CN107796825B - Device detection method - Google Patents
Device detection method Download PDFInfo
- Publication number
- CN107796825B CN107796825B CN201610807384.7A CN201610807384A CN107796825B CN 107796825 B CN107796825 B CN 107796825B CN 201610807384 A CN201610807384 A CN 201610807384A CN 107796825 B CN107796825 B CN 107796825B
- Authority
- CN
- China
- Prior art keywords
- light source
- image
- shadowless
- detection
- tested
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 90
- 230000007547 defect Effects 0.000 claims abstract description 45
- 238000012360 testing method Methods 0.000 claims abstract description 38
- 230000001678 irradiating effect Effects 0.000 claims abstract description 12
- 239000003292 glue Substances 0.000 claims description 73
- 238000000034 method Methods 0.000 claims description 50
- 230000008569 process Effects 0.000 claims description 24
- 238000007689 inspection Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 19
- 238000004026 adhesive bonding Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 8
- 238000005286 illumination Methods 0.000 claims description 8
- 230000002950 deficient Effects 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 239000002245 particle Substances 0.000 description 23
- 230000000007 visual effect Effects 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 6
- 238000010191 image analysis Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 238000000149 argon plasma sintering Methods 0.000 description 4
- 238000007650 screen-printing Methods 0.000 description 4
- 238000011109 contamination Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 239000008188 pellet Substances 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000008187 granular material Substances 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
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 device detection method, which comprises the following steps: irradiating the surface of the device to be tested by using a first light source, and photographing the device to be tested under the irradiation of the first light source to obtain a first image; positioning the device under test according to the first image; irradiating the surface of the tested device by using a second light source, and photographing the tested device under the irradiation of the second light source to obtain a second image; and analyzing the second image to determine whether the tested device is qualified. The invention can carry out positioning detection and defect detection on the device, not only ensures the accurate position of the device, but also can detect whether the device is a qualified device, thereby being beneficial to carrying out subsequent operations such as alignment, assembly and the like on the device and effectively improving the quality of products. In addition, the invention also realizes the integrated execution of positioning and defect detection, and can avoid the transfer of devices among different stations during detection, thereby improving the detection efficiency.
Description
Technical Field
The present invention relates to the field of device inspection, and in particular, to a device inspection method.
Background
In the development of Active Alignment (AA) devices, a Flexible Printed Circuit (FPC) assembly needs to be painted, and the FPC assembly and a lens assembly (the lens assembly includes a lens and a motor, and the motor may be a Voice Coil Motor (VCM), so the lens assembly may be referred to as a VCM assembly) need to be positioned to a pre-defined position before an AA operation can be performed.
In the alignment process, the positions of the FPC assembly and the VCM assembly in the jig may deviate, which may result in the AA operation not being able to accurately align the FPC and the VCM assembly without performing positioning compensation. In utility model patent No. CN 205067834U, a lens suction jig for performing active alignment is disclosed. The jig can adsorb the lens, and can also enable an operator to adjust the relative position of the lens and the motor so as to align. Although this solution allows the alignment of the circuit board with the lens, it does not allow the detection of defects in the lens and the motor.
During actual production, in an AA manufacturing process and a previous manufacturing process of the component, defects such as particles, scratches and dirt are likely to occur on the surfaces of the FPC and the VCM, and if the AA operation is executed without detection, the FPC and the VCM with the defects are assembled, so that the product quality of the camera module is affected.
For the above technical problem, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a device detection method which can effectively detect the device and solve the problem of poor quality of an assembled product.
According to one aspect of the invention, a device inspection method is provided.
The device detection method according to the present invention includes: irradiating the surface of the device to be tested by using a first light source, and photographing the device to be tested by using image acquisition equipment under the irradiation of the first light source to obtain a first image; positioning the device under test according to the first image; irradiating the surface of the tested device by using a second light source, and photographing the tested device by using image acquisition equipment under the irradiation of the second light source to obtain a second image; and analyzing the second image to determine whether the tested device is qualified.
Wherein positioning the device under test from the first image comprises: carrying out binarization processing on the first image; analyzing the first image after the binarization processing, and determining the area of the device to be tested; and performing shape fitting according to the area of the device to be tested, and determining the central position and/or the current angle of the device to be tested.
Further, analyzing the second image includes: compensating the second image according to a preset compensation value, and performing binarization processing on the compensated second image; carrying out run-length coding on the pixel points of the second image after binarization processing, analyzing based on a coding result, and determining the size of a defect area; determining whether the circuit board is qualified or not according to the determined size of the defect area and a preset defect size threshold;
wherein the predetermined compensation value is determined by: and shooting under the irradiation of a second light source in advance to obtain a reference image, carrying out mean value filtering on the reference image, and determining a preset compensation value based on a difference value between the reference image subjected to the mean value filtering and the original reference image.
Specifically, when determining the size of the defective region, determining a connected region according to the result of run-length encoding, and then determining the size of the defective region according to the determined connected region; the determination of the connected region is completed through a plurality of determination processes, each determination process determines connectivity for the run-length nodes corresponding to two adjacent rows of pixels, and when the connectivity is determined, the determination of the connected region is processed in parallel in an OpenGL mode.
In addition, under the condition that the device to be tested is a circuit board, the first light source is a coaxial light source, the second light source is a shadowless light source, the coaxial light source is arranged adjacent to the shadowless light source, and the coaxial light source is arranged between the shadowless light source and the image acquisition equipment.
Further, the device inspection method according to the present invention may further include:
under the condition that the circuit board is qualified and the gluing of the circuit board is finished, photographing the glued surface of the circuit board through image acquisition equipment under the irradiation of a shadowless light source to obtain a third image; carrying out binarization processing on the third image, and extracting rubber threads from the binarized image; performing closed filling operation on the extracted glue line; if the closed filling operation is successfully executed, analyzing the glue line after the closed filling operation, determining the area and/or the width of the glue line, comparing the area and/or the width of the glue line with a preset area threshold and/or a preset width threshold, and judging whether the glue line is qualified; and if the closing and filling operation cannot be successfully performed because the extracted glue line does not form a closing area, judging that the glue line is unqualified.
Optionally, the coaxial light source includes a light emitting device and a reflector, wherein the reflector is located on an outgoing light path of the light emitting device and forms an angle of 45 degrees with an extending direction of the outgoing light path, and the light emitting device is configured to emit infrared light waves or white light. The light emitting device in the shadowless light source is arranged in an annular shape and is used for emitting shadowless blue light.
In addition, when the second image is obtained by photographing, the photographing is carried out by means of dark field illumination, and the distance between the shadowless light source and the circuit board is controlled to be between 5mm and 15 mm.
When the device to be tested is the lens assembly, the first light source is a backlight source, and the second light source is a shadowless light source. The backlight source is used for emitting white light, the shadowless light source is a dome light source, the image acquisition equipment is arranged adjacent to the shadowless light source and located on one side of the shadowless light source, the backlight source is located on the other side of the shadowless light source, and a space is reserved between the backlight source and the shadowless light source.
The invention can realize the following technical effects:
(1) the invention can carry out positioning detection and defect detection on the device, not only ensures the accurate position of the device, but also can detect whether the device is a qualified device, thereby being beneficial to carrying out subsequent operations such as alignment, assembly and the like on the device and effectively improving the quality of products;
(2) the invention realizes the integrated execution of positioning and defect detection, adopts the same image acquisition equipment to shoot the image of the tested device (lens component or circuit board), can shoot the image for positioning and defect detection under the irradiation of different light sources at the same station, can effectively improve the detection efficiency, can reduce the volume of the detection equipment, reduces the complexity of the detection equipment and is beneficial to controlling the cost; meanwhile, the device can be prevented from being transferred among different stations during detection, so that the detection efficiency is improved;
(3) when the defect detection is carried out, the image is compensated through the compensation value in advance, and then binarization processing is carried out, so that the noise in the image can be effectively reduced, the influence of interference (such as signal interference, camera pixel fluctuation and the like) on the detection result is avoided, and the detection accuracy is ensured;
(4) by adopting OpenGL, the hardware acceleration can be carried out on the defect detection process, so that the detection efficiency is improved;
(5) when the circuit board is detected, the glue line is detected in a closed filling mode, so that whether the defect of glue breaking exists can be effectively detected, the width and/or the area of the glue line can be determined, the gluing quality is further ensured, and the potential quality hazard of a device after assembly is effectively avoided;
(6) according to the invention, the infrared light is adopted to irradiate the circuit board (and the chip on the circuit board) to position the circuit board, so that the light can pass through the silk screen of the chip, and the positioning is more accurate and effective;
(7) when defect detection is carried out, a dark field illumination mode is adopted to take a picture by utilizing a shadowless light source, so that defects such as stains, scratches and particles of a detected device can be subjected to transitional exposure and effectively distinguished from a background, the detection accuracy is improved, and misjudgment is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a method for testing FPC and VCM according to a device testing method of an embodiment of the present invention;
FIG. 2 is a flow chart of positioning an FPC assembly according to an embodiment of the present invention;
FIG. 3 is a flow diagram of positioning a VCM assembly according to an embodiment of the present invention;
FIG. 4 is a flow chart of defect detection according to an embodiment of the present invention;
FIG. 5 is a flow chart of run length encoding when detecting FPC surface according to an embodiment of the present invention;
FIG. 6 is a flow chart of blob determination when detecting the FPC surface according to an embodiment of the present invention;
FIG. 7 is a flow chart illustrating the process of glue line detection on the FPC according to an embodiment of the present invention;
fig. 8 is a structural view of a detecting apparatus of a wiring board according to an embodiment of the present invention;
fig. 9 is a structural diagram of a VCM detection apparatus according to an embodiment of the present invention.
Detailed Description
This description of the illustrative embodiments should be taken in conjunction with the accompanying drawings, which are to be considered part of the complete specification. In the drawings, the shape or thickness of the embodiments may be exaggerated and simplified or conveniently indicated. Further, the components of the structures in the drawings are described separately, and it should be noted that the components not shown or described in the drawings are well known to those skilled in the art.
Any reference to directions and orientations to the description of the embodiments herein is merely for convenience of description and should not be construed as limiting the scope of the invention in any way. Relative terms, such as "lower," "higher," "horizontal," "vertical," "above," "below," "upper," "lower," "top" and "| bottom" as well as derivatives thereof (e.g., "horizontally," "downwardly," "upwardly," etc.) should be construed to describe the orientation as then described or as shown in the drawings. These relative terms are for convenience of description only and should not be construed as an explanation of the instrumentation or as specific operations in a particular orientation. Terms such as "attached … …" (affixed), "affixed … …", "attached" and "connected to each other" refer to a relationship wherein a structure is directly or indirectly through intervening structures, affixed or attached to another structure, unless expressly described otherwise, including movable or fixed or associated. Furthermore, the features and advantages of the present invention are described with reference to the preferred embodiments. Thus, the preferred embodiments illustrate possible non-limiting combinations of features that may exist individually or in combination, and the invention is not particularly limited to the preferred embodiments. The scope of the invention is defined by the claims.
According to an embodiment of the present invention, there is provided a device inspection method.
The method can be used for detecting a circuit board (such as an FPC (flexible printed circuit) and an IR (infrared) chip mounted on the FPC) and detecting a lens assembly, can be independently applied to detect a certain device, and can also be executed in parallel on a plurality of devices needing AA (advanced micro electro mechanical systems) process and assembly, so that the devices participating in assembly are aligned with each other and have no defects. The lens assembly described herein includes a lens and a motor, and optionally, the motor in the lens assembly may be a Voice Coil Motor (VCM), and in this case, the lens assembly may be referred to as a VCM assembly.
The device detection method according to the embodiment of the invention comprises the following steps:
step S101, a first light source irradiates the surface of a tested device, and the tested device is photographed through image acquisition equipment under the irradiation of the first light source to obtain a first image;
step S102, positioning the device to be tested according to the first image;
step S103, irradiating the surface of the device to be tested by a second light source, and photographing the device to be tested by image acquisition equipment under the irradiation of the second light source to obtain a second image;
and step S104, analyzing the second image and determining whether the tested device is qualified.
In practical application, the above steps may be reversed, that is, the second image may be taken first to check whether the device under test is qualified, and then the first image may be taken to locate the device under test.
Under the condition that the device to be tested is a circuit board, the surface of the circuit board presents mirror reflection; and in the case where the device under test is a lens assembly, the lens assembly (which may be a VCM assembly, for example) has a light transmitting member (i.e., a light passing hole). In one embodiment, when positioning the device under test according to the first image, specifically, the following steps may be included:
carrying out binarization processing on the first image;
analyzing the first image after the binarization processing, and determining the area of the device to be tested;
and performing shape fitting (for example, rectangular fitting) according to the area of the tested device, and determining the central position and/or the current angle of the tested device.
In addition, in the case of a smooth surface of the device under test, the device under test will exhibit specular reflection, and when a defect such as a Particle (Particle) exists on the surface of the device under test, diffuse reflection will occur thereon. In one embodiment, in order to check whether the device under test has defects such as particles, the following steps may be specifically included in the analysis of the second image:
compensating the second image according to a preset compensation value, and performing binarization processing on the compensated second image;
carrying out run-length coding on pixel points of the second image after binarization processing, analyzing based on a coding result, and determining the size of a defect area (for example, for stains, the area thereof can be determined; for scratches, the length, the depth and/or the area thereof can be determined; for particles, the diameter, the volume and/or the projection area thereof can be determined);
determining whether the circuit board is qualified according to the determined size of the defect area and a preset defect size threshold (for example, whether the area of the stain exceeds the area threshold; whether the length, the depth and/or the area of the scratch exceeds the corresponding threshold; whether the diameter, the volume and/or the projected area of the particle exceeds the corresponding threshold);
wherein the predetermined compensation value is determined by: and shooting under the irradiation of a second light source in advance to obtain a reference image, carrying out mean value filtering on the reference image, and determining a preset compensation value based on a difference value between the reference image subjected to the mean value filtering and the original reference image. In practical application, the reference image may be an image obtained by shooting a first device under test under irradiation of the second light source, and after determining the compensation value, the compensation value may be used for compensating the corresponding image for a subsequently detected device; alternatively, the compensation value may be re-determined for each device under test.
The image to be detected of the detected device is compensated by adopting the compensation value, and then binarization processing is carried out, so that the noise in the image can be effectively reduced, the influence of interference (such as signal interference and camera pixel fluctuation) on the detection result is avoided, and the detection accuracy is ensured. In one embodiment, the compensation value may be less than or equal to a difference between the mean filtered reference image and the original reference image, and may be greater than a fluctuation range of the image acquisition device.
Alternatively, in one embodiment, when determining the area of the defect region, the connected region may be determined according to the result of run-length encoding, and then the area of the defect region may be determined according to the determined connected region; the determination of the connected region is completed through a plurality of determination processes, each determination process determines connectivity for the run-length nodes corresponding to two adjacent rows of pixels, and when the connectivity is determined, the determination of the connected region is processed in parallel in an OpenGL mode. Therefore, the hardware acceleration can be carried out on the defect detection process, and the detection efficiency is improved.
In one embodiment, the device under test is a wiring board. At this time, the surface of the device under test exhibits specular reflection, and for detection, the first light source is a coaxial light source, the second light source is a shadowless light source, the coaxial light source and the shadowless light source are arranged adjacently, and the coaxial light source is arranged between the shadowless light source and the image acquisition equipment for photographing the device under test.
In one embodiment, the detection method can detect the gluing condition of the circuit board, and the glue line can present obvious bulges on the device. In particular, the following steps may be performed to complete the detection of the glue line:
under the condition that the circuit board is qualified and the gluing of the circuit board is finished, photographing the glued surface of the circuit board through image acquisition equipment under the irradiation of a shadowless light source to obtain a third image;
carrying out binarization processing on the third image, and extracting rubber threads from the binarized image;
performing closed filling operation on the extracted glue line;
if the closed filling operation is successfully executed, analyzing the glue line after the closed filling operation, determining the area and/or the width of the glue line, comparing the area and/or the width of the glue line with a preset area threshold and/or a preset width threshold, and judging whether the glue line is qualified;
and if the closing and filling operation cannot be successfully performed because the extracted glue line does not form a closing area, judging that the glue line is unqualified.
The glue line is detected in a closed filling mode, so that whether the defect of glue breaking exists can be effectively detected, the width and/or the area of the glue line can be determined, the gluing quality is further ensured, and the potential quality hazard of a device after assembly is effectively avoided.
Moreover, through adopting same image acquisition equipment to shoot the circuit board, can shoot the image that is used for location, defect detection, gluey line to detect under the light source of difference shines at same station, not only can effectively improve detection efficiency, but also can reduce check out test set's volume, reduce check out test set's complexity, help control cost.
Optionally, when the circuit board is detected, the coaxial light source includes a light emitting device and a reflector, where the reflector is located on an outgoing light path of the light emitting device and forms an angle of 45 degrees with an extending direction of the outgoing light path. In order to enable light to penetrate through the silk screen printing of the chip on the circuit board, the light-emitting device can be used for emitting infrared light waves, and therefore detection is more effective and accurate.
In one embodiment, the light emitting device in the shadowless light source is arranged in a ring shape and used for emitting shadowless blue light when the circuit board is detected. And when the second image is obtained by photographing, photographing is carried out in a dark field illumination mode. Through adopting dark field illumination's mode, can let defects such as the stain of device under test, mar, granule transit exposure, effectively distinguish mutually with the background to improve the degree of accuracy that detects, avoided erroneous judgement. In addition, in order to improve the shooting effect, the distance between the shadowless light source and the circuit board can be controlled to be between 5mm and 15 mm.
In addition, when the device to be measured is a lens unit, a light transmitting member (i.e., a light transmitting hole) is provided in the lens unit, the first light source is a backlight, and the second light source is a shadowless light source.
At the moment, the backlight source is used for emitting white light, the shadowless light source is a dome light source, the image acquisition equipment for photographing the device to be tested is arranged adjacent to the shadowless light source and is positioned on one side of the shadowless light source, the backlight source is positioned on the other side of the shadowless light source, and a space is reserved between the backlight source and the shadowless light source so as to place the lens component to be tested. The lower end face of the lens component is provided with a certain radian usually, so that the dome light source can effectively adapt to the radian, the defects of the lower end face of the lens component are accurately reflected in the photographed image, and the detection accuracy is effectively improved.
Examples of the invention
The detection method according to the present invention will be described below taking an AA device as an example. In this example, the detection methods according to the embodiments of the present invention are performed in parallel, and the FPC assembly and the VCM assembly are positioned and detected, respectively.
As shown in fig. 1, the process of inspecting the FPC assembly and the VCM assembly according to the pre-inspection method of the present invention is as follows.
For FPC assemblies, the following detection steps may be performed:
(1) when the FPC assembly is detected, the positions and parameters (including aperture, exposure time, light source brightness, and the like) of the camera and the light source may be adjusted first, which specifically includes: adjusting the position of the camera in the vertical direction to enable the chip of the FPC assembly to be in a focusing position, adjusting the exposure time and gain of the camera to enable the chip of the FPC assembly to be clearly imaged, and adjusting the positions of the coaxial light source and the shadowless light source respectively to enable the light source to be uniformly irradiated on the chip of the FPC assembly;
(2) and then, calibrating the parameters of the visual system, specifically, calibrating a camera through a calibration board, calculating the proportional relation between the pixel size and the actual size, and storing the proportional relation as the system parameters.
(3) For the detection of the FPC assembly, the equipment parameters and the process parameters can be set for the images of the chip positioning center and the angle of the FPC assembly under a coaxial light source; here, the FPC to be measured needs to be conveyed to a measurement position, and the relative position between the camera and the FPC is adjusted;
(4) and then, respectively carrying out equipment parameter and process parameter setting on the images of the IR surface stain detection and the FPC assembly glue line detection of the FPC assembly under a shadowless light source. The parameters set here mainly include a stain area threshold, a scratch length threshold, a scratch depth threshold, a particle volume threshold, a particle diameter threshold, a glue line area threshold, a glue line width threshold, a glue line gap width threshold (when the presence of a gap in a glue line is detected and the gap width is less than the width threshold, it is considered that no glue break has occurred), and the like.
After the system is started, the camera is operated to the detection position to start detection. For FPC, the following three items can be detected:
item 1: when the coaxial light source is started, a camera takes a picture (obtains a first image of the FPC) and carries out visual image analysis, and the center and the angle of a chip of the FPC assembly are positioned;
item 2: after the chip of the FPC assembly is positioned, the coaxial light source is closed, the shadowless light source is started, the camera photographs (obtains a second image of the FPC) and performs visual image analysis, and particles, scratches, stains and the like on the IR surface of the FPC assembly are detected; if particles, scratches, stains and the like exist and the size of the particles, the scratches, the stains and the like exceeds a preset threshold value, an alarm is given, and the next module test is started after the test is finished;
item 3: if no particles, scratches and the like exist, the glue dispensing mechanism performs glue drawing on the FPC assembly, a shadowless light source is started to perform glue line detection after the glue drawing is completed, a camera photographs (obtains a third image of the FPC) and performs visual image analysis, and the integrity and the glue width of the glue line are detected; and if the glue is broken or the glue width is unqualified, giving an alarm prompt, and ending the test to start the next module test. And if the glue line is normal, the FPC assembly passes the test, waits for the AA process, and starts the test of the next FPC assembly.
Similarly, for the VCM assembly, the setting of the above parameters (including the area threshold of the stain, the length threshold of the scratch, the depth threshold of the scratch, the volume threshold of the pellet, the diameter threshold of the pellet, the area threshold of the glue line, and for the VCM assembly, the parameter threshold related to the glue line may not be set) and the detecting steps are also completed:
(1) for VCM component detection, the position and parameters of the camera and the light source (including aperture, exposure time, light source brightness, etc.) are also adjusted first, and the parameters of the vision system are also calibrated, in a manner similar to that used in the FPC component detection step, and this is not repeated here;
(2) then, setting a VCM component lens positioning parameter under the irradiation of the backlight source;
(3) setting surface particle testing parameters under a Lens02 surface of the VCM component under a dome light source;
(4) then, the camera may be run to the detection position, and the VCM assembly is detected for the following two items:
item 1: and (3) taking a picture (obtaining a first image of the VCM component) by the camera under the condition that the backlight source is started, carrying out visual image analysis, and positioning the center and the angle of the VCM component.
Item 2: after the VCM component Lens is positioned, the backlight source is closed, the dome light source is started, the camera photographs (obtains a second image of the VCM component) and performs visual image analysis, and particles, scratches and the like on the lower end face of the Lens02 of the VCM component are detected; if particles, scratches and the like exist, giving an alarm for prompting, and ending the test to start the next module test; if there are no particles, scratches, etc., the VCM assembly passes the test and the AA process is performed with the FPC assembly.
The method shown in fig. 1 can be applied to AA equipment, and the FPC assembly and the VCM assembly are respectively detected before the FPC assembly and the VCM assembly are aligned and assembled, thereby effectively improving the module yield of the AA process.
FPC assembly positioning method
As shown in fig. 2, based on the first image, the positioning of the FPC assembly may be achieved by:
firstly, acquiring a frame of image;
then, segmenting the image based on the binarization threshold value;
determining the area of a chip of the FPC assembly in a Blob analysis mode;
and the center and the angle of the FPC assembly chip are positioned in a rectangular fitting mode.
VCM component positioning method
As shown in fig. 3, based on the first image, the positioning of the VCM assembly can be achieved by:
firstly, acquiring a frame of image;
then, segmenting the image based on the binarization threshold value;
determining the area of a clear hole (Lens) of the VCM component in a Blob analysis mode;
and positioning the center of the light through hole of the VCM component in a circular fitting mode, and then fitting the angle.
Defect detection method
As shown in fig. 4, for the FPC assembly or the VCM assembly, when detecting the defect from the second image, the following steps may be performed:
firstly, acquiring a frame of image;
then, performing mean filtering to smooth the image;
next, performing dynamic threshold segmentation, and extracting a defect region (which may be a stain, a scratch, or the like, for example);
then, Blob analysis is performed, the area of each stain is calculated, and the area is compared with a process parameter, which may be a predetermined stain area threshold, and if the requirements of the process parameter are met, the product is considered to be a qualified product, otherwise the product is considered to be an unqualified product.
The defect detection method according to the present invention will be described in detail below, taking the surface particle, scratch detection on the IR of the FPC assembly as an example. Similar methods can be used for defect detection of the VCM component, and similar beneficial effects can be achieved.
The inspection of the IR upper surface of the FPC assembly may be performed in a dark field illuminated environment.
Under dark field illumination, the dirty spots such as particles, scratches, etc. are much brighter than the IR surface, and appear as white bright spots, and when surface inspection is performed, the dynamic threshold segmentation can be described as: if the image after the average filtering is g _ mean (x, y), the original image is g _ origin (x, y), and if the detection region satisfies g _ origin (x, y) -g _ mean (x, y) > — offset, it is considered that there is a defect, where offset is a fixed compensation value, and in order to avoid erroneous determination due to fluctuation (noise) of the camera pixels, in this example, the offset may be set to a value larger than the fluctuation range of the camera pixels.
In the case where the image of the device under test photographed under the illumination of the shadowless light source is first compensated by offset and then subjected to the binary segmentation, the binary-segmented image is compensated, and thus a dynamic binary segmentation threshold is used.
After image binarization is realized according to the dynamic threshold, Blob judgment of a fast binary image can be realized by adopting a run length coding mode. The run-length encoding of the image is to represent a series of repeated pixel values by one pixel value and one count value, and the specific algorithm flow is shown in fig. 3.
Referring to fig. 5, when run-length encoding is performed, the method specifically includes the following steps:
scanning binary images line by line, and comparing the relation of adjacent pixels in a line;
when the two pixels show '01' jump, recording the position of 1 pixel as the initial position of the current run;
when the two pixels show '10' jump, recording the position of 1 pixel as the end position of the current run;
recording the information of the run and continuously scanning the next run of the current line;
if the scanning of the line is finished, the next line is switched to, otherwise, the jumping of the pixel is continuously judged; when the next row is switched to, if the current row does not exceed the last row, continuously judging the jump of the pixels on the current row; and if the last line is exceeded, completing scanning and acquiring all runs of the current binary image.
When Blob determination is performed based on the run-length encoding result, the image may be scanned in the order from top to bottom and from left to right, and only two adjacent lines of data in the image may be processed at a time. Assume that the two dynamic linked lists of images, ThisRow and LastRow, point to all the run nodes of the current and previous lines, respectively. And judging the communication relation between each run node in the ThisRow and the eight-connected region between each run node in the last LastRow, and converting the mark of the connected region into the analysis on the connectivity of the run nodes in the dynamic linked list. If the run is connected, merging the run into a Blob class to which the LastRow run belongs; otherwise, a new Blob class is assigned for the run.
As shown in fig. 6, the specific procedure for Blob determination is as follows:
first, scanning a ThisRow line;
then, corresponding processing is carried out according to the connection relation between the runs of the ThisRow lines and the LastRow lines;
judging whether the last run of the ThisRow line is present, and if the last run is present, updating a linked list pointer LastRow-ThisRow and ThisRow + +; otherwise, continuing to process according to the connection relation between the runs of the ThisRow lines and the LastRow lines;
next, if the last line has been exceeded, the process ends; otherwise, the next ThisRow line continues to be scanned.
By the defect detection method, the IR chip can be inspected, the image effective area is morphologically processed, and the sizes of particles, scratches and the like are quantified, so that the subsequent alignment and assembly processes of the IR and VCM assemblies with defects are avoided.
By adopting a compensation means, the binary segmentation of the dynamic threshold can be realized, and the situation that the fixed threshold cannot effectively distinguish the foreground from the background due to the image difference caused by the individual difference of the measured object and the instability of a camera, a light source and the like is prevented.
Glue line inspection method
After the AA process is completed on the FPC assembly chip and the VCM assembly, the UV glue needs to be used for bonding, and the integrity of the glue and the reasonability of the width of the glue directly influence the stability of the subsequent use of the module. Under the condition of shadowless blue light highlight polishing, glue on the FPC assembly is in a black strip shape.
As shown in fig. 7, in one embodiment of the present invention, the glue line detection can be performed by the following scheme:
firstly, acquiring a frame of image;
next, segmenting the image by a binary threshold;
then, performing opening operation;
then, after the image is binarized, eliminating invalid information in the image; extracting effective glue lines through the characteristics of shape, area, length-width ratio and the like; after the glue line is determined, filling the whole area of the glue line so as to judge whether glue break exists;
next, whether the parameters of the filled glue line region meet the parameter requirements or not is compared through Blob analysis, for example, whether the area of the glue line reaches an area threshold or not, and whether the width of the glue line reaches a width threshold or not. Through above-mentioned scheme, realize gluing width and the detection of gluing line integrality with the help of judging the regional area size of gluey line, can prevent that the module from appearing bad scheduling problems such as light leak after accomplishing AA technology, effectively ensured product quality.
FPC detection equipment
In one embodiment of the present invention, the detection device shown in fig. 8 may be employed to detect the FPC assembly.
As shown in fig. 8, the detection apparatus includes: a coaxial light source 11, a shadowless light source 12, an image capture device (which may be a camera, for example) 13, and a lens 14, the coaxial light source 11 being disposed proximate to the shadowless light source 12, the coaxial light source 11 being disposed between the shadowless light source 12 and the lens 14, the lens 14 being connected to the camera 13; the coaxial light source 11 is used for irradiating when positioning a chip of the circuit board; the shadowless light source 12 is used for irradiating when the defect detection is carried out on the chip; the camera 13 is used for taking pictures when the coaxial light source 11 and the shadowless light source 12 are irradiated.
The detection device shown in fig. 8 can be applied to AA processes for positioning identification, glue line detection and dirt detection of the FPC assembly, and positioning identification and dirt detection of the VCM assembly. The image capture device may be a high pixel camera and the lens may be a macro lens.
When the FPC assembly is positioned and identified, the upper surface of the IR of the FPC assembly is made of glass and has good planeness, and a coaxial light source with good verticality and uniformity is selected. And the IR surface has coating films with different components, and for the FPC assembly with silk-screen printing on the IR surface, white light cannot completely penetrate through the IR sheet, and the reflectivity of silk-screen printing is similar to that of the IR, so that the characteristics are not obvious. The light on the surface of the IR can be reflected only by an infrared light source, and meanwhile, the infrared light source with the wavelength of 850nm is selected in consideration of the acceptable light wave wavelength of the industrial camera photosensitive chip; for the FPC assembly without silk screen printing on the IR surface, the chip can be shot by a common visible light penetrating IR surface, and shadowless blue light is selected in consideration of dirt detection.
When the dirt on the IR upper surface of the FPC assembly is detected, the dirt on the IR upper surface is mainly in the forms of particles, dust, scratches and the like, so that the characteristic of light scattering is utilized, and a dark field lighting mode is adopted, so that the bright spots generated by light scattering are overexposed by the dirt, and the dirt is separated from the background. An annular shadowless light source is selected to manufacture a dark field environment, and in addition, blue light with good scattering property and wavelength of 470nm is selected by the system in order to amplify the scattering property of light as much as possible to obtain an image with high contrast.
When the glue on the FPC assembly is broken and the glue width is detected, shadowless blue light can be used, and the glue line is obviously convex, so that the light is reflected at the glue line under high-brightness exposure, and the glue line is in a black strip shape relative to other parts of the FPC assembly.
VCM subassembly check out test set
In one embodiment of the present invention, the detection device shown in FIG. 9 may be employed to detect the VCM assembly.
As shown in fig. 9, the detection apparatus includes: a backlight 21, a dome light source 22, an image capture device (which may be a camera, for example) 23, and a lens 24, one end of the lens 24 being connected to the camera 23, the other end of the lens 24 being connected to the dome light source 22, the backlight 21 being disposed on a side of the dome light source 22 away from the lens 24, and a space being left between the backlight 21 and the dome light source 22; the backlight 21 is used for illuminating when the lens component is positioned; the shadowless light source 22 is used for irradiating when the lens component is subjected to defect detection; the camera 13 is used to take pictures when the backlight 21 and the dome light source 22 are illuminated, respectively.
The detection device shown in fig. 9 may be used for identification and contamination detection of the VCM assembly. The image capture device may be a high pixel camera and the lens may be a macro lens.
When the VCM component is positioned and identified, the center of the VCM component is a Lens light-transmitting hole, and the center of the VCM component is the center of the VCM component. And a high-brightness white backlight source is selected to ensure that the Lens light through hole is bright enough when the camera takes a picture, so that the picture is a white light spot. And under backlight illumination, the VCM component body is imaged to be black, and the edge of the VCM component body is clear in black and white.
When the dirt and the scratch of the end face of the Lens02 face of the VCM component are detected, the dirt mainly takes the forms of particles, dust, scratches and the like, and the characteristic of light scattering is utilized, so that the bright point generated by light scattering is overexposed by the dirt, and the dirt is distinguished from the background. Because the lower end surface of the Lens02 surface of the VCM component is in a certain radian, the round top light with better uniformity is selected.
In summary, the present invention provides a general visual inspection scheme, and the system integrates positioning and inspection functions, reduces the installation space of the device, saves the cost, can be used in the AA device, and realizes the visual auxiliary positioning function of the AA device actuator, and can also realize the inspection functions of stains, scratches and glue lines of the product in the AA manufacturing process. The scheme provided by the invention does not influence equipment UPH, can be used in AA equipment, can be popularized to relevant equipment with the processing procedures of automatic glue drawing, automatic glue dispensing, HA and VCM assembly and the like, can be used for realizing the positioning assistance and detection integrated function in occasions involving detection of automatic glue dispensing, glass contamination, scratch and the like, and HAs wide universality.
The detection scheme of the invention can be used for FPC assembly positioning identification and dirt detection: (1) the scheme can meet the requirements of visual positioning and visual detection precision; (2) the scheme can meet the detection requirements of FPC assembly particles, dirt and scratches and the detection requirements of glue width and glue breakage after glue drawing;
in addition, the detection scheme of the invention can be used for VCM component positioning identification and dirt detection: (1) the scheme can meet the requirements of VCM assembly visual positioning and visual detection precision; (2) the scheme can meet the detection requirement of the end surface contamination and scratch under the Lens02 surface.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (11)
1. A device inspection method, comprising: irradiating the surface of a tested device by using a first light source, and photographing the tested device by using image acquisition equipment under the irradiation of the first light source to obtain a first image; positioning the device under test according to the first image; irradiating the surface of the device to be tested by a second light source, and photographing the device to be tested by the same image acquisition equipment under the irradiation of the second light source to obtain a second image; analyzing the second image to determine whether the device under test is qualified;
the device detection method comprises the following steps of positioning a device to be detected and detecting defects of the device to be detected at the same station;
under the condition that the device to be tested is a circuit board, the first light source is a coaxial light source, the second light source is a shadowless light source, the image acquisition equipment is a camera, the camera is connected with a lens, the coaxial light source is arranged adjacent to the shadowless light source, and the coaxial light source is arranged between the shadowless light source and the image acquisition equipment; the coaxial light source is used for irradiating when a chip of the circuit board is positioned, the shadowless light source is used for irradiating when the chip is subjected to defect detection, and the camera is used for respectively photographing when the coaxial light source and the shadowless light source irradiate.
2. The device inspection method of claim 1, wherein locating the device under test from the first image comprises: carrying out binarization processing on the first image; analyzing the first image after the binarization processing, and determining the area of the device under test; and performing shape fitting according to the area of the device to be measured, and determining the central position and/or the current angle of the device to be measured.
3. The device inspection method of claim 1, wherein analyzing the second image comprises: compensating the second image according to a preset compensation value, and performing binarization processing on the compensated second image; carrying out run-length coding on the pixel points of the second image after binarization processing, analyzing based on a coding result, and determining the size of a defect area; determining whether the circuit board is qualified or not according to the determined size of the defect area and a preset defect size threshold; wherein the predetermined compensation value is determined by: and shooting under the irradiation of the second light source in advance to obtain a reference image, carrying out mean value filtering on the reference image, and determining the preset compensation value based on the difference value between the reference image subjected to mean value filtering and the original reference image.
4. The device inspection method according to claim 3, wherein in determining the size of the defective region, a connected component is determined based on a result of the run-length coding, and then the size of the defective region is determined based on the determined connected component; the determination of the connected region is completed through a plurality of determination processes, each determination process determines connectivity for the run-length nodes corresponding to two adjacent rows of pixels, and when the connectivity is determined, the determination of the connected region is processed in parallel in an OpenGL mode.
5. The device inspection method according to claim 1, further comprising: under the condition that the circuit board is qualified and the gluing of the circuit board is finished, photographing the glued surface of the circuit board through the image acquisition equipment under the irradiation of the shadowless light source to obtain a third image; carrying out binarization processing on the third image, and extracting rubber threads from the binarized image; performing closed filling operation on the extracted glue line; if the closed filling operation is successfully executed, analyzing the glue line after the closed filling operation, determining the area and/or the width of the glue line, comparing the area and/or the width of the glue line with a preset area threshold and/or a preset width threshold, and judging whether the glue line is qualified; and if the closing and filling operation cannot be successfully performed because the extracted glue line does not form a closed area, judging that the glue line is unqualified.
6. The device inspection method according to claim 1, wherein the coaxial light source comprises a light emitting device and a reflector, wherein the reflector is located on an exit light path of the light emitting device and forms an angle of 45 degrees with an extending direction of the exit light path.
7. The device inspection method of claim 6, wherein the light emitting device is configured to emit infrared light or white light.
8. The device inspection method of claim 1, wherein the light emitting devices in the shadowless light source are arranged in a ring shape to emit shadowless blue light.
9. The device inspection method according to claim 1, wherein when the second image is photographed, the photographing is performed by dark field illumination, and a distance between the shadowless light source and the circuit board is controlled to be 5mm to 15 mm.
10. The device inspection method according to claim 1, wherein in a case where the device under test is replaced with a lens assembly, the first light source is a backlight and the second light source is a shadowless light source.
11. The device inspection method of claim 10, wherein the backlight source is configured to emit white light, the shadowless light source is a dome light source, the image capture device is disposed adjacent to and on one side of the shadowless light source, the backlight source is disposed on the other side of the shadowless light source, and a space is left between the backlight source and the shadowless light source.
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 CN107796825A (en) | 2018-03-13 |
| CN107796825B true 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) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108387182B (en) * | 2018-05-17 | 2024-06-14 | 广东省智能制造研究所 | Aperture measuring device and measuring equipment |
| CN109544533B (en) * | 2018-11-23 | 2021-04-02 | 聚时科技(上海)有限公司 | Metal plate defect detection and measurement method 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 |
| CN110208268B (en) * | 2019-05-16 | 2023-04-18 | 昆山弗莱吉电子科技有限公司 | VCM shell fragment detecting system |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
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 |
|---|
| 基于机器视觉的PCB光板缺陷检测技术研究;胡文娟;《中国优秀硕士学位论文全文数据库 信息科技辑》;20071115(第5期);第7-14、16-20、46-61页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107796825A (en) | 2018-03-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107796825B (en) | Device detection method | |
| JP4389982B2 (en) | Substrate visual inspection device | |
| JP5410092B2 (en) | Apparatus and method for inspecting composite structures for inconsistencies | |
| US20130114074A1 (en) | Substrate inspection apparatus and substrate inspection method | |
| KR20170107952A (en) | Optical appearance inspection device and optical appearance inspection system using same | |
| KR101203210B1 (en) | Apparatus for inspecting defects | |
| KR100281881B1 (en) | cream solder inspection apparatus and the method thereof | |
| JP2008249568A (en) | Appearance inspection device | |
| JP2015227793A (en) | Inspection device of optical components and inspection method thereof | |
| TWI495867B (en) | Application of repeated exposure to multiple exposure image blending detection method | |
| JP2011208941A (en) | Flaw inspection device and flaw inspection method | |
| CN204882389U (en) | Optical detection device | |
| JP2010048602A (en) | Printed board inspection device and printed board inspection method | |
| KR20130108971A (en) | Inspection of defects in a contact lens | |
| KR20190114072A (en) | Optical inspection device and method of optical inspection | |
| KR101605000B1 (en) | Apparatus for inspecting substrate | |
| CN209745834U (en) | Optical defect detection system with brightness adjustment | |
| JP2014142256A (en) | Printing inspection device of glass bottle | |
| JP2009150835A (en) | Optical inspection method and optical inspection device | |
| TW202127012A (en) | Optical inspection apparatus and optical inspection method | |
| JP5272784B2 (en) | Optical inspection method and optical inspection apparatus | |
| JP4550610B2 (en) | Lens inspection device | |
| KR101198406B1 (en) | Pattern inspection device | |
| CN113490844B (en) | Foreign matter inspection device and foreign matter inspection method | |
| WO2021033396A1 (en) | Wafer appearance inspection device and method |
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 |