CN205538710U - Inductance quality automatic check out system based on machine vision - Google Patents
Inductance quality automatic check out system based on machine vision Download PDFInfo
- Publication number
- CN205538710U CN205538710U CN201620095068.7U CN201620095068U CN205538710U CN 205538710 U CN205538710 U CN 205538710U CN 201620095068 U CN201620095068 U CN 201620095068U CN 205538710 U CN205538710 U CN 205538710U
- Authority
- CN
- China
- Prior art keywords
- inductance
- unit
- computer system
- card
- ccd camera
- 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.)
- Expired - Fee Related
Links
Abstract
The utility model discloses an inductance quality automatic check out system based on machine vision, it relates to the inductance and detects technical field. The LED light source cooperatees with the CCD camera, and the CCD camera meets image acquisition card, and image acquisition card and the computer system who installs image processing software are connected, and computer system connects the CRT monitor, and the computer system and the control system of control inductance are connected, computer system comprises image processing unit, edge location unit, breakage detection unit and tension releasing detecting element, and image processing unit connects the edge location unit, and the edge location unit is connected with breakage detection unit, tension releasing detecting element respectively, and breakage detection unit, tension releasing detecting element are connected with image processing unit 5. The utility model discloses realize production, detect, the packing integration, detects reliable and stablely, improve production efficiency, reduce workman's intensity of labour, reduction manufacturing cost easily uses widely.
Description
Technical field
The utility model relates to inductance detection technical field, particularly relates to a kind of inductance quality automatic checkout system based on machine vision.
Background technology
Surface defect can directly affect product quality and serviceability, therefore, in inductance quality detecting system, automatically the detection of surface defect is an indispensable link, the method of traditional contact manual detection is the most loaded down with trivial details, labour intensity big, and it is slower to detect speed, it is impossible to eliminate artificial measure error, being also possible to cause the surface of object certain damage during detection, these all make traditional detection method not reach ideal requirement.
Further reinforcement along with industrial automatization, rely on traditional manual detection cannot meet the rate request of the production automation, automatic online detection has become the active demand of many automated production producers, inductance coil is during processing, easily produce some open defects such as loose ends, magnetic core breakage, rely on manual detection cannot meet automated speed requirement at all, reduce production efficiency.
In order to solve the problems referred to above, those skilled in the art is devoted to develop a kind of inductance quality automatic checkout system based on machine vision.
Utility model content
Because the drawbacks described above of prior art, technical problem to be solved in the utility model is to provide a kind of inductance quality automatic checkout system based on machine vision, reasonable in design, realize produce, detection, packaging integrated, detect reliable and stable, improve production efficiency, reduce the labour intensity of workman, reduce production cost, practical, it is easy to promote the use of.
For achieving the above object, the utility model provides a kind of inductance quality automatic checkout system based on machine vision, including LED light source, CCD camera, image pick-up card, computer system, CRT monitor, image processing software device and control system, LED light source matches with CCD camera, CCD camera connects image pick-up card, image pick-up card is connected with the computer system being provided with image processing software device, computer system connects CRT monitor, and computer system is connected with the control system controlling inductance.
nullAs preferably，Described computer system is by graphics processing unit、Edge positioning unit、Damage testing unit and loose ends detector unit composition，The inductance picture that image pick-up card is obtained by graphics processing unit carries out some pretreatment，Graphics processing unit edge fit edge positioning unit，Inductive position in image is positioned by edge positioning unit，The location of workpiece can accurately be found，Facilitate the locating and tracking of remaining processing sequences，Edge positioning unit respectively with damage testing unit、Loose ends detector unit connects，Can to the breakage of inductance and loosen detect，Damage testing unit、Loose ends detector unit is connected with control system，Described damage testing unit includes that ROI region segmentation module and Blob analyze module，ROI region segmentation module meets Blob and analyzes module，Described loose ends detector unit includes Threshold segmentation module and number of edges statistical module，Threshold segmentation module connects number of edges statistical module.
As preferably, described CCD camera uses costarSI-M310 industry black and white camera, and CCD camera uses and can meet the computar MLM-3XMP optical lens that visual field shooting 8mm-10mm requires；Described image pick-up card uses PCI-1409 image pick-up card.
The beneficial effects of the utility model are: achieve inductance produce, detection, packaging integrated, it is greatly increased production efficiency, reduce the labour intensity of workman, labour is reduced for enterprise, reduce production cost, decrease flase drop, the missing inspection situation brought by subjective factors such as artificial fatigues, prevent defective products from outflowing；The real-time data record of system is also followed the tracks of for enterprise product quality management and the condition of production and is provided foundation, facilitates enterprise administrator to know the condition of production in workshop, pinpoints the problems in time, solve in time, it is to avoid waste, the development to enterprise is significant.
Below with reference to accompanying drawing, the technique effect of design of the present utility model, concrete structure and generation is described further, to be fully understood from the purpose of this utility model, feature and effect.
Accompanying drawing explanation
Fig. 1 is system block diagram of the present utility model；
Fig. 2 is that inductance of the present utility model produces overall flow figure.
Detailed description of the invention
With reference to Fig. 1-2, this detailed description of the invention is by the following technical solutions: a kind of inductance quality automatic checkout system based on machine vision, including LED light source 1, CCD camera 2, image pick-up card 3, computer system 4, CRT monitor 5, image processing software device 6 and control system 7, LED light source 1 matches with CCD camera 2, CCD camera 2 connects image pick-up card 3, image pick-up card 3 is connected with the computer system 4 being provided with image processing software device 6, computer system 4 connects CRT monitor 5, and computer system 4 is connected with the control system 7 controlling inductance 8；Described computer system 4 is made up of graphics processing unit 401, edge positioning unit 402, damage testing unit 403 and loose ends detector unit 404, graphics processing unit 401 edge fit edge positioning unit 402, edge positioning unit 402 is connected with damage testing unit 403, loose ends detector unit 404 respectively, and damage testing unit 403, loose ends detector unit 404 are connected with control system 7.
It should be noted that described damage testing unit 403 includes that ROI region segmentation module 405 and Blob analyzes module 406, ROI region segmentation module 405 meets Blob and analyzes module 406；Loose ends detector unit 404 includes Threshold segmentation module 407 and number of edges statistical module 408, and Threshold segmentation module 407 connects number of edges statistical module 408.
Additionally, described LED light source 1 uses blue square diffusing reflection light source, preferably highlight defect characteristic, to reach optimum efficiency；Described CCD camera 2 uses costarSI-M310 industry black and white camera, it is mainly used in gathering inductance image, measured workpiece focuses on CCD sensing element by optical lens, different camera lenses can be matched with operating distance according to the size of workpiece, native system uses computar MLM-3XMP camera lens, meets the requirement of visual field 8mm-10mm；Described image pick-up card 3 uses PCI-1409 image pick-up card, change and store on card the function of mass data for the automatic A/D of Synchronization Control, triggered by computer software and lock-out pulse, under the Synchronization Control driving electrical equipment, the vision signal of CCD output is carried out A/D conversion, it is converted into view data, then it is transferred to calculator memory and video memory in real time by pci bus, carries out various process for computer and operate.
This detailed description of the invention uses machine vision technique to carry out inductance detection, machine vision is exactly the visual performance utilizing computer simulation human eye, information is extracted from image or image sequence, three-dimensional scene and object to objective world carry out form and motion identifies, substitutes human eye and quantitatively detects whether product quality qualified and provide judged result.
nullThe operation principle of this detailed description of the invention: inductance defect automatic checkout system is to increase vision detection system in inductance production line inductance quality is detected monitoring in real time，Prevent defective products from flowing into next procedure: tested inductance 8 moves on the conveyor belt according to certain beat，The CCD camera 2 having adjusted position combines image pick-up card 3 and the irradiation of LED light source 1，Image is captured in real time according to the rhythm Tong Bu with production line，Its image is projected onto optical imaging system，Amplify through lens and focus on the light-sensitive array face of CCD，The optical image that CCD camera 2 is received is converted into vision signal and exports image pick-up card 3，Vision signal is converted into digital image information and processes show with CRT monitor 5 for computer system 4 by image pick-up card 3 again，Computer system 4 uses various image processing algorithm that data are carried out graphical analysis，Judge that it is the most qualified，Then send a signal to control system 7 control machinery and carry out rejecting action.
nullA kind of general program that the image processing software device 6 installed in computer system 4 uses American National instrument (NI) company to develop develops software Vision Builder for Automated Inspection as development platform，Owing to itself comprises polytype image procossing、Image conversion and filtering、The basic function function such as Model Matching and measurement，Therefore program development is simplified，Shorten the construction cycle greatly，VBAI is a configurable machine vision software，It can be utilized to complete prototype create、The actual application such as benchmark setting and application program configuration，VBAI is i.e. scalable in powerful programmed environment (such as LabVIEW) without programming，It is with built-in development interface，Therefore supervision can be quickly completed、Instruct and identify application；VBAI also includes setting up passing through/unsuccessfully judging of complexity, and numeral I/0 equipment is controlled and carried out the function of communication applications by serial device.
Graphics processing unit 401 main purpose in computer system 4 is that the inductance picture obtained by image pick-up card carries out some pretreatment, the image processing algorithm related generally to has medium filtering, the basic thought of median filter is the gray value replacing this pixel by the intermediate value of neighborhood of pixel points gray value, and the method can retain again image edge details while removing impulsive noise, salt-pepper noise；Native system uses 3 × 3 function windows, calculates the function window pixel median step centered by point [i, j] as follows: 1. press brightness value big minispread pixel；2. the median of selected and sorted set of pixels is as the new value of point [i, j].After being processed by medium filtering instrument, the bright image vegetarian refreshments at inductance core two ends is weakened, and centre need not the copper cash of detection and filtered, and facilitates subsequent detection.
Edge positioning unit 402: the image every time collected due to workpiece exists small position difference, so the Inductive position in image must be positioned, native system uses location instrument Find Straight Edge based on edge finding to position x and y direction, just can accurately find the location of workpiece, facilitate the locating and tracking of remaining processing sequences.
Loose ends detector unit 404: 1. ROI region segmentation: inductance breakage shows as exposing core portion at inductance two ends and the open defect such as unfilled corner, pit easily occurs, owing to the image appearance feature of surface fracture is all that comparison is bright, i.e. gray value is brighter, so, the detected region i.e. ROI region of magnetic core surface fracture should take in inductance core two end surfaces region, can not exceed this region, otherwise background bright pixel can produce interference.
2. Blob analyzes: the basis for estimation of inductance core surface fracture is by image carries out after Threshold segmentation the area detecting to surface fracture maximum region, if area exceedes certain threshold value, then it is assumed that this inductance exists open defect.In the present system, use Detect Objects instrument to carry out defect spot detection, can effectively detect open defect and be marked.
Damage testing unit 403: 1. automatic threshold segmentation based on histogram analysis: grey level histogram is the simplest, a most useful instrument in Digital Image Processing, it it is the function of gray value, describe gray level content and the distribution thereof of piece image, by inductance image is carried out histogram analysis, it is more uniform that inductance core and copper cash and background gray levels are distributed ratio, valley point can be selected as the threshold value of segmentation, can preferably inductance two ends magnetic core be come with copper cash and background separation.
2. number of edges statistics: loose ends defect show as inductance easily occur loosening around the end of copper cash, gap is there is with the winding region not loosened, can be by carrying out rim detection at the magnetic core of inductance two ends, a pixel jump point should be only existed if non-defective unit, then illustrate to there is loose ends situation during if there is more than 1；Gap do not occur owing to there being smaller loose ends situation usually to there will be one end, the apertured situation of the other end, so using three, upper, middle and lower position Find Edges instrument to carry out the detection of pixel jump point number.
This detailed description of the invention utilizes the automatic outward appearance detection difficult problem that the mode of machine vision technique non-cpntact measurement successfully solves on inductance production line, achieve production, the integrated production procedure detecting, packing, substantially increase production efficiency, decrease cost of labor, for inductance loose ends, open defect detection method in actually detected stable, reliable, there is higher engineer applied and be worth and wide market application foreground.
Preferred embodiment of the present utility model described in detail above.Should be appreciated that those of ordinary skill in the art just can make many modifications and variations according to design of the present utility model without creative work.Therefore, all technical staff in the art pass through the available technical scheme of logical analysis, reasoning, or a limited experiment on the basis of existing technology according to design of the present utility model, all should be in the protection domain being defined in the patent claims.
Claims (3)
1. an inductance quality automatic checkout system based on machine vision, it is characterized in that: include LED light source (1), CCD camera (2), image pick-up card (3), computer system (4), CRT monitor (5), image processing software device (6) and control system (7), LED light source (1) matches with CCD camera (2), CCD camera (2) connects image pick-up card (3), image pick-up card (3) is connected with the computer system (4) being provided with image processing software device (6), computer system (4) connects CRT monitor (5), computer system (4) is connected with the control system (7) controlling inductance (8)；Described computer system (4) is made up of graphics processing unit (401), edge positioning unit (402), damage testing unit (403) and loose ends detector unit (404), graphics processing unit (401) edge fit edge positioning unit (402), edge positioning unit (402) is connected with damage testing unit (403), loose ends detector unit (404) respectively, and damage testing unit (403), loose ends detector unit (404) are connected with control system (7).
A kind of inductance quality automatic checkout system based on machine vision, it is characterised in that: described CCD camera (2) uses and can meet the computar MLM-3XMP optical lens that visual field shooting 8mm-10mm requires.
A kind of inductance quality automatic checkout system based on machine vision, it is characterised in that: described image pick-up card (3) uses PCI-1409 image pick-up card.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620095068.7U CN205538710U (en) | 2016-01-29 | 2016-01-29 | Inductance quality automatic check out system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620095068.7U CN205538710U (en) | 2016-01-29 | 2016-01-29 | Inductance quality automatic check out system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN205538710U true CN205538710U (en) | 2016-08-31 |
Family
ID=56773564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620095068.7U Expired - Fee Related CN205538710U (en) | 2016-01-29 | 2016-01-29 | Inductance quality automatic check out system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN205538710U (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645200A (en) * | 2016-12-07 | 2017-05-10 | 淮安市奋发电子有限公司 | Intelligent vertical type inductor detecting system |
| CN107063099A (en) * | 2017-04-11 | 2017-08-18 | 吉林大学 | A kind of machinery manufacturing industry online quality monitoring method of view-based access control model system |
| CN107219230A (en) * | 2017-05-31 | 2017-09-29 | 惠州市纬讯科技有限公司 | A kind of inductance appearance images acquisition method |
| CN108873849A (en) * | 2018-08-23 | 2018-11-23 | 广东志高空调有限公司 | A kind of monitoring device of production line beat |
| CN109444148A (en) * | 2018-11-01 | 2019-03-08 | 昆山市泽荀自动化科技有限公司 | Inductance defect identification method |
| CN109444149A (en) * | 2018-11-01 | 2019-03-08 | 昆山市泽荀自动化科技有限公司 | A kind of detection method of inductance detection equipment |
| CN114199895A (en) * | 2021-12-15 | 2022-03-18 | 珠海高纳智能科技有限公司 | Inductance defect visual detection method |
-
2016
- 2016-01-29 CN CN201620095068.7U patent/CN205538710U/en not_active Expired - Fee Related
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645200A (en) * | 2016-12-07 | 2017-05-10 | 淮安市奋发电子有限公司 | Intelligent vertical type inductor detecting system |
| CN107063099A (en) * | 2017-04-11 | 2017-08-18 | 吉林大学 | A kind of machinery manufacturing industry online quality monitoring method of view-based access control model system |
| CN107219230A (en) * | 2017-05-31 | 2017-09-29 | 惠州市纬讯科技有限公司 | A kind of inductance appearance images acquisition method |
| CN108873849A (en) * | 2018-08-23 | 2018-11-23 | 广东志高空调有限公司 | A kind of monitoring device of production line beat |
| CN109444148A (en) * | 2018-11-01 | 2019-03-08 | 昆山市泽荀自动化科技有限公司 | Inductance defect identification method |
| CN109444149A (en) * | 2018-11-01 | 2019-03-08 | 昆山市泽荀自动化科技有限公司 | A kind of detection method of inductance detection equipment |
| CN109444148B (en) * | 2018-11-01 | 2022-02-01 | 昆山市泽荀自动化科技有限公司 | Inductor defect identification method |
| CN114199895A (en) * | 2021-12-15 | 2022-03-18 | 珠海高纳智能科技有限公司 | Inductance defect visual detection method |
| CN114199895B (en) * | 2021-12-15 | 2023-11-21 | 珠海高纳智能科技有限公司 | Visual detection method for inductance defect |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
| CN109454006B (en) | Detection and classification method based on device for online detection and classification of chemical fiber spindle tripping defects | |
| WO2022062812A1 (en) | Screen defect detection method, apparatus, and electronic device | |
| CN109879005A (en) | Device for detecting belt tearing and method | |
| CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| CN111229648A (en) | Solar cell panel flaw detection system and detection method based on machine vision | |
| CN110261391A (en) | A kind of LED chip appearance detection system and method | |
| CN101566582A (en) | Medicine bottle label information online detection system in powder injection production based on mechanical vision | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN111289538A (en) | PCB element detection system and detection method based on machine vision | |
| US11657599B2 (en) | Method for detecting appearance of six sides of chip multi-layer ceramic capacitor based on artificial intelligence | |
| TWI642126B (en) | Semiconductor wafer analyzing sytem and method thereof | |
| CN107895362A (en) | A kind of machine vision method of miniature binding post quality testing | |
| CN110349125A (en) | A kind of LED chip open defect detection method and system based on machine vision | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
| CN114429544A (en) | Method, system and device for detecting damage of screen of vibrating screen based on computer vision | |
| CN116228651A (en) | Cloth defect detection method, system, equipment and medium | |
| CN106370673A (en) | Automatic lens flaw detection method | |
| CN102305797A (en) | Method for automatically detecting foreign matter of medical product package by using machine vision system | |
| CN102305603B (en) | Method for automatically detecting inclination of steel needle of injector by machine vision system | |
| CN112541367A (en) | Multiple two-dimensional code identification method based on deep learning and image processing | |
| CN107121063A (en) | The method for detecting workpiece | |
| CN111028250A (en) | Real-time intelligent cloth inspecting method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160831 Termination date: 20190129 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |