CN104535584A - Vision detection method - Google Patents
Vision detection method Download PDFInfo
- Publication number
- CN104535584A CN104535584A CN201410835050.1A CN201410835050A CN104535584A CN 104535584 A CN104535584 A CN 104535584A CN 201410835050 A CN201410835050 A CN 201410835050A CN 104535584 A CN104535584 A CN 104535584A
- Authority
- CN
- China
- Prior art keywords
- detection method
- visible detection
- image
- product
- vision detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention provides a vision detection method. The vision detection method comprises the steps of(1) establishing a standard template; (2) carrying out image collection on a product byadopting a camera; (3) amplifying collected images; carrying out gray-scale processing, picture enhanced processing and image normalizing processing on the amplified images; (4) carrying out feature extraction, coordinate calculation and area calculation on pictures processed by the step (3), comparing extraction information with the standard template established by the step (1), and detecting whether the uniformity is achieved, whether the surface is scratched and whether damage exists; (5) if any problem is detected in the step (4), marking products with problems and giving an alarm; if no problemis detected in the step (4), transporting the products into a next procedure; and (6) repeating from the step (2) to the step (5). The vision detection method provided by the invention has the beneficial effects that the structure is simple, the operation is simple, the adjustment and theuse are convenient, the production efficiency is high and detection is comprehensive.
Description
Technical field
The invention belongs to detection technique field, especially relate to a kind of visible detection method.
Background technology
In existing technology, the detection of waterproof membrane does not have fairly perfect equipment to operate, and main dependence is manually carried out, and detection efficiency is low, causes whole piece waterproof membrane production line production efficiency low, there is the problems such as cost of labor is high.Waterproof membrane is because of the singularity of its structure, and cause traditional detection method more difficult to its detection, there is adjustment wastes time and energy, the low inferior problem of product quality.
Summary of the invention
The object of this invention is to provide a kind of structure simple, simple to operate, be convenient to regulate use, production efficiency is high, detect comprehensive visible detection method, is especially applicable to the detection of waterproof membrane.
Technical scheme of the present invention is: a kind of visible detection method, comprises the following steps:
(1) Criterion template;
(2) camera is adopted to carry out image acquisition to product;
(3) amplification process is carried out to the image gathered; Image after amplifying is carried out gray proces, photo strengthens process and image normalization process;
(4) picture processed step (3) carries out feature extraction, coordinate calculates, areal calculation, the standard form that information extraction and step (1) are set up is compared, detect its whether evenly, whether surface have scuffing, whether there is breakage;
(5) if step (4) detects any one problem, then in-problem product is marked, and send warning; If it is no problem that step (4) detects, then by Product transport in next process;
(6) step (2) is repeated to step (5).
Preferably, described image enhancement processing comprises noise reduction process, effectively suppresses the noise in image, the cleaning row of protector profile and integrality.
Preferably, CCD camera is adopted to carry out image acquisition.
Preferably, camera pixel is 5,000,000.
Preferably, optical magnification is 1.5-2.0.
Preferably, laser is adopted to mark defective products.
Preferably, once 20PCS can be detected.
The advantage that the present invention has and good effect are: owing to adopting technique scheme, waterproof membrane can be completed by robotization completely by the process of raw material to finished product, with increasingly automated replacement manual operations, save a large amount of cost of labor, and the secondary pollution that manual operations causes can be avoided; Meanwhile, image magnification ratio improves, and it is more accurate to detect, and improves product quality, increases yield rate.
Embodiment
In the present embodiment: a kind of visible detection method, comprises the following steps:
(1) Criterion template;
Select 100 in the product as standard, and image procossing is carried out to it, characteristic information extraction, get its mean value, for step (4) is ready.
(2) CCD camera is adopted to carry out image acquisition to product.
(3) Nonlinear magnify 1.5 times will gathered; Again the image after amplification is carried out gray proces, photo strengthens process and image normalization process;
Described image enhancement processing comprises noise reduction process, effectively suppresses the noise in image, the cleaning row of protector profile and integrality, wherein adopts gaussian filtering to its turnover process, to filtered image;
By threshold value to Image Segmentation Using, retain single complete product image.
(4) picture processed step (3) carries out feature extraction, coordinate calculates, and is compared by the standard form that information extraction and step (1) are set up, and whether whether detect it has scuffing, whether there is breakage in even, surface;
(5) if step (4) detects any one problem, then in-problem product is marked, and send warning; If it is no problem that step (4) detects, then by Product transport in next process;
If the eigenwert calculated is less than the minimum eigenwert extracted from standard form, or is greater than maximum eigenwert, then product quality existing problems, and defective product is marked, give the alarm simultaneously; If between the eigenwert extracted in standard form, then product is qualified.
(6) step (2) is repeated to step (5).
In the present embodiment, camera pixel is 5,000,000; Optical magnification is 1.5-2.0; Laser is adopted to mark defective products; Once 20PCS can be detected.
The course of work of this example: the semi-manufacture waterproof membrane coiled strip discharging in making is to automatic detection instrument left end feed rail, roller bearing is driven to pull material by servomotor, can light inductance, self-feeding, also different stroke distances and the time running single lot inspection can be set according to different product size, then under arriving automatic detection instrument sampling image lens, optical projection is checked, camera lens pixel 5,000,000, optical amplifier 1.5 times-2.0 times, computer display screen 2,000,000-300 ten thousand pixel, position, waterproof membrane hole own is well-proportioned, when occurring holes, scratch, during the phenomenons such as breakage, automatic detection instrument provides feedback signal, combination line quits work, then automatic detection instrument laser marker goes out defective products, provide commencing signal again, then combination line then comes into operation, then by the rolling of right-hand member discharging track.
Above one embodiment of the present of invention have been described in detail, but described content being only preferred embodiment of the present invention, can not being considered to for limiting practical range of the present invention.All equalizations done according to the present patent application scope change and improve, and all should still belong within patent covering scope of the present invention.
Claims (6)
1. a visible detection method, is characterized in that: comprise the following steps:
(1) Criterion template;
(2) camera is adopted to carry out image acquisition to product;
(3) amplification process is carried out to the image gathered; Image after amplifying is carried out gray proces, photo strengthens process and image normalization process;
(4) picture processed step (3) carries out feature extraction, coordinate calculates, areal calculation, the standard form that information extraction and step (1) are set up is compared, detect its whether evenly, whether surface have scuffing, whether there is breakage;
(5) if step (4) detects any one problem, then in-problem product is marked, and send warning; If it is no problem that step (4) detects, then by Product transport in next process;
(6) step (2) is repeated to step (5).
2. a kind of visible detection method according to claim 1, is characterized in that: adopt CCD camera to carry out image acquisition.
3. a kind of visible detection method according to claim 1, is characterized in that: camera pixel is 5,000,000.
4. a kind of visible detection method according to claim 1, is characterized in that: optical magnification is 1.5-2.0.
5. a kind of visible detection method according to claim 1, is characterized in that: adopt laser to mark defective products.
6. a kind of visible detection method according to claim 1, is characterized in that: once can detect 20PCS.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410835050.1A CN104535584A (en) | 2014-12-30 | 2014-12-30 | Vision detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410835050.1A CN104535584A (en) | 2014-12-30 | 2014-12-30 | Vision detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104535584A true CN104535584A (en) | 2015-04-22 |
Family
ID=52851156
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410835050.1A Pending CN104535584A (en) | 2014-12-30 | 2014-12-30 | Vision detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104535584A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104990698A (en) * | 2015-06-30 | 2015-10-21 | 张家港华日法兰有限公司 | Quality detection technology |
CN104990927A (en) * | 2015-06-30 | 2015-10-21 | 张家港华日法兰有限公司 | Method for detecting quality of flanges |
CN105185420A (en) * | 2015-05-26 | 2015-12-23 | 中国科学技术大学 | Automatic detection device and method for cooling water film coverage on nuclear power plant containment surface |
CN106091996A (en) * | 2016-05-26 | 2016-11-09 | 东华大学 | A kind of online visible detection method of stone flatness |
CN106248693A (en) * | 2016-08-31 | 2016-12-21 | 天津日津科技股份有限公司 | The detecting system of a kind of waterproof membrane and detection method thereof |
WO2018121269A1 (en) * | 2016-12-27 | 2018-07-05 | 张家港康得新光电材料有限公司 | Film detection system, detection method, and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09288068A (en) * | 1996-04-23 | 1997-11-04 | Fuji Electric Co Ltd | Appearance inspecting instrument |
JPH11271232A (en) * | 1998-03-23 | 1999-10-05 | Hitachi Eng & Service Co Ltd | Method and device for detecting defect in wiring on printed board |
CN201749088U (en) * | 2010-04-13 | 2011-02-16 | 精量电子(深圳)有限公司 | Detecting device for semiconductor silicon strain gage sensor |
CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
CN102601131A (en) * | 2012-03-09 | 2012-07-25 | 湖南镭目科技有限公司 | Steel billet surface quality online detection device |
-
2014
- 2014-12-30 CN CN201410835050.1A patent/CN104535584A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09288068A (en) * | 1996-04-23 | 1997-11-04 | Fuji Electric Co Ltd | Appearance inspecting instrument |
JPH11271232A (en) * | 1998-03-23 | 1999-10-05 | Hitachi Eng & Service Co Ltd | Method and device for detecting defect in wiring on printed board |
CN201749088U (en) * | 2010-04-13 | 2011-02-16 | 精量电子(深圳)有限公司 | Detecting device for semiconductor silicon strain gage sensor |
CN102221559A (en) * | 2011-03-05 | 2011-10-19 | 河海大学常州校区 | Online automatic detection method of fabric defects based on machine vision and device thereof |
CN102601131A (en) * | 2012-03-09 | 2012-07-25 | 湖南镭目科技有限公司 | Steel billet surface quality online detection device |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105185420A (en) * | 2015-05-26 | 2015-12-23 | 中国科学技术大学 | Automatic detection device and method for cooling water film coverage on nuclear power plant containment surface |
CN105185420B (en) * | 2015-05-26 | 2017-08-29 | 中国科学技术大学 | The cooling moisture film coverage rate automatic detection device and method on nuclear power plant containment shell surface |
CN104990698A (en) * | 2015-06-30 | 2015-10-21 | 张家港华日法兰有限公司 | Quality detection technology |
CN104990927A (en) * | 2015-06-30 | 2015-10-21 | 张家港华日法兰有限公司 | Method for detecting quality of flanges |
CN106091996A (en) * | 2016-05-26 | 2016-11-09 | 东华大学 | A kind of online visible detection method of stone flatness |
CN106248693A (en) * | 2016-08-31 | 2016-12-21 | 天津日津科技股份有限公司 | The detecting system of a kind of waterproof membrane and detection method thereof |
WO2018121269A1 (en) * | 2016-12-27 | 2018-07-05 | 张家港康得新光电材料有限公司 | Film detection system, detection method, and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104535584A (en) | Vision detection method | |
CN103983426B (en) | The detection of a kind of defect of optical fiber based on machine vision and sorting technique | |
CN103759644B (en) | A kind of separation refinement intelligent detecting method of optical filter blemish | |
CN104616275A (en) | Defect detecting method and defect detecting device | |
CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
CN104050446A (en) | Meter pointer image identification method based on pointer width character | |
CN107389693A (en) | A kind of printed matter defect automatic testing method based on machine vision | |
CN103051872A (en) | Method for detecting conveyor belt deviation based on image edge extraction | |
CN104506819A (en) | Multi-camera real-time linkage mutual feedback tracing system and method | |
CN103679146A (en) | Safety belt intelligent detection method based on high-pass filter and Hough conversion | |
CN108088845A (en) | A kind of image-forming correction method and device retained based on Weak Information | |
CN113222938A (en) | Chip defect detection method and system and computer readable storage medium | |
CN102706274A (en) | System for accurately positioning mechanical part by machine vision in industrially-structured scene | |
CN103093451A (en) | Checkerboard intersection recognition algorithm | |
CN102663781A (en) | Sub-pixel level welding center extraction method based on visual sense | |
CN104568989A (en) | Glass substrate defect detecting method | |
CN104992448B (en) | The automatic positioning method of robot antisitic defect grape-picking | |
CN105023018A (en) | Jet code detection method and system | |
CN110782183A (en) | Aluminum product defect detection method based on Faster R-CNN | |
CN108492306A (en) | A kind of X-type Angular Point Extracting Method based on image outline | |
CN105654468A (en) | Tea sprout detection method based on depth learning and image edge information | |
CN113566704A (en) | Bearing assembly ball size detection method based on machine vision | |
CN108663376B (en) | Seamless steel tube quality detection device and detection method | |
WO2020119246A1 (en) | Highlight object surface defect detection system and method based on reflected light | |
CN206684071U (en) | A kind of double surface defect vision inspection apparatus of rapid large-area transparent substrate |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150422 |