CN105004323B - A kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method - Google Patents
A kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method Download PDFInfo
- Publication number
- CN105004323B CN105004323B CN201510386142.0A CN201510386142A CN105004323B CN 105004323 B CN105004323 B CN 105004323B CN 201510386142 A CN201510386142 A CN 201510386142A CN 105004323 B CN105004323 B CN 105004323B
- Authority
- CN
- China
- Prior art keywords
- cap
- area
- bottle cap
- wine bottle
- connected domain
- 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
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 kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method, the method utilizes cap like wine bottle cap characteristics of image, by connective region search and the calculating of center of gravity, location annulus area-of-interest, feature based on the cut part of annulus cleverly, obtain the feature reinforced region of concave and convex direction, effectively calculate the anglec of rotation of cap like wine bottle cap, and angle is sent to Xuan Ping mechanism, when bottle arrives rotation bottle mechanism position, bottle is accurately rotated, it is ensured that the coherence request of bottle anglec of rotation during laser printing.This visible detection method at a high speed, accurately, stably, meets the real-time online detection demand 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 is usually used in the date of manufacture of printed product, shelf-life, batch etc., owing to it has contactless, at a high speed
Etc. feature, it is widely used on industry manufacturing line.Such as, just used in the production line of the cap like wine such as ancient ridge god and swashed
Light stamp equipment, will sell destination, date of manufacture and be printed upon the top of cap like wine, quickly, convenient.But, in actual production
In, owing to cap like wine container class is similar to wine glass-shaped, and cap like wine bottle cap is provided with the draw ring of symmetry, lid in cap pressing process
Can spin, the rotational angle causing different cap like wine is different, and Laser Jet then requires that the anglec of rotation of cap like wine is consistent,
Otherwise, by causing the inconsistent of Laser Jet font and the trade mark angle on wine lid, the quality of trade mark is had a strong impact on.At present, often
Settling mode be artificial range estimation the correcting mode of rotary bottle cover, but this kind of artificial quantity of mode operation is many, long-time
The operation that do not rests easily causes that high cycle fatigue, the duplication of labour is dull, the anglec of rotation is unable to reach the most consistent, therefore, gives raw
Produce enterprise and bring technical bottleneck, a kind of effective solution route of urgent searching.
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, overcomes existing
The problem that when having laser printing on technology high speed production line, the bottle anglec of rotation is inconsistent, the method for the invention can effectively be counted
Calculate the anglec of rotation of cap like wine bottle cap, and angle is sent to Xuan Ping mechanism, when bottle arrives rotation bottle mechanism position, bottle
Accurately rotated, it is ensured that the coherence request of bottle anglec of rotation during laser printing.
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 being positioned in high-speed production lines, be denoted as Image0;
Step 2: bottle cap image Image0 is carried out binarization operation, obtains bianry image Image1;
Being split from background image by cap like wine bottle cap, T1 is for setting binarization segmentation threshold value, and (x y) is Image0
(x, y) gray value of position pixel in image;
Step 3: bianry image Image1 carries out connected domain search operation, searches out connected domain Blob that area is maximum,
And Blob is carried out holes filling;
[bottle cap of cap like wine contains draw ring, lettering, and complex contour, and therefore, simple binarization operation cannot ensure even
Logical territory Blob is solid, and needs in the present invention to use gravity model appoach that bottle cap position is carried out coarse positioning, so, for ensureing bottle cap location
The accuracy at center, need to carry out holes filling.】
Step 4: the annulus area-of-interest RegionDiff of coarse positioning cap like wine bottle cap;
Step 4.1: use gravity model appoach to calculate the center O (x filling largest connected territory Blobo,yo), it is the circle of bottle cap
The heart, M is Blob pixel sum, and calculates the radius R of BlobBlob;
Step 4.2: with O (xo,yo) it is the center of circle, draw border circular areas C1, C2 with R1, R2 for radius respectively;
R1∈(0.5RBlob,0.6RBlob), R2 ∈ (0.35RBlob,0.45RBlob);
[wherein, feature and experimental result according to bottle cap entity obtain, and work as R1=0.56RBlob, R2=0.39RBlobTime,
Circle ring area segmentation effect is preferable.】
Step 4.3: by poor for two border circular areas, it is thus achieved that annulus area-of-interest RegionDiff, RegionDiff=C1-
C2;
[so far, the annulus area-of-interest in cap like wine image is the most divided out, this region of subsequent process Main Analysis
The characteristic of middle white imperfect annulus Ring0, and according to the bending direction of draw ring, select uncovered border circular areas, calculate
Go out the vertical direction of bottle cap, i.e.+90 ° or-90 ° of directions;】
Step 5: annulus area-of-interest RegionDiff is carried out binarization operation, obtains white annulus bianry image
RegionDiff_Bin;
Wherein, G (x, y) be in RegionDiff (x, y) position pixel gray value, T2 be can by white annulus
Fixed threshold separate with background;
Step 6: carry out searching connected domain operation to white annulus bianry image, obtain connected domain set Blobs2, calculate
Go out the size of each connected domain, by area less than S from Blobs2TConnected domain remove, obtain remain connected domain
Blobs2_ring;
Wherein, STFor the connected domain area threshold set;
[purpose is to eliminate the interference of annulus periphery complex appearance, then in Blobs2, remaining connected domain Blobs2_ring is equal
From the white annulus Ring0 in figure;】
Step 7: Blobs2_ring carries out cavity filling, obtains non-cavity connected domain set Blobs2_fillup;
Step 8: connected domains all in Blobs2_fillup are asked or operated, obtains high accuracy connected domain interested
Blob3;
Step 9: calculated the minimum circumscribed circle Circle_out of Blob3 by least square method, it is thus achieved that center of circle OC(x0,y0),
Radius is Rout;
Step 10: with OC(x0,y0) it is the center of circle, 0.85RoutFor radius, draw circular connected domain Circle_fit, and will
Blob3 Yu Circle_fit is poor, is accurately positioned annulus area-of-interest, obtains the annulus area-of-interest that feature strengthens
Segment, Segment=Blob3-Circle_fit;
Wherein, 0.85RoutIt it is the preset parameter requiring acquisition according to concrete segmentation;
Step 11: according to area-method, strengthen, from feature, the first two region finding area maximum area-of-interest
Rout1'、RoutAfter 2', the center of gravity finding both according to gravity model appoach is respectively O1 (x1,y1)'、O2(x2,y2) ':
Step 12: according to two barycentric coodinates, calculate the inclined angle alpha through two-point defined line,Incline
Bevel angle α is the cap like wine anglec of rotation.
[this kind of method is simple, quick, good stability.Angle accuracy reaches 100%.】
Described step 11 strengthens, from feature, the first two region R finding area maximum area-of-interestout1'、Rout2'
Obtain according to following steps:
Step 1) strengthen extraction connected domain area-of-interest from feature;
Wherein, connected domain outer arc angle be the region at obtuse angle as draw ring overlay area, connected domain outer arc angle is the district of acute angle
Territory is not as by draw ring overlay area;
Step 2) utilize feature strengthen the inner circular of annulus in area-of-interest successively with draw ring overlay area and not by
Draw ring overlay area is poor, filters out, by area sort method, two connected domains R that area is maximumout1'、Rout2'。
The mode using IMAQ in described step 1 is trigger-type collection.
[when cap like wine is close to optoelectronic switch, optoelectronic switch triggers industrial CCD collected by camera one two field picture at once;】
Using high brightness diffusing reflection light source to carry out IMAQ, brightness range is 10000~20000lux.
[guarantee the high speed acquisition of image.】
Described light source be radius be the dome diffusing reflection light source of 6cm.
Sending the anglec of rotation of cap like wine to controller, controller sends angle modification and instructs to Xuan Ping mechanism, works as bottle
When body arrives rotation bottle mechanism position, the printed patterns on cap like wine bottle cap is accurately rotated so that Laser Jet is positioned at cap like wine
Immediately below printing image on bottle cap.
Beneficial effect
Compared with prior art, advantages of the present invention be embodied in following some:
(1) present invention employs the effective coverage determination methods being characterized based on line of cut bending direction, had by enhancing
Effect region, the method for decay inactive area, effectively measure the anglec of rotation of cap like wine, total algorithm is simple, efficient, and 100%
Detect the vertical direction of cap like wine;
(2) compared with the method for conventional template coupling, it is lower, because drawing that the measuring method that the present invention proposes is disturbed degree
Ring template, font masters are all affected relatively big by bottle cap profile, environment, light source, and matching degree is low, and fixed threshold cannot meet batch inspection
The demand surveyed;And this method is little affected by the interference of above-mentioned factor, stability is more preferable, 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,
Meet the detection of existing production line real-time online, reliable and stable demand.Artificial handmade rotary cannot accurate correct angle, cause sharp
Light type information is crooked to differ.
Accompanying drawing explanation
Fig. 1 is the flow chart of the present invention;
Fig. 2 processes cap like wine bottle cap image process schematic diagram for application the method for the invention, and wherein, (a) is cap like wine
Bottle cap structure composition schematic diagram;B () is cap like wine feature extraction position schematic diagram;C (), for drawing bad covering annular regions, blocks annulus
Schematic diagram;D () is cut into four area schematic for being truncated annulus;E () is for using inner circular cutting annulus schematic diagram;
F () is characterized image after enhancing;G () is cap like wine bottle cap anglec of rotation line correspondence;
Fig. 3 is modified process schematic for application the method for the invention to example image, and wherein, (a) is for waiting to revise
Original image;B () is the binary image of (a) figure;C () is the annulus area-of-interest extracted from (b);D () is (c)
Binary image;E () carries out connected domain screening for using area-method to figure (d);F () is characterized the area image of enhancing;
G () is two maximum connected domains;H () is that gravity model appoach is found 2 regional center points to obtain the anglec of rotation corresponding straight
Line;I () is for carrying out angle modification schematic diagram according to the anglec of rotation to (a).
Detailed description of the invention
Below in conjunction with drawings and Examples, the present invention is described further.
Face battle array kilomega network CCD camera (Baumer TXG12) that camera uses resolution ratio to be 1080*960 in this example,
Camera lens is 6mm wide viewing angle Computar camera lens, light source be radius be dome diffusing reflection light source (LTS-FM12030-WQ) of 6cm;
As it is shown in figure 1, a kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method, including following
Step:
Step 1: gather the cap like wine bottle cap image being positioned in high-speed production lines, be denoted as Image0, as shown in Fig. 3 (a);
Step 2: bottle cap image Image0 is carried out binarization operation, obtains bianry image Image1, as shown in Fig. 3 (b);
Being split from background image by cap like wine bottle cap, T1 is for setting binarization segmentation threshold value, and (x y) is Image0
(x, y) gray value of position pixel in image;
Step 3: bianry image Image1 carries out connected domain search operation, searches out connected domain Blob that area is maximum,
And Blob is carried out holes filling;
[bottle cap of cap like wine contains draw ring, lettering, and complex contour, and therefore, simple binarization operation cannot ensure even
Logical territory Blob is solid, and needs in the present invention to use gravity model appoach that bottle cap position is carried out coarse positioning, so, for ensureing bottle cap location
The accuracy at center, need to carry out holes filling.Need the position such as Fig. 2 (b) extracted shown;】
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: use gravity model appoach to calculate the center O (x filling largest connected territory Blobo,yo), it is the circle of bottle cap
The heart, M is Blob pixel sum, and calculates the radius R of BlobBlob;
Step 4.2: with O (xo,yo) it is the center of circle, draw border circular areas C1, C2 with R1, R2 for radius respectively;
R1∈(0.5RBlob,0.6RBlob), R2 ∈ (0.35RBlob,0.45RBlob);
[wherein, feature and experimental result according to bottle cap entity obtain, and work as R1=0.56RBlob, R2=0.39RBlobTime,
Circle ring area segmentation effect is preferable.】
Step 4.3: by poor for two border circular areas, it is thus achieved that annulus area-of-interest RegionDiff, RegionDiff=C1-
C2;
[wherein, RegionDiff contains the white annulus as shown in Fig. 2 (a).】
[so far, the annulus area-of-interest in cap like wine image is the most divided out, this region of subsequent process Main Analysis
The characteristic of middle white imperfect annulus Ring0, draws bad covering annular regions, blocks annulus, as shown in Fig. 2 (c), and according to draw ring
Bending direction, selects uncovered border circular areas, calculates the vertical direction of bottle cap, i.e.+90 ° or-90 ° of directions;】
Step 5: annulus area-of-interest RegionDiff is carried out binarization operation, obtains white annulus bianry image
RegionDiff_Bin, as shown in Fig. 3 (d);
Wherein, G (x, y) be in RegionDiff (x, y) position pixel gray value, T2 be can by white annulus
Fixed threshold separate with background;
Step 6: carry out searching connected domain operation to white annulus bianry image, obtain connected domain set Blobs2, calculate
Go out the size of each connected domain, by area less than S from Blobs2TConnected domain remove, obtain remain connected domain, as figure
Shown in 3 (e), Blobs2_ring;
Wherein, STFor the connected domain area threshold set;
[purpose is to eliminate the interference of annulus periphery complex appearance, then in Blobs2, remaining connected domain Blobs2_ring is equal
From the white annulus Ring0 in figure;】
Step 7: Blobs2_ring carries out cavity filling, obtains non-cavity connected domain set Blobs2_fillup;
Step 8: connected domains all in Blobs2_fillup are asked or operated, obtains high accuracy connected domain interested
Blob3;
Step 9: calculated the minimum circumscribed circle Circle_out of Blob3 by least square method, it is thus achieved that center of circle OC(x0,y0),
Radius is Rout;
Step 10: with OC(x0,y0) it is the center of circle, 0.85RoutFor radius, draw circular connected domain Circle_fit, and will
Blob3 Yu Circle_fit is poor, is accurately positioned annulus area-of-interest, obtains the annulus area-of-interest that feature strengthens
Segment, as shown in Fig. 3 (f), Segment=Blob3-Circle_fit;
Wherein, 0.85RoutIt it is the preset parameter requiring acquisition according to concrete segmentation;
Step 11: according to area-method, strengthen, from feature, the first two region finding area maximum area-of-interest
Rout1'、RoutAfter 2', as shown in Fig. 3 (g), the center of gravity finding both according to gravity model appoach is respectively O1 (x1,y1)'、O2(x2,
y2) ':
Step 12: according to two barycentric coodinates, calculate 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%.】
Described step 11 strengthens, from feature, the first two region R finding area maximum area-of-interestout1'、Rout2'
Obtain according to following steps:
Step 1) strengthen extraction connected domain area-of-interest from feature;
Wherein, connected domain outer arc angle be the region at obtuse angle as draw ring overlay area, connected domain outer arc angle is the district of acute angle
Territory is not as by draw ring overlay area;
Step 2) utilize feature strengthen the inner circular of annulus in area-of-interest successively with draw ring overlay area and not by
Draw ring overlay area is poor, filters out, by area sort method, two connected domains R that area is maximumout1'、Rout2'。
It is as follows that Enhanced feature extracts principle:
1. white Ring0 is drawn coating lid by bilateral, and imaging region is divided into four parts, as shown in Fig. 2 (d), capped
The named R in regionin, the named R in uncovered regionout, and the anglec of rotation of cap like wine with through Rout1 and Rout2 centers straight
Line is consistent, therefore, as long as searching out Rout1 and Rout2 regions.
The most still, Rout1、Rout2、Rin1、RinThe size of 2 four connected regions, the matching center of circle etc. are more or less the same, nothing
Method directly tells Rout1、Rout2, to this end, patent of the present invention mainly make use of this invariant feature of outer arc angle of cut zone
Make a distinction.Particularly as follows: draw ring is oval, therefore Rin1、Rin2 are covered by draw ring, and region outer arc angle is obtuse angle, and Rout1、
Rout2 are not covered by draw ring, and outer arc angle is acute angle.
3. according to features described above, and R is further enhancedin1、Rin2 and Rout1、RoutDifferentiation yardstick between 2, the present invention will
Rin1、Rin2、Rout1、Rout2 is poor with fitting circle as shown in Fig. 2 (e) respectively, obtains R as shown in Fig. 2 (f)in1'、Rin2'、
Rout1'、Rout2', wherein, Rin1、Rin2 outer arc angles are obtuse angle, therefore after area difference, large area is eliminated, and retain less
Region;Otherwise, Rout1、Rout2 smaller portions are eliminated, and retain large area, so, substantially increase Rin1、Rin2 and Rout1、
RoutThe differentiation yardstick of 2, it is only necessary to according to the size of connected domain, just may determine that Rout1'、Rout2';
The mode using IMAQ in described step 1 is trigger-type collection.
[when cap like wine is close to optoelectronic switch, optoelectronic switch triggers industrial CCD collected by camera one two field picture at once;】
Using high brightness diffusing reflection light source to carry out IMAQ, brightness range is 10000~20000lux.
[guarantee the high speed acquisition of image.】
Sending the anglec of rotation of cap like wine to controller, controller sends angle modification and instructs to Xuan Ping mechanism, works as bottle
When body arrives rotation bottle mechanism position, the printed patterns on cap like wine bottle cap is accurately rotated so that Laser Jet is positioned at cap like wine
Immediately below printing image on bottle cap, as shown in Fig. 3 (i).This kind of method is simple, quick, good stability.Angle accuracy reaches
100%.
Claims (6)
1. a cap like wine bottle cap rotation angle measurement based on machine vision and modification method, it is characterised in that include following
Step:
Step 1: gather the cap like wine bottle cap image being positioned in high-speed production lines, be denoted as Image0;
Step 2: bottle cap image Image0 is carried out binarization operation, obtains bianry image Image1;
Being split from background image by cap like wine bottle cap, T1 is for setting binarization segmentation threshold value, and (x y) is image to Image0
In (x, y) gray value of position pixel;
Step 3: bianry image Image1 carries out connected domain search operation, searches out connected domain Blob that area is maximum, and right
Blob carries out holes filling;
Step 4: the annulus area-of-interest RegionDiff of coarse positioning cap like wine bottle cap;
Step 4.1: use gravity model appoach to calculate the center O (x filling largest connected territory Blobo,yo), it is the center of circle of bottle cap, M
Total for Blob pixel, and calculate the radius R of BlobBlob;
Step 4.2: with O (xo,yo) it is the center of circle, draw border circular areas C1, C2 with R1, R2 for radius respectively;
R1∈(0.5RBlob,0.6RBlob), R2 ∈ (0.35RBlob,0.45RBlob);
Step 4.3: by poor for two border circular areas, it is thus achieved that annulus area-of-interest RegionDiff, RegionDiff=C1-C2;
Step 5: annulus area-of-interest RegionDiff is carried out binarization operation, obtains white annulus bianry image
RegionDiff_Bin;
Wherein, G (x, y) be in RegionDiff (x, y) position pixel gray value, T2 is can be by white annulus and the back of the body
The separate fixed threshold of scape;
Step 6: carry out searching connected domain operation to white annulus bianry image, obtain connected domain set Blobs2, calculate every
The size of individual connected domain, by area less than S from Blobs2TConnected domain remove, obtain remain connected domain Blobs2_
ring;
Wherein, STFor the connected domain area threshold set;
Step 7: Blobs2_ring carries out cavity filling, obtains non-cavity connected domain set Blobs2_fillup;
Step 8: connected domains all in Blobs2_fillup are asked or operated, obtains high accuracy connected domain Blob3 interested;
Step 9: calculated the minimum circumscribed circle Circle_out of Blob3 by least square method, it is thus achieved that center of circle OC(x0,y0), radius
For Rout;
Step 10: with OC(x0,y0) it is the center of circle, 0.85RoutFor radius, draw circular connected domain Circle_fit, and by Blob3
Poor with Circle_fit, it is accurately positioned annulus area-of-interest, obtains the annulus area-of-interest Segment that feature strengthens,
Segment=Blob3-Circle_fit;
Wherein, 0.85RoutIt it is the preset parameter requiring acquisition according to concrete segmentation;
Step 11: according to area-method, strengthen, from feature, the first two region R finding area maximum area-of-interestout1'、
RoutAfter 2', the center of gravity finding both according to gravity model appoach is respectively O1 (x1,y1)'、O2(x2,y2) ':
Step 12: according to two barycentric coodinates, calculate the inclined angle alpha through two-point defined line,Inclined angle alpha
It is the cap like wine bottle cap anglec of rotation.
A kind of cap like wine bottle cap rotation angle measurement based on machine vision the most according to claim 1 and modification method,
It is characterized in that, described step 11 strengthens, from feature, the first two region R finding area maximum area-of-interestout1'、
Rout2' obtains according to following steps:
Step 1) strengthen extraction connected domain area-of-interest from feature;
Wherein, connected domain outer arc angle be the region at obtuse angle as draw ring overlay area, connected domain outer arc angle be acute angle region make
For not by draw ring overlay area;
Step 2) utilize feature strengthen the inner circular of annulus in area-of-interest successively with draw ring overlay area and not by draw ring
Overlay area is poor, filters out, by area sort method, two connected domains R that area is maximumout1'、Rout2'。
A kind of cap like wine bottle cap rotation angle measurement based on machine vision the most according to claim 2 and modification method,
It is characterized in that, the mode using IMAQ in described step 1 is trigger-type collection.
A kind of cap like wine bottle cap rotation angle measurement based on machine vision the most according to claim 3 and modification method,
It is characterized in that, using high brightness diffusing reflection light source to carry out IMAQ, brightness range is 10000~20000lux.
A kind of cap like wine bottle cap rotation angle measurement based on machine vision the most according to claim 4 and modification method,
It is characterized in that, described light source be radius be the dome diffusing reflection light source of 6cm.
6. according to a kind of based on machine vision the cap like wine bottle cap rotation angle measurement described in any one of claim 1-5 with repair
Correction method, it is characterised in that send the anglec of rotation of cap like wine bottle cap to controller, controller sends angle modification and instructs extremely
Xuan Ping mechanism, when bottle arrives rotation bottle mechanism position, the printed patterns on cap like wine bottle cap is accurately rotated so that laser is beaten
Immediately below code bit printing image 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 CN105004323A (en) | 2015-10-28 |
CN105004323B true CN105004323B (en) | 2016-08-17 |
Family
ID=54377088
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510386142.0A Active 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) |
Families Citing this family (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 |
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 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FI123049B (en) * | 2007-09-03 | 2012-10-15 | Mapvision Ltd Oy | Recording Machine Vision System |
-
2015
- 2015-07-03 CN CN201510386142.0A patent/CN105004323B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
---|
《基于视觉系统可旋转特定角度机械手的设计与实现》;陈友安,关向东;《机械制造》;20121130;第50卷(第579期);25-26页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105004323A (en) | 2015-10-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105004323B (en) | A kind of cap like wine bottle cap rotation angle measurement based on machine vision and modification method | |
WO2020248439A1 (en) | Crown cap surface defect online inspection method employing image processing | |
CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
CN107180416B (en) | Train wheel tread image deformity correction method and system | |
CN105678776B (en) | Weld image feature point extraction method based on laser vision sensor | |
CN101105459A (en) | Empty bottle mouth defect inspection method and device | |
CN101799434A (en) | Printing image defect detection method | |
CN103020970A (en) | Corn ear image grain segmentation method | |
CN111598083A (en) | Method for detecting quality of spray printing and code spraying on bottle bottom mold closing line | |
CN106096606B (en) | A kind of container profile localization method based on straight line fitting | |
CN104458748A (en) | Aluminum profile surface defect detecting method based on machine vision | |
CN107895372A (en) | A kind of adhesive tape skeleton line automatic teaching method and system for robot coating detection | |
CN111862055B (en) | Bubble turning cavity defect detection method based on image processing | |
CN107607540A (en) | A kind of T-shirt on-line checking and method for separating based on machine vision | |
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 | |
CN114783010B (en) | Extraction method of interest region of palm print image | |
CN104897671A (en) | Identification system for fruit stem and calyx of fruit | |
CN104966302B (en) | A kind of detection localization method of any angle laser cross | |
CN114387269B (en) | Fiber yarn defect detection method based on laser | |
CN111426693A (en) | Quality defect detection system and detection method thereof | |
CN106767425B (en) | A kind of vision measuring method of bearing snap spring gap | |
CN114022441A (en) | Defect detection method for irregular hardware | |
CN109945842A (en) | Bundled round steel end face label missing detection and labeling error analysis method | |
JP2006506622A (en) | Automated inspection of colored ophthalmic parts |
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 |