CN108100343A - A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization - Google Patents
A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization Download PDFInfo
- Publication number
- CN108100343A CN108100343A CN201711370410.5A CN201711370410A CN108100343A CN 108100343 A CN108100343 A CN 108100343A CN 201711370410 A CN201711370410 A CN 201711370410A CN 108100343 A CN108100343 A CN 108100343A
- Authority
- CN
- China
- Prior art keywords
- cigarette
- cigarette bag
- focke
- edge
- cigarettes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B19/00—Packaging rod-shaped or tubular articles susceptible to damage by abrasion or pressure, e.g. cigarettes, cigars, macaroni, spaghetti, drinking straws or welding electrodes
- B65B19/28—Control devices for cigarette or cigar packaging machines
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B19/00—Packaging rod-shaped or tubular articles susceptible to damage by abrasion or pressure, e.g. cigarettes, cigars, macaroni, spaghetti, drinking straws or welding electrodes
- B65B19/28—Control devices for cigarette or cigar packaging machines
- B65B19/30—Control devices for cigarette or cigar packaging machines responsive to presence of faulty articles, e.g. incorrectly filled cigarettes
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of cigarette bag automatic positioning methods applied to FOCKE packing machines of optimization, suitable interest region ROI is selected on small box of cigarettes original image, drop shadow curve is obtained by horizontal, upright projection, recycle edge-finding algorithm, realize the automatic positioning of cigarette bound edge edge, and it is compared with the positioning result of standard picture, calculate level, the vertical offset of small box of cigarettes reality, it is added in current small box of cigarettes appearance detection, so as to fulfill the compensation of kinematic error in small box of cigarettes appearance detection process;Before the automatic positioning of FOCKE packing machine cigarettes bag, a kind of method of pretreatment is added, increases the contrast of cigarette bound edge edge and background, realizes the optimization of the automatic cigarette bag location algorithm of FOCKE packing machines.
Description
Technical field
The present invention relates to cigarette bag localization method field, the specifically a kind of cigarette bag applied to FOCKE packing machines of optimization certainly
Motion positioning method.
Background technology
With the progress of cigarette industry science and technology and the aggravation of market competition, tobacco productive corporation is to high-speed packaging device
Demand is more and more.At present, the high speed rigid pack unit of the domestic German FOCKE companies production introduced has completed production domesticization simultaneously
Progressively proceed by batch production.In this high speed manufacturing processes, cigarette bag packages in damaged condition, alice show money or valuables one carries unintentionally, the appearances matter such as anti-package
It is inevitable to measure defect, seriously affects the presentation quality of product.
In the actual production process, as conveyor moves on assembly line, the position all around of cigarette bag can be sent out cigarette bag
Raw offset can influence the accuracy of cigarette bag appearance detection.Therefore, it is necessary to a kind of effective motion compensation method, for solving
The certainly kinematic error problem in small box of cigarettes appearance detection process.In actually detected process, when cigarette bound edge edge and background contrast not
When strong or cigarette bound edge edge is at a slight tilt, the accuracy of the positioning at meeting strong influence small box of cigarettes edge.Therefore, it is necessary to right
Kinematic error compensation in small box of cigarettes appearance detection process optimizes.
The content of the invention
The object of the present invention is to provide a kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization, with solution
The certainly kinematic error problem in prior art small box of cigarettes appearance detection process.
In order to achieve the above object, the technical solution adopted in the present invention is:
A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization, it is characterised in that:
Photoelectric sensor is installed additional directly over cigarette bag, for real time scan cigarette bound edge edge, judges whether cigarette bag will leave
Picture-taking position, while trigger industrial camera to cigarette bag into taking pictures, gathers cigarette bag image and sends controller to and handled;
After controller obtains cigarette bag image, cigarette bag both horizontally and vertically upper suitable interest region, and right is chosen first
Interest region is rotated according to suitable angle, obtains postrotational interest region ROI1 (x, y), ROI2 (x, y);To interest
Region ROI1 (x, y) and ROI2 (x, y) carries out gray processing, horizontal and vertical projection respectively, obtains drop shadow curve;
Then, cigarette bound edge edge is searched and located from fixed-direction using edge-finding algorithm, and by this positioning result with marking
The positioning result of quasi- image is compared, and is calculated level, the vertical offset of smoke bag reality, is added to outside current small box of cigarettes
It sees in detection, realizes the compensation of kinematic error in small box of cigarettes appearance detection process.
A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of the optimization, it is characterised in that:Edge is looked into
Looking for the specific practice of algorithm is:It is searched point by point from horizontal, vertical direction, calculates neighbor pixel luminance difference, work as luminance difference
When being satisfied with setting value delta, then continue to compare whether all pixels point and the luminance difference of the point in continuous boundary width meet
It is required that when meeting, then it is cigarette bound edge edge to mark the point.
A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of the optimization, it is characterised in that:
It is pre-processed first before the automatic cigarette bag positioning of Focke machines:The original each pixel of cigarette bag image is traveled through, calculates each pixel
Then the difference of red component and green component in point is further split the image of acquisition, corrodes;
By Preprocessing Algorithm, the contrast of cigarette bound edge edge and background is increased, to improve positional accuracy, realizes capsule
The optimization of kinematic error compensation in cigarette bag appearance detection process.
The beneficial effects of the invention are as follows:
1st, the present invention selects suitable interest region ROI on small box of cigarettes original image, is obtained by horizontal, upright projection
To drop shadow curve, recycle edge-finding algorithm, realize the automatic positioning of cigarette bound edge edge, and with the positioning result of standard picture into
Row comparison calculates level, the vertical offset of small box of cigarettes reality, is added in current small box of cigarettes appearance detection, so as to
Realize the compensation of kinematic error in small box of cigarettes appearance detection process;Before the automatic positioning of FOCKE packing machine cigarettes bag, add
A kind of method of pretreatment increases the contrast of cigarette bound edge edge and background, realizes the automatic cigarette bag positioning of FOCKE packing machines and calculates
The optimization of method.
2nd, image procossing is a highly developed technology, and the image processing algorithm used in the present invention is all the normal of maturation
With algorithm, these algorithms are all contained in various commercializations or the machine vision function library increased income, developer can directly invoke.
3rd, the algorithm used applied to the cigarette bag automatic positioning method of FOCKE packing machines of a kind of optimization proposed by the present invention
All it is the ripe algorithm in image procossing, corresponding change can be made according to the variation of cigarette bag or type and is applied, is had
It is widely applied space.
Description of the drawings
Fig. 1 is the small box of cigarettes original image f (x, y) that industrial camera collects.
It is interest region ROI1 (x, y) respectively that Fig. 2 a, which are,.
Fig. 2 b are the image ROI1_Gray (x, y) after gray processing.
Fig. 2 c are the image ROI1_Curve (y) after floor projection.
Fig. 3 a are interest region ROI2 (x, y).
Fig. 3 b are the image ROI2_Gray (x, y) after gray processing.
Fig. 3 c are the image ROI2_Curve (x) after floor projection.
Fig. 4 is by red component and green component difference treated image f_R-G (x, y).
Fig. 5 is the image f_R-G_Threshold (x, y) after binaryzation and corrosion treatment.
Fig. 6 is the image ROI1_Gray_Optimized (x, y) and floor projection curve ROI1_Curve_ after optimization
Optimized(y)。
Fig. 7 is the image ROI2_Gray_Optimized (x, y) and floor projection curve ROI2_Curve_ after optimization
Optimized(x)。
Specific embodiment
The present invention provides a kind of cigarette bag automatic positioning methods applied to FOCKE packing machines of optimization, and detailed process is such as
Under:
It installs photoelectric sensor additional directly over small box of cigarettes, for real time scan cigarette bound edge edge, judges that cigarette bag whether will
Leave picture-taking position.At this point, triggering industrial camera to cigarette bag into taking pictures, gather cigarette bag image and simultaneously send at controller
Reason.
After control obtains cigarette bag image, cigarette bag both horizontally and vertically upper suitable interest region, and to emerging is chosen first
Interesting region is rotated according to suitable angle, obtains ROI1 (x, y), ROI2 (x, y).To interest region ROI1 (x, y) and
ROI2 (x, y) carries out gray processing, horizontal and vertical projection respectively, obtains drop shadow curve.Then, cigarette bound edge is searched from fixed-direction
Edge, specific practice are:It is searched point by point from horizontal, vertical direction, neighbor pixel luminance difference is calculated, when luminance difference is satisfied with
During setting value delta, then continue to compare whether all pixels point and the luminance difference of the point in continuous boundary width meet the requirements, it is full
When sufficient, then it is cigarette bound edge edge to mark the point.
Then, the positioning result of this positioning result and standard picture is compared, calculates small box of cigarettes reality
Horizontal, vertical offset is added in current small box of cigarettes appearance detection, realizes to move in small box of cigarettes appearance detection process and miss
The compensation of difference.
The Background color information in original cigarette bag image that makes discovery from observation shows relatively simple (black, white) feature, and
Cigarette bag general color clear in itself, is presented a kind of dominant hue (red).Therefore, during actually detected, in the automatic cigarette of Focke machines
Before bag positioning, the original each pixel of cigarette bag image is traveled through, calculates the difference of red component and green component in each pixel,
Then the image of acquisition is further split, corroded.By Preprocessing Algorithm, the comparison of cigarette bound edge edge and background is increased
Degree, greatly improves positional accuracy, realizes the optimization of kinematic error compensation in small box of cigarettes appearance detection process.
Specific embodiment:
It installs photoelectric sensor additional directly over small box of cigarettes, for real time scan cigarette bound edge edge, judges that cigarette bag whether will
Leave picture-taking position.At this point, triggering industrial camera to cigarette bag into taking pictures, the small box of cigarettes original image collected is as shown in Figure 1.
A kind of automatic cigarette bag localization method of Focke machines is as follows:
The first step, extracts suitable interest region on small box of cigarettes original image f (x, y), and to interest region according to
Suitable angle is rotated, and obtains ROI1 (x, y), ROI2 (x, y) for searching the position of cigarette bag both horizontally and vertically, such as
Shown in Fig. 2 a and Fig. 3 a.Gray processing processing is carried out to image ROI1 (x, y) and ROI2 (x, y), obtain image ROI1_Gray (x,
Y) and ROI2_Gray (x, y), as shown in Fig. 2 b and Fig. 3 b.Then, respectively image ROI1_Gray (x, y) every a line and
Horizontal, upright projection (such as formula 1 and 2) is carried out on each column direction of ROI2_Gray (x, y), obtains floor projection curve
ROI1_Curve (y) and ROI2_Curve (x), as shown in Fig. 2 c and Fig. 3 c.
Second step, according to direction initialization compare neighbor pixel ROI1_Curve (y) and ROI1_Curve (y-1) or
Luminance difference delta between ROI1_Curve (y+1) when demanded, then continues to compare ROI1_Curve (y) and neighbouring N
Whether the luminance difference of a pixel meets the requirements, and when meeting, then the point is marked to realize small box of cigarettes side for cigarette bound edge edge pixel
The automatic positioning of edge.
Then, the positioning result of this positioning result and standard picture is compared, calculates small box of cigarettes reality
Horizontal, vertical offset is added in current small box of cigarettes appearance detection.Finally, realize in small box of cigarettes appearance detection process
The compensation of kinematic error.
During actually detected, before the automatic cigarette bag positioning of Focke machines, original cigarette bag image f (x, y) is located in advance
Reason:Original cigarette bag image f (x, y) all pixels point is traveled through, the difference of current pixel red component and green component is calculated respectively, obtains
To image f_R-G (x, y), as shown in Figure 4.After carrying out binaryzation to image f_R-G (x, y), removed and split by etching operation
Tiny crackle and impure point, have obtained cigarette bag image f_R-G_Threshold (x, y), as shown in Figure 5 in image.It can see
Go out in cigarette bag edge parameters in the case of 10, delta values level, the adjustable extent of vertical direction respectively from:4-77 extends
1-103 is expanded to 1-168,4-12.By Preprocessing Algorithm, the contrast of cigarette bound edge edge and background is increased so that follow-up
Automatic positioning algorithm more can be high, positional accuracy greatly improves, as shown in Figure 6 and Figure 7.
Claims (3)
1. a kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization, it is characterised in that:
Photoelectric sensor is installed additional directly over cigarette bag, for real time scan cigarette bound edge edge, is judged whether cigarette bag will leave and is taken pictures
Position, while trigger industrial camera to cigarette bag into taking pictures, gathers cigarette bag image and sends controller to and handled;
After controller obtains cigarette bag image, cigarette bag both horizontally and vertically upper suitable interest region, and to interest is chosen first
Region is rotated according to suitable angle, obtains postrotational interest region ROI1 (x, y), ROI2 (x, y);To interest region
ROI1 (x, y) and ROI2 (x, y) carries out gray processing, horizontal and vertical projection respectively, obtains drop shadow curve;
Then, cigarette bound edge edge is searched and located from fixed-direction using edge-finding algorithm, and by this positioning result and standard drawing
The positioning result of picture is compared, and calculates level, the vertical offset of smoke bag reality, and be added to current small box of cigarettes appearance inspection
In survey, the compensation of kinematic error in small box of cigarettes appearance detection process is realized.
2. a kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization according to claim 1, feature
It is:The specific practice of edge-finding algorithm is:It is searched point by point from horizontal, vertical direction, calculates neighbor pixel brightness
Difference when luminance difference is satisfied with setting value delta, then continues to compare the brightness of all pixels point and the point in continuous boundary width
Whether difference meets the requirements, and when meeting, then it is cigarette bound edge edge to mark the point.
3. a kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization according to claim 1, feature
It is:It is pre-processed first before the automatic cigarette bag positioning of Focke machines:The original each pixel of cigarette bag image is traveled through, is calculated
The difference of red component and green component in each pixel, is then further split the image of acquisition, corrodes;
By Preprocessing Algorithm, the contrast of cigarette bound edge edge and background is increased, to improve positional accuracy, realizes small box of cigarettes
The optimization of kinematic error compensation in appearance detection process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711370410.5A CN108100343A (en) | 2017-12-19 | 2017-12-19 | A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711370410.5A CN108100343A (en) | 2017-12-19 | 2017-12-19 | A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108100343A true CN108100343A (en) | 2018-06-01 |
Family
ID=62209905
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711370410.5A Pending CN108100343A (en) | 2017-12-19 | 2017-12-19 | A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108100343A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493316A (en) * | 2018-09-21 | 2019-03-19 | 浙江中烟工业有限责任公司 | Cartoning sealing machine cigarette packet based on similarity analysis and feature incremental learning lacks an intelligent detecting method |
CN111103286A (en) * | 2019-12-10 | 2020-05-05 | 红云红河烟草(集团)有限责任公司 | Cigarette stream extraction method under normal illumination condition of factory |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102020036A (en) * | 2010-11-02 | 2011-04-20 | 昆明理工大学 | Visual detection method for transparent paper defect of outer package of strip cigarette |
CN103760170A (en) * | 2013-12-26 | 2014-04-30 | 中国电子科技集团公司第四十一研究所 | Tobacco bale lining defect detection method based on machine vision technology |
CN106097254A (en) * | 2016-06-07 | 2016-11-09 | 天津大学 | A kind of scanning document image method for correcting error |
-
2017
- 2017-12-19 CN CN201711370410.5A patent/CN108100343A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102020036A (en) * | 2010-11-02 | 2011-04-20 | 昆明理工大学 | Visual detection method for transparent paper defect of outer package of strip cigarette |
CN103760170A (en) * | 2013-12-26 | 2014-04-30 | 中国电子科技集团公司第四十一研究所 | Tobacco bale lining defect detection method based on machine vision technology |
CN106097254A (en) * | 2016-06-07 | 2016-11-09 | 天津大学 | A kind of scanning document image method for correcting error |
Non-Patent Citations (2)
Title |
---|
徐黎明等: "自然环境下杨梅果实图像的分割方法研究", 《沈阳农业大学学报》 * |
王珍: "基于机器视觉的香烟条包检测系统的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493316A (en) * | 2018-09-21 | 2019-03-19 | 浙江中烟工业有限责任公司 | Cartoning sealing machine cigarette packet based on similarity analysis and feature incremental learning lacks an intelligent detecting method |
CN109493316B (en) * | 2018-09-21 | 2021-06-15 | 浙江中烟工业有限责任公司 | Intelligent detection method for cigarette packet missing strip of carton sealing machine based on similarity analysis and feature increment learning |
CN111103286A (en) * | 2019-12-10 | 2020-05-05 | 红云红河烟草(集团)有限责任公司 | Cigarette stream extraction method under normal illumination condition of factory |
CN111103286B (en) * | 2019-12-10 | 2022-07-01 | 红云红河烟草(集团)有限责任公司 | Cigarette stream extraction method under normal illumination condition of factory |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8401274B2 (en) | Image processing apparatus and method | |
CN103369347B (en) | Camera blemish defects detection | |
CN103051872B (en) | Based on the belt deflection detection method of Edge extraction | |
JP2017096750A (en) | Positioning method, positioning apparatus, program and computer readable recording medium | |
CN105865329B (en) | The acquisition system and method for the bundled round steel end face center coordinate of view-based access control model | |
CN112837257A (en) | Curved surface label splicing detection method based on machine vision | |
JP5983209B2 (en) | Moving object detection method | |
CN108100343A (en) | A kind of cigarette bag automatic positioning method applied to FOCKE packing machines of optimization | |
US20140185883A1 (en) | Analysis of the digital image of the surface of a tyre and processing of non-measurement points | |
CN109741393B (en) | Diameter measurement and center point positioning method for agaricus bisporus | |
US20150051860A1 (en) | Automatic optical appearance inspection by line scan apparatus | |
CN109324056B (en) | Sewing thread trace measuring method based on machine vision | |
CN109238135A (en) | A kind of view-based access control model precise positioning expects the method for test box | |
CN105184739A (en) | Printed circuit board AOI detection image stitching method | |
US20120274794A1 (en) | Image sensing apparatus and method | |
CN112747864A (en) | Intelligent vision-based automatic vinasse feeding method and system | |
JP3659426B2 (en) | Edge detection method and edge detection apparatus | |
CN106603937A (en) | image stitching method and image stitching device | |
JP2012007952A (en) | Visual inspection device | |
CN106373158A (en) | Automated image detection method | |
KR101574195B1 (en) | Auto Calibration Method for Virtual Camera based on Mobile Platform | |
CN106645174A (en) | Automatic online visual apparent-defect inspection system for general purpose engine | |
CN106231294B (en) | A kind of detection method and device of Stereogram source format | |
JP6960827B2 (en) | Road surface area detector | |
CN115578310A (en) | Binocular vision detection method and system for refractory bricks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180601 |