CN101858734B - Method for detecting PET bottleneck quality - Google Patents
Method for detecting PET bottleneck quality Download PDFInfo
- Publication number
- CN101858734B CN101858734B CN2010101759482A CN201010175948A CN101858734B CN 101858734 B CN101858734 B CN 101858734B CN 2010101759482 A CN2010101759482 A CN 2010101759482A CN 201010175948 A CN201010175948 A CN 201010175948A CN 101858734 B CN101858734 B CN 101858734B
- Authority
- CN
- China
- Prior art keywords
- image
- bottle
- circle
- ovality
- bottleneck
- 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.)
- Active
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method and a device for detecting PET bottleneck quality. The method comprises the steps of positioning, image acquisition, image processing and elimination, wherein the arrival of a PET bottle is detected through a sensor; the identification number of the bottle and a current encoder signal are recorded through a control unit; a camera is notified by the sensor to acquire the current image of the PET bottle; the image is processed by an image processor after the photographing; the processing result is transmitted to the control unit by the image processor to get ready to eliminate the unqualified bottle; and an elimination system is notified by the control unit to eliminate the bottle of the corresponding identification number after the control unit receives a non-qualification signal. The method and the device can perform real-time uninterrupted detection on the sealing property and the ellipticity of the PET bottle on a high-speed automatic production linewith high detection efficiency and high quality.
Description
Technical field
The invention belongs to production line Automatic Measurement Technique field, be specifically related to a kind of method of the PET of detection bottleneck quality, can on high-speed automated production line, carry out real-time non-discontinuity detection the breakage of PET bottleneck, scuffing and ovality.
Background technology
At present, automatic checkout equipment is being brought into play crucial effects in the commercial production now.In order to enhance productivity, must to make checkout equipment carry out online detection, and in time reject and detect underproof product, so contactless online detection instrument is being brought into play more and more important effect not interrupting under the industrial situation.In the process of present beer, food, beverage and pharmaceutical production, require container filling to satisfy corresponding quality standard, before the production can, all to carry out strict detection.For example before PET bottle filled drink, at first to detect the PET bottleneck and whether have defective such as circle of sealing defective and bottleneck.If the bottleneck defectiveness can cause the gas leakage of carbonated beverage, influence the quality of product.Not having before the online detection instrument, all is that the workman utilizes eye-observation to add the method for sampling check generally.Present line speed is very high, high reach 70,000 bottles/time, even low production line also reached 20,000 4 thousand bottles/time.On this high-speed production lines, use artificial naked eyes to detect, because visual fatigue and other human factors, manual detection is difficult to catch up with production requirement.
Summary of the invention
The objective of the invention is: providing a kind of can carry out real-time non-discontinuity detection to PET bottleneck sealing and ovality on high-speed automated production line, detection efficiency height, the measured a kind of method that detects the PET bottleneck quality of matter.
Technical scheme of the present invention is: a kind of method of the PET of detection bottleneck quality comprises following technological process:
The location: the PET bottle arrives to the PET bottle through sensor.
Image acquisition: control module obtains the positional information of bottle, and the while finishes the light source stroboscopic synchronously and camera is taken pictures, and gathers current PE T bottle image.
Flame Image Process: image is carried out cutting apart of area-of-interest, area-of-interest is carried out the image pre-service, pretreated image is carried out graphical analysis and information extraction.Pre-service comprises: a carries out gain process with entire image, makes clear picture bright; B determines the threshold value of image binaryzation according to the grey level histogram of entire image, and it is carried out binaryzation, and background and area-of-interest are tentatively cut apart; C covers the contour area of bottleneck with the round-shaped m of the setting bar detection line of bottleneck on area-of-interest; D as area-of-interest, continues suitable binaryzation with the contour area of bottleneck on detection line; E is inside or outside along the direction of detection line, searches shade of gray and change the point that reaches specified degree on every detection line, forms the array of a point, is designated as Points[m].The step of graphical analysis and information extraction is:
1. detect the ovality defective: with the some Points[m on the detection line] fit to a circle, and the ovality of checking this circle, the ovality of overshoot numerical value is for having the ovality defective.
2. detect the sealing defective: on described m bar detection line, search gray scale earlier along the direction of every detection line and just changing the point that reaches specified degree, be designated as PointsA[m], search the negative point that reaches specified degree that changes of gray scale again, be designated as PointsB[m]; By PointsA[m] and PointsB[m] fit to a circle respectively and be designated as CircleA and CircleB, obtain the center of circle CenterA of CircleA, the center of circle CenterB of diameter DiameterA and CircleB, diameter DiameterB, center of circle mid point with CircleA and CircleB is center of circle Center, diameter with CircleA and CircleB is that inner and outer diameter forms an annulus, be designated as Torus, binaryzation is once more carried out in whole Torus zone, look into the white pixel on several detection lines, circulation addition summation, with defectiveness the place and with entopic and relatively, be the sealing defective when being less than normal value and reaching preset threshold.
Reject: image processor passes to control module with its result, and after control module received ovality defective and sealing defective, the notice eliminating system was rejected the bottle of corresponding identification number.
A kind of device that detects the PET bottleneck quality, comprise bottleneck pick-up unit, mechanical transmission mechanism, sensor, technical grade high-resolution camera system, image processor, industrial control computer and eliminating system, the PET bottle is arranged in the mechanical transmission mechanism, technical grade high-resolution camera system is made up of camera and LED combined light source, camera is arranged on the top of PET bottleneck, the PET bottle is through sensor, sensor is connected with the LED combined light source with camera, camera is connected with image processor, and control module links to each other with sensor, image processor and eliminating system.
Adopt annular low angle light source, prospect light polishing mode is adopted in LED light-emitting particles and horizontal direction angle of inclination between 30 °-60 °, with the outline line feature of bottleneck from extracting the background on every side.Sensor and stroboscopic controller are used, and when the PET bottle triggered sensor, light source reached brightness peak in the short time.
The invention has the beneficial effects as follows: the PET bottle in mechanical transmission mechanism enters this pick-up unit when triggering laser sensor, control module obtain this bottle positional information, the while is finished the light source stroboscopic synchronously and camera is taken pictures.Image processor is handled in real time to captured image, judge whether bottleneck is qualified, defective information sent to control module, after control module receives defective information, by the calculating of interior location information, utilize eliminating system that this bottle is rejected in real time at assigned address.Device of the present invention can be installed in before the bottle blowing machine; also can be installed in after the bottle blowing machine; if be installed in before the bottle blowing machine; this device can be discerned those defectiveness bottle embryos that are about to enter bottle blowing machine and those and can cause axle to load bad and damage the defectiveness bottle embryo of heating lamp; help control bottle embryo to enter bottle blowing machine; minimizing is stopped up and stop time by the bottle blowing machine that defectiveness bottle embryo causes; promote low-carbon economy; save labour and energy resource consumption; if be installed in after the bottle blowing machine; thereby this device can detect and reject the shaping bottle that exists the sealing surface defective to cause to leak after the can, improve production efficiency and product quality.
Description of drawings
Fig. 1 is a process chart of the present invention;
Fig. 2 is a work synoptic diagram of the present invention.
Embodiment
Device of the present invention is by bottleneck pick-up unit, mechanical transmission mechanism, laser sensor, technical grade high-resolution camera system, industrial control computer and form based on the steady eliminating system of air pressure.From process chart of the present invention shown in Figure 1 as can be seen, PET bottle or bottle embryo are through laser sensor, detecting the PET bottle arrives, by control module record bottle identification number, record current encoder signal, optical sensor notice camera is gathered current PE T bottle image, take pictures finish after, by image processor this image is handled, image processor passes to control module with its result, prepare to reject defective bottle, after control module received defective signal, the notice eliminating system was rejected the bottle of corresponding identification number.
Fig. 2 is a work synoptic diagram of the present invention, bottleneck technical grade high-resolution camera system among the present invention is made up of camera 1 and coaxial and annular LED combined light source, adopt annular low angle light source, LED light-emitting particles and horizontal direction angle of inclination are between 30 °-60 °, employing prospect light polishing mode, with the outline line feature of bottleneck from extracting the background on every side.Camera 1 has the double bracket structure, can as much as possible reduce the vibrations of camera 1 under industrial environment, can guarantee the image that high-resolution is stable.When PET bottle 3 enters the bottleneck detecting unit by mechanical transmission mechanism, control module receives the trigger message of bottleneck 2 through laser sensor, output signal to stroboscopic controller trigger point bright light source by control module, the image pick-up card that receives trigger pip is simultaneously gathered the video analog signal of camera 3 outputs.Adopt the light source stroboscopic technique, laser photoelectricity and stroboscopic controller are used, when bottle triggered photoelectricity, light source reached brightness peak in the short time.The combination led light source is than the light source of all the other structures, has the advantage of uniform of throwing light under, the suitable situation of distance coaxial with camera, and we select is the visual field light source that has a bright future, and this light source helps finding the defective on high reflecting material surface.
Technological process of the present invention has: location, image acquisition, Flame Image Process and rejecting.
The location: the PET bottle detects the PET bottle through laser sensor and arrives.
Image acquisition: control module obtains the positional information of bottle, and record bottle identification number, record current encoder signal are finished the light source stroboscopic simultaneously synchronously and camera is taken pictures, and gather current PE T bottle image.Collect set of diagrams as sequence, for each width of cloth image in the image sequence, it all is a two dimensional image array, in this pattern matrix, the pixel of carrying bottleneck image information is not all pixels of whole array image, and the relation of the pixel count of the speed of Flame Image Process own and processing is a directly proportional relation, and what we only paid close attention to is the feature of the pixel region of carrying bottleneck information in the image, so Flame Image Process is handled with regard to only being directed to this part target area.
Flame Image Process: by image processor the image of gathering is handled, the detailed process of each width of cloth treatment of picture in the sequence image of gathering is comprised:
1, image is carried out cutting apart of area-of-interest, area-of-interest is carried out the image pre-service.At first entire image is carried out suitable gain process,, be easy to observe so that clear picture is bright.Determine the threshold value of image binaryzation according to the grey level histogram of entire image, and it is carried out binaryzation, background and area-of-interest (bottleneck region) are tentatively cut apart; The round-shaped m of setting (value of m can be set as required) bar detection line with bottleneck on area-of-interest covers the contour area of bottleneck.Then with the contour area of bottleneck as area-of-interest, on detection line, continue suitable binaryzation.Subsequently, inside or outside along the direction of detection line, on every detection line, search shade of gray and change the point that reaches specified degree, form the array of a point, be designated as Points[m].
2, pretreated image is carried out graphical analysis and information extraction.Concrete steps are as follows:
1. detect the method for ovality defective:
With the some Points[m on the detection line] fit to a circle, and the ovality of checking this circle.Ovality is used for weighing bottleneck circularity, and the computing formula of ovality is:
Ovality=100* (maximum gauge-minimum diameter)/(maximum gauge+minimum diameter)
The ovality of overshoot thinks that promptly this product has the ovality defective, is unacceptable product.Wherein, the setting as required that " ovality of regulation " can be artificial.
Wherein, maximum gauge and minimum diameter are by from Points[m] the maximal value and the minimum value that draw in any 3 formation diameter of a circle.
2. detect the method for sealing defective:
On above-mentioned m bar detection line, search gray scale earlier along the direction of every detection line and just changing the point that reaches specified degree, be designated as PointsA[m], search the negative point that reaches specified degree that changes of gray scale again, be designated as PointsB[m].Wherein positive and negative variation refers to that respectively gray-scale value becomes big and gray-scale value diminishes.By PointsA[m] and PointsB[m] fit to a circle respectively and be designated as CircleA and CircleB, center of circle CenterA, the diameter DiameterA of CircleA and center of circle CenterB, the diameter DiameterB of CircleB obtained.Center of circle mid point with CircleA and CircleB is center of circle Center, is that inner and outer diameter forms an annulus with the diameter of CircleA and CircleB, is designated as Torus.Binaryzation is once more carried out in whole Torus zone, and the degree of binaryzation is can clear resolution defective being criterion.
Look into the white pixel on every detection line of number, be designated as White[m].From being numbered white pixel number on the 0th the detection line, search n (value of n can be set as required) bar detection line continuously, and summation Sum[m], promptly
Sum[i]＝White[i]+Whi?te[i+1]+……+White[i+n](i＝0，1，……，m)
Because the 0th detection line joins end to end with m bar detection line, the addition that can circulate is sued for peace.
With defectiveness the place and with entopic and make comparisons, when being less than normal value and reaching preset threshold, think to be the sealing defective herein.
Reject: set the defective criterion as required, judge whether the information of extracting reaches defective and judge requirement, image processor passes to control module with its result, and after control module received ovality defective and sealing defective, the notice eliminating system was rejected the bottle of corresponding identification number.
In sum, require to adjust above-mentioned each parameter value according to defects detection, if the information parameter of the fields of interest of extracting reaches our setting examination criteria, system is this image recognition defective image, to output signal to control module, and start device for eliminating unacceptable product is rejected.
Claims (2)
1. method that detects the PET bottleneck quality is characterized in that: comprise following technological process:
The location: the PET bottle arrives to the PET bottle through sensor;
Image acquisition: control module obtains the positional information of bottle, and the while finishes the light source stroboscopic synchronously and camera is taken pictures, and gathers current PE T bottle image;
Flame Image Process: image is carried out cutting apart of area-of-interest, area-of-interest is carried out the image pre-service, pretreated image is carried out graphical analysis and information extraction;
Described pre-service comprises: a carries out gain process with entire image, makes clear picture bright; B determines the threshold value of image binaryzation according to the grey level histogram of entire image, and it is carried out binaryzation, and background and area-of-interest are tentatively cut apart; C covers the contour area of bottleneck with the round-shaped m of the setting bar detection line of bottleneck on area-of-interest; D as area-of-interest, continues suitable binaryzation with the contour area of bottleneck on detection line; E is inside or outside along the direction of detection line, searches shade of gray and change the point that reaches specified degree on every detection line, forms the array of a point, is designated as Points[m];
The step of described graphical analysis and information extraction is:
1. detect the ovality defective: with the some Points[m on the detection line] fit to a circle, and the ovality of checking this circle, the ovality of overshoot numerical value is for having the ovality defective;
2. detect the sealing defective: on described m bar detection line, search gray scale earlier along the direction of every detection line and just changing the point that reaches specified degree, be designated as PointsA[m], search the negative point that reaches specified degree that changes of gray scale again, be designated as PointsB[m]; By PointsA[m] and PointsB[m] fit to a circle respectively and be designated as CircleA and CircleB, obtain the center of circle CenterA of CircleA, the center of circle CenterB of diameter DiameterA and CircleB, diameter DiameterB, center of circle mid point with CircleA and CircleB is center of circle Center, diameter with CircleA and CircleB is that inner and outer diameter forms an annulus, be designated as Torus, binaryzation is once more carried out in whole Torus zone, look into the white pixel on several detection lines, circulation addition summation, with defectiveness the place and with entopic and relatively, be the sealing defective when being less than normal value and reaching preset threshold;
Reject: image processor passes to control module with its result, and after control module received ovality defective and sealing defective, the notice eliminating system was rejected the bottle of corresponding identification number.
2. the method for detection PET bottleneck quality according to claim 1, it is characterized in that: the computing formula of described ovality is:
Ovality=100 * (maximum gauge-minimum diameter)/(maximum gauge+minimum diameter)
Maximum gauge and minimum diameter are by from Points[m] the maximal value and the minimum value that draw in any 3 formation diameter of a circle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101759482A CN101858734B (en) | 2010-05-19 | 2010-05-19 | Method for detecting PET bottleneck quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101759482A CN101858734B (en) | 2010-05-19 | 2010-05-19 | Method for detecting PET bottleneck quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101858734A CN101858734A (en) | 2010-10-13 |
| CN101858734B true CN101858734B (en) | 2011-06-29 |
Family
ID=42944775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101759482A Active CN101858734B (en) | 2010-05-19 | 2010-05-19 | Method for detecting PET bottleneck quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101858734B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519972A (en) * | 2011-12-10 | 2012-06-27 | 山东明佳包装检测科技有限公司 | Detection method of PET bottle cap and liquid level |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5863007B2 (en) * | 2011-09-08 | 2016-02-16 | サントリーホールディングス株式会社 | Liquid leak inspection device for containers |
| JP5128699B1 (en) * | 2011-09-27 | 2013-01-23 | シャープ株式会社 | Wiring inspection method and wiring inspection apparatus |
| CN102519359B (en) * | 2011-12-12 | 2014-03-19 | 山东明佳包装检测科技有限公司 | Method for detecting label of polyethylene terephthalate (PET) bottle |
| CN103063137B (en) * | 2012-12-28 | 2016-03-30 | 北京大学深圳医院 | A kind of medicine bottle measuring system based on machine vision and measuring method thereof |
| CN104680509B (en) * | 2013-11-30 | 2017-09-15 | 中国科学院沈阳自动化研究所 | A kind of real-time circular printing image defect detection method |
| CN103606167B (en) * | 2013-12-04 | 2016-08-31 | 天津普达软件技术有限公司 | A kind of outer bottle cap profile for defects detection determines method |
| CN103606128B (en) * | 2013-12-04 | 2016-04-06 | 天津普达软件技术有限公司 | A kind of method detecting outer circle of bottle cap burr |
| CN103606169A (en) * | 2013-12-04 | 2014-02-26 | 天津普达软件技术有限公司 | Method for detecting defects of bottle cap |
| CN104764746B (en) * | 2014-01-06 | 2017-04-05 | 山东明佳包装检测科技有限公司 | A kind of detection method of comprehensive PET bottle lid anti-theft ring defect |
| CN104550051A (en) * | 2014-12-23 | 2015-04-29 | 山东明佳科技有限公司 | Empty bottle sorting system for glass bottle |
| TWI583943B (en) * | 2015-06-15 | 2017-05-21 | Bottle flaw defect detection device and method thereof | |
| BR112018016772A2 (en) * | 2016-02-19 | 2018-12-26 | Gebo Cermex Canada Inc | product detector |
| CN106251352B (en) * | 2016-07-29 | 2019-01-18 | 武汉大学 | A kind of cover defect inspection method based on image procossing |
| CN106053485A (en) * | 2016-08-01 | 2016-10-26 | 苏州宙点自动化设备有限公司 | Machine vision-based novel algorithm of intelligent circular inspection of steel ball surface defects |
| CN107945155B (en) * | 2017-11-13 | 2021-05-25 | 佛山缔乐视觉科技有限公司 | Toothpaste tube shoulder defect detection method based on Gabor filter |
| CN108120353B (en) * | 2017-12-06 | 2019-12-10 | 中国兵器装备集团自动化研究所 | Fire transmission hole detection device and method based on intelligent camera |
| CN108188036A (en) * | 2017-12-29 | 2018-06-22 | 福建猛狮新能源科技有限公司 | The system of automatic detection li battery shell |
| CN109372736B (en) * | 2018-09-20 | 2020-03-24 | 上海雷恩医疗器械有限公司 | Infusion pump inspection system |
| CN110047067B (en) * | 2019-04-02 | 2021-06-22 | 广州大学 | Bottle shoulder detection method for bottle classification |
| CN110333242A (en) * | 2019-07-15 | 2019-10-15 | 武汉楚锐视觉检测科技有限公司 | A kind of detection method and its system of PET bottle quality |
| CN110496789B (en) * | 2019-08-22 | 2024-06-21 | 武汉楚锐视觉检测科技有限公司 | Oilcan on-line detection and rejection system |
| CN112213056A (en) * | 2020-09-14 | 2021-01-12 | 无锡纳纬科技有限公司 | Device and method for detecting sealing angle of beverage bottle |
| CN113554648B (en) * | 2021-09-18 | 2021-11-30 | 四川太平洋药业有限责任公司 | Production line detection method |
| CN113996599B (en) * | 2021-09-30 | 2023-07-11 | 歌尔股份有限公司 | Dirty bonding cleaning mechanism, product dirty clearance and detection device |
| CN115078397B (en) * | 2022-07-20 | 2022-11-15 | 菲特（天津）检测技术有限公司 | Medicine bottle detection system and method and electronic equipment |
| CN117007000B (en) * | 2023-10-07 | 2023-12-08 | 聊城好佳一生物乳业有限公司 | Beverage bottle bottleneck roughness detection device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2858078Y (en) * | 2005-08-03 | 2007-01-17 | 湖南大学 | Multi-vision empty bottle checking robot |
| CN101105459A (en) * | 2007-05-15 | 2008-01-16 | 广州市万世德包装机械有限公司 | Empty bottle mouth defect inspection method and device |
| CN201689062U (en) * | 2010-05-19 | 2010-12-29 | 山东明佳包装检测科技有限公司 | PET bottle mouth quality detection device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09269299A (en) * | 1996-03-29 | 1997-10-14 | Kirin Techno Syst:Kk | Device for examining petbottle |
| JPH11250254A (en) * | 1998-03-03 | 1999-09-17 | Nippon Steel Corp | Method and device for inspecting design quality |
-
2010
- 2010-05-19 CN CN2010101759482A patent/CN101858734B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2858078Y (en) * | 2005-08-03 | 2007-01-17 | 湖南大学 | Multi-vision empty bottle checking robot |
| CN101105459A (en) * | 2007-05-15 | 2008-01-16 | 广州市万世德包装机械有限公司 | Empty bottle mouth defect inspection method and device |
| CN201689062U (en) * | 2010-05-19 | 2010-12-29 | 山东明佳包装检测科技有限公司 | PET bottle mouth quality detection device |
Non-Patent Citations (4)
| Title |
|---|
| JP特开平11-250254A 1999.09.17 |
| JP特开平9-269299A 1997.10.14 |
| 丁挺 等.一种快速的玻璃瓶口裂纹检测算法.《计算机测量与控制》.2007,第15卷(第3期), |
| 丁挺等.一种快速的玻璃瓶口裂纹检测算法.《计算机测量与控制》.2007,第15卷(第3期), * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519972A (en) * | 2011-12-10 | 2012-06-27 | 山东明佳包装检测科技有限公司 | Detection method of PET bottle cap and liquid level |
| CN102519972B (en) * | 2011-12-10 | 2014-04-16 | 山东明佳包装检测科技有限公司 | Detection method of PET bottle cap and liquid level |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101858734A (en) | 2010-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101858734B (en) | Method for detecting PET bottleneck quality | |
| CN201689062U (en) | PET bottle mouth quality detection device | |
| CN102539443B (en) | Bottle body defect automatic detection method based on machine vision | |
| US11213860B2 (en) | Automatic magnetic core sorting system based on machine vision | |
| CN103604808B (en) | A kind of bottle cap defective vision detection method | |
| US10352871B2 (en) | High-speed, 3-D method and system for optically inspecting parts | |
| CN103170459B (en) | Spectacle lens flaw detection system | |
| US7414716B2 (en) | Machine for inspecting glass containers | |
| US6525333B1 (en) | System and method for inspecting containers with openings with pipeline image processing | |
| US7626158B2 (en) | Machine for inspecting glass containers | |
| CN102621156B (en) | Image-processing-based automatic micro part sorting system | |
| CN100547394C (en) | Fruit quality detection system based on image information fusion technology | |
| CN102305793A (en) | Method and equipment for detecting appearance quality of product | |
| CN105865570A (en) | Machine vision-based glass bottle liquid level detection method | |
| JPH10505680A (en) | Container flange inspection system using an annular lens | |
| CN103736672A (en) | Lens online classifying and sorting device | |
| US20080116358A1 (en) | Machine for inspecting glass containers | |
| CN104655643A (en) | Quality detection system for surface welding process of electronic devices | |
| CN103706575A (en) | Device and method for grading and sorting lenses on line based on two-stage image acquisition | |
| CN110208269A (en) | The method and system that a kind of glass surface foreign matter and internal foreign matter are distinguished | |
| CN107664644A (en) | A kind of apparent automatic detection device of object based on machine vision and method | |
| CN110567968A (en) | part defect detection method and device | |
| CN106556607A (en) | The device and method of identification panel surface dust | |
| CN205879814U (en) | Column container inner wall defect stravismus automatic checkout device | |
| US7541572B2 (en) | Machine for inspecting rotating glass containers with light source triggered multiple times during camera exposure time |
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 |