in Figure 3.
Referring to Fig. 5, when carrying out Run- Length Coding, following steps are specifically included：
Bianry image is progressively scanned, compares the relation of adjacent pixel in a line；
When " 01 " saltus step is presented in both pixels, the position of 1 pixel of record is the original position of current run；
When " 10 " saltus step is presented in both pixels, the position of 1 pixel of record is the final position of current run；
The information of the distance of swimming is recorded, continues to scan on next distance of swimming of current line；
If the end of scan of one's own profession, next line is gone to, otherwise continues to judge the saltus step of pixel；Going to next line
When, if currently continuing to judge the saltus step of pixel to current line not departing from last column；If exceeding last column,
Then scanning is completed, and obtains all distances of swimming of current bianry image.
In addition, when carrying out Blob judgements based on Run- Length Coding result, can be according to order from top to bottom, from left to right
Scan image, two row data adjacent in image are only handled every time.It is assumed that two dynamic link table ThisRow of image and
LastRow, it is respectively directed to all distance of swimming nodes of current line and lastrow.Judge each distance of swimming node and lastrow in ThisRow
In LastRow between each distance of swimming node eight connectivity region connected relation, connected component labeling be converted to analyze dynamic link table in
The connectedness of distance of swimming node.If connection, this distance of swimming is integrated into the Blob classes belonging to the LastRow distances of swimming；Otherwise, it is the trip
Journey distributes new Blob classes.
As shown in fig. 6, Blob specific deterministic process is as follows：
First, ThisRow rows are scanned；
Afterwards, respective handling is carried out according to the connected relation between ThisRow rows and the LastRow row distances of swimming；
Judge whether be ThisRow rows the last distance of swimming, if the last distance of swimming, then update chain table pointer LastRow-
ThisRow, ThisRow++；Otherwise continue to be handled according to the connected relation between ThisRow rows and the LastRow row distances of swimming；
If next, exceeding last column, processing terminates；Otherwise, next ThisRow rows are continued to scan on.
By the defect inspection method, IR chips can be checked, Morphological scale-space is carried out to effective image area,
Quantify the size of particle and cut etc., so as to avoid IR the and VCM components to existing defects from carrying out follow-up alignment and assembling
Technique.
By using the means of compensation, the binarization segmentation of dynamic threshold can be realized, prevents the individual difference because of measured object
Different and camera, the factor such as unstability of light source cause image difference, cause fixed threshold can not effectively distinguish prospect and the back of the body
The situation of scape.
Tree lace inspection method
FPC device wafers with VCM components after AA techniques are completed, it is necessary to bonded using UV glue, glue it is complete
The stability that whole property and the reasonability of glue width will directly affect module and subsequently use.Highlighted without shadow blue light under polishing, FPC
Glue is rendered as black bar on component.
As shown in fig. 7, in one embodiment of the invention, tree lace detection can be carried out by following scheme：
First, a two field picture is obtained；
Next, pass through binary-state threshold segmentation figure picture；
Then, operation is carried out out；
Afterwards, after to image binaryzation, the invalid information in image is rejected；Pass through the features such as shape, area and length-width ratio
Extract effective tree lace；After determining tree lace, the whole region of tree lace is filled, so as to judge whether disconnected glue；
Next, whether the parameter in tree lace region meets parameter request, such as tree lace after being filled by Blob com-parison and analysis
Area whether reach area threshold, whether the width of tree lace reaches width threshold value.By such scheme, by judging tree lace area
The size in domain realizes that glue is wide and the detection of tree lace integrality, can prevent module from light leak etc. occur after AA techniques are completed
The problems such as bad, effective guarantee product quality.
FPC detection devices
In one embodiment of the invention, FPC components can be detected using the detection device shown in Fig. 8.
As shown in figure 8, the detection device includes：Coaxial light source 11, shadow-free light source 12, image capture device are (for example, can be with
Camera) 13 and camera lens 14, coaxial light source 11 set close to shadow-free light source 12, coaxial light source 11 be arranged at shadow-free light source 12 with
Between camera lens 14, camera lens 14 is connected to camera 13；Wherein, coaxial light source 11 is used to shine when the chip to wiring board positions
Penetrate；Shadow-free light source 12 is used for the irradiation when carrying out defects detection to chip；Camera 13 is used in coaxial light source 11 and shadow-free light source
Taken pictures respectively during 12 irradiation.
Detection device shown in Fig. 8 can apply to AA techniques, and fixation and recognition, tree lace detection and stolen goods are carried out to FPC components
Dirt detection, and VCM components fixation and recognition and dirty detection.Above-mentioned image capture device can be high pixel camera, above-mentioned mirror
Head can be micro-lens.
When to FPC component fixation and recognitions, due to FPC component IR upper surfaces material for glass and flatness it is preferable, choosing
With perpendicularity and the preferable coaxial light source of uniformity.And IR faces have the plated film of heterogeneity, silk-screen be present for IR surfaces
FPC components, white light can not completely penetrate through IR pieces, and the reflectivity of silk-screen is similar to IR, therefore feature unobvious.Can only be by red
The light on outer light source reflection IR surfaces, while consider the acceptable optical wavelength of industrial camera sensitive chip, it is from wavelength
850nm infrared light supply；There is no the FPC components of silk-screen for IR surfaces, general visible can penetrate IR faces and photograph chip, examine
Dirty detection is considered, from without shadow blue light.
In progress FPC component IR upper surfaces during dirty detection, due to the dirty predominantly particle of IR upper surfaces, dust, draw
The forms such as trace, so the characteristics of using light scattering, using dark-ground illumination mode, make dirty excessively to expose bright spot caused by light scattering
Light, so that dirty distinguish with background.Details in a play not acted out on stage, but told through dialogues environment is manufactured from annular shadow-free light source, in addition, to amplify light as far as possible
Scattering properties obtain high-contrast image, the system from the preferable wavelength of scattering be 470nm blue light.
In the wide detection of break on carrying out FPC components glue, glue, no shadow blue light can be equally used, because tree lace is in obvious convex
Shape is played, under highlighted exposure, light is reflected at tree lace, and relative to FPC component other parts, tree lace is rendered as black bar
Shape.
VCM component detecting equipments
In one embodiment of the invention, VCM components can be detected using the detection device shown in Fig. 9.
As shown in figure 9, the detection device includes：Backlight 21, dome light source 22, image capture device (for example, it may be
Camera) 23 and camera lens 24, one end of camera lens 24 be connected to camera 23, the other end of camera lens 24 is connected to dome light source 22, the back of the body
Light source 21 is arranged on side of the dome light source 22 away from camera lens 24, and spaced between backlight 21 and dome light source 22；
Wherein, backlight 21 is used to irradiate when positioning lens assembly；Shadow-free light source 22 is used to lack to lens assembly
Irradiated when falling into detection；Camera 13 is used to be taken pictures respectively when backlight 21 and dome light source 22 irradiate.
Detection device shown in Fig. 9 can be used for VCM components being identified and dirty detection.Above-mentioned image capture device can
To be high pixel camera, above-mentioned camera lens can be micro-lens.
When carrying out VCM component fixation and recognitions, VCM components center is Lens light holes, and its center is in VCM components
The heart.From highlighted white backlight source, it is ensured that it is bright enough at Lens light holes when camera is taken pictures, it is imaged as white hot spot.
And under backlight polishing, VCM component bodies are imaged as black, and its edge is in sharp contrast.
When carrying out the dirty face lower surfaces of VCM components Lens 02 and the detection of cut, dirty predominantly particle, dust, draw
The forms such as trace, the characteristics of using light scattering, make it is dirty by bright spot overexposure caused by light scattering so that dirty and background area
Point.Because the face lower surfaces of VCM components Lens 02 are in certain radian, from the preferable dome light of uniformity.
In summary, the invention provides a kind of universal vision-based detection scheme, the system is integrated with positioning and detection
Function, installation space is reduced, save cost, cannot be only used in AA equipment, realize regarding for AA equipment executing agency
Feel auxiliary positioning function, the detection function of the stain of product, cut and tree lace in Dutch treatment journey can also be realized.The present invention proposes
Scheme do not influence equipment UPH, can not only be used in AA kind equipments, may extend to band from animation glue, automatically dropping glue, HA, VCM
In the processing procedure associated devices such as assembling, all occasions for being related to the detections such as automatically dropping glue, glass are dirty, scratch, it can use and originally regard
Feel that system schema realizes positioning auxiliary and detection integrated function, there is extensive versatility.
The detection scheme of the present invention can be used for FPC components fixation and recognition and dirty detection：(1) program can meet vision
Positioning and the requirement of vision-based detection precision；(2) program can meet FPC components particle, the dirty and detection of cut, Yi Jihua
Glue is wide with the detection demand of disconnected glue after glue；
In addition, the detection scheme of the present invention can be used for VCM components fixation and recognition and dirty detection：(1) program can expire
The requirement of sufficient VCM components vision positioning and vision-based detection precision；(2) program can meet the face lower surfaces of Lens 02 it is dirty with
The detection demand of cut.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
God any modification, equivalent substitution and improvements made etc., should be included in the scope of the protection with principle.
Claims (12)
- A kind of 1. device inspection method, it is characterised in that including：With the first light source irradiation measured device surface, and under the irradiation of first light source by image capture device to described Measured device is taken pictures, and obtains the first image；The measured device is positioned according to described first image；The measured device surface is irradiated with secondary light source, and set under the irradiation of the secondary light source by described image collection It is standby that the measured device is taken pictures, obtain the second image；Second image is analyzed, determines whether the measured device is qualified.
- 2. device inspection method according to claim 1, it is characterised in that according to described first image to the tested device Part, which carries out positioning, to be included：Binary conversion treatment is carried out to described first image；Described first image after binary conversion treatment is analyzed, determines the region of the measured device；Form fit is carried out according to the region of the measured device, the center of the measured device is determined and/or works as Preceding angle.
- 3. device inspection method according to claim 1, it is characterised in that carrying out analysis to second image includes：Second image is compensated according to predetermined offset, and binaryzation is carried out to second image after compensation Processing；Run- Length Coding is carried out to the pixel of second image after binary conversion treatment, and analyzed based on coding result, Determine the size of defect area；Whether the defects of according to the size of the defect area of determination and pre-setting dimension threshold, determine the wiring board It is qualified；Wherein, the predetermined offset determines in the following manner：Shoot and obtain under the irradiation of the secondary light source in advance Reference picture, mean filter is carried out to the reference picture, based on the reference picture after mean filter and former reference picture Between difference, determine the predetermined offset.
- 4. device inspection method according to claim 3, it is characterised in that it is determined that defect area size when, according to The result of Run- Length Coding determines connected region, determines the size of defect area according to the connected region of determination afterwards；Wherein, The determination of connected region is completed by multiple determination process, distance of swimming section of each determination process corresponding to adjacent rows pixel Point determines connectedness, also, it is determined that when connective, the determination by way of OpenGL to connected region is located parallel Reason.
- 5. device inspection method according to claim 1, it is characterised in that in the situation that the measured device is wiring board Under, first light source is coaxial light source, and the secondary light source is shadow-free light source, the coaxial light source and shadow-free light source phase Neighbour is set, and the coaxial light source is arranged between the shadow-free light source and described image collecting device.
- 6. device inspection method according to claim 5, it is characterised in that further comprise：It is determined that the wiring board is qualified and in the case that the wiring board has completed gluing, the photograph in the shadow-free light source The surface penetrated down after being glued by described image collecting device to the wiring board is taken pictures, and obtains the 3rd image；Binary conversion treatment is carried out to the 3rd image, and tree lace is extracted from the image after binary conversion treatment；Closure padding is carried out to the tree lace of extraction；If the closure padding successful execution, the tree lace after being filled to closure are analyzed, the area of tree lace is determined And/or width, and the area of tree lace and/or width are sentenced compared with the area threshold and/or width threshold value that pre-set Whether the tree lace that breaks is qualified；Enclosed region is not formed if as the tree lace of extraction and can not close padding described in successful execution, then is sentenced The tree lace that breaks is unqualified.
- 7. device inspection method according to claim 5, it is characterised in that the coaxial light source include luminescent device and Speculum, wherein, the speculum is located on the emitting light path of the luminescent device, and with the bearing of trend of the emitting light path In 45 degree of angles.
- 8. device inspection method according to claim 7, it is characterised in that the luminescent device is used to send infrared waves Or white light.
- 9. device inspection method according to claim 5, it is characterised in that the luminescent device in the shadow-free light source is ring Shape is set, for sending no shadow blue light.
- 10. device inspection method according to claim 5, it is characterised in that when taking pictures to obtain second image, lead to The mode for crossing dark-ground illumination is taken pictures, and the distance between the shadow-free light source and the wiring board are controlled in 5mm extremely Between 15mm.
- 11. device inspection method according to claim 1, it is characterised in that in the measured device for lens assembly In the case of, first light source is backlight, and the secondary light source is shadow-free light source.
- 12. device inspection method according to claim 11, it is characterised in that the backlight is used to send white light, institute It is dome light source to state shadow-free light source, and described image collecting device adjacent to setting and is located at the shadow-free light source with the shadow-free light source Side, the backlight is located at the opposite side in the shadow-free light source, and is left between the backlight and the shadow-free light source Space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610807384.7A CN107796825B (en) | 2016-09-01 | 2016-09-01 | Device detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610807384.7A CN107796825B (en) | 2016-09-01 | 2016-09-01 | Device detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107796825A true CN107796825A (en) | 2018-03-13 |
| CN107796825B CN107796825B (en) | 2021-01-05 |
Family
ID=61530007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610807384.7A Active CN107796825B (en) | 2016-09-01 | 2016-09-01 | Device detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107796825B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108387182A (en) * | 2018-05-17 | 2018-08-10 | 广东省智能制造研究所 | A kind of aperture measurement device and measuring apparatus |
| CN109544533A (en) * | 2018-11-23 | 2019-03-29 | 聚时科技(上海)有限公司 | A kind of metal plate defect detection and measure based on deep learning |
| CN109813725A (en) * | 2019-04-02 | 2019-05-28 | 东莞博美特自动化科技有限公司 | A kind of large scale glue defect inspection method |
| CN110208268A (en) * | 2019-05-16 | 2019-09-06 | 昆山弗莱吉电子科技有限公司 | The detection system of VCM elastic slice |
| CN110288584A (en) * | 2019-06-27 | 2019-09-27 | 常州固高智能装备技术研究院有限公司 | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision |
| CN110389131A (en) * | 2019-08-21 | 2019-10-29 | 汕头市结核病防治所(汕头市呼吸系疾病防治所) | A sputum qualified inspection device |
| CN110473250A (en) * | 2019-07-31 | 2019-11-19 | 苏州中科全象智能科技有限公司 | Accelerate the method for Blob analysis in a kind of processing of machine vision |
| CN110636715A (en) * | 2019-08-27 | 2019-12-31 | 杭州电子科技大学 | An automatic welding and defect detection method based on self-learning |
| CN110838149A (en) * | 2019-11-25 | 2020-02-25 | 创新奇智(广州)科技有限公司 | Camera light source automatic configuration method and system |
| CN111083386A (en) * | 2019-12-24 | 2020-04-28 | 维沃移动通信有限公司 | Image processing method and electronic device |
| CN111260622A (en) * | 2020-01-14 | 2020-06-09 | 湖南城市学院 | Equipment for installing electrical devices inside switch cabinet and control method |
| CN111640131A (en) * | 2020-05-29 | 2020-09-08 | 广东利元亨智能装备股份有限公司 | Battery core gluing detection method and device and electronic equipment |
| CN111999314A (en) * | 2020-10-28 | 2020-11-27 | 南京大量数控科技有限公司 | A device and method for automatically inspecting deformation during processing of flexible PCB |
| CN112557407A (en) * | 2021-02-24 | 2021-03-26 | 常州微亿智造科技有限公司 | Optical detection module and optical detection method for detecting corner defects of notebook computer shell |
| CN115082660A (en) * | 2022-07-01 | 2022-09-20 | 联想(北京)有限公司 | Information processing method, device, electronic device and storage medium |
| CN115205273A (en) * | 2022-07-26 | 2022-10-18 | 富联裕展科技(深圳)有限公司 | Size detection method and device, electronic equipment and readable storage medium |
| WO2024182912A1 (en) * | 2023-03-03 | 2024-09-12 | 京东方科技集团股份有限公司 | Image collection method, image collection apparatus and defect detection method |
| CN120765606A (en) * | 2025-07-02 | 2025-10-10 | 大连斯频德环境设备有限公司 | A polyvinyl chloride sheet defect detection method and system based on image recognition |
| CN120765606B (en) * | 2025-07-02 | 2025-12-23 | 大连斯频德环境设备有限公司 | A method and system for defect detection of polyvinyl chloride sheets based on image recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4414533B2 (en) * | 1999-12-27 | 2010-02-10 | 株式会社日立ハイテクノロジーズ | Defect inspection equipment |
| CN201440128U (en) * | 2009-07-13 | 2010-04-21 | 北京航星科技有限公司 | An Automatic Optical Inspection System Oriented to PCB Defect Inspection |
| CN204594418U (en) * | 2015-03-05 | 2015-08-26 | 广州机械科学研究院有限公司 | A kind of Glue Spreading Robot tree lace automatic detection device |
| CN105445277A (en) * | 2015-11-12 | 2016-03-30 | 湖北工业大学 | Visual and intelligent detection method for surface quality of FPC (Flexible Printed Circuit) |
| CN105466951A (en) * | 2014-09-12 | 2016-04-06 | 江苏明富自动化科技股份有限公司 | Automatic optical detection apparatus and detection method thereof |
| CN105701492A (en) * | 2014-11-25 | 2016-06-22 | 宁波舜宇光电信息有限公司 | Machine vision identification system and implementation method thereof |
-
2016
- 2016-09-01 CN CN201610807384.7A patent/CN107796825B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4414533B2 (en) * | 1999-12-27 | 2010-02-10 | 株式会社日立ハイテクノロジーズ | Defect inspection equipment |
| CN201440128U (en) * | 2009-07-13 | 2010-04-21 | 北京航星科技有限公司 | An Automatic Optical Inspection System Oriented to PCB Defect Inspection |
| CN105466951A (en) * | 2014-09-12 | 2016-04-06 | 江苏明富自动化科技股份有限公司 | Automatic optical detection apparatus and detection method thereof |
| CN105701492A (en) * | 2014-11-25 | 2016-06-22 | 宁波舜宇光电信息有限公司 | Machine vision identification system and implementation method thereof |
| CN204594418U (en) * | 2015-03-05 | 2015-08-26 | 广州机械科学研究院有限公司 | A kind of Glue Spreading Robot tree lace automatic detection device |
| CN105445277A (en) * | 2015-11-12 | 2016-03-30 | 湖北工业大学 | Visual and intelligent detection method for surface quality of FPC (Flexible Printed Circuit) |
Non-Patent Citations (1)
| Title |
|---|
| 胡文娟: "基于机器视觉的PCB光板缺陷检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108387182A (en) * | 2018-05-17 | 2018-08-10 | 广东省智能制造研究所 | A kind of aperture measurement device and measuring apparatus |
| CN109544533A (en) * | 2018-11-23 | 2019-03-29 | 聚时科技(上海)有限公司 | A kind of metal plate defect detection and measure based on deep learning |
| CN109813725A (en) * | 2019-04-02 | 2019-05-28 | 东莞博美特自动化科技有限公司 | A kind of large scale glue defect inspection method |
| CN110208268A (en) * | 2019-05-16 | 2019-09-06 | 昆山弗莱吉电子科技有限公司 | The detection system of VCM elastic slice |
| CN110288584A (en) * | 2019-06-27 | 2019-09-27 | 常州固高智能装备技术研究院有限公司 | Ceramic hot-dip aluminizing detection method of surface flaw and device based on machine vision |
| CN110288584B (en) * | 2019-06-27 | 2023-06-23 | 常州固高智能装备技术研究院有限公司 | Ceramic hot dip aluminizing surface defect detection method and device based on machine vision |
| CN110473250A (en) * | 2019-07-31 | 2019-11-19 | 苏州中科全象智能科技有限公司 | Accelerate the method for Blob analysis in a kind of processing of machine vision |
| CN110389131A (en) * | 2019-08-21 | 2019-10-29 | 汕头市结核病防治所(汕头市呼吸系疾病防治所) | A sputum qualified inspection device |
| CN110636715B (en) * | 2019-08-27 | 2021-07-13 | 杭州电子科技大学 | An automatic welding and defect detection method based on self-learning |
| CN110636715A (en) * | 2019-08-27 | 2019-12-31 | 杭州电子科技大学 | An automatic welding and defect detection method based on self-learning |
| CN110838149B (en) * | 2019-11-25 | 2020-10-23 | 创新奇智(广州)科技有限公司 | Camera light source automatic configuration method and system |
| CN110838149A (en) * | 2019-11-25 | 2020-02-25 | 创新奇智(广州)科技有限公司 | Camera light source automatic configuration method and system |
| CN111083386A (en) * | 2019-12-24 | 2020-04-28 | 维沃移动通信有限公司 | Image processing method and electronic device |
| CN111083386B (en) * | 2019-12-24 | 2021-01-22 | 维沃移动通信有限公司 | Image processing method and electronic device |
| CN111260622A (en) * | 2020-01-14 | 2020-06-09 | 湖南城市学院 | Equipment for installing electrical devices inside switch cabinet and control method |
| CN111640131B (en) * | 2020-05-29 | 2021-05-18 | 广东利元亨智能装备股份有限公司 | Cell coating detection method, device and electronic equipment |
| CN111640131A (en) * | 2020-05-29 | 2020-09-08 | 广东利元亨智能装备股份有限公司 | Battery core gluing detection method and device and electronic equipment |
| CN111999314B (en) * | 2020-10-28 | 2021-02-05 | 南京大量数控科技有限公司 | Device and method for automatically checking deformation of flexible PCB in processing process |
| CN111999314A (en) * | 2020-10-28 | 2020-11-27 | 南京大量数控科技有限公司 | A device and method for automatically inspecting deformation during processing of flexible PCB |
| CN112557407A (en) * | 2021-02-24 | 2021-03-26 | 常州微亿智造科技有限公司 | Optical detection module and optical detection method for detecting corner defects of notebook computer shell |
| CN112557407B (en) * | 2021-02-24 | 2023-08-25 | 常州微亿智造科技有限公司 | Optical detection module and optical detection method for detecting corner defects of notebook shell |
| CN115082660A (en) * | 2022-07-01 | 2022-09-20 | 联想(北京)有限公司 | Information processing method, device, electronic device and storage medium |
| CN115205273A (en) * | 2022-07-26 | 2022-10-18 | 富联裕展科技(深圳)有限公司 | Size detection method and device, electronic equipment and readable storage medium |
| WO2024182912A1 (en) * | 2023-03-03 | 2024-09-12 | 京东方科技集团股份有限公司 | Image collection method, image collection apparatus and defect detection method |
| CN120765606A (en) * | 2025-07-02 | 2025-10-10 | 大连斯频德环境设备有限公司 | A polyvinyl chloride sheet defect detection method and system based on image recognition |
| CN120765606B (en) * | 2025-07-02 | 2025-12-23 | 大连斯频德环境设备有限公司 | A method and system for defect detection of polyvinyl chloride sheets based on image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107796825B (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107796825A (en) | Device inspection method | |
| CN104091766B (en) | System and method for inspecting wafer | |
| CN101783306B (en) | Systems and methods for inspecting wafers | |
| JP3560694B2 (en) | Lens inspection system and method | |
| CN102439708B (en) | Method of inspecting bonding structure of substrate and bonding structure inspection apparatus | |
| US6201600B1 (en) | Method and apparatus for the automatic inspection of optically transmissive objects having a lens portion | |
| CN101853797A (en) | Systems and methods for inspecting wafers | |
| TWI695164B (en) | Broadband wafer defect detection system and broadband wafer defect detection method | |
| CN106537110A (en) | System and method for inspecting spectacle lenses | |
| JP2013539052A (en) | Retro-reflective imaging | |
| CN106226270B (en) | The method of the dirty defect of detection image sensor surface | |
| CN101471272B (en) | Automatic flaw detection device and method for substrate laser repairing machine | |
| JP2012242148A (en) | Appearance inspection apparatus and appearance inspection method of transparent bottle | |
| KR102678467B1 (en) | Optical inspection device and method of optical inspection | |
| JPH0886716A (en) | System and method of lens inspection | |
| TWI622764B (en) | Automatic optical inspection system for surface foreign matter detection | |
| CN115714103B (en) | Apparatus and method for wafer bond alignment and inspection | |
| KR102433319B1 (en) | Vision inspection method of diffusing lens for led light source | |
| KR101608891B1 (en) | Defect inspecting apparatus and method for ir filter with ir coating layer | |
| TW201730550A (en) | Inspection apparatus comprising a test object holding means, a defect detection means, and a three-dimensional measurement means, and capable of shortening the time required for the inspection of an object under test | |
| JP2005091025A (en) | Lens fixing device and method | |
| JP3339677B2 (en) | Screen for surface condition inspection and inspection device using the screen | |
| TWI855614B (en) | Automatic optical re-inspecting system for multiple re-inspection and multiple re-inspection method | |
| US20190257876A1 (en) | System and method for detecting defects in an electronic device | |
| CN111175302A (en) | Optical image automatic capture method for complex detection conditions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |