CN105973903A - System and method for detecting oral solution bottle caps - Google Patents
System and method for detecting oral solution bottle caps Download PDFInfo
- Publication number
- CN105973903A CN105973903A CN201610520557.7A CN201610520557A CN105973903A CN 105973903 A CN105973903 A CN 105973903A CN 201610520557 A CN201610520557 A CN 201610520557A CN 105973903 A CN105973903 A CN 105973903A
- Authority
- CN
- China
- Prior art keywords
- bottle
- image
- oral liquid
- camera
- detecting system
- 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.)
- Granted
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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature 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
- 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
Landscapes
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Textile Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a system for detecting oral solution bottle caps. The system is stable in detection result, high in accuracy and low in cost, is safe, radiation-free and noise-free, and is capable of effectively protecting bottle bodies and liquid stored in the bottles. The system comprises a bottle body separating device, an image collecting part, an image processing part and a communication module, wherein the bottle body separating device comprises a transmission belt; grooves are formed in the transmission belt at equal intervals; the transmission belt is used for forwardly transmitting each bottle body and rotating each bottle body at 360 degrees; the image collecting part comprises a strip-shaped light source, a camera and a collection module; the strip-shaped light source irradiates the oral solution bottle caps at a certain inclination angle; the reflected light forms obvious light-dark difference; images shot by the camera are transmitted to the collection module; the image processing part is used for preprocessing images, detecting targets and tracking the bottle caps; the communication module is used for connecting the camera with the collection module and connecting the collection module with the image processing part. The invention also provides a method adopting the system.
Description
Technical field
The invention belongs to produce the technical field of detection, more particularly to a kind of Oral liquid bottle lid detecting system,
And using the detection method of this system, it is mainly used in the defects detection of bottle cap of oral liquid.
Background technology
In traditional oral liquid produces, the defects detection of bottle cap is the important ring in producing.Existing
Detection means still relies primarily on manpower and is detected as main.But the technological means of manpower detection own is more original,
Production efficiency is relatively low, and cost is high, and the feature such as easily make mistakes strongly limit production-scale expansion.So
The technology being badly in need of Aulomatizeted Detect in industry realizes.
Summary of the invention
The technology of the present invention solves problem: overcome the deficiencies in the prior art, it is provided that a kind of Oral liquid bottle lid
Detecting system, its testing result is stable, and precision is high, low cost, and safety is radiationless, noiselessness, it is possible to
Effectively protect the liquid stored in bottle and bottle.
The technical solution of the present invention is: this Oral liquid bottle lid detecting system, and it includes that bottle separates
Device, image acquisition part, image processing section, communication module;
Described bottle segregation apparatus includes equidistant feed belt with groove, and its configuration is by each bottle
Body forwards and carries out 360 degree of rotations;
Described image acquisition part is divided and is included strip source, camera, acquisition module, and strip source is with necessarily
Angle of inclination be pointed into Oral liquid bottle lid, after light is reflected, form strong light and shade poor,
After camera shooting, image is sent to acquisition module;
Described image processing section, its configuration image carried out pretreatment, target detection and bottle cap with
Track;
Described communication module, its configuration connects camera and acquisition module, connects at acquisition module and image
Reason part.
Owing to the strip source of the present invention is pointed into Oral liquid bottle lid with certain angle of inclination, light is reflected
Afterwards, form strong light and shade poor, after camera shooting, image is sent to acquisition module, at described image
Reason part, its configuration carries out pretreatment, target detection and bottle cap and follows the tracks of, uses ripe machine image
Device vision technique means, result is reliable and stable, and precision is high;Completely without contact bottle, it is possible to effectively
The liquid stored in ground protection bottle and bottle;Have only to camera and a small amount of light source can realize, save a large amount of
Peripheral hardware cost;Entirely without radiation, noiselessness, staff be there is no any injury;Owing to inciting somebody to action
Focus is transferred in software development, and hardware resource is less, it is simple to the equipment dimension of the staff in later stage
Protect;Automated production efficiency is high.
Additionally provide the method using this Oral liquid bottle lid detecting system, comprise the following steps:
(1) by bottle segregation apparatus each bottle forwarded and carry out 360 degree of rotations;
(2) strip source is pointed into Oral liquid bottle lid with certain angle of inclination, after light is reflected, and shape
The light and shade becoming strong is poor, after camera shooting, image is sent to acquisition module;
(3) image carries out pretreatment, target detection and bottle cap follow the tracks of;
(4) defect bottle cap detected, and record result.
Accompanying drawing explanation
Fig. 1 is the overall structure schematic diagram of the Oral liquid bottle lid detecting system according to the present invention.
Fig. 2 is the structural representation of the rejecting part of the Oral liquid bottle lid detecting system according to the present invention.
Detailed description of the invention
Because Oral liquid bottle lid is made up of smooth plastic materials and smooth metal material, there is reflective function
Good, the characteristic such as light tight, for defective bottle cap, under the light source of certain angle irradiates, can compare
Significantly gray-value variation.Therefore, applicant expects, is shone with certain angle of inclination by strip source
To the bottle cap of oral liquid.After light is reflected, form strong light and shade poor.After collected by camera image,
Being transferred into computer, software can be according to the difference of gray value as analyzing foundation, it is achieved the inspection to defect
Survey and location.
It is probably the optional position of 360 degree owing to the presence bit of defect is equipped with, therefore during detection,
Will be to major general's bottle rotating 360 degrees, to realize omnibearing detection.
As it is shown in figure 1, this Oral liquid bottle lid detecting system, it includes that bottle segregation apparatus, image are adopted
Collection part, image processing section, communication module;
Described bottle segregation apparatus includes equidistant feed belt with groove, and its configuration is by each bottle
Body forwards and carries out 360 degree of rotations;
Described image acquisition part is divided and is included strip source, camera, acquisition module, and strip source is with necessarily
Angle of inclination be pointed into Oral liquid bottle lid, after light is reflected, form strong light and shade poor,
After camera shooting image is sent to acquisition module (in acquisition module, can be to the figure gathered
As frame per second and the resolution sizes of video data are adjusted, it is possible to specify ROI region, with side
Just the process of image detection module);
Described image processing section, its configuration image carried out pretreatment, target detection and bottle cap with
Track;
Described communication module, its configuration connects camera and acquisition module, connects at acquisition module and image
Reason part.
Owing to the strip source of the present invention is pointed into Oral liquid bottle lid with certain angle of inclination, light is reflected
Afterwards, form strong light and shade poor, after camera shooting, image is sent to acquisition module, at described image
Reason part, its configuration carries out pretreatment, target detection and bottle cap and follows the tracks of, uses ripe machine image
Device vision technique means, result is reliable and stable, and precision is high;Completely without contact bottle, it is possible to effectively
The liquid stored in ground protection bottle and bottle;Have only to camera and a small amount of light source can realize, save a large amount of
Peripheral hardware cost;Entirely without radiation, noiselessness, staff be there is no any injury;Owing to inciting somebody to action
Focus is transferred in software development, and hardware resource is less, it is simple to the equipment dimension of the staff in later stage
Protect;Automated production efficiency is high.
It addition, described camera is industry high definition resolution camera.
It addition, described communication module is USB or RJ45 netting twine.
It addition, described image processing section is in industrial computer host, this main frame connects touch screen and shows
Device.
It addition, as in figure 2 it is shown, this Oral liquid bottle lid detecting system also includes rejecting part, comprising:
Cylinder, photoelectric sensor switch, recovery approach, substandard products retracting device, when bottle cap defect being detected,
Photoelectric sensor switch position starts counting up, and when the bottle of defective locations being detected, cylinder action will be corresponding
Recovery approach shifted onto by bottle, the conveyer belt of recovery approach delivered in substandard products retracting device by bottle.
Additionally provide the method using this Oral liquid bottle lid detecting system, comprise the following steps:
(1) by bottle segregation apparatus each bottle forwarded and carry out 360 degree of rotations;
(2) strip source is pointed into Oral liquid bottle lid with certain angle of inclination, after light is reflected, and shape
The light and shade becoming strong is poor, after camera shooting, image is sent to acquisition module;
(3) image carries out pretreatment, target detection and bottle cap follow the tracks of;
(4) defect bottle cap detected, and record result.
It addition, described step (4) including: when bottle cap defect being detected, in photoelectric sensor switch position
Starting counting up, when the bottle of defective locations being detected, cylinder action shifts respective bottle onto recovery approach,
By the conveyer belt of recovery approach, bottle is delivered in substandard products retracting device.
It addition, described step (4) include following step by step:
(4.1) utilize dynamic threshold algorithm that ROI region is done the Image semantic classification (mesh of Image semantic classification
Mark is to process the image into preferable binary image.According to actual environment, use here
Dynamic threshold algorithm);
(4.2) step (4.1) gained binary image does connection process, analyze connected region, adopt
Profile by Canny algorithm detection connected region;
(4.3) target bottle cap is followed the tracks of based on Kalman filter.
It addition, described step (4.1) include following step by step:
(4.1a) shape filtering processes: is filtered image, filters noise and smooth image procossing;
(4.2b) image carries out local threshold based on Bernsen algorithm process.
Local thresholding method is chosen for gray threshold the function changed with location of pixels change, and it is a kind of
Dynamically select the adaptive approach of threshold value.Algorithm is summarized as follows:
If image pixel (i, j) gray value at place be f (i, j), it is considered to pixel (i, j) centered by
(2 ω+1) (2 ω+1), (2 ω+1 are the length of side of window), calculate each picture point (i, threshold value j) in image
T(i,j)
To each pixel in image, (i, j), with b, (i, j) value pointwise carries out binaryzation.
It addition, described step (4.3) include following step by step:
(4.3a) background model training, obtains representing the code book of initial back-ground model;
(4.3b) input pixel and code book compare judgement, obtain possible foreground pixel point, with
Shi Gengxin code book;
(4.3c) remove shade and highlight regions in possible foreground pixel point, obtain real foreground point,
Update code book simultaneously;
(4.3d) denoising, connected component analysis, eliminate non-according to the length and width of the moving target detected
Vehicle target, splits moving vehicle;
(4.3e) Kalman filter prediction vehicle possible position in the next frame is used;
(4.3f) around estimation range, each bottle cap is carried out matched jamming;Jump to step (4.3b),
Carry out next round tracking.
The unique hierarchy relying primarily on this binary tree successively carries out matching ratio relatively, finally calculates coupling
Value.Concrete matching primitives can utilize this recursive equation following to represent:
This formula represents in the matched jamming of adjacent oral liquid bottle, the most general by appearance similarity degree
Rate coupling weighting, and the nearest Similarity-Weighted of bottle movement position prediction, obtain two bottles of A, B
Minimum error probability, complete tracing detection removing function by statistical average.
The above, be only presently preferred embodiments of the present invention, and the present invention not makees any pro forma limit
System, any simple modification, equivalent that above example is made by the technical spirit of every foundation present invention become
Change and modify, the most still belonging to the protection domain of technical solution of the present invention.
Claims (10)
1. an Oral liquid bottle lid detecting system, it is characterised in that: it includes bottle segregation apparatus, image
Collecting part, image processing section, communication module;
Described bottle segregation apparatus includes equidistant feed belt with groove, and its configuration is by each bottle
Body forwards and carries out 360 degree of rotations;
Described image acquisition part is divided and is included strip source, camera, acquisition module, and strip source is with necessarily
Angle of inclination be pointed into Oral liquid bottle lid, after light is reflected, form strong light and shade poor,
After camera shooting, image is sent to acquisition module;
Described image processing section, its configuration image carried out pretreatment, target detection and bottle cap with
Track;
Described communication module, its configuration connects camera and acquisition module, connects acquisition module and image
Process part.
Oral liquid bottle lid detecting system the most according to claim 1, it is characterised in that: described camera
It it is industry high definition resolution camera.
Oral liquid bottle lid detecting system the most according to claim 2, it is characterised in that: described communication
Module is USB or RJ45 netting twine.
Oral liquid bottle lid detecting system the most according to claim 3, it is characterised in that: described image
Processing partly in industrial computer host, this main frame connects touch-screen display.
Oral liquid bottle lid detecting system the most according to claim 4, it is characterised in that: this oral liquid
Bottle cap detecting system also includes rejecting part, comprising: cylinder, photoelectric sensor switch, recovery
Passage, substandard products retracting device, when bottle cap defect being detected, open in photoelectric sensor switch position
Begin counting, and when the bottle of defective locations being detected, respective bottle is shifted onto reclaim by cylinder action
Passage, is delivered to bottle in substandard products retracting device by the conveyer belt of recovery approach.
6. the method using Oral liquid bottle lid detecting system according to claim 1, its feature
It is: comprise the following steps:
(1) by bottle segregation apparatus each bottle forwarded and carry out 360 degree of rotations;
(2) strip source is pointed into Oral liquid bottle lid with certain angle of inclination, after light is reflected, and shape
The light and shade becoming strong is poor, after camera shooting, image is sent to acquisition module;
(3) image carries out pretreatment, target detection and bottle cap follow the tracks of;
(4) defect bottle cap detected, and record result.
Method the most according to claim 6, it is characterised in that: described step (4) including: works as inspection
When measuring bottle cap defect, start counting up in photoelectric sensor switch position, when defective locations being detected
Bottle time, cylinder action shifts respective bottle onto recovery approach, by the conveyer belt of recovery approach
Bottle is delivered in substandard products retracting device.
Method the most according to claim 7, it is characterised in that: described step (4) includes following point
Step:
(4.1) utilize dynamic threshold algorithm that ROI region is done Image semantic classification;
(4.2) step (4.1) gained binary image does connection process, analyze connected region, adopt
Profile by Canny algorithm detection connected region;
(4.3) target bottle cap is followed the tracks of based on Kalman filter.
Method the most according to claim 8, it is characterised in that: described step (4.1) includes following
Step by step:
(4.1a) shape filtering processes: is filtered image, filters noise and smooth image procossing;
(4.2b) image carries out local threshold based on Bernsen algorithm process.
Method the most according to claim 9, it is characterised in that: described step (4.3) includes following
Step by step:
(4.3a) background model training, obtains representing the code book of initial back-ground model;
(4.3b) input pixel and code book compare judgement, obtain possible foreground pixel point, with
Shi Gengxin code book;
(4.3c) remove shade and highlight regions in possible foreground pixel point, obtain real foreground point,
Update code book simultaneously;
(4.3d) denoising, connected component analysis, eliminate non-according to the length and width of the moving target detected
Vehicle target, splits moving vehicle;
(4.3e) Kalman filter prediction vehicle possible position in the next frame is used;
(4.3f) around estimation range, each bottle cap is carried out matched jamming;Jump to step (4.3b),
Carry out next round tracking.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610520557.7A CN105973903B (en) | 2016-07-04 | 2016-07-04 | A kind of Oral liquid bottle lid detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610520557.7A CN105973903B (en) | 2016-07-04 | 2016-07-04 | A kind of Oral liquid bottle lid detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105973903A true CN105973903A (en) | 2016-09-28 |
CN105973903B CN105973903B (en) | 2019-07-30 |
Family
ID=56953713
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610520557.7A Active CN105973903B (en) | 2016-07-04 | 2016-07-04 | A kind of Oral liquid bottle lid detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105973903B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108787489A (en) * | 2018-07-06 | 2018-11-13 | 东阿阿胶股份有限公司 | A kind of recognition detection system of full automatic lamp detecting machine |
CN112158416A (en) * | 2020-08-20 | 2021-01-01 | 大连恒生塑料制品有限公司 | Arranging, detecting, counting and packaging all-in-one machine |
CN112581393A (en) * | 2020-12-15 | 2021-03-30 | 湖北工业大学 | Unscrewing cap image processing method based on semantic segmentation |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102135416A (en) * | 2010-12-30 | 2011-07-27 | 天津普达软件技术有限公司 | Online image detecting system and method for bottle covers |
CN103439343A (en) * | 2013-08-23 | 2013-12-11 | 昆山海为自动化有限公司 | Bottle cap quality detection system |
CN203772760U (en) * | 2014-04-14 | 2014-08-13 | 北京大恒图像视觉有限公司 | Bottle cap detecting device |
JP5600942B2 (en) * | 2010-01-15 | 2014-10-08 | ウシオ電機株式会社 | Inspection method |
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 |
CN205749332U (en) * | 2016-07-04 | 2016-11-30 | 东阿阿胶股份有限公司 | A kind of Oral liquid bottle lid detecting system |
-
2016
- 2016-07-04 CN CN201610520557.7A patent/CN105973903B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5600942B2 (en) * | 2010-01-15 | 2014-10-08 | ウシオ電機株式会社 | Inspection method |
CN102135416A (en) * | 2010-12-30 | 2011-07-27 | 天津普达软件技术有限公司 | Online image detecting system and method for bottle covers |
CN103439343A (en) * | 2013-08-23 | 2013-12-11 | 昆山海为自动化有限公司 | Bottle cap quality detection system |
CN203772760U (en) * | 2014-04-14 | 2014-08-13 | 北京大恒图像视觉有限公司 | Bottle cap detecting device |
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 |
CN205749332U (en) * | 2016-07-04 | 2016-11-30 | 东阿阿胶股份有限公司 | A kind of Oral liquid bottle lid detecting system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108787489A (en) * | 2018-07-06 | 2018-11-13 | 东阿阿胶股份有限公司 | A kind of recognition detection system of full automatic lamp detecting machine |
CN112158416A (en) * | 2020-08-20 | 2021-01-01 | 大连恒生塑料制品有限公司 | Arranging, detecting, counting and packaging all-in-one machine |
CN112581393A (en) * | 2020-12-15 | 2021-03-30 | 湖北工业大学 | Unscrewing cap image processing method based on semantic segmentation |
CN112581393B (en) * | 2020-12-15 | 2022-04-26 | 湖北工业大学 | Unscrewing cap image processing method based on semantic segmentation |
Also Published As
Publication number | Publication date |
---|---|
CN105973903B (en) | 2019-07-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111661590B (en) | Method for detecting tearing damage of conveying belt of mining belt conveyor | |
CN105023278B (en) | A kind of motion target tracking method and system based on optical flow method | |
CN103150549B (en) | A kind of road tunnel fire detection method based on the early stage motion feature of smog | |
CN102636490B (en) | Method for detecting surface defects of dustproof cover of bearing based on machine vision | |
CN104361353B (en) | A kind of application of localization method of area-of-interest in instrument monitoring identification | |
CN103279765B (en) | Steel wire rope surface damage detection method based on images match | |
CN105158268A (en) | Intelligent online detection method, system and device for defects of fine-blanked parts | |
CN110163852B (en) | Conveying belt real-time deviation detection method based on lightweight convolutional neural network | |
CN109489724A (en) | A kind of tunnel safe train operation environment comprehensive detection device and detection method | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
CN105973903A (en) | System and method for detecting oral solution bottle caps | |
Kumar et al. | A deep learning based automated structural defect detection system for sewer pipelines | |
CN106529551B (en) | Intelligent recognition counting detection method for round-like objects in packaging industry | |
CN115984186A (en) | Fine product image anomaly detection method based on multi-resolution knowledge extraction | |
CN113569943B (en) | Slag piece large-block early warning method, system and device based on deep neural network | |
WO2016203149A1 (en) | Pairing of images of postal articles with descriptors of singularities of the gradient field | |
CN109596620A (en) | Product surface shape defect detection method and system based on machine vision | |
Park et al. | Patch-based crack detection in black box road images using deep learning | |
CN104392201A (en) | Human fall identification method based on omnidirectional visual sense | |
CN103942792A (en) | Impurity detecting method in medicine detection robot based on time domain features of sequence images | |
CN114655655B (en) | Conveyor belt deviation detection method based on UNet network | |
CN105954295A (en) | Helmet top facing defect detection system and method | |
Jo et al. | Pothole detection based on the features of intensity and motion | |
CN205749332U (en) | A kind of Oral liquid bottle lid detecting system | |
CN105404891A (en) | Outdoor facility inspection method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |