CN118947958A - Cigarette end face defect detection system - Google Patents
Cigarette end face defect detection system Download PDFInfo
- Publication number
- CN118947958A CN118947958A CN202411094100.5A CN202411094100A CN118947958A CN 118947958 A CN118947958 A CN 118947958A CN 202411094100 A CN202411094100 A CN 202411094100A CN 118947958 A CN118947958 A CN 118947958A
- Authority
- CN
- China
- Prior art keywords
- cigarette
- face
- image
- cigarette end
- face image
- 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
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 247
- 230000007547 defect Effects 0.000 title claims abstract description 104
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 230000002950 deficient Effects 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000005520 cutting process Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 12
- 239000000779 smoke Substances 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012858 packaging process Methods 0.000 abstract description 3
- 238000004806 packaging method and process Methods 0.000 description 6
- 241000208125 Nicotiana Species 0.000 description 5
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Abstract
The invention discloses a cigarette end face defect detection system, which comprises: the industrial personal computer, the input is connected with the industrial camera, the output is connected with image processing and operation workstation computer, the image processing and operation workstation computer is connected with the database, the database is connected with the early warning platform, wherein: the industrial camera is used for collecting the cigarette end face image; the industrial personal computer is used for storing the cigarette end face image; the image processing and operating workstation computer is used for identifying the defects of the end face of the cigarette according to the images of the end face of the cigarette, and obtaining the type result of the defects of the end face of the cigarette and the positions of the defective cigarettes; the database is used for storing the defect type result and the defect position and sending the defect type result and the defect position to the early warning platform. According to the system for detecting the defects of the end faces of the cigarettes, the images of the end faces of the cigarettes are acquired through the industrial camera, and the end faces of the cigarettes are analyzed through the image processing and operating workstation computer, so that the detection of the defects of the end faces of the cigarettes in all types is realized, and the on-line detection of the quality of the end faces of the cigarettes in the packaging process is realized.
Description
Technical Field
The invention relates to the technical field of cigarette detection, in particular to a cigarette end face defect detection system.
Background
In the tobacco industry, the appearance of special-shaped packaging equipment provides more choices for cigarette production enterprises, and simultaneously brings new difficulties for quality detection of cigarette end faces. The mould box of the special-shaped packaging equipment is different from the conventional packaging equipment, so that the current cigarette end face detection system cannot be used universally. Because the special-shaped packaging equipment is designed into a mould box and cigarettes are transported by adopting a cigarette lattice, the cigarette fulcrum fire end face is easy to wrinkle and scratch, the quality requirements of brands produced by the special-shaped packaging equipment are higher, and the quality detection system is more highly required.
The existing detection system cannot carry out multi-class full detection on cigarettes in a die box in special-shaped packaging equipment, and also cannot timely early warn quality defects, so that defective cigarette packets cannot be timely found to generate serious product quality problems, and the problems of high missing rate of the cigarette defects, poor timeliness and the like can occur by means of a manual extraction method.
Therefore, there is a need for a system for detecting defects in the end face of a cigarette.
Disclosure of Invention
The invention aims to provide a system for detecting defects of end surfaces of cigarettes, which solves the problems in the prior art and can realize comprehensive automatic detection of the defects of the end surfaces of the cigarettes.
The invention provides a cigarette end face defect detection system, which comprises: the industrial personal computer, the input of industrial personal computer is connected with industrial camera, the output of industrial personal computer is connected with image processing and operation workstation computer, image processing and operation workstation computer is connected with the database, the database is connected with the early warning platform, wherein:
The industrial camera is used for collecting an end face image of the cigarette;
The industrial personal computer is used for storing the cigarette end face image and transmitting the cigarette end face image to the image processing and operating workstation computer;
the image processing and operating workstation computer is used for identifying the defects of the cigarette end face according to the cigarette end face image to obtain a cigarette end face defect type result and a defective cigarette position;
The database is used for storing the cigarette end face defect type result and the defective cigarette position and sending the cigarette end face defect type result and the defective cigarette position to the early warning platform;
And the early warning platform is used for generating early warning information according to the cigarette end face defect type result and the defective cigarette position.
In the system for detecting defects of end surfaces of cigarettes, the industrial camera is preferably arranged on one side of a cigarette storage lower smoke channel of the module box conveying chain plate, and is used for photographing the end surfaces of cigarettes in the module box when the module box conveyed on the module box conveying chain plate is conveyed to the cigarette storage lower smoke channel, so that an image of the end surfaces of cigarettes is obtained.
The system for detecting the defects of the end face of the cigarette, which is described above, preferably further comprises a light source connected with the industrial personal computer and used for providing illumination for the industrial camera; the light source is arranged at the front end of the industrial camera.
The system for detecting the defects of the end face of the cigarette according to the above, preferably, the system for detecting the defects of the end face of the cigarette further comprises a staff moving end, a staff PC end and an operator lower computer connected with the early warning platform, and the early warning platform is further used for sending the early warning information to at least one of the staff moving end, the staff PC end and the operator lower computer.
According to the cigarette end face defect detection system, preferably, the database is connected with the input end of the early warning platform, and the staff movable end, the staff PC end and the operator lower computer are connected with the output end of the early warning platform.
The system for detecting defects of end surfaces of cigarettes as described above, wherein preferably, the image processing and operating workstation computer comprises a brightness coefficient calculation module, a brightness abnormality judgment module, an image preprocessing module, a cutting module of end surfaces of cigarettes and an identification module of end surfaces of cigarettes, wherein:
the brightness coefficient calculation module is used for calculating the brightness coefficient of the cigarette end face image;
The brightness abnormality judging module is used for judging whether the brightness of the cigarette end face image is normal or not according to the brightness coefficient;
the image preprocessing module is used for preprocessing the cigarette end face image with normal brightness;
The cigarette end face image slitting module is used for positioning the circle center of each cigarette end face, fitting the radius of the circle, and intercepting the end face image of each cigarette by utilizing the fitting circle corresponding to each cigarette;
the cigarette end face image defect recognition module is used for classifying and judging the end face image of each cut cigarette by using the trained deep neural network model so as to judge whether each cigarette end face has defects.
The cigarette end face defect detection system as described above, wherein preferably, the luminance coefficient calculation module includes a gray-scale image processing unit and a luminance coefficient calculation unit, wherein:
The gray level image processing unit is used for carrying out gray level image processing on the cigarette end face image, obtaining the shape and the line width of the cigarette end face image, and calculating the mean value and the deviation of gray level image pixel points;
The brightness coefficient calculating unit is used for calculating the brightness coefficient of the cigarette end face image according to the mean value and the deviation of the gray image pixel points through the following formula:
（1）
（2）
（3）
wherein, Representing the luminance coefficient of the image,The mean of the representations (image gray values-128),The average deviation is indicated as such,The gray value of the image is represented,The number of pixels of the image is represented,The number of pixels representing each gray level in the gray level histogram.
In the system for detecting defects on a cigarette end face as described above, preferably, the luminance abnormality judging module is specifically configured to: if the brightness coefficient of the image is smaller than or equal to a preset brightness coefficient threshold value, judging that the brightness of the cigarette end face image is normal and is in a reasonable range; if the brightness coefficient of the image is larger than the preset brightness coefficient threshold value, judging that the brightness of the cigarette end face image is abnormal,
The image preprocessing module is specifically used for: and carrying out mean shift filtering noise reduction treatment on the cigarette end face image through a filter.
The system for detecting defects of end surfaces of cigarettes as described above, wherein preferably, the module for cutting end surface images of cigarettes comprises a unit for cutting end surface images of cigarettes and a unit for identifying defects of end surface images of cigarettes, wherein:
the cigarette end face image slitting unit is used for positioning the circle center of each cigarette end face through a Hough circle detection algorithm and fitting out the radius of the circle:
（4）
（5）
（6）
wherein, (x, y) represents coordinates of a cigarette end face point, (a, b) represents center coordinates of a fitting circle, and r represents a radius of the fitting circle;
The cigarette end face image cutting unit is also used for cutting out square images which are centered on the circle center, equal in length and width and larger than the diameter by utilizing the circle center coordinates and the radius of each known cigarette fitting circle according to the circle positioned by the Hough circle method, and cutting out the end face image of each cigarette, wherein the boundary position of the single-cigarette image cutting range of the cigarette end face is calculated by the following formula:
（7）
（8）
（9）
（10）
wherein, Represent the firstThe abscissa of the circle center of the cigarette,Represent the firstThe ordinate of the circle center of the cigarette,Representing the rectangular side length of the range to be intercepted, and obtaining by calculation、、、And determining that the cigarettes intercept single cigarette images.
The system for detecting defects of end surfaces of cigarettes as described above, wherein preferably, the module for identifying defects of end surfaces of cigarettes is specifically configured to: the cut images are sent to a trained and optimized deep neural network model for classification and judging whether defects exist, in the deep neural network model, the cut images are sent to a neural network and enter 3 dense blocks for feature extraction after passing through a convolution block, each dense block comprises two layers of convolution blocks, each convolution block consists of a convolution layer, a Batch Normalization layer and a ReLU function activation layer, after passing through an average pooling layer, a full-connection layer maps the result into two values to indicate whether the cigarettes in the images exist or not.
The invention provides a cigarette end face defect detection system, which is characterized in that an industrial camera is used for collecting an image of a cigarette end face, and an image processing and operating workstation computer is used for analyzing the cigarette end face so as to realize the detection of the full-class quality defects of the cigarette end face and realize the on-line detection of the quality of the cigarette end face in the packaging process of cigarettes; the quality defects of the end faces of the cigarettes can be automatically identified, early warning information can be pushed to functional personnel and operators through the early warning platform, and the mould boxes generated by the defects can be positioned; effectively improves the quality of cigarette products, improves the automatic production level of the rolling equipment, improves the working efficiency, reduces the cost and reduces the working strength of manual spot check.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described with reference to the accompanying drawings, in which:
FIG. 1 is a block diagram of an embodiment of a system for detecting defects in an end surface of a cigarette according to the present invention;
FIG. 2 is a schematic top view of the installation positions of an industrial camera and a light source of an embodiment of a system for detecting defects of end surfaces of cigarettes provided by the invention;
FIG. 3 is a schematic diagram of a workflow of an embodiment of a system for detecting defects in an end surface of a cigarette according to the present invention;
fig. 4 is a schematic diagram of positioning hough circle on the end surface of a cigarette according to an embodiment of the present invention;
Fig. 5 is a schematic diagram of a result of cutting a tobacco rod end surface according to an embodiment of the system for detecting defects of a tobacco rod end surface provided by the present invention.
Reference numerals illustrate: the system comprises a 1-industrial camera, a 2-light source, a 3-industrial personal computer, a 4-image processing and operating workstation computer, a 5-database, a 6-early warning platform, a 7-staff mobile terminal, an 8-staff PC terminal, a 9-operator lower computer, a 10-smoke warehouse smoke discharging channel, an 11-die box and a 12-die box conveying chain plate.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative, and is in no way intended to limit the disclosure, its application, or uses. The present disclosure may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that: the relative arrangement of parts and steps, the composition of materials, numerical expressions and numerical values set forth in these embodiments should be construed as exemplary only and not limiting unless otherwise specifically stated.
"First", "second", as used in this disclosure: and similar words are not to be interpreted in any order, quantity, or importance, but rather are used to distinguish between different sections. The word "comprising" or "comprises" and the like means that elements preceding the word encompass the elements recited after the word, and not exclude the possibility of also encompassing other elements. "upper", "lower", etc. are used merely to denote relative positional relationships, which may also change accordingly when the absolute position of the object to be described changes.
In this disclosure, when a particular element is described as being located between a first element and a second element, there may or may not be intervening elements between the particular element and the first element or the second element. When it is described that a specific component is connected to other components, the specific component may be directly connected to the other components without intervening components, or may be directly connected to the other components without intervening components.
All terms (including technical or scientific terms) used in this disclosure have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs, unless specifically defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and apparatus should be considered part of the specification.
The existing cigarette end face defect detection system compares a tobacco shred pixel interval corresponding to the empty head and the empty loose cigarette with a tobacco shred gray scale interval so as to judge whether the quality defects of the empty head and the empty loose exist on the cigarette end face of the cigarette to be detected, and cannot realize the detection of all types of the cigarette end face. The prior technical proposal has the following defects for measuring the defects of the end face of the cigarette: only empty heads and empty loose defects of the end faces of the cigarettes can be detected, and detection of all types of quality defects of the end faces of the cigarettes cannot be realized; the method can only implement the defect removal of empty head and empty looseness, and can not realize full-platform early warning of the mobile terminal of the functional personnel, the PC terminal and the lower computer of the operator; no legal quality defect is generated, thereby providing guidance for maintenance personnel to repair faults.
As shown in fig. 1, an embodiment of the present invention provides a system for detecting defects of an end surface of a cigarette, which includes: the industrial personal computer 1, the input of industrial personal computer 1 is connected with industrial camera 1, the output of industrial personal computer 1 is connected with image processing and operation workstation computer 4, image processing and operation workstation computer 4 is connected with database 5, database 5 is connected with early warning platform 6, wherein:
the industrial camera 1 is used for acquiring an end face image of the cigarette;
the industrial personal computer 3 is used for storing the cigarette end face image and transmitting the cigarette end face image to the image processing and operating workstation computer 4;
the image processing and operating workstation computer 4 is used for identifying the defects of the cigarette end face according to the cigarette end face image to obtain a cigarette end face defect type result and a defective cigarette position;
the database 5 is used for storing the cigarette end face defect type result and the defective cigarette position, and sending the cigarette end face defect type result and the defective cigarette position to the early warning platform 6;
And the early warning platform 6 is used for generating early warning information according to the cigarette end face defect type result and the defective cigarette position.
As shown in fig. 2, the industrial camera 1 is disposed on one side of a lower smoke channel 10 of a smoke warehouse of a module conveying chain plate 12, and is configured to take a picture of an end face of a cigarette in the module 11 when the module 11 conveyed on the module conveying chain plate 12 is conveyed to the lower smoke channel 10 of the smoke warehouse, so as to obtain an end face image of the cigarette. In a specific implementation, the image transmission system can be used for transmitting the acquired cigarette end face image to the image processing and operating workstation computer 4 for image processing.
In operation, a cigarette end face image is acquired through the industrial camera 1, the cigarette end face image is acquired through the industrial personal computer 3, then the cigarette end face defect identification is carried out through the image processing and operating workstation computer, a cigarette end face defect type result and a defective cigarette position are obtained, when the image processing and operating workstation computer 4 detects the defect image, the defect result is uploaded to the database 5, defect type and position comparison analysis is carried out in the database 5, and the early warning platform 6 is reported according to the defect statistical result.
Further, the cigarette end face defect detection system further comprises a light source 2 connected with the industrial personal computer 3 and used for providing illumination for the industrial camera 1. As shown in fig. 2, the light source 2 is disposed at the front end of the industrial camera 1.
Further, as shown in fig. 1, the system for detecting a defect of an end surface of a cigarette further includes a staff mobile terminal 7, a staff PC terminal 8 and an operator lower computer 9 connected to the early warning platform 6, where the early warning platform 6 is further configured to send the early warning information to at least one of the staff mobile terminal 7, the staff PC terminal 8 and the operator lower computer 9. Specifically, the database 5 is connected with the input end of the early warning platform 6, and the staff mobile end 7, the staff PC end 8 and the operator lower computer 9 are connected with the output end of the early warning platform 6. In some embodiments of the present invention, after the database 5 determines the same defect type and defect location, if the defect images of the same defect type and the same location appear continuously for a recent period of time (e.g., 1 hour), the relevant images are extracted for comparison. After confirming the similarity, the database 5 pushes the result to the early warning platform 6, and the early warning platform 6 pushes early warning information to the staff mobile terminal 7, the staff PC terminal 8 and the operator lower computer 9. In addition, according to the statistical information, the quality defect caused by the reasons of the number of the mold boxes can be obtained, and prompt information is generated for maintenance personnel. And all data are stored in the database, so that the later retrieval of early warning information is convenient for analyzing and judging the quality safety of cigarettes.
Further, the image processing and operating workstation computer 4 includes a brightness coefficient calculation module, a brightness abnormality judgment module, an image preprocessing module, a cigarette end face image slitting module and a cigarette end face image defect recognition module, wherein:
the brightness coefficient calculation module is used for calculating the brightness coefficient of the cigarette end face image;
The brightness abnormality judging module is used for judging whether the brightness of the cigarette end face image is normal or not according to the brightness coefficient;
the image preprocessing module is used for preprocessing the cigarette end face image with normal brightness;
The cigarette end face image slitting module is used for positioning the circle center of each cigarette end face, fitting the radius of the circle, and intercepting the end face image of each cigarette by utilizing the fitting circle corresponding to each cigarette;
the cigarette end face image defect recognition module is used for classifying and judging the end face image of each cut cigarette by using the trained deep neural network model so as to judge whether each cigarette end face has defects.
Specifically, the luminance coefficient calculation module includes a gray-scale image processing unit and a luminance coefficient calculation unit, wherein:
The gray level image processing unit is used for carrying out gray level image processing on the cigarette end face image, obtaining the shape and the line width of the cigarette end face image, and calculating the mean value and the deviation of gray level image pixel points;
The brightness coefficient calculating unit is used for calculating the brightness coefficient of the cigarette end face image according to the mean value and the deviation of the gray image pixel points through the following formula:
（1）
（2）
（3）
wherein, Representing the luminance coefficient of the image,The mean of the representations (image gray values-128),The average deviation is indicated as such,The gray value of the image is represented,The number of pixels of the image is represented,The number of pixels representing each gray level in the gray level histogram.
Further, the luminance abnormality determination module is specifically configured to: if the brightness coefficient of the image is smaller than or equal to a preset brightness coefficient threshold value, judging that the brightness of the cigarette end face image is normal and is in a reasonable range; and if the image brightness coefficient is larger than a preset brightness coefficient threshold value, judging that the brightness of the cigarette end face image is abnormal. And when the brightness is abnormal, indicating that the inner frame paper is absent in the small packet, and rejecting the abnormal cigarette packet. In some embodiments of the present invention, the preset luminance coefficient threshold is 5, when k <5, the image is considered normal, the luminance is within a reasonable range, when k >5, the image is considered abnormal, and it should be noted that the preset luminance coefficient threshold is not specifically limited in the present invention.
Further, the image preprocessing module is specifically configured to: and carrying out mean shift filtering noise reduction treatment on the cigarette end face image through a filter. The mean filtering can effectively eliminate high-frequency noise in the image, and the image smoothing and blurring functions are realized.
Still further, the cigarette end face image slitting module comprises a cigarette end face image slitting unit and a cigarette end face image defect recognition unit, wherein:
As shown in fig. 4, the cigarette end face image splitting unit is configured to locate, by using a hough circle detection algorithm, the center of each cigarette end face and fit the radius of the circle by using the following formula:
（4）
（5）
（6）
wherein, (x, y) represents coordinates of a cigarette end face point, (a, b) represents center coordinates of a fitting circle, and r represents a radius of the fitting circle;
the circle center and the radius are known, so that a circular graph of each cigarette can be drawn, and the position of each cigarette can be positioned through the circle center of the circular graph.
The cigarette end face image slitting unit is further used for intercepting square images which are centered on the circle center, equal in length and width and larger than the diameter by utilizing the circle center coordinates and the radius of each known cigarette fitting circle according to the circles positioned by the Hough circle method, intercepting end face images of each cigarette (slitting results are shown in fig. 5), wherein boundary positions of interception ranges of single-piece images of the cigarette end faces are calculated according to the following formula:
（7）
（8）
（9）
（10）
wherein, Represent the firstThe abscissa of the circle center of the cigarette,Represent the firstThe ordinate of the circle center of the cigarette,Representing the rectangular side length of the range to be intercepted, and obtaining by calculation、、、And determining that the cigarettes intercept single cigarette images.
Through cutting of the cigarette end face image, the whole image of the cigarette end face can be cut, the end face image of each cigarette is cut out, feature extraction is conducted on the image of each cigarette conveniently, accuracy of identifying the cigarette end face can be effectively improved, and the positions of defective cigarettes can be well determined through sorting the cigarette positions.
Further, the cigarette end face image defect identification module is specifically configured to: the cut images are sent to a trained and optimized deep neural network model for classification and judging whether defects exist, in the deep neural network model, the cut images are sent to a neural network and enter 3 dense blocks for feature extraction after passing through a convolution block, each dense block comprises two layers of convolution blocks, each convolution block consists of a convolution layer, a Batch Normalization layer and a ReLU function activation layer, after passing through an average pooling layer, a full-connection layer maps the result into two values to indicate whether the cigarettes in the images exist or not.
Correspondingly, the cigarette end face defect detection flow is shown in fig. 3, a cigarette end face image is obtained through an industrial personal computer of the existing cigarette packet visual detection system, then an image brightness coefficient is calculated, the image brightness is judged to be normal according to the image brightness coefficient, the cigarette end face image with abnormal brightness is removed, if the image brightness is normal, further depth analysis is carried out on the image, specifically, after the image pretreatment is carried out on the cigarette end face image with normal brightness, the cigarette end face image is split, the defect identification is carried out on the cigarette end face image according to the image splitting result, the normal cigarette is not defective, the defect result is uploaded to a database in a defect mode, the defect type and the position are compared and analyzed in the database, and an early warning platform is reported according to the defect statistical result.
According to the system for detecting the defects of the end faces of the cigarettes, provided by the embodiment of the invention, the end face images of the cigarettes are acquired through the industrial camera, and the end faces of the cigarettes are analyzed through the image processing and operating workstation computer, so that the detection of the defects of the end faces of the cigarettes in all types is realized, and the on-line detection of the quality of the end faces of the cigarettes in the packaging process is realized; the quality defects of the end faces of the cigarettes can be automatically identified, early warning information can be pushed to functional personnel and operators through the early warning platform, and the mould boxes generated by the defects can be positioned; effectively improves the quality of cigarette products, improves the automatic production level of the rolling equipment, improves the working efficiency, reduces the cost and reduces the working strength of manual spot check.
Thus, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concepts of the present disclosure, some details known in the art are not described. How to implement the solutions disclosed herein will be fully apparent to those skilled in the art from the above description.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It will be understood by those skilled in the art that the foregoing embodiments may be modified and equivalents substituted for elements thereof without departing from the scope and spirit of the disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (10)
1. A system for detecting defects in an end surface of a cigarette, comprising: the industrial personal computer, the input of industrial personal computer is connected with industrial camera, the output of industrial personal computer is connected with image processing and operation workstation computer, image processing and operation workstation computer is connected with the database, the database is connected with the early warning platform, wherein:
The industrial camera is used for collecting an end face image of the cigarette;
The industrial personal computer is used for storing the cigarette end face image and transmitting the cigarette end face image to the image processing and operating workstation computer;
the image processing and operating workstation computer is used for identifying the defects of the cigarette end face according to the cigarette end face image to obtain a cigarette end face defect type result and a defective cigarette position;
The database is used for storing the cigarette end face defect type result and the defective cigarette position and sending the cigarette end face defect type result and the defective cigarette position to the early warning platform;
And the early warning platform is used for generating early warning information according to the cigarette end face defect type result and the defective cigarette position.
2. The system of claim 1, wherein the industrial camera is disposed on a side of a lower smoke path of a magazine conveyor chain plate, and is configured to take a picture of an end face of a cigarette in the magazine when the magazine conveyed on the magazine conveyor chain plate is conveyed to the lower smoke path of the magazine, so as to obtain the image of the end face of the cigarette.
3. The system of claim 1, further comprising a light source connected to the industrial personal computer for providing illumination to the industrial camera; the light source is arranged at the front end of the industrial camera.
4. The system of claim 1, further comprising a staff mobile terminal, a staff PC terminal, and an operator lower computer coupled to the pre-alarm platform, the pre-alarm platform further configured to send the pre-alarm information to at least one of the staff mobile terminal, the staff PC terminal, and the operator lower computer.
5. The system of claim 4, wherein the database is connected to an input of the pre-warning platform, and the staff member moving end, the staff member PC end, and the operator lower computer are connected to an output of the pre-warning platform.
6. The system of claim 1, wherein the image processing and operating workstation computer comprises a luminance coefficient calculation module, a luminance anomaly determination module, an image preprocessing module, a cigarette end image slitting module, and a cigarette end image defect identification module, wherein:
the brightness coefficient calculation module is used for calculating the brightness coefficient of the cigarette end face image;
The brightness abnormality judging module is used for judging whether the brightness of the cigarette end face image is normal or not according to the brightness coefficient;
the image preprocessing module is used for preprocessing the cigarette end face image with normal brightness;
The cigarette end face image slitting module is used for positioning the circle center of each cigarette end face, fitting the radius of the circle, and intercepting the end face image of each cigarette by utilizing the fitting circle corresponding to each cigarette;
the cigarette end face image defect recognition module is used for classifying and judging the end face image of each cut cigarette by using the trained deep neural network model so as to judge whether each cigarette end face has defects.
7. The system for detecting defects on a cigarette end face according to claim 6, wherein the luminance coefficient calculation module comprises a gray-scale image processing unit and a luminance coefficient calculation unit, wherein:
The gray level image processing unit is used for carrying out gray level image processing on the cigarette end face image, obtaining the shape and the line width of the cigarette end face image, and calculating the mean value and the deviation of gray level image pixel points;
The brightness coefficient calculating unit is used for calculating the brightness coefficient of the cigarette end face image according to the mean value and the deviation of the gray image pixel points through the following formula:
（1）
（2）
（3）
wherein, Representing the luminance coefficient of the image,The mean of the representations (image gray values-128),The average deviation is indicated as such,The gray value of the image is represented,The number of pixels of the image is represented,The number of pixels representing each gray level in the gray level histogram.
8. The system for detecting defects on a cigarette end face according to claim 7, wherein the brightness abnormality judging module is specifically configured to: if the brightness coefficient of the image is smaller than or equal to a preset brightness coefficient threshold value, judging that the brightness of the cigarette end face image is normal and is in a reasonable range; if the brightness coefficient of the image is larger than the preset brightness coefficient threshold value, judging that the brightness of the cigarette end face image is abnormal,
The image preprocessing module is specifically used for: and carrying out mean shift filtering noise reduction treatment on the cigarette end face image through a filter.
9. The system of claim 7, wherein the cigarette end face image slitting module comprises a cigarette end face image slitting unit and a cigarette end face image defect recognition unit, wherein:
the cigarette end face image slitting unit is used for positioning the circle center of each cigarette end face through a Hough circle detection algorithm and fitting out the radius of the circle:
（4）
（5）
（6）
wherein, (x, y) represents coordinates of a cigarette end face point, (a, b) represents center coordinates of a fitting circle, and r represents a radius of the fitting circle;
The cigarette end face image cutting unit is also used for cutting out square images which are centered on the circle center, equal in length and width and larger than the diameter by utilizing the circle center coordinates and the radius of each known cigarette fitting circle according to the circle positioned by the Hough circle method, and cutting out the end face image of each cigarette, wherein the boundary position of the single-cigarette image cutting range of the cigarette end face is calculated by the following formula:
（7）
（8）
（9）
（10）
wherein, Represent the firstThe abscissa of the circle center of the cigarette,Represent the firstThe ordinate of the circle center of the cigarette,Representing the rectangular side length of the range to be intercepted, and obtaining by calculation、、、And determining that the cigarettes intercept single cigarette images.
10. The system for detecting defects of a cigarette end face according to claim 7, wherein the module for identifying defects of an image of a cigarette end face is specifically configured to: the cut images are sent to a trained and optimized deep neural network model for classification and judging whether defects exist, in the deep neural network model, the cut images are sent to a neural network and enter 3 dense blocks for feature extraction after passing through a convolution block, each dense block comprises two layers of convolution blocks, each convolution block consists of a convolution layer, a Batch Normalization layer and a ReLU function activation layer, after passing through an average pooling layer, a full-connection layer maps the result into two values to indicate whether the cigarettes in the images exist or not.
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118947958A true CN118947958A (en) | 2024-11-15 |
Family
ID=
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109772724B (en) | Flexible detection and analysis system for major surface and internal defects of castings | |
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN117152161B (en) | Shaving board quality detection method and system based on image recognition | |
| CN117557570B (en) | Rail vehicle abnormality detection method and system | |
| CN102529019B (en) | Method for mould detection and protection as well as part detection and picking | |
| CN113548419A (en) | Belt tearing detection method, device and system based on machine vision image recognition | |
| CN111683227A (en) | Belt operation intelligent auxiliary method and system based on video anomaly monitoring | |
| KR20210122429A (en) | Method and System for Artificial Intelligence based Quality Inspection in Manufacturing Process using Machine Vision Deep Learning | |
| CN116177146A (en) | Conveying belt detection system and method based on AI and laser monitoring technology | |
| CN118947958A (en) | Cigarette end face defect detection system | |
| CN115218790A (en) | Bar detection method, device and system | |
| CN117952899A (en) | Detection method and detection device for surface defects of aluminum foil and splitting machine | |
| CN117409005A (en) | Defective product detection system and method for plate receiving machine based on image | |
| CN111570313A (en) | Condom packaging box code detection system and detection method based on machine vision | |
| CN114120175A (en) | Method for identifying foreign matters on coal conveying belt based on computer vision | |
| CN114998312B (en) | Tobacco shred width detection method, device and storage medium | |
| CN115593882A (en) | Equipment abnormity detection system and method based on three-dimensional detection robot | |
| CN112330606A (en) | Defect detection method based on machine learning | |
| CN118518590B (en) | Performance data tracking method and system for detection jig | |
| CN113390884A (en) | Cigarette abnormity monitoring method and device for cigarette conveying channel of cigarette equipment | |
| CN219253345U (en) | Pop can conductivity detection device based on visual identification | |
| CN112794022B (en) | Cigarette flow monitoring system | |
| CN115019230A (en) | Automatic plugboard position monitoring method based on video monitoring image recognition | |
| CN115909155A (en) | Inspection method for auxiliary equipment of thermal power plant | |
| CN118858284A (en) | Powder bin caking and foreign matter detection device and method based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |