CN110501347A - A kind of rapid automatized Systems for optical inspection and method - Google Patents
A kind of rapid automatized Systems for optical inspection and method Download PDFInfo
- Publication number
- CN110501347A CN110501347A CN201910593111.0A CN201910593111A CN110501347A CN 110501347 A CN110501347 A CN 110501347A CN 201910593111 A CN201910593111 A CN 201910593111A CN 110501347 A CN110501347 A CN 110501347A
- Authority
- CN
- China
- Prior art keywords
- image
- collecting device
- image collecting
- workpiece
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000007689 inspection Methods 0.000 title claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 89
- 238000013439 planning Methods 0.000 claims abstract description 32
- 238000012876 topography Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims description 19
- 238000005259 measurement Methods 0.000 claims description 13
- 230000007547 defect Effects 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 description 10
- 238000003384 imaging method Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 239000003302 ferromagnetic material Substances 0.000 description 2
- 239000006247 magnetic powder Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
Landscapes
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of rapid automatized Systems for optical inspection and methods, and wherein method is the following steps are included: successively combine global image and topography to carry out detection path planning；According to the position of detection path clustering the first image collecting device and the second image collecting device of planning, and acquire the image information of workpiece to be detected；Optical detection is carried out to workpiece to be detected according to image information.The present invention is realized quickly positioning, and predict camera motion path, to realize High-Speed Automatic path planning, improves the efficiency of optical detection indirectly, can be widely applied to technical field of optical detection by being combined using global image drawn game area image.
Description
Technical field
The present invention relates to technical field of optical detection more particularly to a kind of rapid automatized Systems for optical inspection and methods.
Background technique
Enter automation, intelligentized developing period in industrial system, surface defects detection of the people to industrial products, ruler
Degree measurement request is higher and higher, simultaneously as the increase of human cost, the demand to automatic detection is also more more and more urgent.Especially
It is the product to high-precision degree type, such as display panel, FPC winding displacement, chip etc. should meet inspection during the manufacturing
The requirement of speed and precision is surveyed, while also to consider cost of labor and automation cost, to the need of on-line automaticization detection device
Ask more more and more urgent.
Currently used for the common detection method of high-precision product are as follows: (1) ultrasound examination；Pass through ultrasonic wave and detected material
Interaction carries out detection and the table of microcosmic detection, geometrical property measurement, institutional framework and mechanical property variation to detected material
Sign.This method has particular requirement to material, more to the detection of with complex shape or irregular contour detected material
It is difficult.Hardware limitation due to resolution ratio by its wavelength, the spatial resolution of ultrasound examination is all in hundred micron dimensions.(2)
Magnetic powder inspection detection.This method is contact measurement, is accumulated using magnetic powder near defect to detect at ferromagnetic materials surface
The method of defect, the technology can realize the detection of 0.1 millimeter of precision, have to the inspection of steel material or Surface Flaw crackle
Effect, but it is only applicable to ferromagnetic material, while remanent magnetism may generate certain influence to standby detectable substance surface.(3) Liquid penetrant testing.
This method checks System of Detecting Surface Defects For Material using capillary phenomenon, also belongs to detection method when contact, has certain limitation.
(4) vision-based detection；By machine vision product, certain light-source system of arranging in pairs or groups acquires the image information of detected material, and will figure
It is handled as information is transferred in image processing software.Visible detection method has excellent not available for other detection methods
Point: (a) can be realized non-contact measurement, reduce the possibility to detected material damage occurred in the detection process；(b) it can fit
Ying Xingqiang.Suitable light-source system and image capturing system are chosen to different detected materials, good detection effect can be achieved
Fruit；(c) stability is strong.The detection mode traditional compared to artificial detection etc., vision-based detection has very strong stability, in hardware item
In the case that part is certain, high-intensitive continuous detection may be implemented.
Although vision-based detection has stronger performance, it is directed to the high product testing of required precision, is still had
Question challenge；Wherein, detection speed is one of problem slowly, and current high-precision A OI detection system is high-precision due to needing to carry
Image capturing system is spent, Image Acquisition speed is slower, while the physical size of object to be detected that single acquisition arrives is smaller, causes
The detection speed of whole system is slow.Simultaneously because AOI system uses fixed route scanning imagery, to workpiece positioning requirements ten
It is point stringent, and position workpiece itself is a quite time-consuming processes.
Explanation of nouns:
AOI:Automated Optical Inspection, automatic optics inspection.
FPC:Flexible Printed Circuit, flexible circuit board.
Summary of the invention
In order to solve the above-mentioned technical problem, the object of the present invention is to provide one kind can quickly carry out automation optical detection
System and method.
First technical solution of the present invention is:
A kind of rapid automatized Systems for optical inspection, including image processing module, motion platform, the first image collector
Set, the second image collecting device and third image collecting device, described image processing module respectively with motion platform, the first image
Acquisition device, the second image collecting device are connected with third image collecting device；
The first image acquisition device is used to acquire the topography of workpiece to be detected；
Second image collecting device is used to acquire the image information of workpiece to be detected；
The third image collecting device is used to acquire the global image of workpiece to be detected；
The motion platform is used to control the first image collecting device according to the mobile message received and the second image is adopted
Acquisition means move together；
After described image processing module is for successively combining global image and topography to carry out detection path planning, according to
The detection coordinates measurement mobile message of planning is simultaneously sent to motion platform, and carries out light to workpiece to be detected according to image information
Learn detection.
Further, second image collecting device uses high-resolution industrial camera.
Further, the mobile platform includes X-axis mobile mechanism, Y-axis moving mechanism and Z axis mobile mechanism.
Further, light source is equipped on the first image acquisition device and the second image collecting device.
Second technical solution of the present invention is:
A kind of rapid automatized optical detecting method, comprising the following steps:
S1, successively global image and topography is combined to carry out detection path planning；
S2, the position for detecting path clustering the first image collecting device and the second image collecting device according to planning, and
Acquire the image information of workpiece to be detected；
S3, optical detection is carried out to workpiece to be detected according to image information.
Further, the step S1, specifically includes the following steps:
After global image and local image line pretreatment, the edge feature of global image and topography is extracted respectively；
The current coordinate position of the second image collecting device is obtained according to edge feature；
The mobile next coordinate position of the second image collecting device is obtained according to current coordinate position.
Further, it is adopted in the step S2 according to the first image collecting device of detection path clustering of planning and the second image
The step for position of acquisition means, specifically:
After the image information of the complete present co-ordinate position of the second image acquisition device, moved according to next coordinate position
The position of dynamic first image collecting device and the second image collecting device；
Obtain the topography of present co-ordinate position.
Further, the step S3, specifically includes the following steps:
After the corresponding image information of each coordinate position is carried out image mosaic, stitching image is obtained；
Judge whether stitching image meets preset requirement, if meeting the requirements, to stitching image progress feature extraction, and according to
Whether signature analysis workpiece to be detected has defect；Conversely, returning to step S1.
It further, further include auto-focusing step, the auto-focusing step specifically:
The second image collecting device is judged according to the gray feature value of image information acquisition image, and according to gray feature value
Whether focus state is in；
When detecting that the second image collecting device is in non-focusing state, the second Image Acquisition is adjusted according to focus state
Device is in the position of Z-direction, so that the second image collecting device focuses.
It further, further include position correction step, the position correction step specifically:
Analyzed and determined whether appearance position is inclined with preset coordinate position in conjunction with the image information that current location acquires
Difference, and when checking appearance position deviation, the position of the second image collecting device is adjusted according to position deviation.
The beneficial effects of the present invention are: the present invention using global image drawn game area image by being combined, it is quickly fixed to realize
Position, and camera motion path is predicted, to realize High-Speed Automatic path planning, the effect of optical detection is improved indirectly
Rate.
Detailed description of the invention
Fig. 1 is a kind of structural block diagram of rapid automatized Systems for optical inspection of the present invention；
Fig. 2 is a kind of step flow chart of rapid automatized optical detecting method of the present invention；
Fig. 3 is the structural scheme of mechanism of motion platform in specific embodiment；
Fig. 4 is the operation schematic diagram of the first image collecting device and third image collecting device in specific embodiment；
Fig. 5 is the schematic diagram of the global image of third image acquisition device in Fig. 4；
Fig. 6 is the schematic diagram of the topography of the first image acquisition device in Fig. 4；
Fig. 7 is the operation schematic diagram of the first image collecting device and the second image collecting device in specific embodiment.
Specific embodiment
As shown in figures 1 and 3, a kind of rapid automatized Systems for optical inspection, including image procossing are present embodiments provided
Module, motion platform 4, the first image collecting device 1, the second image collecting device 2 and third image collecting device 3, the figure
As processing module respectively with motion platform 4, the first image collecting device 1, the second image collecting device 2 and third image collector
Set 3 connections；
The first image acquisition device 1 is used to acquire the topography of workpiece 5 to be detected；
Second image collecting device 2 is used to acquire the image information of workpiece 5 to be detected；
The third image collecting device 3 is used to acquire the global image of workpiece 5 to be detected；
The motion platform 4 is used to control the first image collecting device 1 and the second image according to the mobile message received
Acquisition device 2 moves together；
After described image processing module is for successively combining global image and topography to carry out detection path planning, according to
The detection coordinates measurement mobile message of planning is simultaneously sent to motion platform 4, and is carried out according to image information to workpiece 5 to be detected
Optical detection.
When workpiece 5 to be detected needs to be detected, workpiece 5 to be detected is placed under the second image collecting device 2, referring to figure
3, the first image acquisition device 1 and the second image collecting device 2 are installed on motion platform 4, with motion platform 4
Movement moves together position.The first image acquisition device 1 only acquires to be detected 5 make-game domain imaging of workpiece to be detected
The topography of workpiece 5, the third image collecting device 3 are used to acquire work to be detected to the whole imaging of workpiece 5 to be detected
The global image of part 5,3 position of third image collecting device are fixed position.Wherein, the first image acquisition device 1
It can be realized using common industrial camera with third image collecting device 3, high-resolution industrial camera can also be used
To realize.Second image collecting device 2 is used to acquire the image information of workpiece 5 to be detected, and described image information can be used for
Optical detection.
Due to before carrying out Image Acquisition to workpiece for measurement, needing to carry out workpiece for measurement in existing optical detective technology
Positioning, then imaging is scanned to workpiece for measurement using fixedly path, since path is default fixation, can not neatly become
It is dynamic, so needing continuously to scan entire workpiece for measurement, and entire workpiece for measurement scan image is obtained, it is tangible existing
Detection in, and survey workpiece without treating and carry out whole scanning, it is therefore desirable to expending the excessive time carries out image scanning,
The serious efficiency for affecting detection.
Therefore, the present embodiment proposes a kind of system flexibly scanned, and referring to Fig. 4, this system is by third image collecting device 3
Global image 6 is acquired, and topography 7 is acquired by the first image collecting device 1, topography 7 is matched to global image
6, current location information can be rapidly got, positioning work is completed；Wherein, Fig. 5 is the global image of workpiece 5 to be detected
6, Fig. 6 be the topography 7 of workpiece 5 to be detected.Image processing module is equipped with preset program, according to current location information
It can predict next step coordinate position, therefore, when the second image collecting device 2 has acquired the image information of current location, energy
It is enough rapidly to move next step coordinate position, rather than use the existing side Huan Maned while moving and acquire image information
Formula.And this system can neatly change detection path, and obtain corresponding image information, without right according to design
The overall scanning imagery of whole system, accomplishes to shoot the arrow at the target, and greatly improves the efficiency of detection, reduces production indirectly
Cost can be widely used in automation optical detection scene.
System needs to carry out vision calibration work when being detected for the first time, and vision calibration work can be according to single figure
As can collected physical size information planned that and plan the frequency of Image Acquisition, these described technologies can be used
Existing technology is realized.
It is further used as preferred embodiment, second image collecting device uses high-resolution industrial camera.
Second image collecting device of this system can use high-resolution industrial camera, can also use high-definition camera
Using high-resolution industrial camera, the accurate of detection can be improved in the present embodiment in the camera of machine or generic pixel
Degree, is more able to satisfy the high request of optical detection.
It is further used as preferred embodiment, the mobile platform includes X-axis mobile mechanism, Y-axis moving mechanism and Z axis
Mobile mechanism.
Since high-precision AOI measurement accuracy requires all in micron dimension, the resolution ratio of optical lens is also accordingly micro-
Rice magnitude.So limited by current industrial camera imaging face size and optical lens processing, it is remote for what is taken pictures in high precision
The Depth of field of heart camera lens is all smaller.During this results in industrial camera to take pictures, focusing requires accurate.Even if small is inclined
Difference can all lead to image blur, eventually lead to detection algorithm failure.In present technology, it is scanned into workpiece to be detected
When picture, the position of mainly change X-axis and Y-axis then can not effectively make solution, greatly when there is image blur
The detection accuracy that ground influences.
And in the present embodiment when the image information of the second image acquisition device workpiece to be detected, it is mobile by X-axis
Mechanism and Y-axis moving mechanism are mobile in XY detection plane, and the second image collecting device is adjusted by Z axis mobile mechanism
With the height of workpiece to be detected, auto-focusing is realized with this, greatly improves detection accuracy.
Referring to Fig. 7, it is further used as preferred embodiment, the first image acquisition device and the second image collector
It sets and is equipped with light source.
Referring to Fig. 7, the first image collecting device includes the first camera lens 9, the first industrial camera 10 and first light source 8, described
Second image collecting device includes the second camera lens 4, the second industrial camera 5 and second light source 3.
The high precision image acquisition system being made up of the second camera lens 4, the second industrial camera 5 and second light source 3, it is to be detected
The reflection light of workpiece 1 passes through the primary optical axis 2 of the second camera lens, and micron accuracies may be implemented carries out figure to workpiece 1 to be detected
As acquisition, and algorithm process is carried out by image processing module and obtains the information such as the defect, the size that are detected workpiece.By the first mirror
The reflection light of the normal image acquisition system that first 9, first industrial camera 10 and first light source 8 form, workpiece 1 to be detected is passed through
The primary optical axis 7 of first camera lens, can collect the image of certain precision, and image information is converted to position by image processing module
Confidence ceases, and the position of prediction subsequent time Image Acquisition is carried out by algorithm.First image acquisition device is to current
Topography is achieved in closed loop feedback, improves position as feedback information for adjusting the position of the second image collecting device
Mobile precision improves the precision of detection indirectly.Wherein, by configuring light source, it is more advantageous to the second image collecting device
Focusing and acquisition image information.
As shown in Fig. 2, the present embodiment additionally provides a kind of rapid automatized optical detecting method, comprising the following steps:
A1, successively global image and topography is combined to carry out detection path planning；
A2, the position for detecting path clustering the first image collecting device and the second image collecting device according to planning, and
Acquire the image information of workpiece to be detected；
A3, optical detection is carried out to workpiece to be detected according to image information.
The embodiment of the present invention is by combining global image and topography to carry out detection path planning, image processing module root
Mobile first image collecting device and the second image collecting device are neatly controlled according to the detection path of planning, and passes through second
The image information of image acquisition device workpiece to be detected, avoids using conventional methods, and carries out to workpiece to be detected whole
Imaging, greatly improves detection efficiency.During detecting path planning, it can be advised in conjunction with global image and topography
Later period multistep coordinate position is drawn, such as in the fairly simple workpiece to be detected of shape (such as shape of rectangle or other rules
Shape), it can predict multistep coordinate position.Next step coordinate position can also be planned in conjunction with global image and topography, such as
For some workpiece to be detected in irregular shape, it is difficult to plan multistep coordinate position, then to planning next step coordinate position.
By combining using global image drawn game area image, quickly positioning is realized, and carry out to camera motion path pre-
It surveys, to realize High-Speed Automatic path planning, improves the efficiency of optical detection indirectly.
Wherein, step A1 specifically includes step A11~A13:
A11, after pre-processing to global image and local image line, the edge spy of global image and topography is extracted respectively
Sign；
A12, the current coordinate position of the second image collecting device is obtained according to edge feature；
A13, the mobile next coordinate position of the second image collecting device is obtained according to current coordinate position.
The pretreatment includes the processing such as region segmentation, extraction and filtering, carries out feature extraction to pretreated image,
Image information is converted to space location information followed by Feature Conversion by such as edge extracting, Inflexion extracting, and
The current coordinate position of the second image collecting device is obtained, in conjunction with preset algorithm (such as image trace prediction Processing Algorithm),
The mobile next coordinate position of the second image collecting device is obtained according to current coordinate position, which can
It is fast moved for controlling the second image collecting device.
Wherein, step A2 specifically includes step A21~A22:
A21, after the image information of the complete present co-ordinate position of the second image acquisition device, according to next coordinate bit
Set the position of mobile first image collecting device and the second image collecting device；
A22, the topography for obtaining present co-ordinate position, and the image information of acquisition workpiece to be detected.
Second image collecting device often moves on to a position, carries out image information to the workpiece to be detected in the position range
Acquisition, and after the completion of acquisition, it fast moves to next position coordinates, and not successional movement, so as to more
Effectively acquire the image information of workpiece to be detected.Wherein, the topography for getting present co-ordinate position, can be used as feedback letter
Breath, and closed loop feedback is carried out, correct the location information of prediction.
Wherein, step A3 specifically includes step A31~A32:
A31, after the corresponding image information of each coordinate position is carried out image mosaic, stitching image is obtained；
A32, judge whether stitching image meets preset requirement, if meeting the requirements, feature extraction is carried out to stitching image, and
Whether there is defect according to signature analysis workpiece to be detected；Conversely, returning to step A1.
Each coordinate position acquired image information is subjected to image mosaic, and obtains stitching image, the spliced map
Image as can be entire workpiece to be detected, or the parts of images of workpiece to be detected, according to specific detection demand
Setting.In addition, face irregular image, can significantly more efficient carry out Image Acquisition, such as workpiece to be detected shape be ring
Shape, detection technique traditionally need to acquire the area in the middle part of annular, and in the present embodiment, it can targetedly carry out
Acquisition, there is no need to acquire the area in the middle part of annular, more improves the efficiency of acquisition.The technology that wherein image is spliced,
Existing technology can be used, has no special requirement in the present embodiment.Optics is carried out to workpiece to be detected according to stitching image
Detection, to judge whether workpiece to be detected has defect.
It is further used as preferred embodiment, further includes auto-focusing step, the auto-focusing step specifically:
The second image collecting device is judged according to the gray feature value of image information acquisition image, and according to gray feature value
Whether focus state is in；
When detecting that the second image collecting device is in non-focusing state, the second Image Acquisition is adjusted according to focus state
Device is in the position of Z-direction, so that the second image collecting device focuses.
The present embodiment method also provides high-speed automatic focusing function, and the adjustment of camera micron accuracy may be implemented, avoid out
Existing blurred picture improves detection efficiency indirectly, and improves detection precision.
Specifically, automatic focusing, in focus state, image can be realized according to the grey value characteristics of present image
Mean square deviation it is bigger.In non-focusing state, mean square deviation is smaller.It may be implemented fastly according to the gray value of image
Velocity modulation is whole；In addition, when present convergence state can also be judged according to the boundary information of image.The present invention is not limited to
It states two methods and realizes the quick focusing of image in z-direction.
It is further used as preferred embodiment, further includes position correction step, the position correction step specifically:
Analyzed and determined whether appearance position is inclined with preset coordinate position in conjunction with the image information that current location acquires
Difference, and when checking appearance position deviation, the position of the second image collecting device is adjusted according to position deviation.
Image processing module is input to third Image Acquisition by the topography that the first image collecting device obtains first
The resulting global image of device, judges the rough location of current second image collecting device and workpiece to be detected, and predicts simultaneously
Next coordinate position of kinetic control system.By the method, dynamic path planning may be implemented, do not need traditional company
The point by point scanning of continuous ground.After the second image collecting device is moved to next coordinate points simultaneously, pass through the second image collector
The image for setting acquisition is compared with setting position, to generate position deviation, this is fed back to degeneration factor, passes through PD control
Realize the accurate positionin of position.The detection of high speed may be implemented by the combination for feedovering and feeding back.Wherein, the preset coordinate
Position is the next step coordinate position predicted in previous step.
In conclusion Systems for optical inspection and method of the invention are compared with the existing technology, have the following beneficial effects:
(1), automatic path planning.For industrial on-line checking, product supplied materials is mostly arbitrarily put, even if passing through centainly
Positioning fixture is positioned, and positioning accuracy will not be very high.And on-line checking industrial for high-precision, such as FPC winding displacement middle line
The defects detection on road, Glazed fence defects detection are required according to certain path scanning imagery, to realize in detection process
The whole detection of target.In addition, fixed route detection causes system for some special applications scenes, hand fit is generallyd use
Microscopical method, due to artificial judgement, low efficiency, error is big.The present invention is combined using global image drawn game area image,
It realizes quickly positioning, and camera motion path is predicted, to realize High-Speed Automatic path planning.And it is anti-by closed loop
The optimization to track is presented to greatly improve the efficiency and quality of detection to avoid the positioning difficulty of workpiece, very well satisfy
The quickly requirement of detection and high-precision detection.
(2), auto-focusing.Due to being limited by lens design, the depth of field very little of telecentric lens is imaged in high-precision, therefore
The control of image-forming range is very crucial.The present invention realizes camera by the analysis of present image feature at a distance from object to be measured
Quickly adjustment to realize a kind of method of auto-focusing to make up the problem of depth of field deficiency, while realizing that high speed is fast and reading focusing.
The feature and local characteristics of image for utilizing the second image collecting device imaging realize the focusing of detection camera
Range prediction and feedback control.
(3), hardware-accelerated: high-precision A OI detection system at present, it is very stringent to workpiece positioning requirements.Therefore system
It can be run in enclosure space.In order to realize high-precision positioning, machine system is huge, can not be directly compatible with production line.This hair
Bright middle scanning automatic path planning and imaging auto-focusing require the signal processing of high speed.The present invention handles the part parallel
Change, high speed processing is realized by FPGA, improves detection efficiency to a certain extent by hardware-accelerated.
(4), fast algorithm.The quick Processing Algorithm of design and use, reduces the detection time of single.Simultaneously in control principle
On, the present invention method shared using feedforward and feedback, by the process high speed of automatic path planning and imaging focusing.
(5), automation optical detecting method of the invention does not need the scanning imagery overall to whole system, and according to figure
As feature only detects the part that is imaged of needs, to reduce scanning imaging time, high speed detection is realized.
Generally speaking, rapid automatized Systems for optical inspection of the invention and method are realized under conditions of low cost, real
Existing high-speed, high precision optical detection, spatial resolution can achieve micron dimension.The resolution ratio and detection speed of image are substantially
It improves.This system is using automation path planning simultaneously, to planning path adjust automatically while detection, with traditional fixation
Path planning is compared, and detection accuracy is improved.Present invention can apply to the automation path plannings based on mould group, can also be applied to
Based on mechanical arm and other 3D path planning image-pickup methods.The spatial resolution and temporal resolution of Image Acquisition obtain
To large increase.Specifically, present invention can apply to FPC wireline inspection, glass panel quality testing, the detections of PCB visual quality
And the detection scene such as mobile phone screen detection.
It is to be illustrated to preferable implementation of the invention, but the invention is not limited to the implementation above
Example, those skilled in the art can also make various equivalent variations on the premise of without prejudice to spirit of the invention or replace
It changes, these equivalent deformations or replacement are all included in the scope defined by the claims of the present application.
Claims (10)
1. a kind of rapid automatized Systems for optical inspection, which is characterized in that including image processing module, motion platform, the first figure
As acquisition device, the second image collecting device and third image collecting device, described image processing module respectively with motion platform,
First image collecting device, the second image collecting device are connected with third image collecting device；
The first image acquisition device is used to acquire the topography of workpiece to be detected；
Second image collecting device is used to acquire the image information of workpiece to be detected；
The third image collecting device is used to acquire the global image of workpiece to be detected；
The motion platform is used to control the first image collecting device and the second image collector according to the mobile message received
It sets and moves together；
After described image processing module is for successively combining global image and topography to carry out detection path planning, according to planning
Detection coordinates measurement mobile message and be sent to motion platform, and according to image information to workpiece to be detected carry out optics inspection
It surveys.
2. a kind of rapid automatized Systems for optical inspection according to claim 1, which is characterized in that second image is adopted
Acquisition means use high-resolution industrial camera.
3. a kind of rapid automatized Systems for optical inspection according to claim 1, which is characterized in that the mobile platform packet
KuoXZhou mobile mechanism, Y-axis moving mechanism and Z axis mobile mechanism.
4. a kind of rapid automatized Systems for optical inspection according to claim 1, which is characterized in that the first image is adopted
Light source is equipped on acquisition means and the second image collecting device.
5. a kind of rapid automatized optical detecting method, which comprises the following steps:
S1, successively global image and topography is combined to carry out detection path planning；
S2, the position of path clustering the first image collecting device and the second image collecting device is detected according to planning, and acquired
The image information of workpiece to be detected；
S3, optical detection is carried out to workpiece to be detected according to image information.
6. a kind of rapid automatized optical detecting method described in claim 5, which is characterized in that the step S1, it is specific to wrap
Include following steps:
After global image and local image line pretreatment, the edge feature of global image and topography is extracted respectively；
The current coordinate position of the second image collecting device is obtained according to edge feature；
The mobile next coordinate position of the second image collecting device is obtained according to current coordinate position.
7. a kind of rapid automatized optical detecting method as claimed in claim 6, which is characterized in that according to rule in the step S2
The step for position of detection the first image collecting device of path clustering and the second image collecting device drawn, specifically:
After the image information of the complete present co-ordinate position of the second image acquisition device, according to next coordinate position mobile the
The position of one image collecting device and the second image collecting device；
Obtain the topography of present co-ordinate position.
8. a kind of rapid automatized optical detecting method as claimed in claim 7, which is characterized in that the step S3, it is specific to wrap
Include following steps:
After the corresponding image information of each coordinate position is carried out image mosaic, stitching image is obtained；
Judge whether stitching image meets preset requirement, if meeting the requirements, feature extraction is carried out to stitching image, and according to feature
Analyze whether workpiece to be detected has defect；Conversely, returning to step S1.
9. a kind of rapid automatized optical detecting method described in claim 5, which is characterized in that further include auto-focusing step
Suddenly, the auto-focusing step specifically:
Whether the second image collecting device is judged according to the gray feature value of image information acquisition image, and according to gray feature value
In focus state；
When detecting that the second image collecting device is in non-focusing state, the second image collecting device is adjusted according to focus state
In the position of Z-direction, so that the second image collecting device focuses.
10. a kind of rapid automatized optical detecting method as claimed in claim 7, which is characterized in that further include position correction step
Suddenly, the position correction step specifically:
In conjunction with current location acquire image information and preset coordinate position analyzed and determined whether appearance position deviation, and
When checking appearance position deviation, the position of the second image collecting device is adjusted according to position deviation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910593111.0A CN110501347A (en) | 2019-07-03 | 2019-07-03 | A kind of rapid automatized Systems for optical inspection and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910593111.0A CN110501347A (en) | 2019-07-03 | 2019-07-03 | A kind of rapid automatized Systems for optical inspection and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110501347A true CN110501347A (en) | 2019-11-26 |
Family
ID=68585894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910593111.0A Pending CN110501347A (en) | 2019-07-03 | 2019-07-03 | A kind of rapid automatized Systems for optical inspection and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110501347A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110823097A (en) * | 2019-12-13 | 2020-02-21 | 中国计量大学 | Method for measuring size of optical element in automatic assembly of dense wavelength division multiplexer |
| CN110987971A (en) * | 2019-12-19 | 2020-04-10 | 太原理工大学 | Crystal bubble detection device and method based on machine vision |
| CN110987807A (en) * | 2019-12-30 | 2020-04-10 | 浙江力创自动化科技有限公司 | Online detection device capable of realizing AOI intelligent optical detection and control method |
| CN111693546A (en) * | 2020-06-16 | 2020-09-22 | 湖南大学 | Defect detection system, method and image acquisition system |
| CN112557402A (en) * | 2020-12-04 | 2021-03-26 | 北京天科合达半导体股份有限公司 | Dislocation detection system |
| CN112903250A (en) * | 2019-12-04 | 2021-06-04 | 深圳蓝普科技有限公司 | Automatic maintenance system for detection device and splicing display device |
| TWI738232B (en) * | 2020-02-27 | 2021-09-01 | 由田新技股份有限公司 | Board measurement system and method thereof |
| CN113674203A (en) * | 2021-07-14 | 2021-11-19 | 歌尔股份有限公司 | Defect detection model training method and device and defect detection method and device |
| CN114638824A (en) * | 2022-05-11 | 2022-06-17 | 成都数联云算科技有限公司 | Fusion method, device, equipment and medium for collecting images based on AOI equipment |
| CN117589690A (en) * | 2024-01-18 | 2024-02-23 | 常州宝捷冲片有限公司 | Visual inspection system and working method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101924053A (en) * | 2009-01-13 | 2010-12-22 | 联达科技设备私人有限公司 | System and method for inspecting a wafer |
| CN202002896U (en) * | 2011-01-25 | 2011-10-05 | 北京大恒图像视觉有限公司 | Light path detecting device of automatic glass bottle lamp inspector |
| CN102661722A (en) * | 2012-05-16 | 2012-09-12 | 浙江大学 | Image overlaying-based thin sheet part contour automatic detection head and method |
| CN109406533A (en) * | 2018-10-25 | 2019-03-01 | 北京阿丘机器人科技有限公司 | A kind of detection system and method for surface defects of products |
| CN210720188U (en) * | 2019-07-03 | 2020-06-09 | 深圳市一纳科技有限公司 | Rapid automatic optical detection system |
-
2019
- 2019-07-03 CN CN201910593111.0A patent/CN110501347A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101924053A (en) * | 2009-01-13 | 2010-12-22 | 联达科技设备私人有限公司 | System and method for inspecting a wafer |
| CN202002896U (en) * | 2011-01-25 | 2011-10-05 | 北京大恒图像视觉有限公司 | Light path detecting device of automatic glass bottle lamp inspector |
| CN102661722A (en) * | 2012-05-16 | 2012-09-12 | 浙江大学 | Image overlaying-based thin sheet part contour automatic detection head and method |
| CN109406533A (en) * | 2018-10-25 | 2019-03-01 | 北京阿丘机器人科技有限公司 | A kind of detection system and method for surface defects of products |
| CN210720188U (en) * | 2019-07-03 | 2020-06-09 | 深圳市一纳科技有限公司 | Rapid automatic optical detection system |
Non-Patent Citations (1)
| Title |
|---|
| 何博侠;何勇;卜雄洙;商飞;: "机器视觉多视场协同测量方法", 光学精密工程, no. 12, 15 December 2012 (2012-12-15), pages 2821 - 2829 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112903250B (en) * | 2019-12-04 | 2024-01-23 | 深圳蓝普科技有限公司 | Automatic maintenance system of detection device and spliced display device |
| CN112903250A (en) * | 2019-12-04 | 2021-06-04 | 深圳蓝普科技有限公司 | Automatic maintenance system for detection device and splicing display device |
| CN110823097A (en) * | 2019-12-13 | 2020-02-21 | 中国计量大学 | Method for measuring size of optical element in automatic assembly of dense wavelength division multiplexer |
| CN110987971A (en) * | 2019-12-19 | 2020-04-10 | 太原理工大学 | Crystal bubble detection device and method based on machine vision |
| CN110987971B (en) * | 2019-12-19 | 2022-06-24 | 太原理工大学 | Crystal bubble detection device and method based on machine vision |
| CN110987807A (en) * | 2019-12-30 | 2020-04-10 | 浙江力创自动化科技有限公司 | Online detection device capable of realizing AOI intelligent optical detection and control method |
| TWI738232B (en) * | 2020-02-27 | 2021-09-01 | 由田新技股份有限公司 | Board measurement system and method thereof |
| CN111693546A (en) * | 2020-06-16 | 2020-09-22 | 湖南大学 | Defect detection system, method and image acquisition system |
| CN112557402A (en) * | 2020-12-04 | 2021-03-26 | 北京天科合达半导体股份有限公司 | Dislocation detection system |
| CN113674203A (en) * | 2021-07-14 | 2021-11-19 | 歌尔股份有限公司 | Defect detection model training method and device and defect detection method and device |
| CN114638824A (en) * | 2022-05-11 | 2022-06-17 | 成都数联云算科技有限公司 | Fusion method, device, equipment and medium for collecting images based on AOI equipment |
| CN117589690A (en) * | 2024-01-18 | 2024-02-23 | 常州宝捷冲片有限公司 | Visual inspection system and working method |
| CN117589690B (en) * | 2024-01-18 | 2024-03-19 | 常州宝捷冲片有限公司 | Visual inspection system and working method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110501347A (en) | A kind of rapid automatized Systems for optical inspection and method | |
| CN110596129B (en) | Sheet glass edge flaw detection system based on image acquisition | |
| CN110006905B (en) | Large-caliber ultra-clean smooth surface defect detection device combined with linear area array camera | |
| US7386161B2 (en) | Method and apparatus for flat patterned media inspection | |
| CN108956645A (en) | A kind of the optical mirror slip defect detecting device and method of more vision systems | |
| CN108765416A (en) | PCB surface defect inspection method and device based on fast geometric alignment | |
| CN203069151U (en) | Three-dimensional hole form detection system based on optical coherence tomography scanning | |
| CN110186375A (en) | Intelligent high-speed rail white body assemble welding feature detection device and detection method | |
| Zeng et al. | A visual weld edge recognition method based on light and shadow feature construction using directional lighting | |
| CN110238520B (en) | Automatic precise laser welding method based on CCD visual detection | |
| Yang et al. | An automatic aperture detection system for LED cup based on machine vision | |
| CN112540089A (en) | Application method of digital imaging system in concrete bridge crack detection and analysis | |
| CN112033971A (en) | Visual flaw detection system and method | |
| CN114136975A (en) | Intelligent detection system and method for surface defects of microwave bare chip | |
| CN109632007A (en) | A kind of edge point extracting method and gear high-precision vision measuring system | |
| CN209992407U (en) | Large-caliber ultra-clean smooth surface defect detection device combined with linear array camera | |
| CN109470698A (en) | Across scale field trash quick analytic instrument device and method based on microphotograph matrix | |
| CN116402797A (en) | Large-breadth micro defect detection system and method based on double-precision imaging module | |
| CN117670887B (en) | Tin soldering height and defect detection method based on machine vision | |
| CN210720188U (en) | Rapid automatic optical detection system | |
| CN1518085B (en) | High-speed in-line electro-optics testing method and system for defects on chip | |
| CN109829897A (en) | A kind of gear burr detection method and gear high-precision vision measuring system | |
| CN208623750U (en) | Intelligent industrial camera | |
| KR102618194B1 (en) | Semiconductor package board processing hole 3d automatic process inspection method and system | |
| CN112435220B (en) | Self-positioning porous characteristic moving window splicing method for part detection |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200714 Address after: 518000 520, building 4, Qidi Xiexin, No. 333, Longfei Avenue, huanggekeng community, Longcheng street, Longgang District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Mingrui Instrument Co.,Ltd. Address before: 301-8, floor 3, qidixiexin Science Park, Qingchun Road, Longcheng street, Longgang District, Shenzhen City, Guangdong Province Applicant before: Shenzhen Yina Technology Co.,Ltd. |