CN102621156B - Image-processing-based automatic micro part sorting system - Google Patents
Image-processing-based automatic micro part sorting system Download PDFInfo
- Publication number
- CN102621156B CN102621156B CN201210057870.3A CN201210057870A CN102621156B CN 102621156 B CN102621156 B CN 102621156B CN 201210057870 A CN201210057870 A CN 201210057870A CN 102621156 B CN102621156 B CN 102621156B
- Authority
- CN
- China
- Prior art keywords
- image
- processing
- module
- micro parts
- detection
- Prior art date
Links
- 238000000034 methods Methods 0.000 claims abstract description 12
- 238000006243 chemical reactions Methods 0.000 claims description 9
- 239000003570 air Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 4
- 281000001425 Microsoft companies 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 239000010410 layers Substances 0.000 claims description 2
- 239000000203 mixtures Substances 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 206010011376 Crepitations Diseases 0.000 description 4
- 230000002950 deficient Effects 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 3
- 238000005516 engineering processes Methods 0.000 description 3
- 241001157067 Leucoagaricus meleagris Species 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 281000123689 Arms industry companies 0.000 description 1
- 230000023298 conjugation with cellular fusion Effects 0.000 description 1
- 230000000875 corresponding Effects 0.000 description 1
- 230000001808 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reactions Methods 0.000 description 1
- 230000001186 cumulative Effects 0.000 description 1
- 238000010586 diagrams Methods 0.000 description 1
- 239000007789 gases Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 239000004800 polyvinyl chloride Substances 0.000 description 1
- 229920000915 polyvinyl chlorides Polymers 0.000 description 1
- 238000003908 quality control methods Methods 0.000 description 1
- 230000021037 unidirectional conjugation Effects 0.000 description 1
- 238000009333 weeding Methods 0.000 description 1
Abstract
Description
Technical field
The present invention relates to rapid sorting system, be specifically related to a kind of micro parts Automated Sorting System based on image processing.
Background technology
Micro parts refers to that External Shape physical dimension is less than the part of 5mm.Due to micro parts being widely used in military products, civilian goods and industrial goods, its piece surface Defect Detection is an important content for part quality detection and precision control during part is produced.Traditional still relies on manual detection to the detection of micro parts, and because the part detecting is little, manual detection labour intensity is large, and efficiency is low, and loss is high, certainly will cause the defect of part quality control, thereby in the urgent need to a kind of online automatic checkout system.Although image processing techniques has use at a lot of detection fields, major part be all for larger part detection, or for the detection of accessory size.In the production of micro parts, generally with short production cycle, product quantity is large, and the detection method one adopting is at present to be difficult to meet its accuracy of detection and resolution requirement, the 2nd, be difficult to meet its detection speed requirement, particularly requiring detection speed to reach per minute more than 3000.
In current existing patent, patent of invention CN101832951A discloses a kind of " the PVC circular pipe surface blemish online test method based on Vision Builder for Automated Inspection ", it is mainly to detect for large pipe surface quality, its detection method only limits to large-scale part, and do not need to detect the work such as automatic screening sequence and the automatic rejection in later stage in early stage, cannot meet the requirement of sorting speed that micro parts proposes in detecting, thereby and not be suitable for the sorting work of micro parts.
From the document of publishing at present " micro parts physical dimension automatic detection device " (" war industry's robotization " in Dec, 2009): its size mainly for micro parts detects, and cannot realize the detection to concavo-convex, the pit in end face circle, crackle etc.
To sum up, for overcoming for small cylindrical part screening difficulty, disturb each other large and the higher problem of detection resolution, need to detect the defects such as concavo-convex, the scratch, crackle, pit of piece surface simultaneously, be necessary to develop a kind of novel sorting system for micro parts.
Summary of the invention
Technical matters to be solved by this invention is: a kind of micro parts Automated Sorting System based on image processing is provided, this sorting system can be realized online motion detection sorting to small cylindrical part, particularly can play accurate differentiation rejecting for defects such as concavo-convex, the scratch of piece surface, crackle, pits; Can process the image of this micro parts, reached higher accuracy of detection simultaneously.
The present invention solves its technical matters and adopts following technical scheme:
Micro parts Automated Sorting System based on image processing provided by the invention, is made up of workpiece screening module, detection module, software control system and detection post-processing module, wherein: detection module is in workpiece screening module track both sides; Detection module is connected with the software control system on computing machine by data line; Detect post-processing module and be directly connected with detection module, be subject to the control of computer software control system simultaneously.
Described workpiece screening module is mainly made up of feed mechanism, hyperchannel screening track, gear driver plate, barrel, and this module is screened, sorted for micro parts, makes micro parts become same direction equidistantly to arrange and enter measurement.
Described detection module looks like to gather to the end view drawing of micro parts, and its hardware device comprises CCD industrial camera, industrial lens, image pick-up card and light-source system, wherein: industrial lens is connected with CCD industrial camera by C/CS interface; CCD industrial camera is connected with image pick-up card by data line; Image pick-up card is connected with computing machine by computer PCI slot; Light-source system provides the illumination condition of requirement to detection module.
Described detection post-processing module receives by PLC control system the testing result signal that software control system provides, and controls the valve switch of air gun, and rejected part is rejected.
Described software control system looks like to process in real time to the end view drawing collecting, and judges.
Described software control system adopts Microsoft Visual C++6.0 exploitation, can carry out hardware communications with image pick-up card, and the micro parts image that image pick-up card is collected is processed in real time and judges, and meets the requirements of resolution and precision.
The step that described software control system carries out processing in real time for micro parts image comprises:
(1) pre-service of image: the processing of coloured image gray processing, filtering processing.The coloured image collecting is transformed into gray level image, and is carried out filtering processing, the interference while processing to reduce;
(2) binary conversion treatment of image.Gray level image is carried out to binary conversion treatment, to facilitate subsequent treatment work;
(3) adopt hough conversion to carry out circularity matching, to improve accuracy of detection, and obtain image center of circle parameter;
(4) according to the image center of circle parameter obtaining, take the center of circle as benchmark, its center of circle is overlapped whole image translation with the home position of standard masterplate;
(5) by workpiece image to be detected and standard stencil matching.
The present invention, in utilizing CCD application technology to obtain workpiece image, looks like to process to the micro parts end view drawing obtaining based on image processing techniques, therefore compares and has following major advantage with existing technology:
One. can carry out rapid sorting to micro parts, in the process of part sorting, the screening of part and rejected Automatic Control, without manual intervention, the sorting time is short, and efficiency is high, and accuracy of detection can reach 0.02mm.
They are two years old. and easy to use, simple to operate.After rigging up and debugging is complete, only need a people to get final product operation control software, click completely without manual intervention, can complete sorting work after starting to detect.
Specifically being calculated as follows of accuracy of detection:
According to hardware parameter, what the industrial CCD camera adopting adopted is 1/3 〞 area array CCD, its target surface is of a size of: h (level) × v (vertically)=4.8mm × 3.6mm, according to camera lens instructions, the lens focus f=17.64mm adopting, detect object distance D=50mm clearly, according to visual field computing formula:
Can be calculated: h ˊ=13.6mm, v ˊ=10.2mm
According to the view data of actual acquisition, its image pixel is H × V=720 pixel × 576 pixels,
Horizontal resolution:
Vertical resolution:
Be that accuracy of detection is about 0.02mm.
In a word, the present invention has mainly solved in current micro parts production low for surface quality of workpieces detection efficiency, and loss is high, the problem that cost of labor is large.This sorting system mainly comprises workpiece screening module, detection module, software control system and detects post-processing module.The present invention is mainly used in solving: to online detection the sorting of small cylindrical part, particularly can play accurate differentiation rejecting for defects such as concavo-convex, the scratch of piece surface, crackle, pits, the qualification rate of the product that guarantee sorts out, and require to reach higher sorting speed.
Brief description of the drawings
Fig. 1 is structural representation of the present invention.
Fig. 2 is the topology layout figure of Fig. 1.
Fig. 3 is the process flow diagram of micro parts image processing.
In Fig. 2: 1. feed mechanism; 2. hyperchannel screening track; 3. barrel; 4. gear driver plate; 5. micro parts; 6.CCD backlight; 7. CCD industrial camera; 8. air gun; 9. unacceptable product storehouse; 10. certified products storehouse; 11.PLC controller; 12. computing machines; 13. image pick-up cards.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the invention will be further described.
Micro parts Automated Sorting System based on image processing provided by the invention, its structure as shown in Figure 1, formed by workpiece screening module, detection module, software control system and detection post-processing module, wherein: detection module is in workpiece screening module track both sides; Detection module is connected with the software control system on computing machine by data line; Detect post-processing module and be directly connected with detection module, be subject to the control of computer software control system simultaneously.
Described workpiece screening module is mainly the screening and sequencing work for micro parts.The structure of this module as shown in Figure 2, formed by parts such as feed mechanism 1, hyperchannel screening track 2, barrel 3, gear driver plates 4, wherein hyperchannel screening track can be to screening, sort for micro parts 5, and prevent rotation, the rolling of micro parts on delivery track with special track, make it become same direction equidistantly to arrange and enter measurement.Described special track is the Baltimore groove track mating with External Shape, prevents that the motion of delivery track from causing rotation and the rolling of micro parts.
Described workpiece screening module, its course of work is: micro parts 5 is sent into hyperchannel screening track 2 by feed mechanism 1, through the three level screen of hyperchannel screening track, make micro parts 5 become the single-row arrangement of individual layer, then pass through the calibration of gear driver plate 3, make its equidistant calibration, then pass through spatial attitude adjustment, described part enters Baltimore groove track, enters detection.
Described detection module is that the end view drawing of micro parts is looked like to gather, and its hardware device comprises CCD industrial camera 7, industrial lens, image pick-up card and light-source system, wherein: industrial lens is connected with CCD industrial camera by C/CS interface; CCD industrial camera is connected with image pick-up card by data line; Image pick-up card is connected with computing machine by computer PCI slot; Light-source system provides the illumination condition of requirement to detection module.
Described detection post-processing module is mainly, for the result detecting, rejected part is carried out to Weeding.This detection post-processing module receives by PLC control system the testing result signal that software control system provides, and controls the valve switch of air gun, and rejected part is rejected.
Described software control system looks like to process in real time and judge to the end view drawing collecting.This control system can adopt Microsoft Visual C++6.0 exploitation, can carry out hardware communications with image pick-up card, the micro parts image that image pick-up card is collected is processed in real time and judges, and meet the requirements of resolution and precision, as shown in Figure 3, its processing for micro parts mainly comprises the steps:
(1) pre-service of image: the processing of coloured image gray processing, filtering processing.The coloured image collecting is transformed into gray level image, and is carried out filtering processing, the interference while processing to reduce.
(2) binary conversion treatment of image.Gray level image is carried out to binary conversion treatment, to facilitate subsequent treatment work.
(3) adopt hough conversion to carry out circularity matching, to improve accuracy of detection, and obtain image center of circle parameter.
It is specifically implemented as follows:
The equation that is located at the circle under cartesian coordinate system is:
??????????????????????????????(1)
The solution of radius of a circle R is:
?????????????????????????(2)
Get number of edge points N=100, marginal point in image at parameter space in projection coordinate's point set be combined into .
Traversal is centered by marginal point, and all pixels in the square that 2R is the length of side, if marginal point is mapped to the element in coordinate points set in parameter space, parameter space totalizer (totalizer initial value is all 0), cumulative maximum value in last totalizer P corresponding coordinate is central coordinate of circle .
(4) according to the image center of circle parameter obtaining, take the center of circle as benchmark, its center of circle is overlapped whole image translation with the home position of standard masterplate.
The image central coordinate of circle detecting for step (3), bidding quasi-mode version home position is , translational movement:
, ??????????????????????????(3)
Each point on image to be detected is done , translation.
(5) by workpiece image to be detected and standard stencil matching:
Standard workpiece bianry image and bianry image to be detected are carried out to phase reducing, if coupling, on each pixel, gray-scale value is 0, and workpiece to be detected is qualified; If do not mate, the upper gray-scale value of partial pixel point is not 0, and workpiece to be detected is defective.Wherein: standard masterplate is before detection, first to detect multiple qualified part to obtain, and its detecting step is (1)-(4), and obtains its radius error allowed band, and is deposited in Computer Database.
To detect annular workpiece as example, referring to Fig. 2, sketch the course of work of the present invention below.
After the complete equipment of Installation and Debugging, pour workpiece into feed mechanism 1, switch on to control desk, press start and stop master switch on control desk, power to whole system, workpiece starts to enter screening and sequencing, in the time that the workpiece of marshalling enters detection station, light-source system irradiates workpiece end face, light after 6 reflections of CCD backlight is received by CCD industrial camera 7 through camera lens, now, the picture signal that CCD industrial camera 7 collects is an analog quantity, through the A/D modular converter in image pick-up card 13, image is converted in the buffer memory that digital picture stores computing machine 12 into, by clicking the detection software on computing machine, software reads the image collecting from Computer Cache, process differentiation, and count, to underproof workpiece number record in storer, and send command signal to PLC controller 11, due to the uniform motion of conveying belt, after the set time, this defective workpiece arrives before the air gun 8 of PLC control, PLC time delay transmitted signal, control electromagnetic valve switch, the pressure gas of air gun rifle mouth ejection is rejected this defective workpiece in unacceptable product storehouse 9, qualified workpiece enters certified products storehouse 10, thereby reach the object of sorting.
Claims (4)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210057870.3A CN102621156B (en) | 2012-03-07 | 2012-03-07 | Image-processing-based automatic micro part sorting system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210057870.3A CN102621156B (en) | 2012-03-07 | 2012-03-07 | Image-processing-based automatic micro part sorting system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102621156A CN102621156A (en) | 2012-08-01 |
CN102621156B true CN102621156B (en) | 2014-12-03 |
Family
ID=46561199
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210057870.3A CN102621156B (en) | 2012-03-07 | 2012-03-07 | Image-processing-based automatic micro part sorting system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102621156B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102901735B (en) * | 2012-08-29 | 2015-02-25 | 上海美迪索科电子科技有限公司 | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer |
CN102914546A (en) * | 2012-10-09 | 2013-02-06 | 昆山广达科技设备有限公司 | System and method for detecting mist spray tank covers on the basis of machine vision |
CN103808730B (en) * | 2013-01-25 | 2016-05-25 | 常州先进制造技术研究所 | Engine cam component surface defect inspection method |
CN103163156A (en) * | 2013-03-21 | 2013-06-19 | 万新光学集团有限公司 | Automatic grading method of lens defects based on machine vision technology |
CN105457898A (en) * | 2014-09-03 | 2016-04-06 | 深圳市佳晨科技有限公司 | Product sorting method and product sorting system |
CN105478529B (en) * | 2015-02-02 | 2017-10-27 | 广东工业大学 | Full-automatic stamping line products surface quality on-line detecting system and method |
CN105004371A (en) * | 2015-06-30 | 2015-10-28 | 张家港华日法兰有限公司 | Method for detecting flange quality |
CN105004370A (en) * | 2015-06-30 | 2015-10-28 | 张家港华日法兰有限公司 | Method for detecting flange quality |
CN105043262A (en) * | 2015-09-02 | 2015-11-11 | 哈尔滨工业大学 | Threaded hole component measuring and sorting device based on embedded and machine vision |
CN105426926B (en) * | 2016-01-04 | 2019-09-24 | 京东方科技集团股份有限公司 | A kind of couple of AMOLED carries out the method and device of detection classification |
CN109332211A (en) * | 2018-11-29 | 2019-02-15 | 芜湖常瑞汽车部件有限公司 | A kind of part size detection system and method based on image processing techniques |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6032534A (en) * | 1998-07-20 | 2000-03-07 | Sonix, Inc. | Ultrasonic apparatus and method of simultaneously inspecting microcomponents for defects |
CN2903980Y (en) * | 2006-04-29 | 2007-05-23 | 丁少华 | Fast tester for surface defect of small column part |
JP3917020B2 (en) * | 2002-06-25 | 2007-05-23 | ヤマハファインテック株式会社 | Method, apparatus and program for visual inspection of micro parts |
CN201170774Y (en) * | 2008-02-22 | 2008-12-24 | 福建省建筑科学研究院 | Detector with numeral photo and amplifying function |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2791598Y (en) * | 2005-04-30 | 2006-06-28 | 西安工业学院 | Micro abnormal-shape pipece automatic detecting device |
CN101269395A (en) * | 2008-04-30 | 2008-09-24 | 长春理工大学 | Discontinuously conveying and positioning device for round bench or circular column workpiece with different size |
-
2012
- 2012-03-07 CN CN201210057870.3A patent/CN102621156B/en not_active IP Right Cessation
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6032534A (en) * | 1998-07-20 | 2000-03-07 | Sonix, Inc. | Ultrasonic apparatus and method of simultaneously inspecting microcomponents for defects |
JP3917020B2 (en) * | 2002-06-25 | 2007-05-23 | ヤマハファインテック株式会社 | Method, apparatus and program for visual inspection of micro parts |
CN2903980Y (en) * | 2006-04-29 | 2007-05-23 | 丁少华 | Fast tester for surface defect of small column part |
CN201170774Y (en) * | 2008-02-22 | 2008-12-24 | 福建省建筑科学研究院 | Detector with numeral photo and amplifying function |
Non-Patent Citations (4)
Title |
---|
徐锐.微小零件尺寸及表面缺陷的机器视觉检测技术研究.《CNKI中国优秀硕士学位论文全文数据库》.2011, * |
微小零件几何尺寸自动检测装置;杜玉军等;《兵工自动化》;20091230;第28卷(第12期);全文 * |
微小零件尺寸及表面缺陷的机器视觉检测技术研究;徐锐;《CNKI中国优秀硕士学位论文全文数据库》;20111230;摘要、第9-12、16-17、20、54页 * |
杜玉军等.微小零件几何尺寸自动检测装置.《兵工自动化》.2009,第28卷(第12期), * |
Also Published As
Publication number | Publication date |
---|---|
CN102621156A (en) | 2012-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102788803B (en) | On-line high-speed detection system of train wheel set tread and wheel rim and detection method thereof | |
CN101799431B (en) | Machine visual on-line detection method and equipment for tank cover quality in high-speed production line | |
CN104111260A (en) | Nondestructive ceramic detection device and detection method thereof | |
CN102495069B (en) | Method for detecting defects of chain belts of zipper on basis of digital image processing | |
CN101576509B (en) | Method and device for automatically detecting surface defects of spherules based on machine vision | |
KR101772673B1 (en) | Multiple optics vision inspection system | |
CN103736672B (en) | A kind of eyeglass is classified sorting equipment online | |
CN1329132C (en) | On-line fruit quality detection and classification apparatus and method based on three camera chains | |
CN103706568A (en) | System and method for machine vision-based robot sorting | |
US10209200B2 (en) | High-speed, 3-D method and system for optically inspecting parts | |
CN202649134U (en) | Bottle cap quality detection device | |
CN103175847B (en) | Grating surface defect detecting device | |
CN102095733B (en) | Machine vision-based intelligent detection method for surface defect of bottle cap | |
CN104597058B (en) | The white wine foreign matter in bottles automatic detection device and method of a kind of view-based access control model | |
CN101858734B (en) | Method for detecting PET bottleneck quality | |
CN101303316B (en) | Method and apparatus for automatic detection on large infusion production line | |
WO2012158670A1 (en) | Method and system for optically inspecting parts | |
CN102735695B (en) | Rapid lens flaw detection method and apparatus thereof | |
CN201555812U (en) | Visual surface blemish detecting instrument of steel balls | |
CN105548212B (en) | A kind of touched panel glass surface blemish on-line automaticization detection system and method | |
CN106903426B (en) | A kind of laser welding localization method based on machine vision | |
CN103090804B (en) | Automatic detection system and detection method of finished product magnet ring image | |
CN201421436Y (en) | Surface spot and size detection device of product | |
CN103645573A (en) | Liquid crystal display (LCD) detection method and system based on machine vision | |
CN203824934U (en) | Optical system for mirror appearance inspection of trademark |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
EXPY | Termination of patent right or utility model | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141203 Termination date: 20150307 |