CN103529053B - Bottle mouth defect detection method - Google Patents
Bottle mouth defect detection method Download PDFInfo
- Publication number
- CN103529053B CN103529053B CN201310452499.5A CN201310452499A CN103529053B CN 103529053 B CN103529053 B CN 103529053B CN 201310452499 A CN201310452499 A CN 201310452499A CN 103529053 B CN103529053 B CN 103529053B
- Authority
- CN
- China
- Prior art keywords
- ring
- region
- detection
- area
- defective
- 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
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a kind of bottle mouth defect detection method, comprising: S1, surveyed area division is carried out to described bottleneck, be divided into the first inner ring, the second inner ring, assessment ring, sealing ring and inner seal ring region, and each region is detected; S2, each testing result to be gathered, export the comprehensive detection result to bottleneck, if all detection results are normally, then export this empty bottle inspection normal, otherwise it is abnormal to export this empty bottle inspection.The bottle mouth defect detection method that the present invention proposes, detection speed is fast, precision is high, stable performance, debugging are convenient, is applicable to high-speed automated streamline detects the long-time uninterrupted in real time of bottle mouth defect.
Description
Technical field
The present invention relates to industrial automation detection technique field, particularly a kind of bottle mouth defect detection method.
Background technology
At present, the Food safety management system of China advances fast, and the common people strengthen further for the degree of concern of food security, and the HACCP standard in Europe and the GB4927-91 standard of China all propose strict requirement to the detection of beer bottle empty bottle.In the production run of existing beer, beverage and medicine, all require that container filling meets corresponding quality standard, produce each step all to need to check, when defective bottle comes into the market, not only consumer may come to harm, and also can suffer damage for its economy of production producer and reputation.Current beer bottle Empty Bottle mainly relies on the method for manual detection to realize, but manual detection exists following shortcoming: (1) detection speed is slow, inefficiency.China was that the output of the glass object drink of representative increases fast with beer in recent years, beer production since two thousand two surely occupies first place in the world always, Beer Brewage linear velocity is domestic be also increased to fast 20,000 four to four ten thousand bottles per hour, external prestissimo is per hour more than 70,000 bottles.Rely under such speed manually to carry out detecting and be difficult to realize; (2) along with the quick increase of human cost in recent years, manual detection becomes further expensive; (3) people examines need of work personnel and measures greatly, but this work is uninteresting, intensity large, is ready that the young man being engaged in this work is fewer and feweri, causes enterprise to be advertised for workers difficult; (4) owing to being subject to the impacts such as personnel's fatigue, mood, the bottle quality after people's inspection and quality conformance all poor, be difficult to meet the quality requirements that day by day improves.So, adopt automatic mode to be used by Rapid Popularization the vial empty bottle bottle checker that vial empty bottle detects just at home and abroad.
External vial empty bottle bottle checker has had some successful stories, its product has customers widely in European and American areas, but import bottle checker is used for Domestic Beer manufacturing enterprise exists following problem: (1) is expensive, delivery cycle is long, China's beer annual production and production line quantity all occupy first place in the world, but fancy price and the non-most of enterprise of maintenance cost can bear, and the general supply of material in early stage and the after-sales service cycle all longer; (2) standard is different, and import bottle checker is mostly based on European examination criteria algorithm for design and parameter, and there is inconsistent situation with the national standard of China, to Beer Brewage, manufacturer brings puzzlement; (3) bottle source is different, and the beer bottle of China is greater than 80% for returnable bottle, and 20% is new bottle, and contrary in European ratio.The new bottle production of China is generally Duo Jia vial factory and produces simultaneously, and new bottle quality, profile are also each variant.Returnable bottle mostly is and repeatedly uses, and it is comparatively serious that bottle knocks damage, scuffing, crackle.Then lose the dirigibility to domestic bottle source and each manufacturer's quality requirements according to import bottle checker in this case, often cannot meet the demand of Domestic Beer manufacturer, make import bottle checker occur the situation of " not acclimatized ".So, research and greatly develop the Own Brand bottle checker equipment with complete independent intellectual property right for promote China have the control of core technology by oneself and sci-tech innovation ability significant, to the lifting of China's food beverage industry safe and sanitary, there is actual value.
As the important step of vial Empty Bottle, empty bottle inspection is very valued by Beer Brewage manufacturer, when bottleneck badly broken, may damage drinking person, even and if small defect, also wine rapid deterioration in shipping storage process can be caused due to gas leakage, so empty bottle inspection requires to have very high precision.On the other hand, because the bottle of bottle mouth defect is generally discarded bottle, so mostly underproof for empty bottle inspection bottle is directly rejected and smashed by Beer Brewage manufacturer, then return and get back to chain road after bottle washing machine cleans again as the link such as at the bottom of sidewall, bottle detects underproof bottle and carry out Empty Bottle again.So require that the mistake rejecting rate of empty bottle inspection must be very low, otherwise a large amount of qualified bottle is smashed the economic loss that beer producers can be caused considerable by mistake rejecting.
Carry out in some colleges and universities for the research work of empty bottle inspection at present.But due to bottle checker product requirement at a high speed, stable, high precision, strong adaptability, be convenient to many actual requirements such as slip-stick artist's debugging, need to weigh above-mentioned various factors in the algorithm design process of vial empty bottle inspection, the particularly requirement of speed and stability aspect, exploitation is suitable for the vial empty bottle mouth detection algorithm of industrialization promotion.
Summary of the invention
(1) technical matters that will solve
The technical problem to be solved in the present invention is: how to provide a kind of high-speed, high precision bottle mouth defect detection method, slow for the speed solving empty bottle bottle mouth defect detection method on the filling automation production flow line of existing high speed vial, precision is low and the problem of poor stability.
(2) technical scheme
For solving the problem, the invention provides a kind of bottle mouth defect detection method, comprising: S1, surveyed area division is carried out to described bottleneck, be divided into the first inner ring, the second inner ring, assessment ring, sealing ring and inner seal ring region, and each region is detected; S2, each testing result to be gathered, export the comprehensive detection result to bottleneck, if all detection results are normally, then export this empty bottle inspection normal, otherwise it is abnormal to export this empty bottle inspection.
Preferably, in described step S1, adopt parallel computation mechanism to detect described first inner ring, the second inner ring, assessment ring, sealing ring and inner seal ring region, every detection has walked abreast simultaneously.
Preferably, carry out detection comprise described first endocyclic area: S111, carry out binaryzation operation to after described first endocyclic area filtering, normal region is black, and abnormal area is white; S112, connected domain analysis is carried out to described white portion, when largest connected territory area is greater than given threshold value, then returns the first inner ring and detect abnormal, otherwise return the first inner ring and detect normal.
Preferably, carry out detection comprise described assessment ring region: S131, carry out binary conversion treatment by after described assessment ring region filtering, normal region is black, and abnormal area is white, then carries out polar coordinates expansion; S132, observe the white pixel number of often row pixel along described assessment ring radial direction, if certain row white pixel number exceedes given range, then mark this and be classified as defective; If S133 detects that certain row is defective, then improper value increases, otherwise if qualified, improper value reduces, if improper value peak value exceedes given threshold value, then exports defective, is defective if export, then return assessment ring and detect abnormal, otherwise it is normal to return the detection of assessment ring.
Preferably, carry out detection comprise described sealing ring region: S141, carry out binary conversion treatment by after described sealing ring region filtering, normal region is black, and abnormal area is white, then carries out polar coordinates expansion; S142, observe the white pixel number of often row pixel along sealing ring radial direction, if certain row white pixel number is lower than set-point, then marks this and be classified as defective; If S143 detects that certain row is defective, then improper value increases, otherwise if qualified, improper value minimizing, if improper value peak value exceedes given threshold value, then exports defective, if export as defective, then return sealing ring and detect abnormal, otherwise it is normal to return sealing ring detection.
Preferably, carry out detection to described inner seal ring region to comprise: S151, will gray threshold be utilized after the filtering of inner seal ring region to carry out Iamge Segmentation to this region, being less than this threshold region, to arrange gray scale be black, as a setting region, be greater than this threshold region gray scale constant, as foreground area; S152, will add gray scale after foreground area is averaged as threshold value after biased, foreground area is carried out binary conversion treatment, and what be less than this threshold value is set to black, and what be greater than this threshold value is set to white; S153, white portion is carried out opening operation, remove the impact of tiny striped and fritter false areas; The connected domain information of S154, calculating white portion, the bound of the detections such as setting connected domain area, width and height, return inner seal ring abnormal, otherwise it is normal to return inner seal ring when at least all information of existence connected domain is simultaneously in limited range.
(3) beneficial effect
The bottle mouth defect detection method that the present invention proposes, detection speed is fast, precision is high, stable performance, debugging are convenient, is applicable to high-speed automated streamline detects the long-time uninterrupted in real time of bottle mouth defect.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the bottle mouth defect detection method according to one embodiment of the present invention;
Fig. 2 is the empty bottle inspection image schematic diagram according to one embodiment of the present invention;
Fig. 3 is the empty bottle inspection image capturing system schematic diagram according to one embodiment of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples for illustration of the present invention, but are not used for limiting the scope of the invention.
The invention provides a kind of bottle mouth defect detection method, comprising:
S1, surveyed area division is carried out to bottleneck, adopt parallel computation mechanism to detect in the region such as the first inner ring, the second inner ring, assessment ring, sealing ring and inner seal ring simultaneously;
S2, each testing result to be gathered, finally export the comprehensive detection result to bottleneck, be no less than 1 detection output abnormality if exist, then testing result be exception, otherwise testing result is normal.
Wherein, the employing parallel computation mechanism in described step S1 detects in the region such as the first inner ring, the second inner ring, assessment ring, sealing ring and inner seal ring simultaneously, and each detection has walked abreast, and every do not have coupled relation in testing process, and its idiographic flow is:
S11, the first inner ring detect, and first to region filtering, binaryzation operation, normal region is black, abnormal area is white, then carries out connected domain analysis to white portion, if maximum area exceedes threshold value, then returning the first inner ring detects abnormal, otherwise it is normal to return the first inner ring detection;
S12, the second inner ring detect, and its testing process detects identical with the first inner ring;
S13, assessment ring detect, first to region filtering, binaryzation operation, normal region is black, abnormal area is white, then adds up, when the white pixel number of certain row is beyond normal range along the white pixel number of assessment ring radial direction to every row pixel, marking this is classified as defective, if the defective row of weighting exceed given threshold value, then return assessment ring and detect abnormal, otherwise it is normal to return the detection of assessment ring;
S14, sealing ring detect, first to region filtering, binaryzation operation, normal region is black, abnormal area is white, then adds up, if certain row white pixel number is less than set-point along the white pixel number of sealing ring radial direction to every row pixel, then mark these row defective, if the defective row of weighting exceed given threshold value, then return sealing ring and detect abnormal, otherwise it is normal to return sealing ring detection;
S15, inner seal ring detect, first to the foreground area being divided into gray-scale value constant and the background area for black.Then binary conversion treatment is carried out, what be less than threshold value is set to black, i.e. background area, what be greater than threshold value is set to white, white portion is carried out opening operation by the 3rd, the connected domain information of the 4th calculating white portion, the bound of the detections such as setting connected domain area, width and height, return inner seal ring when at least all information of existence connected domain is simultaneously in limited range abnormal, otherwise it is normal to return inner seal ring.
The flow process of the bottle mouth defect detection method proposed in the present embodiment as shown in Figure 1.Captured image and each surveyed area mark are as shown in Figure 2.Wherein outer circular bright ring is sealing ring, and inner circular bright ring is inner seal ring, and the first inner ring is between sealing ring and inner seal ring, and the second inner ring is within inner seal ring, and the region of sealing ring inwardly after outer extension one fixed width is assessment ring.As shown in Figure 3, the bottleneck in wherein annular LED light source 2 oblique illumination bottle 3, light enters CCD camera 1 to the acquisition system of bottleneck image after bottleneck surface reflection.When bottleneck smooth surface is complete, image is the bright ring shape of complete specifications, and when bottleneck surface damage, disconnecting or having bulk hickie phenomenon appears in the bright ring of image.
The key step detected comprises:
S11. the first inner ring detects.When bottleneck exists larger breach or ground, can occur the hickie of larger area at the first endocyclic area, namely the detection of the first endocyclic area detects mainly for above-mentioned defect.Its detection method is:
S111, carry out binaryzation operation to after the first endocyclic area filtering, make normal region be black, abnormal area is in white;
S112, connected domain analysis is carried out to white portion, when largest connected territory area is greater than given threshold value, then returns the first inner ring and detect abnormal, otherwise return the first inner ring and detect normal;
S12. the second inner ring detects.When having larger foreign matters from being blocked at bottleneck, then may there is the hickie of larger area at the second endocyclic area.Namely the detection of the second endocyclic area detects mainly for above-mentioned defect.Its detection method detects identical with the first inner ring, does not repeat them here.
S13. assess ring to detect.When bottleneck exists defect, there will be the situation that sealing ring disconnects, if when there is ground, there will be situation about to occur around sealing ring compared with Great White Spot.Namely the detection in assessment ring region detects mainly for above-mentioned defect.Its detection method is:
S131, carry out binary conversion treatment by after the region filtering of assessment ring, then carry out polar coordinates expansion;
S132, edge assessment ring radial direction observe the white pixel number of often row pixel, if certain row white pixel number exceedes given range, then mark this and are classified as defective;
If S133 detects that certain row is defective, then improper value increases, otherwise if qualified, improper value reduces.If improper value peak value exceedes given threshold value, then export defective.
If export as defective, then return assessment ring and detect abnormal, otherwise return assessment ring and detect normal.
S14. sealing ring detects.When bottleneck exists defect, sealing ring can disconnect, and sealing ring detects and namely detects for this kind of defect, and be also in each detection most important one, its detection method is:
S141, carry out binary conversion treatment by after the filtering of sealing ring region, then carry out polar coordinates expansion;
S142, observe the white pixel number of often row pixel along sealing ring radial direction, if certain row white pixel number is lower than set-point, then marks this and be classified as defective.；
If S143 detects that certain row is defective, then improper value increases, otherwise if qualified, improper value reduces, if improper value peak value exceedes given threshold value, then exports defective.
If export as defective, then return sealing ring and detect abnormal, otherwise it is normal to return sealing ring detection.
S15. inner seal ring detects.When in bottleneck along when occurring damaged, there will be inner seal ring and occur hickie, but different due to edge in bottleneck, cause inner seal ring imaging different, its brightness, width and texture are different, this adds increased the difficulty of detection, and the detection method of inner seal ring is:
S151, will gray threshold be utilized after the filtering of inner seal ring region to carry out Iamge Segmentation to this region, being less than this threshold region, to arrange gray scale be black, as a setting region; Be greater than this threshold region gray scale constant, as foreground area;
S152, will add gray scale after foreground area is averaged as threshold value after biased, foreground area is carried out binary conversion treatment, and what be less than this threshold value is set to black, and what be greater than this threshold value is set to white;
S153, white portion is carried out opening operation, remove the impact of tiny striped and fritter false areas;
The connected domain information of S154, calculating white portion, the bound of the detections such as setting connected domain area, width and height, return inner seal ring abnormal, otherwise it is normal to return inner seal ring when at least all information of existence connected domain is simultaneously in limited range.
S2. testing result gathers.The testing result of each detection is carried out the result that comprehensive rear output is final, if all location item and detection result are normally, then export this empty bottle inspection normal, otherwise it is abnormal to export this empty bottle inspection.
In sum, the present invention has some advantage following:
1. detection speed is fast.In algorithm aspect, each detection is completely independent, therefore can adopt multithreads computing when program composition.When collection image is 640 × 480 pixels, in the enterprising row operation of the computing machine of I5CPU, the operation time of every width image, this speed can meet the needs of beer production line the fastest in the world at present within 14ms.
2. accuracy of detection is high, and false drop rate is low.This method is utilized can accurately to detect bottleneck 5mm
2defect.Effectively can resist interference, false drop rate is not higher than 0.1% simultaneously.
3. stable performance.In the trace routine operational process that this algorithm generates EMS memory occupation and handling capacity little, and can not run-time error be caused when the input of optimum configurations unreasonable or non-bottleneck image.Therefore long-play is difficult to occur operation exception situation generations such as crashing, internal memory exhausts.
4. slip-stick artist debugs conveniently, lower to the requirement of slip-stick artist.Testing result is insensitive to the parameter except precision threshold; Need the parameter of setting visual and understandable, setting parameter can be adjusted direction by simple analysis image simultaneously.Therefore the slip-stick artist that theoretical level and experience are not too high also can be competent at field adjustable work.
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the prerequisite not departing from the technology of the present invention principle; can also make some improvement and replacement, these improve and replace and also should be considered as protection scope of the present invention.
Claims (5)
1. a bottle mouth defect detection method, is characterized in that, comprising:
S1, surveyed area division is carried out to described bottleneck, be divided into the first inner ring, the second inner ring, assessment ring, sealing ring and inner seal ring region, and each region is detected;
Carry out detection to described inner seal ring region to comprise:
S151, will gray threshold be utilized after the filtering of inner seal ring region to carry out Iamge Segmentation to this region, being less than this threshold region, to arrange gray scale be black, as a setting region, is greater than this threshold region gray scale constant, as foreground area;
S152, will add gray scale after foreground area is averaged as threshold value after biased, foreground area is carried out binary conversion treatment, and what be less than this threshold value is set to black, and what be greater than this threshold value is set to white;
S153, white portion is carried out opening operation, remove the impact of tiny striped and fritter false areas;
The connected domain information of S154, calculating white portion, the bound of the detections such as setting connected domain area, width and height, return inner seal ring abnormal, otherwise it is normal to return inner seal ring when at least all information of existence connected domain is simultaneously in limited range;
S2, each testing result to be gathered, export the comprehensive detection result to bottleneck, if all detection results are normally, then export this empty bottle inspection normal, otherwise it is abnormal to export this empty bottle inspection.
2. method according to claim 1, is characterized in that, in described step S1, adopt parallel computation mechanism to detect described first inner ring, the second inner ring, assessment ring, sealing ring and inner seal ring region, every detection has walked abreast simultaneously.
3. method according to claim 1 and 2, is characterized in that, carries out detection comprise described first endocyclic area:
S111, carry out binaryzation operation to after described first endocyclic area filtering, normal region is black, and abnormal area is white;
S112, connected domain analysis is carried out to described white portion, when largest connected territory area is greater than given threshold value, then returns the first inner ring and detect abnormal, otherwise return the first inner ring and detect normal.
4. method according to claim 1 and 2, is characterized in that, carries out detection comprise described assessment ring region:
S131, carry out binary conversion treatment by after described assessment ring region filtering, normal region is black, and abnormal area is white, then carries out polar coordinates expansion;
S132, observe the white pixel number of often row pixel along described assessment ring radial direction, if certain row white pixel number exceedes given range, then mark this and be classified as defective;
If S133 detects that certain row is defective, then improper value increases, otherwise if qualified, improper value reduces, if improper value peak value exceedes given threshold value, then exports defective, is defective if export, then return assessment ring and detect abnormal, otherwise it is normal to return the detection of assessment ring.
5. method according to claim 1 and 2, is characterized in that, carries out detection comprise described sealing ring region:
S141, carry out binary conversion treatment by after described sealing ring region filtering, normal region is white, and abnormal area is black, then carries out polar coordinates expansion;
S142, observe the white pixel number of often row pixel along sealing ring radial direction, if certain row white pixel number is lower than set-point, then marks this and be classified as defective;
If S143 detects that certain row is defective, then improper value increases, otherwise if qualified, improper value minimizing, if improper value peak value exceedes given threshold value, then exports defective, if export as defective, then return sealing ring and detect abnormal, otherwise it is normal to return sealing ring detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310452499.5A CN103529053B (en) | 2013-09-27 | 2013-09-27 | Bottle mouth defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310452499.5A CN103529053B (en) | 2013-09-27 | 2013-09-27 | Bottle mouth defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103529053A CN103529053A (en) | 2014-01-22 |
| CN103529053B true CN103529053B (en) | 2015-12-02 |
Family
ID=49931239
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310452499.5A Active CN103529053B (en) | 2013-09-27 | 2013-09-27 | Bottle mouth defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103529053B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105241888B (en) * | 2015-09-25 | 2018-11-02 | 上海金啤包装检测科技有限公司 | A kind of detection method and detection device of bottle mouth defect |
| CN105717123A (en) * | 2015-10-29 | 2016-06-29 | 山东明佳科技有限公司 | Method and equipment for comprehensively detecting defect of blank support rings for PET (polyethylene terephthalate) bottles |
| CN107282460B (en) * | 2016-11-14 | 2019-03-01 | 燕京啤酒(桂林漓泉)股份有限公司 | Beer packaging production scene bottle checker operates normally effect evaluation method |
| CN106846294B (en) * | 2016-12-16 | 2020-11-27 | 深圳市海科瑞科技有限公司 | Visual detection method, device and equipment |
| CN114813787A (en) * | 2017-02-06 | 2022-07-29 | 东洋玻璃株式会社 | Glass bottle inspection device |
| CN107472601A (en) * | 2017-09-01 | 2017-12-15 | 广西德保新贝侬酒厂有限公司 | A kind of alcoholic workshop lamp checking device |
| CN109063708B (en) * | 2018-06-21 | 2022-10-28 | 歌尔股份有限公司 | Industrial image feature identification method and system based on contour extraction |
| CN109297984B (en) * | 2018-11-13 | 2021-02-19 | 正大天晴药业集团股份有限公司 | Bubble cap packaging defect detection method, device and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1050768A (en) * | 1989-10-06 | 1991-04-17 | 埃尔帕特朗尼股份公司 | Be used to check the device of bottle or congener |
| JP2000321214A (en) * | 1999-05-10 | 2000-11-24 | Kawasaki Steel Corp | Defect-detecting method and device |
| CN101063662A (en) * | 2007-05-15 | 2007-10-31 | 广州市万世德包装机械有限公司 | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP |
| CN103257144A (en) * | 2013-05-15 | 2013-08-21 | 华南理工大学 | Plastic bottleneck excess material detecting method and device based on machine vision |
| CN103308523A (en) * | 2013-05-28 | 2013-09-18 | 清华大学 | Method for detecting multi-scale bottleneck defects, and device for achieving method |
-
2013
- 2013-09-27 CN CN201310452499.5A patent/CN103529053B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1050768A (en) * | 1989-10-06 | 1991-04-17 | 埃尔帕特朗尼股份公司 | Be used to check the device of bottle or congener |
| JP2000321214A (en) * | 1999-05-10 | 2000-11-24 | Kawasaki Steel Corp | Defect-detecting method and device |
| CN101063662A (en) * | 2007-05-15 | 2007-10-31 | 广州市万世德包装机械有限公司 | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP |
| CN103257144A (en) * | 2013-05-15 | 2013-08-21 | 华南理工大学 | Plastic bottleneck excess material detecting method and device based on machine vision |
| CN103308523A (en) * | 2013-05-28 | 2013-09-18 | 清华大学 | Method for detecting multi-scale bottleneck defects, and device for achieving method |
Non-Patent Citations (1)
| Title |
|---|
| 《基于机器视觉的啤酒瓶瓶口检测系统的研究》;张田田;《中国优秀硕士学位论文全文数据库信息科技辑》;20111231(第S1期);第44页4.4节第2-3段，第55页5.4节第1段，第18页第3段，50页第2段，第55页第1-2段，47-49页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103529053A (en) | 2014-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103529053B (en) | Bottle mouth defect detection method | |
| CN101844633B (en) | Label detection system and detection method thereof | |
| CN201143502Y (en) | Device for testing, analyzing and counting bar-code | |
| CN108465648A (en) | A kind of magnetic core Automated Sorting System based on machine vision | |
| CN205436353U (en) | Bearing sorting machine | |
| CN101105460A (en) | Multifunctional bottle checker | |
| CN201135974Y (en) | Magnetic steel automatic detection system | |
| CN103063137B (en) | A kind of medicine bottle measuring system based on machine vision and measuring method thereof | |
| CN106370659A (en) | Visual inspection method for bottle packaging quality | |
| CN103344577A (en) | Non-destructive detection method for freshness of livestock meat based on multispectral imaging technology | |
| CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
| CN105403147A (en) | Embedded bottle pre-form detection system and detection method | |
| CN105954301A (en) | Bottleneck quality detection method based on machine vision | |
| CN104118609A (en) | Labeling quality detecting method and device | |
| CN108580333A (en) | Level sensing study of platform based on machine vision and design | |
| CN104550051A (en) | Empty bottle sorting system for glass bottle | |
| CN204731167U (en) | A kind of bottled product outer package label coding defect detecting system | |
| CN103308523A (en) | Method for detecting multi-scale bottleneck defects, and device for achieving method | |
| CN204544803U (en) | A kind of vial empty bottle sorting system | |
| CN202066794U (en) | Full-automatic key detection device | |
| CN103523491B (en) | Bottleneck localization method | |
| CN201689317U (en) | Label detecting system | |
| CN203672800U (en) | Wine filling production line quality detecting system | |
| CN105241888B (en) | A kind of detection method and detection device of bottle mouth defect | |
| Yang et al. | Design of drug and wine bottlecap defect detection system based on machine vision |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100084 Beijing Haidian District Tsinghua Yuan 100084-82 mailbox Co-patentee after: SHANDONG MINGJIA TECHNOLOGY CO., LTD. Patentee after: Tsinghua University Address before: 100084 Beijing Haidian District Tsinghua Yuan 100084-82 mailbox Co-patentee before: Shandong Mingjia Package Inspection Technology Co., Ltd. Patentee before: Tsinghua University |