CN105004323A - Machine vision-based pouring cup bottle cap rotation angle measuring and correcting method - Google Patents
Machine vision-based pouring cup bottle cap rotation angle measuring and correcting method Download PDFInfo
- Publication number
- CN105004323A CN105004323A CN201510386142.0A CN201510386142A CN105004323A CN 105004323 A CN105004323 A CN 105004323A CN 201510386142 A CN201510386142 A CN 201510386142A CN 105004323 A CN105004323 A CN 105004323A
- Authority
- CN
- China
- Prior art keywords
- area
- cap
- bottle cap
- connected domain
- blob
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000005484 gravity Effects 0.000 claims abstract description 13
- 238000004519 manufacturing process Methods 0.000 claims abstract description 12
- 230000007246 mechanism Effects 0.000 claims abstract description 10
- 238000005259 measurement Methods 0.000 claims description 11
- 238000002715 modification method Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000001154 acute effect Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000007639 printing Methods 0.000 claims description 3
- 101150014742 AGE1 gene Proteins 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000007648 laser printing Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000005693 optoelectronics Effects 0.000 description 4
- 238000005452 bending Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a machine vision-based pouring cup bottle cap rotation angle measuring and correcting method. According to the machine vision-based pouring cup bottle cap rotation angle measuring and correcting method, connected region searching and gravity center calculation are adopted to realize circular ring region of interest positioning based on pouring cup bottle cap image characteristics; characteristic strengthened regions in a concave and convex direction are obtained skillfully based on the characteristics of circular ring cut parts; effective calculation of the pouring cup bottle cap rotation angle is realized; the data of the pouring cup bottle cap rotation angle is send to a bottle rotating mechanism, and when bottle bodies are delivered to the bottle rotating mechanism, the bottle bodies are rotated accurately so as to ensure the uniformity of bottle body rotating angle in laser printing. The machine vision-based pouring cup bottle cap rotation angle measuring and correcting method is high in speed, and accuracy, is stable, and is capable of satisfying real-time on-line detection requirements of high speed production lines.
Description
Technical field
The present invention relates to a kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method.
Background technology
Laser Jet be usually used in date of manufacture of printed product, the shelf-life, batch etc., because it has the features such as contactless, high speed, be widely used on industrial manufacturing line.Such as, wait in the production line of cap like wine ancient ridge god and just used Laser Jet equipment, by the top of selling destination, the date of manufacture is printed on cap like wine, fast, conveniently.But, in actual production, because cap like wine container class is similar to wine glass-shaped, and cap like wine bottle cap is provided with symmetrical draw ring, in cap pressing process, lid can spin, and causes the rotational angle of different cap like wine different, Laser Jet then requires that the anglec of rotation of cap like wine is consistent, otherwise inconsistent by the trade mark angle that causes Laser Jet font and wine to cover, has a strong impact on the quality of trade mark.At present, conventional settling mode is the correcting mode of artificial visually examine rotary bottle cover, but this kind of artificial quantity of mode operation is many, the operation that do not rest for a long time easily causes high cycle fatigue, the duplication of labour is dull, the anglec of rotation cannot reach accurately consistent, therefore, technical bottleneck is brought, a kind of effective solution route of urgent searching to manufacturing enterprise.
Summary of the invention
The present invention proposes a kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method, the problem that when overcoming laser printing on prior art high speed production line, bottle rotation angle is inconsistent, the method of the invention effectively can calculate the anglec of rotation of cap like wine bottle cap, and angle is sent to Xuan Ping mechanism, when bottle arrive revolve bottle mechanism position time, bottle is accurately rotated, the coherence request of bottle rotation angle during guarantee laser printing.
Based on cap like wine bottle cap rotation angle measurement and the modification method of machine vision, comprise the following steps:
Step 1: gather the cap like wine bottle cap image be positioned in high-speed production lines, be denoted as Image0;
Step 2: binaryzation operation is carried out to bottle cap image Image0, obtains bianry image Image1;
Split from background image by cap like wine bottle cap, T1 is setting binarization segmentation threshold value, and Image0 (x, y) is the gray-scale value of (x, y) position pixel in image;
Step 3: carry out connected domain seek operations to bianry image Image1, finds out the connected domain Blob that area is maximum, and carries out holes filling to Blob;
[bottle cap of cap like wine contains draw ring, lettering, and complex contour, therefore, simple binaryzation operation cannot ensure that connected domain Blob is solid, and needs in the present invention to adopt gravity model appoach to carry out coarse positioning to bottle cap position, so, for ensureing the accuracy of the bottle cap centre of location, holes filling need be carried out.】
Step 4: the annulus area-of-interest RegionDiff of coarse positioning cap like wine bottle cap;
Step 4.1: adopt gravity model appoach to calculate the center O (x filling largest connected territory Blob
o, y
o), be the center of circle of bottle cap, M is Blob pixel sum, and calculates the radius R of Blob
blob;
Step 4.2: with O (x
o, y
o) be the center of circle, respectively with R1, R2 for radius draws border circular areas C1, C2;
R1∈(0.5R
Blob,0.6R
Blob),R2∈(0.35R
Blob,0.45R
Blob);
[wherein, the characteristic sum experimental result according to bottle cap entity obtains, and works as R1=0.56R
blob, R2=0.39R
blobtime, circle ring area segmentation effect is better.】
Step 4.3: by poor for two border circular areas, obtains annulus area-of-interest RegionDiff, RegionDiff=C1-C2;
[so far, annulus area-of-interest in cap like wine image is out divided, the characteristic of white imperfect annulus Ring0 in this region of subsequent process Main Analysis, and according to the bending direction of draw ring, select not capped border circular areas, calculate the vertical direction of bottle cap, i.e.+90 ° or-90 ° of directions; ]
Step 5: carry out binaryzation operation to annulus area-of-interest RegionDiff, obtains white annulus bianry image RegionDiff_Bin;
Wherein, G (x, y) for (x, y) position pixel gray-scale value in RegionDiff, T2 be the fixed threshold that white annulus and background can be separated;
Step 6: the operation of search connected domain is carried out to white annulus bianry image, obtains connected domain set B lobs2, calculate the size of each connected domain, from Blobs2, area is less than S
tconnected domain remove, obtain remain connected domain Blobs2_ring;
Wherein, S
tfor the connected domain area threshold of setting;
[object eliminates the interference of annulus periphery complex appearance, then in Blobs2 remaining connected domain Blobs2_ring all from the white annulus Ring0 in figure; ]
Step 7: cavity is carried out to Blobs2_ring and fills, obtain non-empty connected domain set B lobs2_fillup;
Step 8: asking or operating connected domains all in Blobs2_fillup, obtains high precision connected domain Blob3 interested;
Step 9: the minimum circumscribed circle Circle_out being calculated Blob3 by least square method, obtains center of circle O
c(x
0, y
0), radius is R
out;
Step 10: with O
c(x
0, y
0) be the center of circle, 0.85R
outfor radius, draw circular connected domain Circle_fit, and Blob3 and Circle_fit is poor, and accurately location annulus area-of-interest, obtains the annulus area-of-interest Segment that feature strengthens, Segment=Blob3-Circle_fit;
Wherein, 0.85R
outit is the preset parameter requiring acquisition according to concrete segmentation;
Step 11: according to area-method, strengthens from feature the first two region R finding area maximum area-of-interest
out1', R
outafter 2', the center of gravity both finding according to gravity model appoach is respectively O1 (x
1, y
1) ', O2 (x
2, y
2) ':
Step 12: according to two barycentric coordinates, calculates the inclined angle alpha through two-point defined line,
inclined angle alpha is the cap like wine anglec of rotation.
[this kind of method is simple, quick, good stability.Angle accuracy reaches 100%.】
Strengthen from feature the first two region R finding area maximum area-of-interest in described step 11
out1', R
out2' obtains according to following steps:
Step 1) from feature enhancing area-of-interest, extract connected domain;
Wherein, connected domain outer arc angle be the region at obtuse angle as draw ring overlay area, connected domain outer arc angle is that the region of acute angle is not as by draw ring overlay area;
Step 2) utilize feature to strengthen the annulus in area-of-interest inner circular successively with draw ring overlay area and not poor by draw ring overlay area, filter out two maximum connected domain R of area by area sort method
out1', R
out2'.
The mode of image acquisition is adopted to be trigger-type collection in described step 1.
[when cap like wine is close to optoelectronic switch, optoelectronic switch triggers industrial CCD collected by camera one two field picture at once; ]
Adopt high brightness diffuse reflection light source to carry out image acquisition, brightness range is 10000 ~ 20000lux.
[guarantee the high speed acquisition of image.】
The dome diffuse reflection light source of described light source to be radius be 6cm.
The anglec of rotation of cap like wine is sent to controller, controller sends angle modification instruction to Xuan Ping mechanism, when bottle arrive revolve bottle mechanism position time, the printed patterns on cap like wine bottle cap is accurately rotated, immediately below the printing images that Laser Jet is positioned on cap like wine bottle cap.
Beneficial effect
Compared with prior art, advantage applies of the present invention following some:
(1) present invention employs based on line of cut bending direction is the effective coverage determination methods of feature, by strengthening effective coverage, the method for decay inactive area, effectively measures the anglec of rotation of cap like wine, total algorithm is simple, efficient, 100% vertical direction detecting cap like wine;
(2) compared with the method for mating with conventional template, it is lower that the measuring method that the present invention proposes is disturbed degree, because draw ring template, font masters all affect comparatively large by bottle cap profile, environment, light source, matching degree is low, and fixed threshold cannot meet the demand of batch detection; And this method is hardly by the interference of above-mentioned factor, stability is better, and speed is faster;
(3) compared with existing manual method, this detection algorithm has the advantages such as accuracy of detection is high, speed is fast, reproducible, meets the detection of existing production line real-time online, reliable and stable demand.Artificial handmade rotary cannot accurate correct angle, causes that laser printing information is crooked to differ.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention;
Fig. 2 is application the method for the invention process cap like wine bottle cap image process schematic diagram, and wherein, (a) is cap like wine Bottle cap structure composition schematic diagram; B () is cap like wine feature extraction position schematic diagram; C () badly covers annular regions for drawing, block annulus schematic diagram; D () is cut into four area schematic for being truncated annulus; E () is for adopting inner circular cutting annulus schematic diagram; F () be rear image for feature strengthens; G () is cap like wine bottle cap anglec of rotation line correspondence;
Fig. 3 carries out makeover process schematic diagram for applying the method for the invention to example image, and wherein, (a) is original image to be revised; B () is the binary image of (a) figure; C () is the annulus area-of-interest extracted from (b); D () is the binary image of (c); E () carries out connected domain screening for adopting area-method to figure (d); F area image that () strengthens for feature;
G () is maximum two connected domains; H () is found 2 regional center points for gravity model appoach and is obtained anglec of rotation line correspondence; I () is for carrying out angle modification schematic diagram according to the anglec of rotation to (a).
Embodiment
Below in conjunction with drawings and Examples, the present invention is described further.
Camera employing resolution is face battle array kilomega network CCD camera (Baumer TXG12) of 1080*960 in this example, camera lens is 6mm wide viewing angle Computar camera lens, the dome diffuse reflection light source (LTS-FM12030-WQ) of light source to be radius be 6cm;
As shown in Figure 1, a kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method, comprise the following steps:
Step 1: gather the cap like wine bottle cap image be positioned in high-speed production lines, be denoted as Image0, as shown in Fig. 3 (a);
Step 2: binaryzation operation is carried out to bottle cap image Image0, obtains bianry image Image1, as shown in Fig. 3 (b);
Split from background image by cap like wine bottle cap, T1 is setting binarization segmentation threshold value, and Image0 (x, y) is the gray-scale value of (x, y) position pixel in image;
Step 3: carry out connected domain seek operations to bianry image Image1, finds out the connected domain Blob that area is maximum, and carries out holes filling to Blob;
[bottle cap of cap like wine contains draw ring, lettering, and complex contour, therefore, simple binaryzation operation cannot ensure that connected domain Blob is solid, and needs in the present invention to adopt gravity model appoach to carry out coarse positioning to bottle cap position, so, for ensureing the accuracy of the bottle cap centre of location, holes filling need be carried out.Need the position of extracting as shown in Fig. 2 (b); ]
Step 4: the annulus area-of-interest RegionDiff of coarse positioning cap like wine bottle cap, as shown in Fig. 3 (c);
Step 4.1: adopt gravity model appoach to calculate the center O (x filling largest connected territory Blob
o, y
o), be the center of circle of bottle cap, M is Blob pixel sum, and calculates the radius R of Blob
blob;
Step 4.2: with O (x
o, y
o) be the center of circle, respectively with R1, R2 for radius draws border circular areas C1, C2;
R1∈(0.5R
Blob,0.6R
Blob),R2∈(0.35R
Blob,0.45R
Blob);
[wherein, the characteristic sum experimental result according to bottle cap entity obtains, and works as R1=0.56R
blob, R2=0.39R
blobtime, circle ring area segmentation effect is better.】
Step 4.3: by poor for two border circular areas, obtains annulus area-of-interest RegionDiff, RegionDiff=C1-C2;
[wherein, in RegionDiff, contain the white annulus as shown in Fig. 2 (a).】
[so far, annulus area-of-interest in cap like wine image is out divided, the characteristic of white imperfect annulus Ring0 in this region of subsequent process Main Analysis, draw and badly cover annular regions, block annulus, as shown in Fig. 2 (c), and according to the bending direction of draw ring, select not capped border circular areas, calculate the vertical direction of bottle cap, i.e.+90 ° or-90 ° of directions; ]
Step 5: carry out binaryzation operation to annulus area-of-interest RegionDiff, obtains white annulus bianry image RegionDiff_Bin, as shown in Fig. 3 (d);
Wherein, G (x, y) for (x, y) position pixel gray-scale value in RegionDiff, T2 be the fixed threshold that white annulus and background can be separated;
Step 6: the operation of search connected domain is carried out to white annulus bianry image, obtains connected domain set B lobs2, calculate the size of each connected domain, from Blobs2, area is less than S
tconnected domain remove, obtain remain connected domain, as shown in Fig. 3 (e), Blobs2_ring;
Wherein, S
tfor the connected domain area threshold of setting;
[object eliminates the interference of annulus periphery complex appearance, then in Blobs2 remaining connected domain Blobs2_ring all from the white annulus Ring0 in figure; ]
Step 7: cavity is carried out to Blobs2_ring and fills, obtain non-empty connected domain set B lobs2_fillup;
Step 8: asking or operating connected domains all in Blobs2_fillup, obtains high precision connected domain Blob3 interested;
Step 9: the minimum circumscribed circle Circle_out being calculated Blob3 by least square method, obtains center of circle O
c(x
0, y
0), radius is R
out;
Step 10: with O
c(x
0, y
0) be the center of circle, 0.85R
outfor radius, draw circular connected domain Circle_fit, and Blob3 and Circle_fit is poor, accurate location annulus area-of-interest, obtains the annulus area-of-interest Segment that feature strengthens, as shown in Fig. 3 (f), Segment=Blob3-Circle_fit;
Wherein, 0.85R
outit is the preset parameter requiring acquisition according to concrete segmentation;
Step 11: according to area-method, strengthens from feature the first two region R finding area maximum area-of-interest
out1', R
outafter 2', as shown in Fig. 3 (g), the center of gravity both finding according to gravity model appoach is respectively O1 (x
1, y
1) ', O2 (x
2, y
2) ':
Step 12: according to two barycentric coordinates, calculates the inclined angle alpha through two-point defined line,
as shown in Fig. 3 (h), inclined angle alpha is the cap like wine anglec of rotation.
[this kind of method is simple, quick, good stability.Angle accuracy reaches 100%.】
Strengthen from feature the first two region R finding area maximum area-of-interest in described step 11
out1', R
out2' obtains according to following steps:
Step 1) from feature enhancing area-of-interest, extract connected domain;
Wherein, connected domain outer arc angle be the region at obtuse angle as draw ring overlay area, connected domain outer arc angle is that the region of acute angle is not as by draw ring overlay area;
Step 2) utilize feature to strengthen the annulus in area-of-interest inner circular successively with draw ring overlay area and not poor by draw ring overlay area, filter out two maximum connected domain R of area by area sort method
out1', R
out2'.
It is as follows that Enhanced feature extracts principle:
1. white Ring0 is drawn lid to cover by bilateral, and imaging region is divided into four parts, as shown in Fig. 2 (d), and coated region called after R
in, non-coated region called after R
out, and the anglec of rotation of cap like wine with through R
out1 and R
outthe straight line at 2 centers is consistent, therefore, as long as find out R
out1 and R
out2 regions.
2. still, R
out1, R
out2, R
in1, R
inthe size, the matching center of circle etc. of 2 four connected regions are more or less the same, and directly cannot tell R
out1, R
out2, for this reason, this invariant feature of outer arc angle that patent of the present invention mainly make use of cut zone is distinguished.Be specially: draw ring is for oval, therefore R
in1, R
in2 are covered by draw ring, and region outer arc angle is obtuse angle, and R
out1, R
out2 are not covered by draw ring, and outer arc angle is acute angle.
3. according to above-mentioned feature, and R is strengthened further
in1, R
in2 and R
out1, R
outdifferentiation yardstick between 2, the present invention is by R
in1, R
in2, R
out1, R
out2 is poor with fitting circle shown in such as Fig. 2 (e) respectively, obtains R as Suo Shi Fig. 2 (f)
in1', R
in2', R
out1', R
out2', wherein, R
in1, R
in2 outer arc angles are obtuse angle, therefore after area difference, comparatively large regions is eliminated, and retain comparatively zonule; Otherwise, R
out1, R
out2 smaller portions are eliminated, and retain comparatively large regions, like this, substantially increase R
in1, R
in2 and R
out1, R
outthe differentiation yardstick of 2, only needs the size according to connected domain, just can judge R
out1', R
out2';
The mode of image acquisition is adopted to be trigger-type collection in described step 1.
[when cap like wine is close to optoelectronic switch, optoelectronic switch triggers industrial CCD collected by camera one two field picture at once; ]
Adopt high brightness diffuse reflection light source to carry out image acquisition, brightness range is 10000 ~ 20000lux.
[guarantee the high speed acquisition of image.】
The anglec of rotation of cap like wine is sent to controller, controller sends angle modification instruction to Xuan Ping mechanism, when bottle arrive revolve bottle mechanism position time, printed patterns on cap like wine bottle cap is accurately rotated, immediately below the printing images making Laser Jet be positioned on cap like wine bottle cap, as shown in Fig. 3 (i).This kind of method is simple, quick, good stability.Angle accuracy reaches 100%.
Claims (6)
1., based on cap like wine bottle cap rotation angle measurement and the modification method of machine vision, it is characterized in that, comprise the following steps:
Step 1: gather the cap like wine bottle cap image be positioned in high-speed production lines, be denoted as Image0;
Step 2: binaryzation operation is carried out to bottle cap image Image0, obtains bianry image Image1;
Split from background image by cap like wine bottle cap, T1 is setting binarization segmentation threshold value, and Image0 (x, y) is the gray-scale value of (x, y) position pixel in image;
Step 3: connected domain seek operations is carried out to bianry image Im age1, finds out the connected domain Blob that area is maximum, and holes filling is carried out to Blob;
Step 4: the annulus area-of-interest Re gionDiff of coarse positioning cap like wine bottle cap;
Step 4.1: adopt gravity model appoach to calculate the center O (x filling largest connected territory Blob
o, y
o), be the center of circle of bottle cap, M is Blob pixel sum, and calculates the radius R of Blob
blob;
Step 4.2: with O (x
o, y
o) be the center of circle, respectively with R1, R2 for radius draws border circular areas C1, C2;
R1∈(0.5R
Blob,0.6R
Blob),R2∈(0.35R
Blob,0.45R
Blob);
Step 4.3: by poor for two border circular areas, obtains annulus area-of-interest Re gionDiff, Re gionDiff=C1-C2;
Step 5: carry out binaryzation operation to annulus area-of-interest Re gionDiff, obtains white annulus bianry image Re gionDiff_Bin;
Wherein, G (x, y) for (x, y) position pixel gray-scale value in Re gionDiff, T2 be the fixed threshold that white annulus and background can be separated;
Step 6: the operation of search connected domain is carried out to white annulus bianry image, obtains connected domain set B lobs2, calculate the size of each connected domain, from Blobs2, area is less than S
tconnected domain remove, obtain remain connected domain Blobs2_ring;
Wherein, S
tfor the connected domain area threshold of setting;
Step 7: cavity is carried out to Blobs2_ring and fills, obtain non-empty connected domain set B lobs2_fillup;
Step 8: asking or operating connected domains all in Blobs2_fillup, obtains high precision connected domain Blob3 interested;
Step 9: the minimum circumscribed circle Circle_out being calculated Blob3 by least square method, obtains center of circle O
c(x
0, y
0), radius is R
out;
Step 10: with O
c(x
0, y
0) be the center of circle, 0.85R
outfor radius, draw circular connected domain Circle_fit, and Blob3 and Circle_fit is poor, and accurately location annulus area-of-interest, obtains the annulus area-of-interest Segment that feature strengthens, Segment=Blob3-Circle_fit;
Wherein, 0.85R
outit is the preset parameter requiring acquisition according to concrete segmentation;
Step 11: according to area-method, strengthens from feature the first two region R finding area maximum area-of-interest
out1', R
outafter 2', the center of gravity both finding according to gravity model appoach is respectively O1 (x
1, y
1) ', O2 (x
2, y
2) ':
Step 12: according to two barycentric coordinates, calculates the inclined angle alpha through two-point defined line,
inclined angle alpha is the cap like wine anglec of rotation.
2. a kind of cap like wine bottle cap rotation angle measurement based on machine vision according to claim 1 and modification method, is characterized in that, strengthens the first two region R finding area maximum area-of-interest in described step 11 from feature
out1', R
out2' obtains according to following steps:
Step 1) from feature enhancing area-of-interest, extract connected domain;
Wherein, connected domain outer arc angle be the region at obtuse angle as draw ring overlay area, connected domain outer arc angle is that the region of acute angle is not as by draw ring overlay area;
Step 2) utilize feature to strengthen the annulus in area-of-interest inner circular successively with draw ring overlay area and not poor by draw ring overlay area, filter out two maximum connected domain R of area by area sort method
out1', R
out2'.
3. a kind of cap like wine bottle cap rotation angle measurement based on machine vision according to claim 2 and modification method, is characterized in that, adopts the mode of image acquisition to be trigger-type collection in described step 1.
4. a kind of cap like wine bottle cap rotation angle measurement based on machine vision according to claim 3 and modification method, is characterized in that, adopt high brightness diffuse reflection light source to carry out image acquisition, brightness range is 10000 ~ 20000lux.
5. a kind of cap like wine bottle cap rotation angle measurement based on machine vision according to claim 4 and modification method, is characterized in that, the dome diffuse reflection light source of described light source to be radius be 6cm.
6. a kind of cap like wine bottle cap rotation angle measurement based on machine vision according to any one of claim 1-5 and modification method, it is characterized in that, the anglec of rotation of cap like wine is sent to controller, controller sends angle modification instruction to Xuan Ping mechanism, when bottle arrive revolve bottle mechanism position time, printed patterns on cap like wine bottle cap is accurately rotated, immediately below the printing images that Laser Jet is positioned on cap like wine bottle cap.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510386142.0A CN105004323B (en) | 2015-07-03 | 2015-07-03 | A kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510386142.0A CN105004323B (en) | 2015-07-03 | 2015-07-03 | A kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105004323A true CN105004323A (en) | 2015-10-28 |
CN105004323B CN105004323B (en) | 2016-08-17 |
Family
ID=54377088
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510386142.0A Expired - Fee Related CN105004323B (en) | 2015-07-03 | 2015-07-03 | A kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105004323B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106097308A (en) * | 2016-05-31 | 2016-11-09 | 长沙理工大学 | A kind of New energy electric vehicle based on machine vision charging hole detection and localization method |
CN106886784A (en) * | 2017-02-16 | 2017-06-23 | 长沙理工大学 | A kind of modified joint sparse based on template renewal represents foreign matter tracking in big transfusion |
CN109532043A (en) * | 2018-12-07 | 2019-03-29 | 三峡大学 | Anti-fake tooth-like white wine lid smart group based on image recognition fills device and method |
CN114030856A (en) * | 2021-11-10 | 2022-02-11 | 佛山市三水飞马包装有限公司 | Automatic handle sleeving device based on visual identification and intelligent control method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100259608A1 (en) * | 2007-09-03 | 2010-10-14 | Antti Knuuttila | Recording machine vision system |
CN102945368A (en) * | 2012-10-17 | 2013-02-27 | 西安理工大学 | Method for positioning and identifying laser character of beer bottle cap |
CN103389121A (en) * | 2013-08-21 | 2013-11-13 | 成都实唯物联网科技有限公司 | Angle detection device and method based on machine vision |
CN103761534A (en) * | 2014-01-22 | 2014-04-30 | 哈尔滨工业大学 | Method for detecting vision localization of QFP element |
-
2015
- 2015-07-03 CN CN201510386142.0A patent/CN105004323B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100259608A1 (en) * | 2007-09-03 | 2010-10-14 | Antti Knuuttila | Recording machine vision system |
CN102945368A (en) * | 2012-10-17 | 2013-02-27 | 西安理工大学 | Method for positioning and identifying laser character of beer bottle cap |
CN103389121A (en) * | 2013-08-21 | 2013-11-13 | 成都实唯物联网科技有限公司 | Angle detection device and method based on machine vision |
CN103761534A (en) * | 2014-01-22 | 2014-04-30 | 哈尔滨工业大学 | Method for detecting vision localization of QFP element |
Non-Patent Citations (1)
Title |
---|
陈友安,关向东: "《基于视觉系统可旋转特定角度机械手的设计与实现》", 《机械制造》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106097308A (en) * | 2016-05-31 | 2016-11-09 | 长沙理工大学 | A kind of New energy electric vehicle based on machine vision charging hole detection and localization method |
CN106886784A (en) * | 2017-02-16 | 2017-06-23 | 长沙理工大学 | A kind of modified joint sparse based on template renewal represents foreign matter tracking in big transfusion |
CN109532043A (en) * | 2018-12-07 | 2019-03-29 | 三峡大学 | Anti-fake tooth-like white wine lid smart group based on image recognition fills device and method |
CN114030856A (en) * | 2021-11-10 | 2022-02-11 | 佛山市三水飞马包装有限公司 | Automatic handle sleeving device based on visual identification and intelligent control method |
CN114030856B (en) * | 2021-11-10 | 2023-12-22 | 佛山市三水飞马包装有限公司 | Automatic handle sleeving device based on visual recognition and intelligent control method |
Also Published As
Publication number | Publication date |
---|---|
CN105004323B (en) | 2016-08-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020248439A1 (en) | Crown cap surface defect online inspection method employing image processing | |
CN108827316B (en) | Mobile robot visual positioning method based on improved Apriltag | |
CN104897062B (en) | Visual measurement method and device for shape and position deviation of part non-coplanar parallel holes | |
CN105004323A (en) | Machine vision-based pouring cup bottle cap rotation angle measuring and correcting method | |
CN104167003B (en) | Method for fast registering remote-sensing image | |
CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
CN104050446B (en) | Meter pointer image identification method based on pointer width character | |
CN105678776B (en) | Weld image feature point extraction method based on laser vision sensor | |
CN109308700A (en) | A kind of visual identity defect inspection method based on printed matter character | |
CN105488503B (en) | A kind of non-coding circular ring shape mark point center of circle image coordinate detection method | |
CN106951905A (en) | Apple identification and localization method on a kind of tree based on TOF camera | |
CN110108712A (en) | Multifunctional visual sense defect detecting system | |
CN110651686B (en) | Tapping method and system based on tapping mechanical arm | |
CN113989379B (en) | Hub welding seam three-dimensional characteristic measuring device and method based on linear laser rotation scanning | |
CN101315338A (en) | Defect detecting system and method for glass product | |
CN115311294A (en) | Glass bottle body flaw identification and detection method based on image processing | |
CN109324061A (en) | A kind of burr detection device and method of lithium battery pole slice | |
CN114783010B (en) | Extraction method of interest region of palm print image | |
EP3916380A1 (en) | Method and machine for controlling a forming method | |
CN102818544A (en) | On-line measurement method for pitch circle center of automobile hub bolt hole and central eccentric distance of central hole | |
JP2015524059A (en) | Optical method for inspecting transparent or translucent containers with visible patterns | |
CN107133962A (en) | A kind of diamond saw blade extracting thermal crack method based on rim detection | |
CN106546185B (en) | A kind of profile quality determining method based on Machine Vision Detection | |
CN107169967A (en) | A kind of diamond saw blade crack detecting method based on image procossing | |
CN110503096A (en) | The bar section tagging scheme and character picture antidote of horizontal double-flag point |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160817 |