CN105000411A - Bobbin surplus detecting method based on machine vision technology - Google Patents
Bobbin surplus detecting method based on machine vision technology Download PDFInfo
- Publication number
- CN105000411A CN105000411A CN201510418902.1A CN201510418902A CN105000411A CN 105000411 A CN105000411 A CN 105000411A CN 201510418902 A CN201510418902 A CN 201510418902A CN 105000411 A CN105000411 A CN 105000411A
- Authority
- CN
- China
- Prior art keywords
- obbbin
- imageing sensor
- vertical projection
- surplus
- bobbin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H26/00—Warning or safety devices, e.g. automatic fault detectors, stop-motions, for web-advancing mechanisms
- B65H26/06—Warning or safety devices, e.g. automatic fault detectors, stop-motions, for web-advancing mechanisms responsive to predetermined lengths of webs
-
- A—HUMAN NECESSITIES
- A24—TOBACCO; CIGARS; CIGARETTES; SIMULATED SMOKING DEVICES; SMOKERS' REQUISITES
- A24C—MACHINES FOR MAKING CIGARS OR CIGARETTES
- A24C5/00—Making cigarettes; Making tipping materials for, or attaching filters or mouthpieces to, cigars or cigarettes
Landscapes
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a bobbin surplus detecting method based on the machine vision technology. Residual bobbin side face (thickness) images are collected through an image sensor and transmitted to a computer. The computer processes the side face images through the image processing technology and judges the surplus, and when the set value is reached, a switching signal is sent to a winding and connecting unit. The bobbin surplus can be controlled to be very low, and waste caused by the original excessive surplus is avoided; the bobbin surplus detecting method can be suitable for scrolls with different diameters and bobbins with different thicknesses, and wide application space is achieved.
Description
Technical field
The present invention relates to cigarette rolling up and connecting machine obbbin method of inspection field, specifically a kind of obbbin excess detection method based on machine vision technique.
Background technology
Cigarette cigarette making and tipping machine has two pallets to fix obbbin, and in the process that cigarette cigarette is produced, unit was switched to another dish to keep the continuity of producing before current obbbin is finished.The principle of current detection obbbin surplus is as follows: obbbin tray edge has equidistant detent projection, detent projection is detected by proximity switch, obbbin often turns around, proximity switch can produce the pulse of fixed qty, generally this pulse sum (namely obbbin rotation number of total coils) is set at machine primary controller, system utilizes proximity switch to detect the number of total coils of obbbin rotation, has arrived the laggard row obbbin of pre-fixing turn and has switched.Because Fu Cai provider does not strictly control the overall length of obbbin, also difference is comparatively large for the diameter of spool in addition, and therefore the number of total coils of every bobbin paper is also different.In order to avoid the setting number of turns not then obbbin be just finished and caused shutdown, operating personal is generally all arranged on tens circles obbbin surplus.So each remaining bobbin length often has tens meters to tens meters, accumulates over a long period and can cause very large waste.
At home and abroad in tobacco business, the application of machine vision technique is more and more extensive, is mainly used in the foreign body detecting etc. in packet appearance quality testing, barrel appearance quality detection and Primary Processing.Along with the continuous maturation of machine vision technique, machine vision technique can be adopted to detect the surplus of obbbin.
Summary of the invention
The object of this invention is to provide a kind of obbbin excess detection method based on machine vision technique, to detect cigarette rolling up and connecting machine obbbin surplus.
In order to achieve the above object, the technical solution adopted in the present invention is:
A kind of obbbin excess detection method based on machine vision technique, it is characterized in that: adopt imageing sensor to coordinate strip source to gather obbbin side image in cigarette rolling up and connecting machine, described imageing sensor just can represent the side of thickness to obbbin, the optical lens of imageing sensor is perpendicular to obbbin side, strip source is symmetricly set on imageing sensor both sides, and strip source emergent light direction to tilt miter angle respectively relative to imageing sensor optical lens direction, the obbbin side image collected is sent to computing machine by imageing sensor, in a computer successively filtering is carried out to the obbbin side image that imageing sensor collects, gray processing, after dividing processing, again vertical projection is carried out to the image after segmentation, then method of finite difference is adopted in vertical projection, to search search obbbin both sides of the edge and calculate obbbin width pixel count, average again after the obbbin width pixel count finally calculated method of finite difference carries out quadratic fit, obtain obbbin width pixel count more accurately, thus obtain obbbin surplus.
Described a kind of obbbin excess detection method based on machine vision technique, it is characterized in that: during dividing processing, adopt the method for local sampling, Iamge Segmentation after gray processing is become many fritters, in each fritter, the crooked radian of obbbin is ignored, can regard as straight, then respectively to each fritter vertical projection, then adopt method of finite difference in vertical projection, search search obbbin both sides of the edge and calculate obbbin width pixel count.
The invention has the beneficial effects as follows:
The obbbin excess detection method that the present invention proposes is compared with current method of inspection, and accuracy of detection improves greatly, and the length of residue obbbin can be accurate to each circle, avoids the waste in the past remaining tens circles.And adopt the method for vision-based detection can adapt to the spool of different-diameter and the obbbin of different-thickness, have a wide range of applications space.
Accompanying drawing explanation
Fig. 1 is imageing sensor of the present invention and light source setting angle figure.
Fig. 2 is the original image that imageing sensor gathers.
Fig. 3 is filtered image.
Fig. 4 is the image after gray scale.
Fig. 5 is that original image compares with filtered image vertical projection, wherein:
Fig. 5 a is original image, and Fig. 5 b is filtered image.
Fig. 6 is region-of-interest vertical projection diagram, wherein:
Fig. 6 a is the 8th region-of-interest vertical projection diagram, and Fig. 6 b is the 14th region-of-interest vertical projection diagram.
Fig. 7 is region-of-interest vertical projection difference curves figure, wherein:
Fig. 7 a is the 8th region-of-interest vertical projection difference curves figure,
Fig. 7 b is the 14th region-of-interest vertical projection difference curves figure.
Detailed description of the invention
A kind of obbbin excess detection method based on machine vision technique, imageing sensor is adopted to coordinate strip source to gather obbbin side image in cigarette rolling up and connecting machine, imageing sensor just can represent the side of thickness to obbbin, the optical lens of imageing sensor is perpendicular to obbbin side, strip source is symmetricly set on imageing sensor both sides, and strip source emergent light direction to tilt miter angle respectively relative to imageing sensor optical lens direction, the obbbin side image collected is sent to computing machine by imageing sensor, in a computer successively filtering is carried out to the obbbin side image that imageing sensor collects, gray processing, after dividing processing, again vertical projection is carried out to the image after segmentation, then method of finite difference is adopted in vertical projection, to search search obbbin both sides of the edge and calculate obbbin width pixel count, average again after the obbbin width pixel count finally calculated method of finite difference carries out quadratic fit, obtain obbbin width pixel count more accurately, thus obtain obbbin surplus.
During dividing processing, adopt the method for local sampling, Iamge Segmentation after gray processing is become many fritters, in each fritter, the crooked radian of obbbin is ignored, can regard as straight, then respectively to each fritter vertical projection, method of finite difference is then adopted in vertical projection, to search search obbbin both sides of the edge and calculate obbbin width pixel count.
The setting angle of imageing sensor and light source as shown in Figure 1, imageing sensor is just installed the side of obbbin, optical lens and obbbin lateral vertical, the direct picture of what imageing sensor photographed is obbbin side, middle white obbbin and the dark-background of both sides form sharp contrast.Two strip sources are loaded on imageing sensor both sides, and tilt about 45 degree, the irradiating angle of light source is fine-tuning, and this lighting system had not only ensured that being illuminated by obbbin but also avoid obbbin reflected light rays to enter camera lens affected image quality.
Fig. 2 is the original image that imageing sensor collects, noise is had because the factors such as external context cause on the image gathering and, after vertical projection, image is understood some little burr, as shown in Fig. 5 (a), although these little burrs are not obvious, when segmenting the image into many fritters, these little burrs can cause interference to query search obbbin edge after projection, so adopt mean filter first to carry out filtering to original image, remove these little noises.Fig. 3 is the filtered image adopting mean filter method to obtain.Fig. 5 (b) is the vertical projection of filtered image, can see, after filtering, curve is obvious much smooth, and the impact of little burr has diminished.Fig. 4 is to result after filtered image gray processing.Gray processing is that the coloured image in order to be photographed by imageing sensor is converted to gray level image, if employing is black and white image sensor, does not need to carry out gray processing process.
Because the image of obbbin has certain radian, the obbbin width error that the direct edge adopting the method for projection to search obbbin obtains can be larger, the present invention adopts the mode of local sampling, Iamge Segmentation after gray processing is become many fritters, in each fritter, the crooked radian of obbbin is ignored, and can regard as vertical.Then to each fritter vertical projection, search obbbin edge by method of finite difference and obtain obbbin width, then quadratic fit is carried out to obbbin width data, average, obtain obbbin width accurately.Concrete steps are as follows:
1. choose k region-of-interest in the image after gray processing, the width of each region-of-interest is the width of image, is highly n pixel.The mode chosen is for from top to bottom, and the height every n pixel gets a region-of-interest.N value is less, and the result obtained is more accurate, and computational processing is also larger simultaneously, can select suitable n value according to demand.
2. carry out vertical projection respectively to the image of this k region-of-interest, computing formula is as follows:
Wherein P
m[j] is the drop shadow curve of m region-of-interest, Q
m(i, j) be m region-of-interest gray level image on the i-th row, jth row pixel gray value, width is the width of gray level image, can obtain k One Dimensional Projection array like this.Shown in Fig. 6 (a) He (b) is Liang Ge region-of-interest drop shadow curve wherein.
3. in the drop shadow curve of region-of-interest, have obbbin and the regional luminance without obbbin widely different, as shown in Figure 6, centre has obbbin regional luminance very high, searches they made a distinction by method of finite difference.By one-dimension array P
mdifference function S can be obtained with itself subtracting each other in [j] after data shift right two
m[j], shown in institute Fig. 7, figure (a) and (b) are the difference curves corresponding to Tu6Zhong Liangge region-of-interest drop shadow curve, can see, can form an obvious precipitous crest and trough at obbbin left and right edges place.To difference function S
m[j] searches, and records S
mj value X when [j] maxim and minimum value
r[m] and X
l[m], computing formula is as follows:
The left hand edge position X of k group obbbin can be obtained
l(m) and right hand edge position X
r(m).Then the right hand edge position of each region-of-interest is deducted its left hand edge position and can obtain obbbin width Y [m].
4. pair k group obbbin width data Y [m] quadratic fit: ask Y [m] aviation value, itself and Y [m] are compared, remove the data that difference is greater than c, obtain new data M (x), again M (x) is averaged, can obtain obbbin width data Ave accurately, computing formula is as follows:
In this example, obbbin thickness is about 0.04mm, and the imageing sensor of employing respectively rate is 1280*960.
Get the obbbin width data that k=20, n=18 calculate by above-mentioned steps as shown in table 1.After quadratic fit, obbbin width is 131 pixels, and now the obbbin number of turns is 42 circles, then the pixel of often enclosing is about 3, and the length of residue obbbin can be accurate to each circle, and compared with current method of inspection, accuracy of detection improves greatly.If detect the obbbin that thickness is less, more high-resolution imageing sensor can be adopted.
Table 1 is that after choosing 20 region-of-interests, vertical projection searches the obbbin left and right sides boundary position obtained
Claims (2)
1. the obbbin excess detection method based on machine vision technique, it is characterized in that: adopt imageing sensor to coordinate strip source to gather obbbin side image in cigarette rolling up and connecting machine, described imageing sensor just can represent the side of thickness to obbbin, the optical lens of imageing sensor is perpendicular to obbbin side, strip source is symmetricly set on imageing sensor both sides, and strip source emergent light direction to tilt miter angle respectively relative to imageing sensor optical lens direction, the obbbin side image collected is sent to computing machine by imageing sensor, in a computer successively filtering is carried out to the obbbin side image that imageing sensor collects, gray processing, after dividing processing, again vertical projection is carried out to the image after segmentation, then method of finite difference is adopted in vertical projection, to search search obbbin both sides of the edge and calculate obbbin width pixel count, average again after the obbbin width pixel count finally calculated method of finite difference carries out quadratic fit, obtain obbbin width pixel count more accurately, thus obtain obbbin surplus.
2. a kind of obbbin excess detection method based on machine vision technique according to claim 1, it is characterized in that: during dividing processing, adopt the method for local sampling, Iamge Segmentation after gray processing is become many fritters, in each fritter, the crooked radian of obbbin is ignored, can regard as straight, then respectively to each fritter vertical projection, then adopt method of finite difference in vertical projection, search search obbbin both sides of the edge and calculate obbbin width pixel count.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510418902.1A CN105000411B (en) | 2015-07-14 | 2015-07-14 | A kind of obbbin excess detection method based on machine vision technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510418902.1A CN105000411B (en) | 2015-07-14 | 2015-07-14 | A kind of obbbin excess detection method based on machine vision technique |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105000411A true CN105000411A (en) | 2015-10-28 |
| CN105000411B CN105000411B (en) | 2018-11-16 |
Family
ID=54373338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510418902.1A Active CN105000411B (en) | 2015-07-14 | 2015-07-14 | A kind of obbbin excess detection method based on machine vision technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105000411B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056617A (en) * | 2016-05-31 | 2016-10-26 | 中国电子科技集团公司第四十研究所 | Cigarette carton sealing machine hot melt adhesive detection method |
| CN107218929A (en) * | 2017-04-18 | 2017-09-29 | 中国电子科技集团公司第四十研究所 | A kind of cork paper flanging detection method based on machine vision technique |
| CN107444712A (en) * | 2017-08-30 | 2017-12-08 | 红云红河烟草(集团)有限责任公司 | Device and method for detecting surplus of small box aluminum foil paper of packaging machine |
| CN110834981A (en) * | 2019-11-21 | 2020-02-25 | 成都忠信机电技术有限公司 | Bobbin paper splicing method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090086217A1 (en) * | 2007-09-27 | 2009-04-02 | Kabushiki Kaisha Toshiba | Sheet thickness measuring device and image forming apparatus |
| CN101503123A (en) * | 2009-02-18 | 2009-08-12 | 王万年 | Bobbin detector |
| CN203946659U (en) * | 2014-05-06 | 2014-11-19 | 南京文采科技有限责任公司 | Imaging type passim obbbin surplus Detection & Controling device |
| CN105011358A (en) * | 2015-06-12 | 2015-11-04 | 中国电子科技集团公司第四十一研究所 | Dish paper remnant detection apparatus based on machine vision technology |
-
2015
- 2015-07-14 CN CN201510418902.1A patent/CN105000411B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090086217A1 (en) * | 2007-09-27 | 2009-04-02 | Kabushiki Kaisha Toshiba | Sheet thickness measuring device and image forming apparatus |
| CN101503123A (en) * | 2009-02-18 | 2009-08-12 | 王万年 | Bobbin detector |
| CN203946659U (en) * | 2014-05-06 | 2014-11-19 | 南京文采科技有限责任公司 | Imaging type passim obbbin surplus Detection & Controling device |
| CN105011358A (en) * | 2015-06-12 | 2015-11-04 | 中国电子科技集团公司第四十一研究所 | Dish paper remnant detection apparatus based on machine vision technology |
Non-Patent Citations (1)
| Title |
|---|
| 张义伟等: ""基于机器视觉的烟支检测装置设计"", 《工业控制计算机》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056617A (en) * | 2016-05-31 | 2016-10-26 | 中国电子科技集团公司第四十研究所 | Cigarette carton sealing machine hot melt adhesive detection method |
| CN107218929A (en) * | 2017-04-18 | 2017-09-29 | 中国电子科技集团公司第四十研究所 | A kind of cork paper flanging detection method based on machine vision technique |
| CN107218929B (en) * | 2017-04-18 | 2019-08-30 | 中国电子科技集团公司第四十一研究所 | A kind of cork paper flanging detection method based on machine vision technique |
| CN107444712A (en) * | 2017-08-30 | 2017-12-08 | 红云红河烟草(集团)有限责任公司 | Device and method for detecting surplus of small box aluminum foil paper of packaging machine |
| CN110834981A (en) * | 2019-11-21 | 2020-02-25 | 成都忠信机电技术有限公司 | Bobbin paper splicing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105000411B (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103471512B (en) | A kind of glass plate width detecting system based on machine vision | |
| CN105000411A (en) | Bobbin surplus detecting method based on machine vision technology | |
| CN102680481B (en) | Detection method for cotton fiber impurities | |
| EP3416370A1 (en) | Photography focusing method, device, and apparatus for terminal | |
| CN101547286B (en) | Image reading apparatus and control method thereof | |
| CN109489566A (en) | Lithium battery diaphragm material cuts checking method for width, detection system and device | |
| US9674424B2 (en) | Imaging apparatus and control method | |
| CN105011358B (en) | Dish paper remnant detection apparatus based on machine vision technology | |
| CN105841716A (en) | Vision auxiliary control method and device for wire arrangement consistency of optical fiber winding machine | |
| CN103630544B (en) | A kind of vision on-line detecting system | |
| CN109900723A (en) | Glass surface defects detection method and device | |
| CN102988052B (en) | Method and system for measuring foot length | |
| CN103763458B (en) | A kind of scene-change detecting method and device | |
| CN105701809B (en) | A kind of method for correcting flat field based on line-scan digital camera scanning | |
| CN110231018B (en) | Structured light distance measuring method and device and computer readable storage medium | |
| CN108805940B (en) | Method for tracking and positioning zoom camera in zooming process | |
| CN106989681A (en) | The dimension measurement method and measuring apparatus of a kind of via | |
| CN103605203A (en) | Automatic focusing method in digital slicing scanning process | |
| CN108230385B (en) | Method and device for detecting number of ultra-high laminated and ultra-thin cigarette labels by single-camera motion | |
| CN113643206A (en) | Cow breathing condition detection method | |
| CN106225765A (en) | A kind of many line scan image sensors obtain device and the formation method of hyperfocal distance scanning imagery | |
| CN204837981U (en) | Obbbin surplus detection device based on machine vision technique | |
| CN105606623A (en) | Linear array camera based steel plate surface defect detection system | |
| WO2014073590A1 (en) | Three-dimensional measuring device and three-dimensional measuring method | |
| CN206114545U (en) | Singly take photograph wide visual field of camera vision thread detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |