CN117237275A - Tobacco box strip missing detection method, device and system based on machine vision - Google Patents
Tobacco box strip missing detection method, device and system based on machine vision Download PDFInfo
- Publication number
- CN117237275A CN117237275A CN202310807814.5A CN202310807814A CN117237275A CN 117237275 A CN117237275 A CN 117237275A CN 202310807814 A CN202310807814 A CN 202310807814A CN 117237275 A CN117237275 A CN 117237275A
- Authority
- CN
- China
- Prior art keywords
- dimensional code
- cigarette
- information
- tobacco
- machine vision
- 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
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 90
- 238000001514 detection method Methods 0.000 title claims abstract description 65
- 244000061176 Nicotiana tabacum Species 0.000 title 1
- 235000019504 cigarettes Nutrition 0.000 claims abstract description 112
- 241000208125 Nicotiana Species 0.000 claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 11
- 239000000779 smoke Substances 0.000 claims description 50
- 239000011159 matrix material Substances 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 230000001502 supplementing effect Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application discloses a machine vision-based method for detecting the absence of a cigarette carton, which comprises the steps of obtaining a stacking image of the cigarette carton; extracting information from the stacked images, and identifying a two-dimensional code area of the tobacco rod; traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes, and identifying the two-dimensional code information; generating a tobacco bar missing detection result according to the two-dimensional code information, the number of the tobacco bars and the tobacco bar position information, and acquiring a stacking image of the tobacco bars; generating the number of the cigarettes and the position information of the cigarettes, identifying the two-dimensional code information, and further comparing to generate a missing detection result of the cigarettes, wherein the detection result has high accuracy and simple structure and does not need manual intervention. The application also discloses a device and a system for detecting the absence of the tobacco box strip based on machine vision.
Description
Technical Field
The application relates to the technical field of tobacco production and packaging, in particular to a machine vision-based tobacco box strip missing detection method.
Background
The widely used case sealer of cigarette factory still possesses the cigarette case and lacks strip detection function at present, nevertheless because its detection effect is not good, leads to the fact the detection omission easily, and the cigarette case lacks strip condition more. The shortage of the cigarette box belongs to serious quality accidents, and economic disputes between cigarette factories and distributors are easily caused. Various types of smoke box strip missing detection are added in various factories in a dispute mode. Currently, detection methods commonly adopted in the art are: gravimetric, radiographic and visual detection methods. The weight detection method judges whether the tobacco boxes are short by weighing the finished tobacco boxes and comparing and calculating the weight, has higher detection accuracy, but needs to carry out large-scale reconstruction on the existing conveying belt, and cigarettes with different brands need to be provided with different standard weights, so that the reconstruction cost is high; the ray detection method utilizes rays or photons to penetrate through the smoke box and then generates corresponding images on the signal receiver to achieve the detection purpose, but certain radiation exists; the visual detection method utilizes a single camera or a plurality of cameras to be arranged at the rear side of the box-entering propulsion device of the box sealing machine, utilizes the clearance time in the box-pushing process to shoot the real-time images of the lower exhaust smoke and the upper exhaust smoke for analysis and treatment, and needs a corresponding graphic processing system.
Disclosure of Invention
The application aims to provide a novel technical scheme of a machine vision-based smoke box strip missing detection method, which is characterized in that the number of the smoke strips and the position information of the smoke strips are generated by acquiring stacked images of the smoke strips, two-dimensional code information is identified, and then a smoke strip missing detection result is generated by comparison, so that the accuracy of the detection result is high, the structure is simple, and manual intervention is not required.
According to a first aspect of the application, there is provided a machine vision-based smoke box strip missing detection method, comprising:
acquiring a stacking image of the tobacco rod;
extracting information from the stacked images, and identifying a two-dimensional code area of the tobacco rod;
traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes, and identifying the two-dimensional code information;
and generating a tobacco rod missing detection result according to the two-dimensional code information, the number of the tobacco rods and the tobacco rod position information.
Optionally, the acquiring a stacked image of the tobacco rod specifically includes:
obtaining the number and arrangement modes of stacking and boxing the tobacco rods, and generating a tobacco rod boxing arrangement matrix;
splitting the boxing arrangement matrix to generate a stacking sequence;
arranging the rods in the stacking order;
the tobacco rods in each stacking order are photographed and a stacked image is generated.
Optionally, extracting information from the stacked image, and identifying a two-dimensional code area of the tobacco rod, which specifically includes:
sequentially acquiring cigarette bar stacking images according to a stacking sequence;
identifying a two-dimensional code area of the stack of the cigarettes in each stacking order;
comparing the two-dimensional code area with the two-dimensional code area of the stacked tobacco rods in the last stacking order;
and when the two-dimensional code areas in all the stacked images are compared, recording all the two-dimensional code areas.
Optionally, traversing the two-dimensional code area to generate the number of the cigarettes and the position information of the cigarettes, which specifically comprises: generating a positioning template according to the two-dimensional code area of the stacked image;
setting a mark point of the positioning template;
positioning the central coordinate position of each cigarette according to the position relation between the mark point and each cigarette;
and generating a pixel area of each cigarette according to the central position of each cigarette, and recording the position information of the cigarette.
Optionally, traversing the two-dimensional code area to identify two-dimensional code information, which specifically includes:
performing binarization processing on the pixel area to generate a binarized pixel area;
dividing pixel points of the pixel area to generate a segmented stacked image;
calculating the gray value of each pixel point;
and identifying and calculating two-dimensional code information according to the gray value.
Optionally, the number of the obtained cigarette carton stacking boxes is 25, the arrangement mode of the cigarette carton stacking boxes is 5×5, and the generated cigarette carton box arrangement matrix is a 5×5 matrix.
Optionally, the number of pixel point divisions of the stacked image is 25.
Optionally, the generating a detection result of missing tobacco rods according to the two-dimensional code information, the number of tobacco rods and the position information of the tobacco rods specifically includes:
acquiring all two-dimensional code information, the number of tobacco rods and the tobacco rod position information, and generating an incidence matrix;
traversing the two-dimensional code information on each position;
and if the two-dimensional code information comparison result is repeated or the two-dimensional code information is inconsistent with the number of the tobacco rods, judging that the tobacco rods in the tobacco box are missing, and generating missing position information. According to another aspect of the present application, the present application further provides a machine vision-based smoke box strip missing detection device, including:
the image acquisition module is used for acquiring a stacked image of the tobacco rods;
the information extraction module is used for extracting information from the stacked images and identifying a two-dimensional code area of the tobacco rod;
the identification module is used for traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes, and identifying the two-dimensional code information;
and the detection module is used for generating a tobacco rod missing detection result according to the two-dimensional code information, the number of the tobacco rods and the tobacco rod position information.
According to still another aspect of the present application, there is provided a machine vision-based smoke box strip missing detection system, including a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program is executed by the processor, the machine vision-based smoke box strip missing detection method.
According to the embodiment of the disclosure, the number of the cigarettes and the position information of the cigarettes are generated by acquiring the stacked images of the cigarettes, the two-dimensional code information is identified, and then the detection result of the missing of the cigarettes is generated by comparison, so that the accuracy of the detection result is high, the structure is simple, and manual intervention is not needed.
Other features of the present application and its advantages will become apparent from the following detailed description of exemplary embodiments of the application, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flow chart of a machine vision-based smoke box strip missing detection method.
Fig. 2 is a flow chart of acquiring a stacked image of a tobacco rod in accordance with the present application.
Fig. 3 is a flowchart of identifying a two-dimensional code area of a tobacco rod according to the present application.
Fig. 4 is a flowchart for identifying two-dimensional code information according to the present application.
Fig. 5 is a flowchart of traversing the two-dimensional code area according to the present application.
Fig. 6 is a flowchart of the result of detecting missing cigarette sticks according to the present application.
Fig. 7 is a schematic diagram of a machine vision-based smoke box strip missing detection device according to the application.
Fig. 8 is a schematic diagram of automatic positioning of a two-dimensional code according to the present application.
Fig. 9 is a functional flowchart of the present application.
Fig. 10 is a schematic diagram of a machine vision-based smoke box strip missing detection system according to the present application.
Detailed Description
Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present application unless it is specifically stated otherwise.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the application, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.
As shown in fig. 1, the present application provides a method for detecting a missing tobacco carton based on machine vision, which comprises the following steps:
step S110, obtaining a stacking image of the tobacco rods;
step S120, extracting information from the stacked images, and identifying a two-dimensional code area of the tobacco rod;
step S130, traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes, and identifying the two-dimensional code information;
and step 140, generating a tobacco rod missing detection result according to the two-dimensional code information, the number of tobacco rods and the tobacco rod position information.
Specifically, according to the embodiment, the stacked images of the tobacco rods are obtained, the number of the tobacco rods and the position information of the tobacco rods are generated, the two-dimensional code information is identified, and then the detection result of the missing tobacco rods is generated through comparison, so that the accuracy of the detection result is high, the structure is simple, and manual intervention is not needed.
As shown in fig. 2, acquiring a stacked image of a tobacco rod specifically includes:
step S111, obtaining the number and arrangement modes of stacking and boxing the tobacco rods, and generating a tobacco rod boxing arrangement matrix;
s112, splitting the boxing arrangement matrix to generate a stacking sequence;
step S113, arranging the tobacco rods according to the stacking sequence;
step S114, capturing a stack image of the tobacco rods in each stacking order.
Specifically, in this embodiment, the cigarette strips are packed in the box in multiple times to form a stacking order, the stacking order can be designed according to practical situations, and after each stacking is completed, a photographing is performed to form a stacking image, and the number of the cigarette strips can be simply compared according to the stacking image of each time, so that the detection flow of missing cigarette strips is simplified.
As shown in fig. 3, the method includes extracting information from the stacked image, and identifying a two-dimensional code area of the tobacco rod, specifically including:
step S121, sequentially acquiring cigarette bar stacking images according to a stacking sequence;
step S122, identifying a two-dimensional code area of the tobacco rod stacking in each stacking order;
step 123, comparing the two-dimensional code area with the two-dimensional code area of the stacked tobacco rods in the last stacking order;
step S124, when the two-dimensional code areas in all the stacked images are compared, recording all the two-dimensional code areas.
Specifically, in this embodiment, by sequentially comparing two-dimensional code regions in each stacked image, recording and generating all two-dimensional code regions, and simply comparing two-dimensional code region information in each stacking order, it is possible to check the photographed information of the tobacco rod image after each stacking, and further detect the missing information of the tobacco rod preliminarily.
As shown in fig. 4, in a preferred embodiment, traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes specifically includes:
step S131, generating a positioning template according to the two-dimensional code area of the stacked image;
step S132, setting a mark point of the positioning template;
step S133, positioning the central coordinate position of each cigarette according to the position relation between the mark point and each cigarette;
and step S134, generating a pixel area of each cigarette according to the central position of each cigarette, and recording the position information of the cigarette.
As shown in fig. 5, in a preferred embodiment, traversing the two-dimensional code area, and identifying two-dimensional code information specifically includes:
step S141, performing binarization processing on the pixel area to generate a pixel area after the binarization processing;
step S142, dividing pixel points of the pixel area to generate a segmented stacked image;
step S143, calculating the gray value of each pixel point;
and S144, identifying and calculating two-dimensional code information according to the gray value.
Specifically, in this embodiment, the stacked images are extracted through pixel point segmentation and binarization processing, so that the two-dimensional code area can be efficiently screened, and the recognition accuracy of the two-dimensional code is improved.
In a preferred embodiment, the number of stacked cigarette rod bins is 25, the arrangement of the stacked cigarette rod bins is 5 x 5, and a 5 x 5 matrix of the stacked cigarette rod bin arrangement is generated.
In a preferred embodiment, the number of pixel divisions of the stacked image is 25.
As shown in fig. 6, according to the two-dimensional code information, the number of the cigarettes and the position information of the cigarettes, a detection result of missing cigarettes is generated, which specifically includes:
step 151, acquiring all two-dimensional code information, the number of tobacco rods and the tobacco rod position information, and generating an incidence matrix;
step 152, traversing the two-dimensional code information at each position;
and step 153, if the two-dimensional code information is repeated or the two-dimensional code information quantity is inconsistent with the cigarette rod quantity, judging that the cigarette rod in the cigarette box is missing, and generating missing position information.
As shown in fig. 7, in a preferred embodiment, the present application further provides a machine vision-based smoke box strip missing detection device, including: an image acquisition module 210, an information extraction module 220, an identification module 230, and a detection module 240.
The image acquisition module 210 is used for acquiring a stacked image of the tobacco rod; the information extraction module 220 is used for extracting information from the stacked images and identifying a two-dimensional code area of the tobacco rod; the identification module 230 is used for traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes, and identifying the two-dimensional code information; the detection module 240 is configured to generate a detection result of missing tobacco rods according to the two-dimensional code information, the number of tobacco rods and the position information of the tobacco rods.
As shown in fig. 8, the working process of the machine vision-based smoke box strip missing detection device is taken as an example for further explanation:
taking the cigarette factory rod packing process as an example, in this embodiment, 50 cigarettes are packed in each rod box, and the rods are arranged in a rectangular parallelepiped shape in a combination of 2 end faces of 5×5. In the embodiment, the two-dimensional code of the cigarette carton is printed at the center of the end face of the cigarette carton, and the size of the two-dimensional code is 11 multiplied by 11m. The two-dimensional code of each cigarette is unique, and the two-dimensional code information comprises information such as brand specification, production time and the like of the cigarettes.
The image acquisition module 210 adopts a camera, and the camera is installed at the tobacco rod stacking pushing-in position, and when 25 cigarettes reach the stacking to the detection station, the image acquisition module 210 photographs the 25 cigarette stacking. When the case sealer pushes the first layer 25 cigarettes into the smoke box, the image acquisition module 210 takes a stacked photo containing 25 pieces of cigarette information, stores the stacked photo in the database, reads two-dimensional code information of all the cigarettes, and compares and stores the two-dimensional code information. If 25 two-dimensional code information is correctly read and has no abnormality such as repetition, deletion and the like, the layer of cigarettes can be judged to have no abnormality such as strip missing and the like. Then, the second layer 25 cigarettes are pushed into the smoke box, and the image acquisition module 210 shoots again, reads and compares the two-dimensional codes. Similarly, 25 two-dimensional code information is correctly read without repetition or deletion, and the second-layer tobacco rod stacking is judged to be normal. After the two-dimensional codes of 50 cigarettes are correctly identified, the system judges that the cigarette box is qualified in boxing. When the smoke box arrives at the position of the image acquisition module 210, the image acquisition module 210 reads the first engineering traceability code of the smoke box, and the 50 two-dimensional codes and the traceability code of the identification module 230 are associated and stored in a database, so that later calling or inquiry is facilitated. In a preferred embodiment, the camera further comprises a light supplementing lamp, wherein the light supplementing lamp is used for supplementing light to the image acquisition module 210, so that the photo taking quality is improved.
In a specific embodiment, the detection device is composed of an industrial personal computer, an image acquisition card, two cameras, two light supplementing lamps, an I/O control card, a remover and the like.
The two-dimensional code of a cigarette is printed at the center of the end face of the cigarette, the size of the two-dimensional code is 11 x 11m, the two-dimensional code of each cigarette is unique, and the two-dimensional code information comprises information such as brand specification, production time and manufacturing equipment of cigarettes. When the stack reaches the stacking station, the camera takes a picture of the stack. In order to ensure that the two-dimensional code on the cigarette is clear, the light filling lamp is used for filling light to the end part of the cigarette. In order to eliminate the influence of reflection of the transparent paper of the strip box on the image shooting quality, the included angle between the light supplementing lamp and the axis of the camera is 60-75 degrees, the light supplementing lamp is arranged at a position close to the stacking position, and meanwhile, a polarizer is arranged on the lens of the camera.
Under normal conditions, the two-dimensional code information of each smoke box consists of 50 cigarette two-dimensional codes and 1 smoke box one-number engineering traceability code, and is stored in a database after being associated. After the two-dimensional codes of 50 cigarettes are correctly identified, the system judges that the cigarettes are qualified in boxing, and the first engineering traceability code on the cigarettes is read and related, so that later calling or inquiry is facilitated. Because 5*5 cigarette bars are stacked neatly, the two-dimensional code positions of 25 cigarettes are relatively fixed. In the embodiment, the two-dimensional code is positioned by adopting the automatic two-dimensional code positioning method with the position geometric relationship, so that the purpose of rapidly and accurately detecting the two-dimensional code can be realized. First, the mark point MP in the image is positioned through template matching, and the relative position information of 5*5 tobacco rod stacking and the pixel origin point P0 is obtained. And then positioning the central coordinate position of each cigarette according to the position relation between the mark point MP and each cigarette, and expressing by using a formula:
x m ＝Δx+s 1 +(m-1)·s 2
y n ＝Δy+r 1 +(n-1)·r 2
wherein: m corresponds to the number of columns of the tobacco rods in the stack, n corresponds to the number of rows, and m and n are positive integers from 1 to 5; Δx and Δy are the abscissa and ordinate distances from the pixel point coordinate origin P0 to the mark point MP, respectively; s is(s) 1 And r 1 The distances from the mark point MP to the abscissa and the ordinate of the first cigarette two-dimensional code are respectively. And automatically generating 25 areas (ROIs) of interest of the two-dimensional code of the cigarette with 350 x 350 pixels at the positions of the central points of the cigarette.
As shown in fig. 9-10, the application also provides a smoke box strip missing detection system based on machine vision, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the program is executed by the processor to perform a smoke box strip missing detection method based on the vision of a timing device.
First, an image is acquired: acquiring an image acquired by a CCD camera;
decoding and optimizing: creating a two-dimensional code template, setting the scanning number of the two-dimensional codes and the type parameters of the two-dimensional code model, and improving the recognition rate of the two-dimensional codes;
positioning a two-dimensional code: positioning image mark points (positioning accuracy is 0.52 mm) according to template matching, and determining 25 ROI areas;
image preprocessing: image preprocessing is carried out on the ROI, and means such as graying, average filtering, contrast enhancement, morphological analysis and the like can be adopted according to actual conditions, so that the two-dimensional code recognition rate is improved;
ROI cyclic detection: detecting and identifying each ROI one by one;
two-dimensional code identification: realizing two-dimension code information identification by a two-dimension code analysis library;
stack 1/2 identification: it is determined whether the two-dimensional code of 50 cigarettes in the smoke box has been scanned (stacks 1 and 2 are scanned separately).
Two-dimensional code recognition accuracy judgment: and (3) carrying out recognition and judgment on the collected 2 x 25 two-dimensional codes (2 stacks of 50 cigarettes are reset, each stack of 25 two-dimensional codes is totalized to 50 two-dimensional codes). And comparing information such as whether the 50 two-dimensional code is valid, whether the two-dimensional code is repeated and the like. And if the comparison is successful, judging that the smoke box is qualified and has no strip shortage. And the tobacco boxes with the missing tobacco strips are removed at a removing station.
Camera 2 image acquisition: the reject station is scanned for a number one project code (bar code) on the smoke box.
Identifying and associating with the first engineering code: and carrying out data association on the first engineering code and 50 cigarette bar two-dimensional codes in the cigarette box.
The application aims to provide a novel technical scheme of a machine vision-based smoke box strip missing detection method, which is characterized in that the number of the smoke strips and the position information of the smoke strips are generated by acquiring stacked images of the smoke strips, two-dimensional code information is identified, and then a smoke strip missing detection result is generated by comparison, so that the accuracy of the detection result is high, the structure is simple, and manual intervention is not required.
The application also provides a smoke box strip missing detection method based on machine vision, which extracts the stacked images through pixel point segmentation and binarization processing, can efficiently screen out two-dimensional code areas, improves the recognition accuracy of the two-dimensional codes, and passes through the two-dimensional code areas.
While certain specific embodiments of the application have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the application. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the application. The scope of the application is defined by the appended claims.
Claims (10)
1. A machine vision-based smoke box strip missing detection method is characterized by comprising the following steps of:
acquiring a stacking image of the tobacco rod;
extracting information from the stacked images, and identifying a two-dimensional code area of the tobacco rod;
traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes, and identifying the two-dimensional code information;
and generating a tobacco rod missing detection result according to the two-dimensional code information, the number of the tobacco rods and the tobacco rod position information.
2. The machine vision-based method for detecting missing cigarette rods in a cigarette case according to claim 1, wherein the step of obtaining a stacked image of the cigarette rods specifically comprises:
obtaining the number and arrangement modes of stacking and boxing the tobacco rods, and generating a tobacco rod boxing arrangement matrix;
splitting the boxing arrangement matrix to generate a stacking sequence;
arranging the rods in the stacking order;
the tobacco rods in each stacking order are photographed and a stacked image is generated.
3. The machine vision-based smoke box strip missing detection method according to claim 2, wherein the information extraction is performed on the stacked image, and a two-dimensional code area of the smoke strip is identified, and specifically comprises:
sequentially acquiring cigarette bar stacking images according to a stacking sequence;
identifying a two-dimensional code area of the stack of the cigarettes in each stacking order;
comparing the two-dimensional code area with the two-dimensional code area of the stacked tobacco rods in the last stacking order;
and when the two-dimensional code areas in all the stacked images are compared, recording all the two-dimensional code areas.
4. The machine vision-based smoke box strip missing detection method of claim 3, wherein traversing the two-dimensional code area generates the number of smoke strips and the position information of the smoke strips, and specifically comprises:
generating a positioning template according to the two-dimensional code area of the stacked image;
setting a mark point of the positioning template;
positioning the central coordinate position of each cigarette according to the position relation between the mark point and each cigarette;
and generating a pixel area of each cigarette according to the central position of each cigarette, and recording the position information of the cigarette.
5. The machine vision-based smoke box strip missing detection method of claim 4, wherein traversing the two-dimensional code area identifies two-dimensional code information, and specifically comprises:
performing binarization processing on the pixel area to generate a binarized pixel area;
dividing pixel points of the pixel area to generate a segmented stacked image;
calculating the gray value of each pixel point;
and calculating two-dimensional code information according to the gray value.
6. The machine vision based method for detecting missing cigarette boxes of claim 5, wherein the number of obtained cigarette carton stacking boxes is 25, the arrangement mode of the cigarette carton stacking boxes is 5×5, and the generated cigarette carton box arrangement matrix is 5×5 matrix.
7. The machine vision-based smoke box strip detection method according to claim 6, wherein the number of pixel point divisions of the stacked image is 25.
8. The machine vision-based smoke box strip missing detection method of claim 7, wherein the generating a smoke strip missing detection result according to the two-dimensional code information, the number of smoke strips and the smoke strip position information specifically comprises:
acquiring all two-dimensional code information, the number of tobacco rods and the tobacco rod position information, and generating an incidence matrix;
traversing the two-dimensional code information on each position;
and if the two-dimensional code information comparison result is repeated or the two-dimensional code information is inconsistent with the number of the tobacco rods, judging that the tobacco rods in the tobacco box are missing, and generating missing position information.
9. Machine vision-based smoke box strip missing detection device, which is characterized by comprising:
the image acquisition module is used for acquiring a stacked image of the tobacco rods;
the information extraction module is used for extracting information from the stacked images and identifying a two-dimensional code area of the tobacco rod;
the identification module is used for traversing the two-dimensional code area, generating the number of the cigarettes and the position information of the cigarettes, and identifying the two-dimensional code information;
and the detection module is used for generating a tobacco rod missing detection result according to the two-dimensional code information, the number of the tobacco rods and the tobacco rod position information.
10. A machine vision-based smoke box strip detection system, comprising a processor, a memory, and a program stored on the memory and executable on the processor, the program when executed by the processor implementing the machine vision smoke box strip detection method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310807814.5A CN117237275A (en) | 2023-07-03 | 2023-07-03 | Tobacco box strip missing detection method, device and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310807814.5A CN117237275A (en) | 2023-07-03 | 2023-07-03 | Tobacco box strip missing detection method, device and system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117237275A true CN117237275A (en) | 2023-12-15 |
Family
ID=89081439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310807814.5A Pending CN117237275A (en) | 2023-07-03 | 2023-07-03 | Tobacco box strip missing detection method, device and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237275A (en) |
-
2023
- 2023-07-03 CN CN202310807814.5A patent/CN117237275A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11087484B2 (en) | Camera apparatus and method of detecting a stream of objects | |
| CN102020036A (en) | Visual detection method for transparent paper defect of outer package of strip cigarette | |
| CN110580481B (en) | Light field image key position detection method based on EPI | |
| CN111161263B (en) | Package flatness detection method and system, electronic equipment and storage medium | |
| CN111461133B (en) | Express delivery surface single item name identification method, device, equipment and storage medium | |
| CN111144151A (en) | High-speed dynamic bar code real-time detection method based on image recognition | |
| CN112052702B (en) | Method and device for identifying two-dimensional code | |
| CN110554052A (en) | artificial board surface defect detection method and system | |
| CN114782437A (en) | Computer mainboard quality detection method and system based on artificial intelligence | |
| CN111178445A (en) | Image processing method and device | |
| CN113095445A (en) | Target identification method and device | |
| CN111294594B (en) | Security inspection method, device, system and storage medium | |
| CN117237275A (en) | Tobacco box strip missing detection method, device and system based on machine vision | |
| CN112614176A (en) | Belt conveyor material volume measuring method and device and storage medium | |
| CN114792369B (en) | Cigarette carton filling state detection method and system based on light projection | |
| CN105975910A (en) | Technology processing method used for carrying out video identification on moving object and system thereof | |
| US11752524B2 (en) | Method for recovering a posteriori information about the operation of a plant for automatic classification and sorting of fruit | |
| CN113409297A (en) | Aggregate volume calculation method, particle form grading data generation method, system and equipment | |
| CN116580026B (en) | Automatic optical detection method, equipment and storage medium for appearance defects of precision parts | |
| CN111340795B (en) | Method and device for determining quality of article | |
| CN103294783B (en) | Product picture group technology and device | |
| CN117456473B (en) | Vehicle assembly detection method, device, equipment and storage medium | |
| JP7405915B2 (en) | Methods and apparatus for analyzing products, training methods, systems, computer programs, and computer-readable storage media | |
| JP7090899B2 (en) | Image processing equipment and image processing programs that use encoded illumination patterns | |
| EP3376435B1 (en) | Image processing apparatus, image processing system, image processing method, and program |
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 |