CN106841229A - A kind of online PE bottles of detection method of bottle sealing defect based on machine vision - Google Patents

A kind of online PE bottles of detection method of bottle sealing defect based on machine vision Download PDF

Info

Publication number
CN106841229A
CN106841229A CN201611192004.XA CN201611192004A CN106841229A CN 106841229 A CN106841229 A CN 106841229A CN 201611192004 A CN201611192004 A CN 201611192004A CN 106841229 A CN106841229 A CN 106841229A
Authority
CN
China
Prior art keywords
bottles
bottle sealing
machine vision
online
value
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
Application number
CN201611192004.XA
Other languages
Chinese (zh)
Inventor
陈建
胡俊康
王建勇
赵晓
李鑫
陈琨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang University of Technology ZJUT
Original Assignee
Zhejiang University of Technology ZJUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang University of Technology ZJUT filed Critical Zhejiang University of Technology ZJUT
Priority to CN201611192004.XA priority Critical patent/CN106841229A/en
Publication of CN106841229A publication Critical patent/CN106841229A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • 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
    • G06T7/0008—Industrial image inspection checking presence/absence
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection

Abstract

A kind of online PE bottles of detection method of bottle sealing defect based on machine vision, detects on Machine Vision Detection platform to PE bottles of seal defect, including step：(1) collect PE bottleneck images, be converted to gray-scale map；(2) gray-scale map pre-process and obtain Threshold segmentation figure；(3) inside and outside contour for obtaining bottle sealing tinfoil is detected by rim detection；(4) filling inside and outside contour forms annulus, and annulus is divided into uniform decile, calculates and compares with given threshold value scope per Equal round pixel value, judges that defect whether there is.The method accurately can judge bottle sealing defect soon on the conveyer belt of high-speed motion, it is adaptable to PE bottles of detection sorting on automatic assembly line.Precision of the present invention is higher, reliability good, operating efficiency is higher.

Description

A kind of online PE bottles of detection method of bottle sealing defect based on machine vision
Technical field
The invention belongs to technical field of image processing, more particularly to a kind of online PE bottles of bottle sealing based on machine vision The detection method of defect.
Background technology
Traditional filling bottle quality testing is that, by artificial candler, employee is checked on streamline using naked eyes.But It is this mode from efficiency to precision and artificial vision's fatigue everyway does not reach examination criteria, is especially producing in enormous quantities In the case of detection, the situation omitted and judge by accident is often led to, cause the underproof bottled drink in part to come into the market, influence enterprise Industry image.Therefore after filling finishing, it is desirable to provide a kind of method ensures PE bottles of reliability and rapidity of detection, based on machine PE bottles of detection technique of vision overcomes the shortcomings of manual detection, meets the high-speed, high precision detection in industrial automation production, and The online PE bottles of bottle sealing defects detection based on machine vision is an essential process.
The content of the invention
In order to overcome, the precision of existing PE bottles of detection technique manual detection is relatively low, reliability is poor, operating efficiency is relatively low Deficiency, the present invention provides the online PE bottles of bottle based on machine vision that a kind of precision is higher, reliability is good, operating efficiency is higher The detection method of mouth seal defect.
The technical solution adopted for the present invention to solve the technical problems is：
A kind of online PE bottles of detection method of bottle sealing defect based on machine vision, the detection method step is such as Under：
(1) PE bottleneck images are gathered, gray-scale map is converted to；
(2) gray-scale map pre-process and obtain Threshold segmentation figure；
(3) inside and outside contour for obtaining bottle sealing tinfoil is detected by rim detection；
(4) annulus is divided into uniform equal portions, calculates and justify pixel value per equal portions, and be compared with given threshold value scope, Judge that defect whether there is.
Further, in the step (1), selection and laying, the IMAQ of camera, and the gray scale of lighting source become Change, process is as follows：Select red polarization ring light source and isight7200 the cameras shooting above bottleneck；Using encoder Record conveyer belt displacement, sends outer triggering signal control camera and takes pictures, and the PE bottleneck images that will be collected are exported to treatment Device completes the grey scale change of image.
Further, in the step (2), using iteration best threshold method to carrying out image threshold segmentation, first according to image Minimum and maximum gray value calculates an initial threshold T1, image is divided into two regions using this threshold value, then distinguish Obtain two average gray value H in region1And H2, calculate new threshold value T2, until H1And H2Value no longer change, otherwise Continue iteration：
Further, in the step (3), binary map inside and outside contour is detected using canny operators, and be filled with annulus Type；
In the step (4), judged that process is as follows using region area feature：If one do not have it is defective Bottleneck image, is averaged from the center of circle and is divided into N parts, then this every part pixel value should be approximately equalised；But when this Existing defects part in certain equal portions, then obvious error will occurs in contrast to the pixel value without defect area；When this Error can just be judged to defective more than the threshold value of setting.
In the step (4), step is as follows：
4.1) link is positioned by target, determines home position；
4.2) from the center of circle, whole region area is divided with N bars straight uniform, the value of N=360/ ɑ, ɑ according to Precision may be selected different angles；
4.3) after decile is completed, the pixel value for starting the sector region that statistics is split by each bar straight uniform angle is total With, then an error range value is set, when the pixel summation for having sector region is outside this, judge the region existing defects.
Beneficial effects of the present invention are mainly manifested in：Precision is higher, reliability is good, operating efficiency is higher.
Brief description of the drawings
Fig. 1 is the online PE bottle flow chart of the detection method of bottle sealing defect of the present invention based on machine vision.
Fig. 2 is the camera light source installation position figure of the online PE bottles of detection of bottle sealing defect based on machine vision, its In, 1 is testee, and 2 is light source, and 3 is camera lens, and 4 is CCD camera.
Fig. 3 is PE bottles of bottleneck gray-scale map, wherein, (a) is that do not have defective bottleneck, and (b) is a kind of defective bottleneck, (c) be it is another in defective bottleneck.
Fig. 4 is the PE bottles of iteration best threshold method flow chart of bottle sealing defect.
Fig. 5 is PE bottles of bottleneck etc. point circule method design sketch, wherein, (a) is that do not have defective bottleneck, and (b) is a kind of defective Bottleneck, (c) be it is another in defective bottleneck.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.
1~Fig. 5 of reference picture, a kind of online PE bottles of detection method of bottle sealing defect based on machine vision, step is such as Under：
(1) selection of lighting source and laying, the IMAQ of camera, and greyscale transformation, present invention selection red Polarization ring light source and isight7200 cameras shoot as shown in Figure 2 perpendicular to bottleneck top；Using encoder record conveyer belt position Move, send outer triggering signal control camera and take pictures, and the PE bottleneck images that will be collected are exported and complete image to processor Grey scale change.
(2) Threshold segmentation figure is obtained as Fig. 3 to gray-scale map pre-process, herein using iteration best threshold method to image Threshold segmentation, calculates an initial threshold T according to the minimum and maximum gray value of image first1, using this threshold value by image It is divided into two regions, two average gray value H in region is then obtained respectively1And H2, calculate new threshold value T2, until H1And H2 Value no longer change, otherwise continue iteration, flow chart is as shown in Figure 4：
(3) inside and outside contour for obtaining bottle sealing tinfoil is detected by rim detection, using canny operators in binary map Outline is detected, and is filled with annulus, as shown in Figure 5；
(4) annulus is divided into uniform equal portions, calculates circle pixel value and given threshold value scope, multilevel iudge defect per equal portions Whether there is.
The method judged using region area feature.If one does not have defective bottleneck image, go out from the center of circle Hair is averaged and is divided into N parts, then this every part pixel value should be approximately equalised.But when existing defects portion in this certain equal portions Point, then obvious error will occurs in contrast to the pixel value without defect area.When this error exceedes the threshold value of setting Can just be judged to it is defective, using etc. point circule method step it is as follows：
4.1) link is positioned by target, it is determined that home position；
4.2) from the center of circle, whole region area is divided with N bars straight uniform, the value of N=360/ ɑ, ɑ according to Precision may be selected different angles, it is desirable to which precision is higher, and the value of ɑ is smaller；
4.3) after decile is completed, the pixel value for starting the sector region that statistics is split by each bar straight uniform angle is total With, then set an error range value, when the pixel summation for having sector region is outside this, it is possible to judge, the region is deposited In defect.
Sentence experiment for the defect of decile circule method, binary map can be divided into centered on the center of circle respectively 4 equal portions, 6 equal portions, 8 equal portions, the pixel value in computation partition region, is about 16256, it is known that 4 equal portions according to standard picture circle ring area pixel value respectively The pixel value of qualified PE bottles of image respectively may be about 4064 further according to the data that obtain of experiment with qualified PE bottles of comparing, if In the range of allowable error, it is believed that the region zero defect, such as table have recorded 5 groups PE bottles in the case of 4 equal portions of decile circule method number According to value, table 1 is decile circule method testing result.
Table 1
Value of the decile circule method each PE bottles of image zoning can be seen that when area pixel value reaches with 4064 gaps During certain error, it is believed that the corresponding PE bottlenecks of the image are existing defects, and the method is time-consuming shorter.In sum, originally Invention is according to PE bottles of bottle mouth defect feature, and analysis obtains a kind of fast and accurately detection method, and flat in the detection of actual conveyer belt Platform is verified, can completed to quick PE bottles of mobile bottle sealing defects detection, and algorithm robustness is strong.

Claims (6)

1. a kind of online PE bottles of detection method of bottle sealing defect based on machine vision, it is characterised in that：The detection side Method step is as follows：
(1) PE bottleneck images are gathered, gray-scale map is converted to；
(2) gray-scale map pre-process and obtain Threshold segmentation figure；
(3) inside and outside contour for obtaining bottle sealing tinfoil is detected by rim detection；
(4) annulus is divided into uniform equal portions, calculates and justify pixel value per equal portions, and be compared with given threshold value scope, judged Defect whether there is.
2. the online PE bottles of detection method of bottle sealing defect of machine vision is based on as claimed in claim 1, and its feature exists In：In the step (1), selection and laying, the IMAQ of camera, and the greyscale transformation of lighting source, process are as follows：Choosing The polarization ring light source and isight7200 cameras for selecting red shoot perpendicular to bottleneck top；Using encoder record conveyer belt position Move, send outer triggering signal control camera and take pictures, and the PE bottleneck images that will be collected are exported and complete image to processor Grey scale change.
3. the online PE bottles of detection method of bottle sealing defect of machine vision, its feature are based on as claimed in claim 1 or 2 It is：In the step (2), using iteration best threshold method to carrying out image threshold segmentation, first according to the minimum and maximum ash of image Angle value calculates an initial threshold T1, image is divided into two regions using this threshold value, two regions are then obtained respectively Average gray value H1And H2, calculate new threshold value T2, until H1And H2Value no longer change, otherwise continue iteration.
4. the online PE bottles of detection method of bottle sealing defect of machine vision is based on as claimed in claim 1 or 2, and its feature exists In：In the step (3), binary map inside and outside contour is detected using canny operators, and be filled with circular ring type.
5. the online PE bottles of detection method of bottle sealing defect based on machine vision as shown in claim 1 or 2, its feature It is：In the step (4), judged that process is as follows using region area feature：If one does not have defective bottleneck Image, is averaged from the center of circle and is divided into N parts, then this every part pixel value should be approximately equalised；But certain etc. when this Existing defects part in part, then obvious error will occurs in contrast to the pixel value without defect area；When this error Can be just judged to more than the threshold value of setting defective.
6. the online PE bottles of detection method of bottle sealing defect based on machine vision as stated in claim 5, its feature exists In：In the step (4), step is as follows：
4.1) link is positioned by target, determines home position；
4.2) from the center of circle, whole region area is divided with N bars straight uniform, the value of N=360/ ɑ, ɑ is according to precision Different angles may be selected；
4.3) after decile is completed, the pixel value summation of the sector region that statistics is split by each bar straight uniform angle is started, so One error range value is set afterwards, when the pixel summation for having sector region is outside this, the region existing defects is judged.
CN201611192004.XA 2016-12-20 2016-12-20 A kind of online PE bottles of detection method of bottle sealing defect based on machine vision Pending CN106841229A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611192004.XA CN106841229A (en) 2016-12-20 2016-12-20 A kind of online PE bottles of detection method of bottle sealing defect based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611192004.XA CN106841229A (en) 2016-12-20 2016-12-20 A kind of online PE bottles of detection method of bottle sealing defect based on machine vision

Publications (1)

Publication Number Publication Date
CN106841229A true CN106841229A (en) 2017-06-13

Family

ID=59135127

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611192004.XA Pending CN106841229A (en) 2016-12-20 2016-12-20 A kind of online PE bottles of detection method of bottle sealing defect based on machine vision

Country Status (1)

Country Link
CN (1) CN106841229A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108898594A (en) * 2018-06-27 2018-11-27 湖北工业大学 A kind of detection method of homogeneous panel defect
CN111182173A (en) * 2019-11-27 2020-05-19 绍兴柯桥浙工大创新研究院发展有限公司 Image transmission processing method and system
CN111652842A (en) * 2020-04-26 2020-09-11 佛山读图科技有限公司 Real-time visual detection method and system for high-speed penicillin bottle capping production line
CN112991284A (en) * 2021-03-05 2021-06-18 佛山科学技术学院 Temperature controller guide frame defect detection method and system
CN116977310A (en) * 2023-08-01 2023-10-31 山东明佳科技有限公司 Image detection method, system, equipment and storage medium for bottle mouth gap of milk glass bottle

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5126556A (en) * 1989-12-04 1992-06-30 Coors Brewing Company Bottle thread imaging apparatus having a light seal means between the light assembly means and the thread
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
US20090066944A1 (en) * 2006-05-10 2009-03-12 Saverglass Sas Device and method for detecting a defect in a finnish ring of a glass
CN102519973A (en) * 2011-12-10 2012-06-27 山东明佳包装检测科技有限公司 Method for detecting lip defect of PET bottle or bottle parison
CN104406986A (en) * 2014-12-12 2015-03-11 天津普达软件技术有限公司 Medicine bottle machine vision detecting system
CN104502359A (en) * 2014-12-10 2015-04-08 天津普达软件技术有限公司 Method for accurately detecting bottle blank and bottle opening defects
CN105954301A (en) * 2016-06-22 2016-09-21 广东省自动化研究所 Bottleneck quality detection method based on machine vision

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5126556A (en) * 1989-12-04 1992-06-30 Coors Brewing Company Bottle thread imaging apparatus having a light seal means between the light assembly means and the thread
US20090066944A1 (en) * 2006-05-10 2009-03-12 Saverglass Sas Device and method for detecting a defect in a finnish ring of a glass
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
CN102519973A (en) * 2011-12-10 2012-06-27 山东明佳包装检测科技有限公司 Method for detecting lip defect of PET bottle or bottle parison
CN104502359A (en) * 2014-12-10 2015-04-08 天津普达软件技术有限公司 Method for accurately detecting bottle blank and bottle opening defects
CN104406986A (en) * 2014-12-12 2015-03-11 天津普达软件技术有限公司 Medicine bottle machine vision detecting system
CN105954301A (en) * 2016-06-22 2016-09-21 广东省自动化研究所 Bottleneck quality detection method based on machine vision

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张田田: "基于机器视觉的啤酒瓶瓶口检测系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
章祎: "药用管制瓶图像检测系统的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108898594A (en) * 2018-06-27 2018-11-27 湖北工业大学 A kind of detection method of homogeneous panel defect
CN111182173A (en) * 2019-11-27 2020-05-19 绍兴柯桥浙工大创新研究院发展有限公司 Image transmission processing method and system
CN111182173B (en) * 2019-11-27 2021-10-01 绍兴柯桥浙工大创新研究院发展有限公司 Image transmission processing method and system
CN111652842A (en) * 2020-04-26 2020-09-11 佛山读图科技有限公司 Real-time visual detection method and system for high-speed penicillin bottle capping production line
CN111652842B (en) * 2020-04-26 2021-05-11 佛山读图科技有限公司 Real-time visual detection method and system for high-speed penicillin bottle capping production line
CN112991284A (en) * 2021-03-05 2021-06-18 佛山科学技术学院 Temperature controller guide frame defect detection method and system
CN112991284B (en) * 2021-03-05 2022-11-01 佛山科学技术学院 Temperature controller guide frame defect detection method and system
CN116977310A (en) * 2023-08-01 2023-10-31 山东明佳科技有限公司 Image detection method, system, equipment and storage medium for bottle mouth gap of milk glass bottle
CN116977310B (en) * 2023-08-01 2024-01-26 山东明佳科技有限公司 Image detection method, system, equipment and storage medium for bottle mouth gap of milk glass bottle

Similar Documents

Publication Publication Date Title
CN106841229A (en) A kind of online PE bottles of detection method of bottle sealing defect based on machine vision
CN108765416B (en) PCB surface defect detection method and device based on rapid geometric alignment
CN106824816B (en) A kind of detection of PE bottle and method for sorting based on machine vision
KR101951576B1 (en) Inspection device and inspection method
CN109772733B (en) Defect bamboo block detecting and sorting device and method based on vision
US7570794B2 (en) System and method for evaluating a machined surface of a cast metal component
US20230196096A1 (en) Deep Learning Platforms for Automated Visual Inspection
CN110108711A (en) The vision detection system of annulus side wall defect
CN106501272B (en) Machine vision soldering tin positioning detection system
CN101315338A (en) Defect detecting system and method for glass product
CN104483320A (en) Digitized defect detection device and detection method of industrial denitration catalyst
CN107664644A (en) A kind of apparent automatic detection device of object based on machine vision and method
CN116993682B (en) Cornea shaping mirror flaw area extraction method based on image data analysis
CN109693140A (en) A kind of intelligent flexible production line and its working method
CN106052792A (en) Method and device for detecting liquid level of PET bottle based on machine vision
CN114359253A (en) Image pollution detection method and system based on convolutional neural network
CN109877437B (en) Centering detection device and method for resistance welding gun
KR100884582B1 (en) Semiconductor package inspection system and inspection method using semiconductor package inspection system
CN110412055A (en) A kind of lens white haze defect inspection method based on multiple light courcess dark-ground illumination
CN117214178A (en) Intelligent identification method for appearance defects of package on packaging production line
CN205620320U (en) Defect detecting device based on multitube foot
CN209606340U (en) Transparent medicine bottle bottom buildup defect detecting system
CN2858078Y (en) Multi-vision empty bottle checking robot
KR20130031331A (en) Glass bottle inspection device
CN213516933U (en) Piston defect detection device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for 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: 20170613