CN101696945B - On-line detection method of machine vision system to photovoltaic glass flaws - Google Patents
On-line detection method of machine vision system to photovoltaic glass flaws Download PDFInfo
- Publication number
- CN101696945B CN101696945B CN 200910210887 CN200910210887A CN101696945B CN 101696945 B CN101696945 B CN 101696945B CN 200910210887 CN200910210887 CN 200910210887 CN 200910210887 A CN200910210887 A CN 200910210887A CN 101696945 B CN101696945 B CN 101696945B
- Authority
- CN
- China
- Prior art keywords
- image
- photovoltaic glass
- flaw
- turn
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses an on-line detection method of a machine vision system to photovoltaic glass flaws. The diameter of an in-built air bubble, the length of an open air bubble and the length of a nick are set as detection parameters; the detection precision and the qualified range of the different detection parameters are set according to the requirements of a user; a camera is started by outer triggering and control signals for shooting an image of on-line running photovoltaic glass in real time; the shot image is transmitted to a computer for detection; the computer is used for extracting an image with the photovoltaic glass with flaws by image algorithm processing and computing three flaw sizes to judge whether products are qualified products or discarded products by the computed flaw sizes; and two kinds of products are separated from different discharge holes by the outer triggering and control signals. The method has the advantages of high detection precision and high direction speed of the photovoltaic glass and can effectively ensure the qualified ratio of the products.
Description
Technical field
The present invention relates to the technical field of utilizing Vision Builder for Automated Inspection to detect online, relate in particular in the photovoltaic glass production scene method of utilizing Vision Builder for Automated Inspection that photovoltaic glass flaws is detected online.
Background technology
On-the-spot at the photovoltaic glass workshop of line production, the flaw of photovoltaic glass is detected online.In the prior art, online detection to photovoltaic glass flaws relies on the artificial magnifier special that uses to detect, produce the machine side at photovoltaic glass and establish specific purpose tool detection and the processing that about 30 people carry out photovoltaic glass flaws, testing result is divided into certified products (such as inner steam bubble dia＜0.5mm, and opening steam bubble length＜0.2mm, and cut length＜0.5mm, and do not have other flaws) and unacceptable product (such as inner steam bubble dia 〉=0.5mm, or opening steam bubble length 〉=0.2mm, or cut length 〉=0.5mm, or above three kinds of other flaws are in addition arranged).
The shortcoming that manual detection exists mainly contains: the on-the-spot dust of workshop is many, noise is large, and workman's testing environment is abominable, can't directly use range estimation (needing to use the Special handheld magnifier), and labour intensity is large; The normal eye namely can dim eyesight, the discomfort such as eye is swollen about uninterrupted observation moving object 30min, and for a long time non-stop run of testing staff can't guarantee the product export qualification rate; The photovoltaic glass flaws detection is the detection with the quantity precision, and human eye is difficult to judge that accurately error is large that the chance of makeing mistakes is a lot, can't guarantee to detect quality; The speed that the professional detects photovoltaic glass is up to 0.016m
2/ s has very big restriction to throughput rate.
The content of invention
Online detection dependence to photovoltaic glass flaws manually detects for prior art, the workman produces visual fatigue easily, labour intensity is large, can't guarantee product percent of pass and detect quality, the problems such as monitoring velocity is low the invention provides a kind of Vision Builder for Automated Inspection to the online test method of photovoltaic glass flaws, and it reduces workman's detection labour intensity greatly, accuracy of detection is high, speed is fast, the qualification rate of the product that can effectively guarantee to dispatch from the factory.
Technical scheme of the present invention is as follows:
A kind of Vision Builder for Automated Inspection may further comprise the steps the online test method of photovoltaic glass flaws:
(1) the little 1800D type industrial camera of looking in Beijing of the image of on-line operation photovoltaic glass flaws is taken in preparation one, and described camera is controlled by outer triggering signal;
(2) take the parameter of camera according to the size adjustment of photovoltaic glass to be detected, comprise aperture size, time shutter, in order to obtain clearly photographic images;
(3) set the detection parameter, comprise the diameter of built-in steam bubble, the length of opening steam bubble and the length of cut, and accuracy of detection and the acceptability limit of described detection parameter are set according to customer requirements;
(4) start the image that described camera is taken the on-line operation photovoltaic glass flaws in real time by external trigger and control signal, and image transmitting to the computing machine of taking is supplied to detect;
(5) computing machine is processed by image algorithm, judges whether to exist flaw, and extracts photovoltaic glass image defective; If through finding not have the flaw image after the image algorithm processing, belong to certified products, sort out from certified products sorting mouth, otherwise carry out next step.
(6) computing machine calculates the shape of described photovoltaic glass flaws and the size of flaw;
(7) flaw shape and the flaw size by calculating, the acceptability limit of setting with step (3) compares, and judges that this product is to belong to certified products/waste product, sorts two series products from control signal by external trigger from different discharging openings.
And further technical scheme is:
To described (7) step, judge that at first flaw is circular, oval or linear, if circle then turns to (7A) step, if ellipse then turns to (7B) step, if linearly then turn to (7C) step:
(7A) judge circular flaw image diameter whether acceptability limit (＜0.5mm), as then turning to (8A) step at acceptability limit, if greater than specialized range (〉=0.5mm) then turn to (8B) step;
(7B) judge oval flaw image length whether acceptability limit (＜0.2mm), as then turning to (8A) step at acceptability limit, if greater than specialized range (〉=0.2mm) then turn to (8B) step;
(7C) judge linear flaw image length whether acceptability limit (＜0.5mm), as then turning to (8A) step at acceptability limit, if greater than specialized range (〉=0.5mm) then turn to (8B) step;
(8) carry out respectively following operation according to the testing result of each step of front:
(8A) sort as certified products;
(8B) directly as goods rejection.
And further technical scheme is:
To described (7) step, when detecting product and be waste product, computing machine will carry out picture cues by man-machine interface, and start warning device.
Useful technique effect of the present invention is:
The present invention adopts Vision Builder for Automated Inspection that photovoltaic glass flaws is detected online, replaces manual detection, and the user can carry out the adjusting of accuracy of detection automatically.Have the record, classification, statistics, storage, the query function that product are detected certified products, this two series products of waste product.And in image, point out the unacceptable product situation by friendly man-machine interface, and give sound, light alarm, greatly reduce workman's detection labour intensity.
Manual detection speed is generally 0.016m
2/ s, and the Vision Builder for Automated Inspection detection speed can reach 0.1m
2About/s, the product detection speed of Vision Builder for Automated Inspection is artificial 6～7 times, has greatly improved production efficiency.
Manual detection can't uninterruptedly be carried out product quality in 24 hours and detect owing to environment and physiological reason, adopted Vision Builder for Automated Inspection to detect and then made it become possibility.The production time of equipment can prolong to greatest extent, has improved the utilization factor of equipment.
The artificial detection because neighbourhood noise is large, dust is many, the vision fatiguability is difficult to the Continuous Tracking product quality.Quantize to detect by artificial being difficult to and guarantee that improper defect rate generally about 8～10%, has caused the significant wastage of the resources of production and production cost; The detection dimensional accuracy of Vision Builder for Automated Inspection is up to 0.1mm, and precision can every 0.1mm degree be that a gradient is adjusted, and is set to several accuracy classes such as 0.1,0.2,0.3,0.4,0.5 degree, thereby greatly improves product percent of pass and detect quality.
Description of drawings
Fig. 1 is the photovoltaic glass image that inner steam bubble is arranged.
Fig. 2 is the photovoltaic glass image that the opening steam bubble is arranged.
Fig. 3 is the photovoltaic glass image of cut.
Fig. 4 is process sequence diagram of the present invention.
Embodiment
Below in conjunction with accompanying drawing the specific embodiment of the present invention is described further.
Fig. 1,2, the 3rd takes directly over the photovoltaic glass and image after treatment.
In the photographic images shown in Fig. 1,2,3, in order better to distinguish figure, flaw partly adopts circle, ellipse and the lines of standard to represent the flaw classification among the figure; Blank parts is the transparent space after the photovoltaic glass image is processed through denoising software all around.
Embodiment one, to the detection of inner steam bubble flaw product is arranged:
Inside steam bubble flaw image as shown in Figure 1, wherein black part is divided into the visual pattern that inner steam bubble forms.
Beijing little 1800D of looking type industrial camera is fixed on directly over photovoltaic glass vertical, and camera is 40cm apart from the distance of glass surface, uses the manual zoom zoom of 5.5mm COMPUTAR camera lens, and aperture is transferred to maximal value, and the time shutter is adjusted to 0.58ms.Inner steam bubble accuracy of detection is set to 0.1mm, and setting the normal steam bubble dia of certified products is 0.5mm.Adopt special red LED background light source, shine from photovoltaic glass below, and use and semiclosedly block the metal framework, in order to obtain visual pattern more stablely, embody the obvious characteristic of the inner steam bubble of photovoltaic glass.The power supply of display light source is constant pressure and flow, is the stabilized light source that tool does not become frequently or high frequency becomes, in order to can photograph clearly image more stablely, and is shown in the screen of computing machine.Adopt the roll shaft transmission system on the production line to carry out the glass conveying, guarantee that glass enters pick-up unit by certain direction and speed.
Computing machine is according to the different control system of institute of different production firm production equipment, obtain the synchronous triggering of camera and production process and control signal, start described industrial camera and take the image of the photovoltaic glass of on-line operation, and with the inside glass steam bubble image that obtains, be stored in the computing machine.
Computing machine carries out image to captured image by edge extracting, smoothing denoising, binary conversion treatment, Fourier Tranform scheduling algorithm to be processed, and makes image more clear, more meets the truth of the inner steam bubble of photovoltaic glass.The algorithm that adopts in the above-mentioned image processing process is conventional algorithm of the prior art.
Computing machine calculates the diameter of glass steam bubble.This diameter is that described inner steam bubble passes through the distance between two point of crossing of straight line and steam bubble edge in the center of circle, and this distance value also is the diameter value of described steam bubble.
Be 0.4mm such as detected diameter value, then this product is certified products; Be 0.6mm such as detected diameter value, then this product is unacceptable product.Computing machine records, classifies, adds up warehouse-in to such certified products.
Embodiment two, to the detection of opening steam bubble flaw product is arranged:
Opening steam bubble flaw image as shown in Figure 2, wherein the oval part of black is the visual pattern of opening steam bubble formation.
Beijing little 1800D of looking type industrial camera is fixed on directly over photovoltaic glass vertical, and camera is 40cm apart from the distance of glass surface, uses the manual zoom zoom of 5.5mm COMPUTAR camera lens, and aperture is transferred to maximal value, and the time shutter is adjusted to 0.58ms.Opening steam bubble accuracy of detection is set to 0.1mm, and setting the normal steam bubble dia of certified products is 0.2mm.Adopt special red LED background light source, shine from photovoltaic glass below, and use and semiclosedly block the metal framework, in order to obtain visual pattern more stablely, embody the obvious characteristic of photovoltaic glass opening steam bubble.The power supply of display light source is constant pressure and flow, is the stabilized light source that tool does not become frequently or high frequency becomes, in order to can photograph clearly image more stablely, and is shown in the screen of computing machine.Adopt the roll shaft transmission system on the production line to carry out the glass conveying, guarantee that glass enters pick-up unit by certain direction and speed.
Computing machine is according to the different control system of institute of different production firm production equipment, obtain the synchronous triggering of camera and production process and control signal, start described industrial camera and take the image of the photovoltaic glass of on-line operation, and with the glass open steam bubble image that obtains, be stored in the computing machine.
Computing machine carries out image to captured image by edge extracting, smoothing denoising, binary conversion treatment, Fourier Tranform scheduling algorithm to be processed, and makes image more clear, more meets the truth of photovoltaic glass opening steam bubble.The algorithm that adopts in the above-mentioned image processing process is conventional algorithm of the prior art.
Computing machine calculates the length of glass open steam bubble.This length is the farthest distance between the two-end-point of described opening steam bubble, and this distance value also is the length value of described steam bubble.
Be 0.1mm such as detected length value, then this product is certified products; Be 0.3mm such as detected length value, then this product is unacceptable product.Computing machine records, classifies, adds up warehouse-in to such certified products.
Embodiment 3, to the detection of cut flaw product is arranged:
Cut flaw image as shown in Figure 3, wherein black part is divided into the visual pattern that cut forms.
Beijing little 1800D of looking type industrial camera is fixed on directly over photovoltaic glass vertical, and camera is 40cm apart from the distance of glass surface, uses the manual zoom zoom of 5.5mm COMPUTAR camera lens, and aperture is transferred to maximal value, and the time shutter is adjusted to 0.58ms.Inner scratch detection precision setting is 0.1mm, and setting the normal cut length of certified products is 0.5mm.Adopt special red LED background light source, shine from photovoltaic glass below, and use and semiclosedly block the metal framework, in order to obtain visual pattern more stablely, embody the obvious characteristic of photovoltaic glass cut.The power supply of display light source is constant pressure and flow, is the stabilized light source that tool does not become frequently or high frequency becomes, in order to can photograph clearly image more stablely, and is shown in the screen of computing machine.Adopt the roll shaft transmission system on the production line to carry out the glass conveying, guarantee that glass enters pick-up unit by certain direction and speed.
Computing machine is according to the different control system of institute of different production firm production equipment, obtain the synchronous triggering of camera and production process and control signal, start described industrial camera and take the image of the photovoltaic glass of on-line operation, and with the glass scratch image that obtains, be stored in the computing machine.
Computing machine carries out image to captured image by edge extracting, smoothing denoising, binary conversion treatment, Fourier Tranform scheduling algorithm to be processed, and makes image more clear, more meets the truth of photovoltaic glass cut.The algorithm that adopts in the above-mentioned image processing process is conventional algorithm of the prior art.
Computing machine calculates the length of glass scratch.This length is the distance between 2 of the described cut distal-most end, and this distance value also is the length value of described cut.
Be 0.3mm such as detected length value, then this product is certified products; Be 0.7mm such as detected length value, then this product is unacceptable product.Computing machine records, classifies, adds up warehouse-in to such certified products.
In above-mentioned 3 embodiment, also have other unknown flaw images to occur if process discovery through image algorithm, think that then this photovoltaic glass is unacceptable product, rejects this photovoltaic glass as waste product.
More than the control system (hardware and software) of the image capture device (camera, radiation source, power supply, image pick-up card etc.) that uses among all embodiment and storage device (hard disk, CD, floppy disk etc.), image processing equipment (hardware of image processor and software), image display (hardware and software), warning device and each part mentioned above all adopt prior art to design and produce or directly adopt relevant commercially available prod.
Above-described processing step of the present invention is shown in Fig. 4.Specifically may further comprise the steps:
(1) the little 1800D type industrial camera of looking in Beijing of the image of on-line operation photovoltaic glass flaws is taken in preparation one, and described camera is controlled by outer triggering signal;
(2) take the parameter of camera according to the size adjustment of photovoltaic glass to be detected, comprise aperture size, time shutter, in order to obtain clearly photographic images;
(3) set the detection parameter, comprise the diameter of built-in steam bubble, the length of opening steam bubble and the length of cut, and accuracy of detection and the acceptability limit of described detection parameter are set according to customer requirements;
(4) start the image that described camera is taken the on-line operation photovoltaic glass flaws in real time by external trigger and control signal, and image transmitting to the computing machine of taking is supplied to detect;
(5) computing machine is processed by image algorithm, judges whether to exist flaw, and extracts photovoltaic glass image defective; If through finding not have the flaw image after the image algorithm processing, belong to certified products, sort out from certified products sorting mouth, otherwise carry out next step.
(6) computing machine calculates the shape of described photovoltaic glass flaws and the size of flaw;
(7) flaw shape and the flaw size by calculating, the acceptability limit of setting with step (3) compares, and judges that this product is to belong to certified products/waste product, sorts two series products from control signal by external trigger from different discharging openings.
Do you to described (7) step, judge at first whether circular flaw is? if circle then turns to (7A) step; Do you otherwise judge whether oval flaw is? if ellipse then turns to (7B) step; Do you otherwise judge whether linear flaw is? if linear then turn to (7C) goes on foot; Otherwise belong to other flaw types, directly turn to (8B) step:
(7A) judge circular flaw image diameter whether acceptability limit (＜0.5mm), as then turning to (8A) step at acceptability limit, if greater than specialized range (〉=0.5mm) then turn to (8B) step;
(7B) judge oval flaw image length whether acceptability limit (＜0.2mm), as then turning to (8A) step at acceptability limit, if greater than specialized range (〉=0.2mm) then turn to (8B) step;
(7C) judge linear flaw image length whether acceptability limit (＜0.5mm), as then turning to (8A) step at acceptability limit, if greater than specialized range (〉=0.5mm) then turn to (8B) step;
(8) carry out respectively following operation according to the testing result of each step of front:
(8A) sort as certified products;
(8B) directly as goods rejection.
To described (7) step, when detecting product and be waste product, computing machine will carry out picture cues by man-machine interface, and start warning device.
It should be noted that at last above-described only is preferred implementation of the present invention, the invention is not restricted to above embodiment.Be appreciated that other improvement and variation that those skilled in the art directly derive or associate under the prerequisite that does not break away from spirit of the present invention and design, all should think to be included within protection scope of the present invention.
Claims (2)
1. a Vision Builder for Automated Inspection is characterized in that the online test method of photovoltaic glass flaws, may further comprise the steps:
(1) the little 1800D type industrial camera of looking in Beijing of the image of on-line operation photovoltaic glass flaws is taken in preparation one, and described camera is controlled by outer triggering signal;
(2) take the parameter of camera according to the size adjustment of photovoltaic glass to be detected, comprise aperture size, time shutter, in order to obtain clearly photographic images;
(3) set the detection parameter, comprise the diameter of built-in steam bubble, the length of opening steam bubble and the length of cut, and accuracy of detection and the acceptability limit of described detection parameter are set according to customer requirements;
(4) start the image that described camera is taken the on-line operation photovoltaic glass flaws in real time by external trigger and control signal, and image transmitting to the computing machine of taking is supplied to detect;
(5) computing machine is processed by image algorithm, judges whether to exist flaw, and extracts photovoltaic glass image defective;
In this step (5), if through finding not have the flaw image after the image algorithm processing, belong to certified products, sort out from certified products sorting mouth;
(6) computing machine calculates the shape of described photovoltaic glass flaws and the size of flaw;
(7) flaw shape and the flaw size by calculating, the acceptability limit of setting with step (3) compares, and judges that this product is to belong to certified products/waste product, sorts two series products from control signal by external trigger from different discharging openings; Be specially: judge that at first whether flaw is circular, if circle then turns to (7A) step, if not, then continues to determine whether ellipse; If ellipse then turns to (7B) step, if not, then continue to determine whether linear; If linear then turn to (7C) goes on foot; Otherwise belong to other flaw types, directly turn to (8B) step:
(7A) whether judge circular flaw image diameter at the acceptability limit less than 0.5mm, as then turn to (8A) step at acceptability limit, if then turn to (8B) step in the scope more than or equal to 0.5mm;
(7B) whether judge oval flaw image length at the acceptability limit less than 0.2mm, as then turn to (8A) step at acceptability limit, if then turn to (8B) step in the scope more than or equal to 0.2mm;
(7C) whether judge linear flaw image length at the acceptability limit less than 0.5mm, as then turn to (8A) step at acceptability limit, if then turn to (8B) step in the scope more than or equal to 0.5mm;
(8) carry out respectively following operation according to the testing result of each step of front:
(8A) sort as certified products;
(8B) directly as goods rejection.
2. Vision Builder for Automated Inspection according to claim 1 is to the online test method of photovoltaic glass flaws, it is characterized in that, to described (7) step, when detecting product and be waste product, computing machine will carry out picture cues by man-machine interface, and start warning device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910210887 CN101696945B (en) | 2009-11-13 | 2009-11-13 | On-line detection method of machine vision system to photovoltaic glass flaws |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910210887 CN101696945B (en) | 2009-11-13 | 2009-11-13 | On-line detection method of machine vision system to photovoltaic glass flaws |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101696945A CN101696945A (en) | 2010-04-21 |
| CN101696945B true CN101696945B (en) | 2013-01-09 |
Family
ID=42142061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200910210887 Expired - Fee Related CN101696945B (en) | 2009-11-13 | 2009-11-13 | On-line detection method of machine vision system to photovoltaic glass flaws |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101696945B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102235980B (en) * | 2010-04-27 | 2013-10-23 | 英利能源（中国）有限公司 | Device for detecting photovoltaic cell assembly on line |
| CN101995412B (en) * | 2010-08-30 | 2012-09-05 | 中国科学院计算技术研究所 | Robust glass scratch defect detection method and device thereof |
| CN102495072A (en) * | 2011-11-14 | 2012-06-13 | 无锡众望四维科技有限公司 | Automatic detection method for flaw of transfusion catheter through machine vision system |
| CN102495077A (en) * | 2011-11-14 | 2012-06-13 | 无锡众望四维科技有限公司 | Automatic detecting method of machine vision system for detecting flaws of infusion bottle |
| CN102495074A (en) * | 2011-11-14 | 2012-06-13 | 无锡众望四维科技有限公司 | Automatic detecting method of machine vision system for detecting flaws of infusion bag |
| CN102590222A (en) * | 2012-03-06 | 2012-07-18 | 英利能源（中国）有限公司 | Photovoltaic component defect detection method and system |
| CN103175844A (en) * | 2012-03-16 | 2013-06-26 | 沈阳理工大学 | Detection method for scratches and defects on surfaces of metal components |
| CN103926256A (en) * | 2014-03-20 | 2014-07-16 | 上海华力微电子有限公司 | CMP scratch automatic detection system |
| CN104655646A (en) * | 2014-04-24 | 2015-05-27 | 东旭集团有限公司 | Glass substrate internal defect checking system and checking method for height position of internal defect |
| CN104359925A (en) * | 2014-11-17 | 2015-02-18 | 上海埃蒙特自动化系统有限公司 | System for realizing automatic detection of electronic glass defects |
| CN107014831B (en) * | 2016-03-10 | 2020-03-06 | 上海帆煊科技有限公司 | Detection method of ITO conductive glass detection device |
| CN106770334B (en) * | 2017-02-21 | 2019-06-25 | 连云港同达科技有限公司 | A kind of automatic detection platform and its detection method for tempered glass |
| CN106984555A (en) * | 2017-04-14 | 2017-07-28 | 中建材（宜兴）新能源有限公司 | A kind of multistation glass lower piece device |
| CN108445016B (en) * | 2018-02-23 | 2020-07-21 | 杭州开浦科技有限公司 | Automatic detection sorting device |
| CN112098428A (en) * | 2020-09-04 | 2020-12-18 | 杭州百子尖科技股份有限公司 | Intelligent flaw identification system based on machine vision in sheet building material manufacturing |
-
2009
- 2009-11-13 CN CN 200910210887 patent/CN101696945B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN101696945A (en) | 2010-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101696945B (en) | On-line detection method of machine vision system to photovoltaic glass flaws | |
| CN101509766B (en) | On-line detecting method for spring end plane angle by machine vision system | |
| CN101696943B (en) | On-line detection method of machine vision system to medical surgical knife flaws | |
| CN102303017B (en) | Method for automatically detecting bending of injector steel needles by using machine vision system | |
| CN104614379A (en) | Plate surface defect detection system and method | |
| CN101696877A (en) | On-line detection method of machine vision system to spring verticality | |
| CN102494773A (en) | Automatic detection method of machine vision system on snap-fastener chromatic aberration | |
| CN102303018B (en) | Method for automatically detecting burrs of injector steel needles by using machine vision system | |
| CN101726265A (en) | Online detection method of parallelism of spring by machine vision system | |
| CN108333188A (en) | A kind of online apparent visual detection device of battery pole piece | |
| CN106896110A (en) | Product quality detection means and method based on monocular camera machine vision | |
| CN106770330A (en) | A kind of body surface scratch detection device and its detection method | |
| CN104132945A (en) | On-line surface quality visual inspection device for bar based on optical fiber conduction | |
| CN109507205A (en) | A kind of vision detection system and its detection method | |
| WO2024055796A1 (en) | Defect detection system, method and apparatus, electronic device, and storage medium | |
| CN102305603B (en) | Method for automatically detecting inclination of steel needle of injector by machine vision system | |
| CN105844282A (en) | Method for detecting defects of fuel injection nozzle O-Ring through line scanning camera | |
| CN102305597A (en) | Method for automatically detecting abnormal shape of injector part by using mechanical vision system | |
| CN102305797A (en) | Method for automatically detecting foreign matter of medical product package by using machine vision system | |
| CN111000286A (en) | Anti-interference cigarette appearance quality online detection device and method | |
| CN102305592A (en) | Method for automatically detecting back-stitching of steel needle of injector by using mechanical vision system | |
| CN102495072A (en) | Automatic detection method for flaw of transfusion catheter through machine vision system | |
| CN102305950A (en) | Method for automatically detecting missed accessory during automatic assembly of injector by using machine visual system | |
| CN102303019B (en) | Method for automatically detecting scales of injector needle cylinders by using machine vision system | |
| CN102495077A (en) | Automatic detecting method of machine vision system for detecting flaws of infusion bottle |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130109 Termination date: 20151113 |
|
| EXPY | Termination of patent right or utility model |