CN108344743A - One kind being based on machine vision drug blister package defect inspection method and system - Google Patents
One kind being based on machine vision drug blister package defect inspection method and system Download PDFInfo
- Publication number
- CN108344743A CN108344743A CN201810107074.3A CN201810107074A CN108344743A CN 108344743 A CN108344743 A CN 108344743A CN 201810107074 A CN201810107074 A CN 201810107074A CN 108344743 A CN108344743 A CN 108344743A
- Authority
- CN
- China
- Prior art keywords
- image
- machine vision
- drug
- blister package
- detection method
- 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
- 239000003814 drug Substances 0.000 title claims abstract description 71
- 229940079593 drug Drugs 0.000 title claims abstract description 71
- 230000007547 defect Effects 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 title claims description 18
- 238000007689 inspection Methods 0.000 title claims description 6
- 238000001514 detection method Methods 0.000 claims abstract description 57
- 230000009466 transformation Effects 0.000 claims abstract description 12
- 239000000284 extract Substances 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000003709 image segmentation Methods 0.000 claims abstract description 8
- 238000003708 edge detection Methods 0.000 claims abstract description 7
- 230000002708 enhancing effect Effects 0.000 claims abstract description 5
- 238000013500 data storage Methods 0.000 claims abstract description 4
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 4
- 230000010365 information processing Effects 0.000 claims abstract description 4
- 238000011084 recovery Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000010191 image analysis Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000001174 ascending effect Effects 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 230000005693 optoelectronics Effects 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000012856 packing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 241001292396 Cirrhitidae Species 0.000 description 2
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003706 image smoothing Methods 0.000 description 2
- 239000002398 materia medica Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 229910052710 silicon Inorganic materials 0.000 description 2
- 239000010703 silicon Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000015096 spirit Nutrition 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000003934 vacuole Anatomy 0.000 description 1
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
- G01N21/8851—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
Abstract
The invention discloses one kind being based on machine vision drug blister package detection method and system comprising following steps：Step 1, Image Acquisition acquire image information using on laser transmitter projects to packaged bubble-cap；Enhancing, recovery, coding and the greyscale transformation of step 2, Image Information Processing, including image carry out image the removal of noise；Step 3, image segmentation, threshold values setting；Step 4, Image edge tracking utilize Canny edge detection algorithms detection bubble-cap edge；Step 5 extracts characteristics of image, carries out threshold value setting to the image of decomposition, threshold values extracts the characteristics of image of corresponding region；Step 6, the color of extraction segmentation drug, position, size and shape；Step 7, select tablet position, size, shape and surface defect size tolerance；Step 8 stores standard form, tablet feature and tolerance；Step 9, it is tagged to defect tablet and corresponding bubble-cap；Step 10 finally carries out data storage.
Description
Technical field
The present invention relates to bubble-cap detection technique fields, more particularly to one kind to be lacked based on machine vision drug blister package
Fall into detection method and system.
Background technology
The factor for influencing materia medica packaging quality includes mainly vacuole, tablet incompleteness and surface color.On the one hand traditional
Contact type measurement limitation of the technology drug bubble-cap detection efficiency and accuracy of detection, on the other hand traditional offline, static measurement skill
Art can not meet the requirement of modern measure again, cannot detect pharmaceutical packing defect in time, seriously affect materia medica packaging quality.
If can not achieve, speed is fast, precision is high, online automatic detection, can reduce enterprises production efficiency, or even directly affect enterprise
Economic benefit.In addition, traditional Key works Drug packing detection is manual operation, detection result and efficiency rely primarily on reviewer, people
For influence factor is big, omission factor is high, the degree of automation is low.In addition, pure artificial detection operation there is also labor intensities big, work
It is very low to make efficiency.
Therefore, the existing technology needs to be improved and developed.
Invention content
The purpose of the present invention is to provide one kind being based on machine vision drug blister package defect inspection method and system, purport
Slow in the bubble-cap detection speed for solving existing Key works Drug packing, precision is low, and the degree of automation is low, and using the labour of artificial detection
It is slight big, the low technical problem of efficiency.
Technical scheme is as follows：One kind being based on machine vision drug blister package detection method comprising following
Step：
Step 1, Image Acquisition acquire image information using on laser transmitter projects to packaged bubble-cap；
Step 2, Image Information Processing, the enhancing of image, recovery, coding and greyscale transformation, using median filtering method to collecting
Image carries out the removal of noise；
Step 3, image segmentation（Object or boundary）, threshold values setting；
Step 4, Image edge tracking utilize Canny edge detection algorithms detection bubble-cap edge；
Step 5 extracts characteristics of image, carries out threshold value setting to the image of decomposition, threshold values extracts the characteristics of image of corresponding region；
Step 6, the color of extraction segmentation drug, position, size and shape；
Step 7, select tablet position, size, shape and surface defect size tolerance；
Step 8 stores standard form, tablet feature and tolerance；
Step 9, it is tagged to defect tablet and corresponding bubble-cap；
Step 10, data storage show corresponding inspection result simultaneously related defects information preservation in corresponding lane database
Face.
It is described based on machine vision drug blister package detection method, wherein acquire image information in the step 1
Mode is to obtain corresponding artificial texture, then acquire image by industrial CCD camera on laser transmitter projects to drug bubble-cap
Information.
Described is based on machine vision drug blister package detection method, wherein the industrial CCD camera passes through silk
Bar is connect with servo motor, and drives down conversion camera site in servo motor.
It is described based on machine vision drug blister package detection method, wherein the median filter method of the step 2
It is：To pending current pixel, a template is selected, which is its neighbouring several pixels composition, to the picture of template
Element is ascending to be ranked up, then the value of original pixel is substituted with the intermediate value of template.
It is described based on machine vision drug blister package detection method, wherein the template is weight coefficient matrix template,
Formula is：
；
g=median[(x-1,y-1)+f(x,y-1)+f(x+1,y-1)+f(x-1,y)+f(x,y)+f(x+1,y) +f(x-1,y+
1)+f(x,y+1)+f(x+1,y+1)]。
It is described based on machine vision drug blister package detection method, wherein the step of the Canny edge detection algorithms
It is rapid as follows：
The first step：Noise is eliminated in such a way that 2D gaussian filtering templates carry out convolution to carry out noise elimination；
Second step：The finite difference that the amplitude of calculating gradient and direction use single order local derviation carries out correlation computations,
The partial derivative in two directions of gradation of image is found using derivative operator (such as Prewitt operators, Sobel operators)
(Gx, Gy), and find out the size of gradient；；
Third walks：The direction of gradient is calculated using the result of second step；Further according to formula：；It obtains
Edge direction, so that it may the gradient direction at edge is broadly divided into following four direction：Horizontal, vertical, 45 degree and 135 degree of sides
To；Then the adjacent pixels in this pixel gradient direction are found according to the direction of gradient；
4th step：Edge is detected and connected with dual threashold value-based algorithm；Two threshold values are calculated using accumulative histogram.
It is described based on machine vision drug blister package detection method, wherein it is described Step 5: Step 6: Step 7:
Step 8 and step 10, which carry, to be realized by machine vision software Halcon.
A kind of detecting system based on machine vision drug blister package detection method comprising laser lighting light source is provided
Laser emitter, photoelectric sensor switch, ccd image sensor, image processor, control unit, transmission device, machinery positioning
Device and executive device；Described control unit respectively with transmission device, mechanical positioner, executive device, image processor, swash
Optical transmitting set, photoelectric sensor switch are connected with ccd image sensor；The executive device is connect with industrial CCD camera.
The detecting system based on machine vision drug blister package detection method, wherein described image processor
Including image pre-processing unit, image segmentation unit, the feature extraction unit for extracting characteristics of image, the classification for carrying out image classification
Unit and the image analysis of mechanism unit for carrying out image analysis；Described image analysis of mechanism unit is connect with control unit；It is described
Image pre-processing unit is connect with industrial CCD camera.
The detecting system based on machine vision drug blister package detection method, wherein the industrial CCD camera
By the principle of opto-electronic conversion it is digital signal by photoelectric signal transformation by the image information of acquisition, is then transferred to image and locates in advance
Manage unit.
Beneficial effects of the present invention：
One, by the way of forming artificial texture on laser transmitter projects to drug bubble-cap, effectively enhance the detected sun
The orderliness feature of energy silicon chip.
Two, it is calculated using image preprocessing used by the image pre-processing unit in drug blister package vision detection system
Method, including image smoothing, image gray-scale transformation, histogram equalization processing and modified medium filtering, to enhance image matter
Amount is laid a good foundation to improve detection reliability.
Three, by the way that lead screw and servo motor is arranged, during drug bubble-cap defects detection, industrial CCD camera is being adopted
The image process for collecting drug bubble-cap, according to the type of drug bubble-cap to be detected, host computer send the corresponding type of drug bubble-cap to
In PLC, screw rod transmission is driven by servo motor, camera is moved to corresponding position, is realized to different size drug blister pack
The Image Acquisition of dress, it is easy to use.
Four, using controlling screw rod transmission through servo motor, lead screw drives slide block movement again, to realize to various specifications drug
The Image Acquisition of bubble-cap, high degree of automation, accurate positioning.
Description of the drawings
Fig. 1 is the step block diagram of the present invention.
Fig. 2 is the structural schematic diagram of the present invention.
Fig. 3 is the functional block diagram of image processor.
Fig. 4 is the work flow diagram of the present invention.
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer and more explicit, develop simultaneously embodiment pair referring to the drawings
The present invention is further described.
As shown in Figure 1, the invention discloses one kind being based on machine vision drug blister package detection method comprising following
Step：
Step 1, Image Acquisition acquire image information using on laser transmitter projects to packaged bubble-cap；
Step 2, Image Information Processing, the enhancing of image, recovery, coding and greyscale transformation, using median filtering method to collecting
Image carries out the removal of noise；
Step 3, image segmentation（Object or boundary）, threshold values setting；
Step 4, Image edge tracking utilize Canny edge detection algorithms detection bubble-cap edge；
Step 5 extracts characteristics of image, carries out threshold value setting to the image of decomposition, threshold values extracts the characteristics of image of corresponding region；
Step 6, the color of extraction segmentation drug, position, size and shape；
Step 7, select tablet position, size, shape and surface defect size tolerance；
Step 8 stores standard form, tablet feature and tolerance；
Step 9, it is tagged to defect tablet and corresponding bubble-cap；
Step 10, data storage show corresponding inspection result simultaneously related defects information preservation in corresponding lane database
Face.
After the above method, compared with prior art, the present embodiment uses laser transmitter projects to method of the invention
Onto drug bubble-cap, to obtain corresponding image artificial texture, effectively enhancing is detected the orderliness feature of drug bubble-cap.Together
When, in the process for removing noise to image in addition to using median filtering method is improved, effectively reducing error, improving the reliable of detection
Property.
As shown in Fig. 2, the schematic device that detection method uses in the present invention comprising camera bellows 1, conveyer belt 2, industry
CCD camera 3 and laser emitter 4, the laser emitter 4 and industrial CCD camera 3 are separately mounted to the top of camera bellows 1, are used for
Image information is acquired, the drug 5 is placed on the conveyer belt transmission past, is collected the image of drug bubble-cap during transmission
Then the image information of acquisition is fed back to image processor, is handled by information；It is single that handling result is transferred to control again
Member is stored in into row label, and by testing result in corresponding database by control unit control executive device.
It is described based on machine vision drug blister package detection method, wherein acquire image information in the step 1
Mode is to obtain corresponding artificial texture, then acquire image by industrial CCD camera on laser transmitter projects to drug bubble-cap
Information.
Described is based on machine vision drug blister package detection method, wherein the industrial CCD camera passes through silk
Bar is connect with servo motor, and drives down conversion camera site in servo motor.
It is described based on machine vision drug blister package detection method, wherein the median filter method of the step 2
It is：To pending current pixel, a template is selected, which is its neighbouring several pixels composition, to the picture of template
Element is ascending to be ranked up, then the value of original pixel is substituted with the intermediate value of template.
It is described based on machine vision drug blister package detection method, wherein the template is weight coefficient matrix template,
Formula is：
；
g=median[(x-1,y-1)+f(x,y-1)+f(x+1,y-1)+f(x-1,y)+f(x,y)+f(x+1,y) +f(x-1,y+
1)+f(x,y+1)+f(x+1,y+1)]。
The present invention can inhibit image effect very well by this method, and the clear analysis degree of image is kept substantially, ensure that
The picture quality of acquisition.
In order to obtain ideal tablet image border, the present invention is using Canny operators to image edge processing；It is described
The step of Canny edge detection algorithms, is as follows：
The first step：Noise is eliminated in such a way that 2D gaussian filtering templates carry out convolution to carry out noise elimination；
Second step：The finite difference that the amplitude of calculating gradient and direction use single order local derviation carries out correlation computations,
The partial derivative in two directions of gradation of image is found using derivative operator (such as Prewitt operators, Sobel operators)
(Gx, Gy), and find out the size of gradient；；
Third walks：The direction of gradient is calculated using the result of second step；Further according to formula：；It obtains
Edge direction, so that it may the gradient direction at edge is broadly divided into following four direction：Horizontal, vertical, 45 degree and 135 degree of sides
To；Then the adjacent pixels in this pixel gradient direction are found according to the direction of gradient；
4th step：Edge is detected and connected with dual threashold value-based algorithm；Two threshold values are calculated using accumulative histogram.
It is described based on machine vision drug blister package detection method, wherein it is described Step 5: Step 6: Step 7:
Step 8 and step 10, which carry, to be realized by machine vision software Halcon.
Above-mentioned HALCON is the machine vision algorithm packet of a set of perfect standard of German MVtec companies exploitation, is possessed
Widely used machine vision Integrated Development Environment.It has saved product cost, shortens software development cycle -- HALCON spirits
Framework living is convenient for machine vision, the quick exploitation of medical image and image analysis application.In Europe and the industrial quarters of Japan
It has been to generally acknowledge the Machine Vision softwares with best efficiency.
A kind of detecting system based on machine vision drug blister package detection method comprising laser lighting light source is provided
Laser emitter, photoelectric sensor switch, ccd image sensor, image processor, control unit, transmission device, machinery positioning
Device and executive device；Described control unit respectively with transmission device, mechanical positioner, executive device, image processor, swash
Optical transmitting set, photoelectric sensor switch are connected with ccd image sensor；The executive device is connect with industrial CCD camera.
The detecting system based on machine vision drug blister package detection method, wherein described image processor
Including image pre-processing unit, image segmentation unit, the feature extraction unit for extracting characteristics of image, the classification for carrying out image classification
Unit and the image analysis of mechanism unit for carrying out image analysis；Described image analysis of mechanism unit is connect with control unit；It is described
Image pre-processing unit is connect with industrial CCD camera.
The detecting system based on machine vision drug blister package detection method, wherein the industrial CCD camera
By the principle of opto-electronic conversion it is digital signal by photoelectric signal transformation by the image information of acquisition, is then transferred to image and locates in advance
Manage unit.
As shown in figure 3, the basic function figure of the image processor in the present invention is disclosed, including image input, being used for will
Photoelectric signal transformation is at digital signal；Image preprocessing carries out image enhancement, coding, greyscale transformation and medium filtering；Image point
It cuts, is used for detection image boundary；Characteristics of image is extracted, image carries out classification and image analysis of mechanism.
As shown in figure 4, the present invention work flow diagram it is as follows, be first begin to, read read standard form, drug characteristic and
Tolerance；There is trigger signal when then looking at, if having, captures drug bubble-cap image to be detected, it is no, then it returns and whether touches
Alerting phase；Then image procossing and correction are carried out, then carries out image segmentation, extraction drug position, size, shape and face
Color；And carry out characteristic value comparison with standard form；After comparison, it was found that defective drug, stamps defective drug corresponding
Label；Ultimately produce the correspondence flaw indication of drug；Then judge whether to continue to detect, it is no, then terminate；It is touched if so, returning
Alerting phase.
Beneficial effects of the present invention：
One, by the way of forming artificial texture on laser transmitter projects to drug bubble-cap, effectively enhance the detected sun
The orderliness feature of energy silicon chip.
Two, it is calculated using image preprocessing used by the image pre-processing unit in drug blister package vision detection system
Method, including image smoothing, image gray-scale transformation, histogram equalization processing and modified medium filtering, to enhance image matter
Amount is laid a good foundation to improve detection reliability.
Three, by the way that lead screw and servo motor is arranged, during drug bubble-cap defects detection, industrial CCD camera is being adopted
The image process for collecting drug bubble-cap, according to the type of drug bubble-cap to be detected, host computer send the corresponding type of drug bubble-cap to
In PLC, screw rod transmission is driven by servo motor, camera is moved to corresponding position, is realized to different size drug blister pack
The Image Acquisition of dress, it is easy to use.
Four, using controlling screw rod transmission through servo motor, lead screw drives slide block movement again, to realize to various specifications drug
The Image Acquisition of bubble-cap, high degree of automation, accurate positioning.
It is manual operation the present invention overcomes the detection of traditional Key works Drug packing, detection result and efficiency rely primarily on identifier
Member, the defects such as artifical influence factor is big, omission factor is high, the degree of automation is low.Exist in addition, overcoming in pure artificial detection operation
Labor intensity greatly and ineffective technical problem.
It should be understood that the application of the present invention is not limited to the above for those of ordinary skills can
With improvement or transformation based on the above description, all these modifications and variations should all belong to the guarantor of appended claims of the present invention
Protect range.
Claims (10)
1. one kind being based on machine vision drug blister package detection method, which is characterized in that include the following steps：
Step 1, Image Acquisition acquire image information using on laser transmitter projects to packaged bubble-cap；
Step 2, Image Information Processing, the enhancing of image, recovery, coding and greyscale transformation, using median filtering method to collecting
Image carries out the removal of noise；
Step 3, image segmentation（Object or boundary）, threshold values setting；
Step 4, Image edge tracking utilize Canny edge detection algorithms detection bubble-cap edge；
Step 5 extracts characteristics of image, carries out threshold value setting to the image of decomposition, threshold values extracts the characteristics of image of corresponding region；
Step 6, the color of extraction segmentation drug, position, size and shape；
Step 7, select tablet position, size, shape and surface defect size tolerance；
Step 8 stores standard form, tablet feature and tolerance；
Step 9, it is tagged to defect tablet and corresponding bubble-cap；
Step 10, data storage show corresponding inspection result simultaneously related defects information preservation in corresponding lane database
Face.
2. according to claim 1 be based on machine vision drug blister package detection method, which is characterized in that the step
It is to obtain corresponding artificial texture, then pass through work on laser transmitter projects to drug bubble-cap that image information mode is acquired in one
Industry CCD camera acquires image information.
3. according to claim 2 be based on machine vision drug blister package detection method, which is characterized in that described
Industrial CCD camera is connect by lead screw with servo motor, and drives down conversion camera site in servo motor.
4. according to claim 1 be based on machine vision drug blister package detection method, which is characterized in that the step
Two median filter method is：To pending current pixel, it is its several neighbouring pixel to select a template, the template
Composition, it is ascending to the pixel of template to be ranked up, then the value of original pixel is substituted with the intermediate value of template.
5. according to right want described in 4 based on machine vision drug blister package detection method, which is characterized in that the template is
Weight coefficient matrix template, formula are：
；
g=median[(x-1,y-1)+f(x,y-1)+f(x+1,y-1)+f(x-1,y)+f(x,y)+f(x+1,y) +f(x-1,y+
1)+f(x,y+1)+f(x+1,y+1)]。
6. according to claim 1 be based on machine vision drug blister package detection method, which is characterized in that described
The step of Canny edge detection algorithms, is as follows：
The first step：Noise is eliminated in such a way that 2D gaussian filtering templates carry out convolution to carry out noise elimination；
Second step：The finite difference that the amplitude of calculating gradient and direction use single order local derviation carries out correlation computations,
The partial derivative in two directions of gradation of image is found using derivative operator (such as Prewitt operators, Sobel operators)
(Gx, Gy), and find out the size of gradient；；
Third walks：The direction of gradient is calculated using the result of second step；Further according to formula：；Side is obtained
Edge direction, so that it may the gradient direction at edge is broadly divided into following four direction：Horizontal, vertical, 45 degree and 135 degree of sides
To；Then the adjacent pixels in this pixel gradient direction are found according to the direction of gradient；
4th step：Edge is detected and connected with dual threashold value-based algorithm；Two threshold values are calculated using accumulative histogram.
7. according to claim 1 be based on machine vision drug blister package detection method, which is characterized in that the step
Five, Step 6: Step 7: step 8 and step 10, which carry, to be realized by machine vision software Halcon.
8. a kind of detection system based on machine vision drug blister package detection method as described in claim 1-7 any one
System, which is characterized in that laser emitter, photoelectric sensor switch, ccd image sensor, figure including providing laser lighting light source
As processor, control unit, transmission device, mechanical positioner and executive device；Described control unit respectively with transmission device,
Mechanical positioner, executive device, image processor, laser emitter, photoelectric sensor switch are connected with ccd image sensor；
The executive device is connect with industrial CCD camera.
9. the detecting system according to claim 8 based on machine vision drug blister package detection method, feature exist
In, described image processor include image pre-processing unit, image segmentation unit, the feature extraction unit for extracting characteristics of image,
It carries out the taxon of image classification and carries out the image analysis of mechanism unit of image analysis；Described image analysis of mechanism unit with
Control unit connects；Described image pretreatment unit is connect with industrial CCD camera.
10. the detecting system according to claim 1 based on machine vision drug blister package detection method, feature exist
In, photoelectric signal transformation is digital signal by the principle of opto-electronic conversion by the industrial CCD camera by the image information of acquisition,
It is then transferred to image pre-processing unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810107074.3A CN108344743A (en) | 2018-02-02 | 2018-02-02 | One kind being based on machine vision drug blister package defect inspection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810107074.3A CN108344743A (en) | 2018-02-02 | 2018-02-02 | One kind being based on machine vision drug blister package defect inspection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108344743A true CN108344743A (en) | 2018-07-31 |
Family
ID=62959904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810107074.3A Pending CN108344743A (en) | 2018-02-02 | 2018-02-02 | One kind being based on machine vision drug blister package defect inspection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108344743A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109406539A (en) * | 2018-11-28 | 2019-03-01 | 广州番禺职业技术学院 | A kind of transparent medicine bottle bottom buildup defect detecting system and method |
| CN109443255A (en) * | 2018-11-07 | 2019-03-08 | 中国建材检验认证集团股份有限公司 | The solar battery sheet area measuring instrument and measuring system |
| CN109884070A (en) * | 2019-03-08 | 2019-06-14 | 武汉大学 | A kind of aluminium aluminium blister package tablet defect inspection method based on machine vision |
| CN110018172A (en) * | 2019-04-25 | 2019-07-16 | 伟创力电子设备(深圳)有限公司 | Products detection system and method |
| CN110032946A (en) * | 2019-03-21 | 2019-07-19 | 西安交通大学 | A kind of aluminium based on machine vision/aluminium blister package tablet identification and localization method |
| CN110044910A (en) * | 2019-05-09 | 2019-07-23 | 河南大学 | A kind of automobile sets glass box components detection system and a detection method |
| CN111242177A (en) * | 2020-01-02 | 2020-06-05 | 天津瑟威兰斯科技有限公司 | Method, system and equipment for detecting medicine package based on convolutional neural network |
| CN111398308A (en) * | 2020-03-27 | 2020-07-10 | 上海健康医学院 | Automatic detection method and system for packaging quality of aluminum-plastic bubble caps of tablets and capsules |
| CN111562267A (en) * | 2020-05-29 | 2020-08-21 | 重庆施鲁逊智能科技有限公司 | Visual detection system for assembling automobile fuse box |
| CN111562260A (en) * | 2020-04-14 | 2020-08-21 | 江苏大学 | Lotus root mud hole detection method and device based on machine vision |
| CN111965187A (en) * | 2020-07-24 | 2020-11-20 | 杭州慧全科技有限公司 | Bubble-cap medicine image detection device and bubble-cap medicine detection method |
| CN112345534A (en) * | 2020-10-30 | 2021-02-09 | 上海电机学院 | Vision-based bubble plate particle defect detection method and system |
| CN113466233A (en) * | 2020-03-31 | 2021-10-01 | 北京配天技术有限公司 | Visual inspection method, visual inspection apparatus, and computer storage medium |
| CN113808108A (en) * | 2021-09-17 | 2021-12-17 | 太仓中科信息技术研究院 | Visual inspection method and system for defects of printed film |
| CN113984774A (en) * | 2021-10-28 | 2022-01-28 | 成都市度道科技有限公司 | Bubble-cap medicine detection method based on visual technology |
| CN115482234A (en) * | 2022-10-08 | 2022-12-16 | 浙江花园药业有限公司 | High-precision defect detection method and system for aluminum-plastic blister medicines |
| CN117664984A (en) * | 2023-12-01 | 2024-03-08 | 上海宝柏新材料股份有限公司 | Defect detection method, device, system and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110317907A1 (en) * | 2000-12-29 | 2011-12-29 | Cognex Corporation | Optimized Distribution of Machine Vision Processing |
| US20120243790A1 (en) * | 2011-03-22 | 2012-09-27 | Mitutoyo Corporation | Edge location measurement correction for coaxial light images |
| CN104614372A (en) * | 2015-01-20 | 2015-05-13 | 佛山职业技术学院 | Detection method of solar silicon wafer |
| CN105784711A (en) * | 2014-12-25 | 2016-07-20 | 锐视（厦门）科技有限公司 | Cod liver oil soft capsule appearance defect visual detection method and device |
| CN105891233A (en) * | 2016-05-26 | 2016-08-24 | 福州大学 | Intelligent detection system for surface defects of lens based on machine vision and implementation method of intelligent detection system |
| CN107525808A (en) * | 2017-07-27 | 2017-12-29 | 佛山市南海区广工大数控装备协同创新研究院 | Blister medication classification and the online visible detection method of defect on a kind of production line |
-
2018
- 2018-02-02 CN CN201810107074.3A patent/CN108344743A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110317907A1 (en) * | 2000-12-29 | 2011-12-29 | Cognex Corporation | Optimized Distribution of Machine Vision Processing |
| US20120243790A1 (en) * | 2011-03-22 | 2012-09-27 | Mitutoyo Corporation | Edge location measurement correction for coaxial light images |
| CN105784711A (en) * | 2014-12-25 | 2016-07-20 | 锐视（厦门）科技有限公司 | Cod liver oil soft capsule appearance defect visual detection method and device |
| CN104614372A (en) * | 2015-01-20 | 2015-05-13 | 佛山职业技术学院 | Detection method of solar silicon wafer |
| CN105891233A (en) * | 2016-05-26 | 2016-08-24 | 福州大学 | Intelligent detection system for surface defects of lens based on machine vision and implementation method of intelligent detection system |
| CN107525808A (en) * | 2017-07-27 | 2017-12-29 | 佛山市南海区广工大数控装备协同创新研究院 | Blister medication classification and the online visible detection method of defect on a kind of production line |
Non-Patent Citations (1)
| Title |
|---|
| 吴婉: "机器视觉中泡罩药品包装缺陷检测算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109443255A (en) * | 2018-11-07 | 2019-03-08 | 中国建材检验认证集团股份有限公司 | The solar battery sheet area measuring instrument and measuring system |
| CN109406539A (en) * | 2018-11-28 | 2019-03-01 | 广州番禺职业技术学院 | A kind of transparent medicine bottle bottom buildup defect detecting system and method |
| CN109406539B (en) * | 2018-11-28 | 2024-04-09 | 广州番禺职业技术学院 | Transparent medicine bottle bottom accumulated material defect detection system and method |
| CN109884070A (en) * | 2019-03-08 | 2019-06-14 | 武汉大学 | A kind of aluminium aluminium blister package tablet defect inspection method based on machine vision |
| CN110032946B (en) * | 2019-03-21 | 2021-02-12 | 西安交通大学 | Aluminum/aluminum blister packaging tablet identification and positioning method based on machine vision |
| CN110032946A (en) * | 2019-03-21 | 2019-07-19 | 西安交通大学 | A kind of aluminium based on machine vision/aluminium blister package tablet identification and localization method |
| CN110018172A (en) * | 2019-04-25 | 2019-07-16 | 伟创力电子设备(深圳)有限公司 | Products detection system and method |
| CN110018172B (en) * | 2019-04-25 | 2021-12-07 | 伟创力电子设备(深圳)有限公司 | Product detection system and method |
| CN110044910A (en) * | 2019-05-09 | 2019-07-23 | 河南大学 | A kind of automobile sets glass box components detection system and a detection method |
| CN110044910B (en) * | 2019-05-09 | 2024-02-13 | 河南大学 | Automobile cup box part detection system and detection method |
| CN111242177A (en) * | 2020-01-02 | 2020-06-05 | 天津瑟威兰斯科技有限公司 | Method, system and equipment for detecting medicine package based on convolutional neural network |
| CN111398308B (en) * | 2020-03-27 | 2023-01-17 | 上海健康医学院 | Automatic detection method and system for packaging quality of aluminum-plastic bubble caps of tablets and capsules |
| CN111398308A (en) * | 2020-03-27 | 2020-07-10 | 上海健康医学院 | Automatic detection method and system for packaging quality of aluminum-plastic bubble caps of tablets and capsules |
| CN113466233A (en) * | 2020-03-31 | 2021-10-01 | 北京配天技术有限公司 | Visual inspection method, visual inspection apparatus, and computer storage medium |
| CN111562260A (en) * | 2020-04-14 | 2020-08-21 | 江苏大学 | Lotus root mud hole detection method and device based on machine vision |
| CN111562267A (en) * | 2020-05-29 | 2020-08-21 | 重庆施鲁逊智能科技有限公司 | Visual detection system for assembling automobile fuse box |
| CN111965187A (en) * | 2020-07-24 | 2020-11-20 | 杭州慧全科技有限公司 | Bubble-cap medicine image detection device and bubble-cap medicine detection method |
| CN112345534A (en) * | 2020-10-30 | 2021-02-09 | 上海电机学院 | Vision-based bubble plate particle defect detection method and system |
| CN112345534B (en) * | 2020-10-30 | 2023-08-04 | 上海电机学院 | Defect detection method and system for particles in bubble plate based on vision |
| CN113808108A (en) * | 2021-09-17 | 2021-12-17 | 太仓中科信息技术研究院 | Visual inspection method and system for defects of printed film |
| CN113984774A (en) * | 2021-10-28 | 2022-01-28 | 成都市度道科技有限公司 | Bubble-cap medicine detection method based on visual technology |
| CN115482234A (en) * | 2022-10-08 | 2022-12-16 | 浙江花园药业有限公司 | High-precision defect detection method and system for aluminum-plastic blister medicines |
| CN115482234B (en) * | 2022-10-08 | 2023-09-15 | 浙江花园药业有限公司 | High-precision defect detection method and system for aluminum-plastic blister medicines |
| CN117664984A (en) * | 2023-12-01 | 2024-03-08 | 上海宝柏新材料股份有限公司 | Defect detection method, device, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108344743A (en) | One kind being based on machine vision drug blister package defect inspection method and system | |
| CN107203990B (en) | Label breakage detection method based on template matching and image quality evaluation | |
| CN109772733B (en) | Defect bamboo block detecting and sorting device and method based on vision | |
| CN106824806A (en) | The detecting system and detection method of the low module plastic gear based on machine vision | |
| CN102020036A (en) | Visual detection method for transparent paper defect of outer package of strip cigarette | |
| CN105865570A (en) | Machine vision-based glass bottle liquid level detection method | |
| CN110567976A (en) | mobile phone cover plate silk-screen defect detection device and detection method based on machine vision | |
| CN104056790A (en) | Intelligent potato sorting method and apparatus | |
| CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
| CN109978940B (en) | Visual measurement method for SAB safety airbag size | |
| CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
| CN108489394A (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device and method | |
| CN205732019U (en) | A kind of three quick testing machine of universal miscellaneous goods | |
| CN113251926B (en) | Method and device for measuring size of irregular object | |
| CN107301634A (en) | A kind of robot automatic sorting method and system | |
| CN104034638A (en) | Diamond wire particle online quality inspection method based on machine vision | |
| CN106780437B (en) | A kind of quick QFN chip plastic packaging image obtains and amplification method | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN104034637B (en) | Based on the online quality inspection device of diamond wire particle of machine vision | |
| CN114549504A (en) | Appearance quality detection method based on machine vision | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN102854195B (en) | Method for detecting defect coordinates on color filter | |
| CN208042989U (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device | |
| TW419634B (en) | Automatic detection system and method using bar code positioning | |
| CN107507130A (en) | A kind of quickly QFN chip pins image obtains and amplification method |
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: 20180731 |