CN105865570A - Machine vision-based glass bottle liquid level detection method - Google Patents
Machine vision-based glass bottle liquid level detection method Download PDFInfo
- Publication number
- CN105865570A CN105865570A CN201610439907.7A CN201610439907A CN105865570A CN 105865570 A CN105865570 A CN 105865570A CN 201610439907 A CN201610439907 A CN 201610439907A CN 105865570 A CN105865570 A CN 105865570A
- Authority
- CN
- China
- Prior art keywords
- liquid level
- image
- bottle cap
- region
- vial
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)
- Filling Of Jars Or Cans And Processes For Cleaning And Sealing Jars (AREA)
Abstract
The invention relates to a machine vision-based glass bottle liquid level detection method which comprises the following steps: placing a certain qualified glass bottle at a station to be detected, and collecting a template for subsequent matching treatment; after the glass bottle to be detected arrives at a shooting station through a conveying belt, shooting a liquid level image of the glass bottle; binarizing the preprocessed image; matching a bottle cover through a geometric matching method to detect the position of the bottle cover; establishing a coordinate system; setting a region of interest (ROI) of a liquid level-qualified region; matching a liquid level line through the geometric matching method. An algorithm used in the machine vision-based glass bottle liquid level detection method is simple, and the number of steps is small; quick detection based on the image is realized, and the detection efficiency is high; the influence caused by the environment is less, and the accuracy is high.
Description
Technical field
The present invention relates to a kind of vial liquid-level detecting method, belong to field of machine vision.
Background technology
In the industrial production line such as beverage, medicated beer, the method for artificial range estimation is mostly used to check that bottle is the most qualified.
During particularly fill produces, the liquid level of bottled drink is the most consistent, the most uniform, to enterprise's shadow in market
Sound is the hugest.But manual detection has that many defects such as speed is slow, efficiency is low, detection quality is unstable,
Often there will be missing inspection or flase drop, cause unstable product quality, once defect ware is produced, and can cause wave
Take.The defect existed for above-mentioned manual detection, carries out bottle cap based on machine vision detection research, sets up a set of light and study
Picture, image acquisition and numeral image process and analysis are the detecting system of platform, not only have theoretical foundation, and have the biggest
Economic worth, it can be ensured that reduce in maximum magnitude and stop above-mentioned phenomenon and occur, improve product quality.
Machine Vision Detection has been applied at a lot of detection fields, also has and much apply precedent in terms of Level Detection,
But it is the actual height value being obtained liquid level by various means mostly, such as patent " a kind of liquid level after beverage filling inspection
Survey device and method " (patent No.: CN101858768A), this method often algorithm is complicated, the longest, and measures liquid level
There is bigger error.In industrial production line, per second at least to detect more than 5 bottles, if defective will make mark or
Reject.The real-time of detecting system and software processes is all had higher requirements by this.Therefore, the present invention proposes a kind of to regard based on machine
The vial Level Detection felt, just can reach the purpose of Level Detection by simple geometric match.
Summary of the invention
The technical problem to be solved is the office of weak point and the Level Detection overcoming manual detection to exist
Sex-limited, it is provided that a kind of simple efficient glass glass bottle liquid-level detecting method based on machine vision.
Technical scheme is as follows:
A kind of vial liquid-level detecting method based on machine vision, comprises the following steps:
1) certain grade glass bottle is placed on station to be measured, illuminates vial liquid level position to be measured with LED white backlight plate,
Collected by camera bottle cap liquid level information, regulation camera and light source, make the vial liquid level of collection separate with beverage below, obtain one
Bar liquid level line clearly, in order to follow-up matching treatment;
2) vial to be measured arrives shooting station by conveyer belt, and photoelectric sensor receives signal triggering camera shooting and treats it
Liquid level image, carries out medium filtering pretreatment to image, to remove noise jamming and to strengthen detection target information;
3) pretreated image is carried out two-value process, adjust suitable threshold value according to actual environment, after making binaryzation
Image effectively by liquid level and background separately;
4) use geometric match method coupling bottle cap, intercept the bottle cap side view of vial image to be measured, set bottle cap several
What central point is coupling basic point, and the edge of extraction bottle cap, as the template of geometric match, detects bottle cap by geometric match
Position;
5) coordinate system is set up according to the coupling basic point of step 4 as initial point;
6) coordinate origin set up with step 5 is as a reference point, according to the qualified region of liquid level relative in bottle cap geometry
The principle that heart point position does not changes, sets the region of interest ROI in the qualified region of liquid level;
7) reuse geometric match method matching fluid bit line, intercept a section of liquid level line, extract its edge as geometry
The template of coupling, carries out rim detection, if there is liquid level in the region of interest ROI by the qualified region of geometric match liquid level
Then the match is successful, it is determined that for qualified products, if not having liquid level in qualified region, is then judged to defective.
The invention has the beneficial effects as follows:
First, algorithm used by the method is simple, and step is few, it is achieved that the quick detection of image, detection efficiency is high;Secondly,
The method is affected by environment less, and accuracy rate is high;Using photoelectricity to trigger to take pictures, real-time is good;This detection method is novel, is suitable for model
Enclose wide, the most applicable for the detection of industrial glass bottled product;The method can be attached on existing production line, realizes production limit, limit
The on-line checking of detection.The present invention is vial Level Detection work after fill be applicable to automated production.
Accompanying drawing explanation
Fig. 1 is for the vial liquid-level detecting method device schematic diagram based on machine vision of the present invention.
Fig. 2 present invention based on machine vision to vial liquid-level detecting method flow chart.
The liquid level image that the original level image to be measured of Fig. 3 (a) and (b) the respectively present invention and step 1 collect.
Qualified liquid level that Fig. 4 (a) (b) (c) respectively the invention detects that, sentence beyond qualified liquid level with less than qualified liquid level
Determine result figure.
Detailed description of the invention
The present invention will be further described with instantiation below in conjunction with the accompanying drawings.
See Fig. 1, the system and device of a kind of vial liquid level defective work labelling based on machine vision, functionally divide
6 modules, i.e. conveyer belt 1, image capture module 2, optical trigger 3, lighting module 4, image procossing and identification 5 and output control
Device 6 processed.Above-mentioned image capture module 2 uses 1,200,000 pixel CCD camera, and lighting module 4 uses LED-backlit plate, image procossing
Industrial computer is used with identification module 5.The nozzle that output-controlling device is controlled by electromagnetic valve forms.Conveyer belt 1 is by defeated for bottle to be measured
Delivering to station of taking pictures, described photoelectric trigger device 3 is used for detecting whether bottle arrives picture-taking position, in order to produce pulse signal defeated
Delivering to industrial computer 5, industrial computer sends signal triggering camera 2 and takes pictures;There is provided illumination with raising figure when LED-backlit plate is taken pictures for camera
Picture element amount, CCD camera is positioned at directly over conveyer belt 1, takes pictures the vial liquid level part before backlight, and the image of shooting is defeated
Deliver to industrial computer processes.
See Fig. 2, the present invention based on the machine vision flow chart to vial fill liquid-level detecting method.Step is such as
Under:
(1) any correct bottle is placed on station to be measured, illuminates vial liquid level position to be measured with LED white backlight plate
Put, gather bottle cap liquid level information, regulation camera and light source with high resolution camera, make the vial liquid level of collection and drink below
Material separates, and obtains a liquid level line clearly.
(2) starting conveyer belt, bottle to be measured arrives camera site with conveyer belt, triggers camera and obtains bottle cap image to be measured,
Through channel transfer to industrial computer image processing system.
(3) image being carried out medium filtering pretreatment, after process, image liquid level information is obviously enhanced.Image after process enters
Row binary conversion treatment, adjusts suitable threshold value according to grey level histogram, increases image recognition rate, makes the image after binaryzation effective
Liquid level and background are separated by ground.
(4) use the position of geometric match method coupling bottle cap, intercept the bottle cap side view of vial image to be measured, extract
The edge of bottle cap, as the template of geometric match, sets bottle cap geometric center point as coupling basic point.Set coupling number as 1, coupling
Angular range be-10+10, matching algorithm is rim detection, and smallest match score is 500, complete matching score 1000.With
Coupling basic point is that initial point sets up coordinate system
(5) as a reference point with initial point, set one long by 360, the rectangular area of wide 250 is set to as the qualified region of liquid level
Region of interest ROI (Region Of Interest).
(6) reuse geometric match method matching fluid bit line, intercept the part of one section of relatively standard of liquid level line, extract it
Edge is as the template of geometric match, and the same coupling number that sets is as 1, and the angular range of coupling is-10+10, and matching algorithm is
Rim detection.If by there is liquid level in the qualified region of geometric match, the match is successful, it is determined that for qualified products, if qualified
There is no liquid level in region, be then judged to defective.
Shown in Fig. 3, left image is that camera shoots original image, and right figure is to adjust collection after camera exposure rate and light source
It is simpler that image, the so image after regulation make subsequent treatment judge.
Seeing Fig. 4, upper figure is the judged result of qualified liquid level, can be seen that and set for reference point with bottle cap geometric center in figure
In fixed qualified detection region, match liquid level line.Middle figure is liquid level testing result when being higher than qualified region, and figure below is
Liquid level is less than the testing result in qualified region, it can be seen that all can be judged as defective product when fill liquid level is too high or too low
Product.
Claims (1)
1. a vial liquid-level detecting method based on machine vision, comprises the following steps:
1) certain grade glass bottle is placed on station to be measured, illuminates vial liquid level position to be measured, camera with LED white backlight plate
Gather bottle cap liquid level information, regulation camera and light source, make the vial liquid level of collection separate with beverage below, obtain one clearly
Clear liquid level line, in order to follow-up matching treatment;
2) vial to be measured arrives shooting station by conveyer belt, and photoelectric sensor receives signal triggering camera shooting and treats its liquid level
Image, carries out medium filtering pretreatment to image, to remove noise jamming and to strengthen detection target information;
3) pretreated image is carried out two-value process, adjust suitable threshold value according to actual environment, make the figure after binaryzation
As effectively liquid level and background being separated;
4) use geometric match method coupling bottle cap, intercept the bottle cap side view of vial image to be measured, set in bottle cap geometry
Heart point is coupling basic point, and the edge of extraction bottle cap, as the template of geometric match, detects the position of bottle cap by geometric match;
5) coordinate system is set up according to the coupling basic point of step 4 as initial point;
6) coordinate origin set up with step 5 is as a reference point, according to the qualified region of liquid level relative to bottle cap geometric center point
The principle that position does not changes, sets the region of interest ROI in the qualified region of liquid level;
7) reuse geometric match method matching fluid bit line, intercept a section of liquid level line, extract its edge as geometric match
Template, carry out rim detection, if there is liquid level in the region of interest ROI by the qualified region of geometric match liquid level,
It is made into merit, it is determined that for qualified products, if there is no liquid level in qualified region, be then judged to defective.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610439907.7A CN105865570A (en) | 2016-06-15 | 2016-06-15 | Machine vision-based glass bottle liquid level detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610439907.7A CN105865570A (en) | 2016-06-15 | 2016-06-15 | Machine vision-based glass bottle liquid level detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105865570A true CN105865570A (en) | 2016-08-17 |
Family
ID=56650900
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610439907.7A Pending CN105865570A (en) | 2016-06-15 | 2016-06-15 | Machine vision-based glass bottle liquid level detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105865570A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106441493A (en) * | 2016-09-28 | 2017-02-22 | 山西彤康食品有限公司 | Device and method for online detecting liquid level of transparent bottle |
CN107045633A (en) * | 2016-12-26 | 2017-08-15 | 上海大学 | A kind of digital locating segmentation method of the energy measurement table tool based on ST MSER |
CN107044981A (en) * | 2016-12-20 | 2017-08-15 | 浙江工业大学 | A kind of detection method of the PE bottle filling rates based on machine vision |
CN108154500A (en) * | 2017-12-18 | 2018-06-12 | 天津普达软件技术有限公司 | A kind of method for detecting bottle cap deformation |
CN108160520A (en) * | 2017-12-18 | 2018-06-15 | 天津普达软件技术有限公司 | A kind of method that bottle cap deformation defective products is rejected |
CN108171684A (en) * | 2017-12-18 | 2018-06-15 | 天津普达软件技术有限公司 | A kind of method for detecting bottle cap abscission ring |
CN108171685A (en) * | 2017-12-18 | 2018-06-15 | 天津普达软件技术有限公司 | A kind of method that bottle cap abscission ring defective products is rejected |
CN108580333A (en) * | 2018-04-17 | 2018-09-28 | 湖北理工学院 | Level sensing study of platform based on machine vision and design |
CN108844594A (en) * | 2018-04-17 | 2018-11-20 | 广州博通信息技术有限公司 | The alarm method and system of compressor of air conditioner liquid level identification |
CN110013574A (en) * | 2019-05-10 | 2019-07-16 | 上海市东方医院(同济大学附属东方医院) | Drainage liquid amount real-time monitoring method |
CN111531544A (en) * | 2020-05-13 | 2020-08-14 | 深圳赛动生物自动化有限公司 | Robot control system based on image geometric matching and control method thereof |
CN112509039A (en) * | 2020-12-16 | 2021-03-16 | 广州大学 | Bottled liquid level detection method and system and storage medium |
CN113188633A (en) * | 2021-04-27 | 2021-07-30 | 睿科集团(厦门)股份有限公司 | Liquid level detection and measurement method based on machine vision |
CN113516702A (en) * | 2021-07-16 | 2021-10-19 | 中国科学院自动化研究所 | Method and system for detecting liquid level of automatic liquid preparation ampoule bottle and method for detecting proportion of liquid medicine |
CN116721103A (en) * | 2023-08-10 | 2023-09-08 | 山东明佳科技有限公司 | Image detection method, system, equipment and storage medium for purity of inner bottom of milk glass bottle |
CN117474902A (en) * | 2023-12-25 | 2024-01-30 | 山东明佳科技有限公司 | Method, system, equipment and storage medium for detecting missing of barrel fabric package |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101929913A (en) * | 2010-05-14 | 2010-12-29 | 山东大学 | Device and method for detecting airtightness of bottle cap based on sound signal processing |
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 |
CN204789384U (en) * | 2015-07-16 | 2015-11-18 | 南京汇川工业视觉技术开发有限公司 | Bottled product extranal packing bottle lid defect detecting system |
CN105301003A (en) * | 2015-11-05 | 2016-02-03 | 天津大学 | Method for detecting bottle cap surface production date based on machine vision |
EP3018483A1 (en) * | 2014-11-07 | 2016-05-11 | photrack AG | Method and system for determining the velocity and level of a moving fluid surface |
-
2016
- 2016-06-15 CN CN201610439907.7A patent/CN105865570A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101929913A (en) * | 2010-05-14 | 2010-12-29 | 山东大学 | Device and method for detecting airtightness of bottle cap based on sound signal processing |
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 |
EP3018483A1 (en) * | 2014-11-07 | 2016-05-11 | photrack AG | Method and system for determining the velocity and level of a moving fluid surface |
CN204789384U (en) * | 2015-07-16 | 2015-11-18 | 南京汇川工业视觉技术开发有限公司 | Bottled product extranal packing bottle lid defect detecting system |
CN105301003A (en) * | 2015-11-05 | 2016-02-03 | 天津大学 | Method for detecting bottle cap surface production date based on machine vision |
Non-Patent Citations (1)
Title |
---|
王梁: "基于机器视觉的啤酒灌装质量检测系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106441493A (en) * | 2016-09-28 | 2017-02-22 | 山西彤康食品有限公司 | Device and method for online detecting liquid level of transparent bottle |
CN107044981A (en) * | 2016-12-20 | 2017-08-15 | 浙江工业大学 | A kind of detection method of the PE bottle filling rates based on machine vision |
CN107045633A (en) * | 2016-12-26 | 2017-08-15 | 上海大学 | A kind of digital locating segmentation method of the energy measurement table tool based on ST MSER |
CN108154500A (en) * | 2017-12-18 | 2018-06-12 | 天津普达软件技术有限公司 | A kind of method for detecting bottle cap deformation |
CN108160520A (en) * | 2017-12-18 | 2018-06-15 | 天津普达软件技术有限公司 | A kind of method that bottle cap deformation defective products is rejected |
CN108171684A (en) * | 2017-12-18 | 2018-06-15 | 天津普达软件技术有限公司 | A kind of method for detecting bottle cap abscission ring |
CN108171685A (en) * | 2017-12-18 | 2018-06-15 | 天津普达软件技术有限公司 | A kind of method that bottle cap abscission ring defective products is rejected |
CN108844594A (en) * | 2018-04-17 | 2018-11-20 | 广州博通信息技术有限公司 | The alarm method and system of compressor of air conditioner liquid level identification |
CN108580333A (en) * | 2018-04-17 | 2018-09-28 | 湖北理工学院 | Level sensing study of platform based on machine vision and design |
CN108844594B (en) * | 2018-04-17 | 2021-03-12 | 广州博通信息技术有限公司 | Alarm method and system for liquid level identification of air conditioner compressor |
CN110013574A (en) * | 2019-05-10 | 2019-07-16 | 上海市东方医院(同济大学附属东方医院) | Drainage liquid amount real-time monitoring method |
CN111531544A (en) * | 2020-05-13 | 2020-08-14 | 深圳赛动生物自动化有限公司 | Robot control system based on image geometric matching and control method thereof |
CN112509039A (en) * | 2020-12-16 | 2021-03-16 | 广州大学 | Bottled liquid level detection method and system and storage medium |
CN113188633A (en) * | 2021-04-27 | 2021-07-30 | 睿科集团(厦门)股份有限公司 | Liquid level detection and measurement method based on machine vision |
CN113516702A (en) * | 2021-07-16 | 2021-10-19 | 中国科学院自动化研究所 | Method and system for detecting liquid level of automatic liquid preparation ampoule bottle and method for detecting proportion of liquid medicine |
CN116721103A (en) * | 2023-08-10 | 2023-09-08 | 山东明佳科技有限公司 | Image detection method, system, equipment and storage medium for purity of inner bottom of milk glass bottle |
CN116721103B (en) * | 2023-08-10 | 2023-10-27 | 山东明佳科技有限公司 | Image detection method, system, equipment and storage medium for purity of inner bottom of milk glass bottle |
CN117474902A (en) * | 2023-12-25 | 2024-01-30 | 山东明佳科技有限公司 | Method, system, equipment and storage medium for detecting missing of barrel fabric package |
CN117474902B (en) * | 2023-12-25 | 2024-03-12 | 山东明佳科技有限公司 | Method, system, equipment and storage medium for detecting missing of barrel fabric package |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105865570A (en) | Machine vision-based glass bottle liquid level detection method | |
CN106052793A (en) | Machine vision based liquid level sub-quality product marking method | |
CN101566582B (en) | Medicine bottle label information online detection system in powder injection production based on mechanical vision | |
CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
CN101858734B (en) | Method for detecting PET bottleneck quality | |
CN106824816B (en) | A kind of detection of PE bottle and method for sorting based on machine vision | |
WO2019032101A1 (en) | Image processing techniques for plunger depth measurement | |
CN108344743A (en) | One kind being based on machine vision drug blister package defect inspection method and system | |
CN101907453B (en) | Online measurement method and device of dimensions of massive agricultural products based on machine vision | |
CN108896574B (en) | Bottled liquor impurity detection method and system based on machine vision | |
CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
CN203750868U (en) | Computer vision-based burr detection device | |
CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
CN105181714A (en) | Image processing-based bottled liquid impurity detection system and detection method thereof | |
US9881367B1 (en) | Image processing techniques for plunger depth measurement | |
CN108120353B (en) | Fire transmission hole detection device and method based on intelligent camera | |
CN109461156B (en) | Threaded sealing plug assembly detection method based on vision | |
CN101565109A (en) | Aluminum cap packaging online detection system in medical powder injection production based on mechanical vision | |
CN107084992A (en) | A kind of capsule detection method and system based on machine vision | |
CN105301003A (en) | Method for detecting bottle cap surface production date based on machine vision | |
CN105023018A (en) | Jet code detection method and system | |
CN106875441A (en) | A kind of online PE bottles of recognition positioning method based on machine vision | |
CN201689062U (en) | PET bottle mouth quality detection device | |
CN111060518A (en) | Stamping part defect identification method based on instance segmentation | |
CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160817 |