CN114505239A - Tobacco shred foreign matter removing equipment and removing method - Google Patents
Tobacco shred foreign matter removing equipment and removing method Download PDFInfo
- Publication number
- CN114505239A CN114505239A CN202111633976.9A CN202111633976A CN114505239A CN 114505239 A CN114505239 A CN 114505239A CN 202111633976 A CN202111633976 A CN 202111633976A CN 114505239 A CN114505239 A CN 114505239A
- Authority
- CN
- China
- Prior art keywords
- foreign matter
- multispectral
- matter removing
- tobacco
- camera
- 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 80
- 238000000034 method Methods 0.000 title claims abstract description 23
- 244000061176 Nicotiana tabacum Species 0.000 title 1
- 241000208125 Nicotiana Species 0.000 claims abstract description 79
- 230000010365 information processing Effects 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000001228 spectrum Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 8
- 238000005286 illumination Methods 0.000 claims abstract description 5
- 230000002159 abnormal effect Effects 0.000 claims description 27
- 230000007480 spreading Effects 0.000 claims description 18
- 238000003892 spreading Methods 0.000 claims description 18
- 229910052736 halogen Inorganic materials 0.000 claims description 15
- 150000002367 halogens Chemical class 0.000 claims description 15
- 238000007405 data analysis Methods 0.000 claims description 9
- 230000003595 spectral effect Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000017105 transposition Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 2
- 230000005856 abnormality Effects 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 19
- 239000010410 layer Substances 0.000 description 4
- 235000019504 cigarettes Nutrition 0.000 description 3
- 239000012535 impurity Substances 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 1
- 210000003746 feather Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/363—Sorting apparatus characterised by the means used for distribution by means of air
Abstract
The invention discloses a tobacco foreign matter removing device and a removing method, wherein the tobacco foreign matter removing device comprises a thinning device, a conveying device, a multi-spectrum camera detection device, a light source device, a foreign matter removing device, an information processing system and a controller, wherein the thinning device is arranged above a conveying belt, and a gap is formed between the thinning device and the conveying belt; the multi-spectral camera detection device comprises a multi-spectral camera, wherein a lens face of the multi-spectral camera faces the conveying belt and is parallel to the length direction of the conveying belt, and the multi-spectral camera is in communication connection with the information processing system and is used for linearly scanning and collecting multi-spectral image data of the tobacco shreds; the light source device is used for meeting the illumination intensity of the multispectral camera when acquiring multispectral image data; the direction of the air flow sprayed by the air flow nozzle is parallel to the width direction of the conveying belt, and the foreign matter removing device is in communication connection with the controller so as to remove foreign matters in the tobacco shreds. The tobacco foreign matter removing equipment and the tobacco foreign matter removing method provided by the invention have the advantages that the production cost is reduced, and the production efficiency is improved.
Description
Technical Field
The invention relates to the technical field of tobacco production and manufacturing, in particular to tobacco shred foreign matter removing equipment and a tobacco shred foreign matter removing method.
Background
In the processes of purchase, transportation and production processing, tobacco can be mixed with impurities such as plastic, feather, rubber, paper and the like to different degrees, and in order to ensure the purity of cigarette raw materials, cigarette enterprises take different measures to remove the impurities in different production flows.
Among the prior art, the metal detection edulcoration has been equipped with on the production line of production cigarette, the selection by winnowing edulcoration, the edulcoration system based on image and laser, because different equipment can only reject to a certain class of debris, to the size, the colour, when proportion and tobacco difference are not big, equipment is difficult to discern, need artifical the choosing, take a lot of trouble and hard, in addition, tobacco shreds back is difficult to discern and rejects more, it picks to have special personnel, the manual work is very difficult to pick, and need shut down after discovering the foreign matter, carry out subsequent the choosing after collecting the material case with all pipe tobaccos that probably contain the foreign matter, above-mentioned in-process, the work load of artifical selection is big, high in production cost, low in production efficiency.
Disclosure of Invention
In view of this, the present invention provides a device and a method for removing foreign matters from tobacco shreds, so as to reduce the production cost and improve the production efficiency.
Based on the above purpose, the present invention provides a tobacco shred foreign matter removing device, which comprises a thinning device, a conveying device, a multi-spectrum camera detection device, a light source device, a foreign matter removing device, an information processing system and a controller, wherein: the conveying device comprises a conveying belt, an input end and an output end; the spreading device is arranged above the conveying belt and is positioned at the input end, and a gap is formed between the spreading device and the conveying belt, so that the cut tobacco is spread by a thin layer after passing through the gap; the multi-spectral camera detection device comprises a multi-spectral camera, the multi-spectral camera is arranged right above the width direction of the conveying belt, a lens surface of the multi-spectral camera faces the conveying belt and is parallel to the length direction of the conveying belt, the multi-spectral camera is in communication connection with the information processing system, and the multi-spectral camera is used for linearly scanning and collecting multi-spectral image data of the tobacco shreds; the light source device is electrically connected with a power supply, and the light source device surrounds the multispectral camera so as to meet the illumination intensity of the multispectral camera when acquiring the multispectral image data; the foreign matter removing device is arranged at the output end and comprises an air flow nozzle, the air flow direction sprayed by the air flow nozzle is parallel to the width direction of the conveying belt, and the foreign matter removing device is in communication connection with the controller to remove foreign matters in the tobacco shreds.
Optionally, the light source device is a plurality of halogen lamps, the plurality of halogen lamps are divided into two groups, the two groups of halogen lamps are respectively located on two sides of the length direction of the conveyor belt and on two sides of the multispectral camera, and the power of the halogen lamps is greater than 200W.
Optionally, the vertical distance between the multispectral camera and the conveyor belt is 0.8m-1m, and the field angle of the multispectral camera is 30-40 °.
Optionally, the spreading device is one of a star roller spreading device, a scraper device and a vibration conveying spreading device.
Optionally, the multispectral camera is a filter-splitting linear scanning camera, the number of the wave bands is greater than 5, the multispectral camera comprises a 475nm wave band, a 590nm wave band, a 758nm wave band, a 805nm wave band and a 990nm wave band, and the linear scanning frame rate is greater than 1000 fps.
Optionally, the gap is 2-3cm, and the belt speed is 2-3 m/s.
Optionally, the information processing system includes a multispectral information storage module, a multispectral data preprocessing module, a multispectral data analysis module, and an image marking module, where the multispectral information storage module and the multispectral data preprocessing module are respectively used for storing and processing spectral information, so as to smooth and reduce noise of the multispectral image data; the multispectral data analysis module is used for realizing dimension reduction, feature extraction and spectral data analysis of the multispectral image data and extracting the feature spectrum and position information of the foreign matter; the image marking module is used for marking the position and the shape of the foreign matter so as to analyze and process the multispectral image data collected by the multispectral camera, mark the position where the foreign matter appears in an image, and transmit corresponding abnormal signals and position information to the foreign matter removing device.
Based on the same invention concept, the invention also provides a tobacco foreign matter removing method, which is used for removing tobacco foreign matters by using the tobacco foreign matter removing equipment in any technical scheme and comprises the following steps: turning on the light source device and the multispectral camera, and performing multispectral camera linear scanning on the cut tobacco which is positioned on the input end and passes through the spreading device; acquiring each single frame of multispectral image data, and simultaneously carrying out anomaly detection on the single frame of multispectral image data; calculating the similarity between each pixel in the single-frame multispectral image data and the line data as a background, and returning the gray value of each pixel; performing threshold segmentation on the single-frame multispectral image data, and marking the data position of an abnormal pixel; when three continuous abnormal pixels appear transversely or longitudinally, position information is transmitted to the information processing system, and the controller controls the foreign matter removing device to remove foreign matters.
Optionally, each single frame of multispectral image data acquired by the multispectral camera is subjected to anomaly detection and is segmented into the abnormal pixels by a threshold, and when 3 or more abnormal pixels continuously appear in the transverse direction or the longitudinal direction, the image marking module records the center positions of the continuously marked abnormal pixels by the following steps: the first step is as follows: when the multispectral camera linearly scans and acquires multispectral image data of each single frame, all pixels of the row are used as background pixels, the spectral mean mu and the covariance matrix K of P dimensions of the background pixels are calculated, and the method is realized by the following formula:
r represents the row of pixels to be detected;
the second step is that: calculating the likelihood fraction sigma of each pixel of the row and the background is realized by the following formula:
σ＝(r-μ)TK-1(r-μ)
t represents matrix transposition;
the third step: dividing the row of data by using a threshold value, wherein the division threshold value is omega, abnormal pixels are larger than omega, and background cut tobacco is smaller than omega;
the fourth step: when more than three adjacent pixels in each row or each column are marked as abnormal pixels, the information processing system sends the position information of the foreign matters to the foreign matter removing device according to the central position of the adjacent abnormal pixels;
the fifth step: the foreign matter removing device receives a removing instruction of the controller and controls the airflow nozzle to remove the foreign matters at the marked positions.
The invention provides a tobacco foreign matter removing device and a removing method, wherein the tobacco foreign matter removing device comprises a spreading device, a conveying device, a multi-spectral camera detection device, a light source device, a foreign matter removing device, an information processing system and a controller.
Drawings
The objects and advantages of the present invention will be understood by the following detailed description of the preferred embodiments of the invention, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic structural view of a tobacco foreign matter removing device according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for removing foreign matters from tobacco shreds according to an embodiment of the present invention.
Description of reference numerals:
1: a thinning device; 2: a conveying device; 3: a multispectral camera detection device; 4: a light source device; 5: a foreign matter removing device; 6: an information processing system; 7: a controller;
21: a conveyor belt; 22: an input end; 23: an output end;
31: a multispectral camera; 32: a lens surface.
Detailed Description
The present invention will be described in detail with reference to examples. In which like parts are designated by like reference numerals. It should be noted that the terms "front," "back," "left," "right," "upper" and "lower" used in the following description refer to directions in the drawings, and the terms "inner" and "outer" refer to directions toward and away from, respectively, the geometric center of a particular component.
As shown in fig. 1, the device for removing foreign matters from tobacco shreds provided by the present invention comprises a spreading device 1, a conveying device 2, a multi-spectrum camera detection device 3, a light source device 4, a foreign matter removing device 5, an information processing system 6 and a controller 7, wherein: the conveying device 2 comprises a conveying belt 21, an input end 22 and an output end 23; the spreading device 1 is arranged above the conveying belt 21 and is positioned at the input end 22, and a gap is formed between the spreading device 1 and the conveying belt 21, so that the cut tobacco is spread by a thin layer after passing through the gap; the multi-spectral camera detection device 3 comprises a multi-spectral camera 31, the multi-spectral camera 31 is arranged right above the width direction of the conveying belt 21, a lens surface 32 of the multi-spectral camera 31 faces the conveying belt 21 and is parallel to the length direction of the conveying belt 21, the multi-spectral camera is in communication connection with the information processing system 6, and the multi-spectral camera is used for linearly scanning and collecting multi-spectral image data of tobacco shreds; the light source device 4 is electrically connected with a power supply, and the light source device 4 surrounds the periphery of the multispectral camera so as to meet the illumination intensity of the multispectral camera when acquiring multispectral image data; the foreign matter removing device 5 is arranged at the output end 23, the foreign matter removing device 5 comprises an air flow nozzle, the air flow direction sprayed by the air flow nozzle is parallel to the width direction of the conveying belt 21, and the foreign matter removing device 5 is in communication connection with the controller 7 so as to remove foreign matters in tobacco shreds.
It should be noted that: the spreading device 1, the conveying device 2, the multi-spectrum camera detection device 3, the light source device 4 and the foreign matter removing device 5 can be erected and installed on the ground.
The invention provides tobacco shred foreign matter removing equipment which comprises a thinning device 1, a conveying device 2, a multi-spectrum camera detection device 3, a light source device 4, a foreign matter removing device 5, an information processing system 6 and a controller 7, wherein when tobacco shreds are positioned at an input end 22 and pass through a gap between the thinning device 1 and a conveying belt 21, the tobacco shreds are paved by a thin layer, a multi-spectrum camera 31 acquires multi-spectrum image data of the tobacco shreds, the information processing system 6 processes the multi-spectrum image data, and when foreign matters are found in the tobacco shreds, the controller 7 controls an air flow nozzle in the foreign matter removing device 5 to spray air flow so as to remove the foreign matters from the tobacco shreds, thereby avoiding the manual removal of the foreign matters in the tobacco shreds, reducing the production cost and improving the production efficiency.
As shown in fig. 1, the light source device 4 is a plurality of halogen lamps, the plurality of halogen lamps are divided into two groups, the two groups of halogen lamps are respectively located at two sides of the length direction of the conveyor belt 21 and at two sides of the multispectral camera 31, and the power of the halogen lamps is greater than 200W. In this embodiment, specifically, four halogen lamps may be used, and the halogen lamps with power greater than 200W can provide sufficient illumination intensity for the multispectral camera 31 when acquiring image data, and the halogen lamps are cheap and easy to acquire, so that the production cost of the tobacco shred foreign matter removing device is reduced.
In one embodiment of the invention, the vertical distance between the multispectral camera 31 and the conveying belt 21 is 0.8m-1m, the field angle of the multispectral camera is 30-40 degrees, multispectral image data of tobacco shreds can be better collected, and the use reliability of the tobacco shred foreign matter removing equipment is improved.
In an embodiment of the invention, the spreading device 1 is one of a star roller type spreading device, a scraper type device and a vibration conveying spreading device 1, and the device is convenient to use, so that the use convenience of the tobacco foreign matter removing equipment is improved.
In an embodiment of the invention, the multispectral camera 31 is a filter light-splitting linear scanning camera, the number of the wave bands is more than 5, the wave bands comprise 475nm wave bands, 590nm wave bands, 758nm wave bands, 805nm wave bands and 990nm wave bands, the linear scanning frame rate is more than 1000fps, multispectral image data of tobacco shreds can be well collected, and the use reliability of the tobacco shred foreign matter removing equipment is improved.
In one embodiment of the invention, the gap is 2-3cm, the belt speed is 2-3m/s, and foreign matters can be exposed on the surface layer of the cut tobacco as much as possible while the cut tobacco is spread to be thin, so that the foreign matters can be effectively removed, and the production efficiency of the cut tobacco foreign matter removing equipment is improved.
In one embodiment of the invention, the information processing system 6 comprises a multispectral information storage module, a multispectral data preprocessing module, a multispectral data analysis module and an image marking module, wherein the multispectral information storage module and the multispectral data preprocessing module are respectively used for storing and processing spectral information so as to realize smoothing and noise reduction of multispectral image data; the multispectral data analysis module is used for realizing dimension reduction, feature extraction, spectral data analysis and extraction of feature spectrum and position information of foreign matters of multispectral image data; the image marking module is used for marking the position and the form of the foreign body, analyzing and processing multispectral image data collected by the multispectral camera 31, marking the position where the foreign body appears in an image, and transmitting a corresponding abnormal signal and position information to the foreign body removing device 5, so that the foreign body can be effectively detected in tobacco shreds, the foreign body is removed, and the production efficiency of the tobacco shred foreign body removing device is improved.
As shown in fig. 1 and 2, based on the same inventive concept, an embodiment of the present invention further provides a method for removing foreign matters from tobacco shreds, where the method for removing foreign matters from tobacco shreds using the apparatus for removing foreign matters from tobacco shreds according to any of the embodiments includes the following steps: turning on the light source device 4 and the multispectral camera, and performing linear scanning on the tobacco shreds on the input end 22 after passing through the thinning device 1 by using the multispectral camera 31; acquiring each single-frame multispectral image data, and simultaneously carrying out anomaly detection on the single-frame multispectral image data; calculating the similarity between each pixel in the single-frame multispectral image data and the line data as a background, and returning the gray value of each pixel; carrying out threshold segmentation on the single-frame multispectral image data, and marking the data position of an abnormal pixel; when three continuous abnormal pixels appear transversely or longitudinally, the position information is transmitted to the information processing system 6, and the controller 7 controls the foreign matter removing device 5 to remove foreign matters.
In an embodiment of the present invention, each single frame of multispectral image data collected by the multispectral camera 31 is subjected to anomaly detection and is segmented into abnormal pixels by a threshold, and when 3 or more abnormal pixels continuously appear in the transverse direction or the longitudinal direction, the image marking module records the center positions of the continuously marked abnormal pixels by the following steps: the first step is as follows: when the multispectral camera 31 linearly scans and acquires multispectral image data of each single frame, all pixels of the row are used as background pixels, and the spectral mean mu and the covariance matrix K of P dimensions of the background pixels are calculated and are realized through the following formulas:
r represents the row of pixels to be detected;
the second step is that: calculating the likelihood fraction sigma of each pixel of the row and the background is realized by the following formula:
σ＝(r-μ)TK-1(r-μ)
t represents matrix transposition;
the third step: dividing the row of data by using a threshold value, wherein the division threshold value is omega, abnormal pixels are larger than omega, and background cut tobacco is smaller than omega;
the fourth step: when more than three adjacent pixels in each row or each column are marked as abnormal pixels, the information processing system 6 sends the position information of the foreign matters to the foreign matter removing device 5 according to the central position of the adjacent abnormal pixels;
the fifth step: the foreign matter removing device 5 receives a removing instruction from the controller 7, and controls the air flow nozzle to remove the foreign matter at the marked position.
The invention provides a tobacco foreign matter removing device and a removing method, wherein the tobacco foreign matter removing device comprises a thinning device 1, a conveying device 2, a multi-spectral camera detection device 3, a light source device 4, a foreign matter removing device 5, an information processing system 6 and a controller 7, when tobacco is positioned at an input end 22 and passes through a gap between the thinning device 1 and a conveying belt 21, the tobacco is paved by a thin layer, a multi-spectral camera 31 acquires multi-spectral image data of the tobacco, the information processing system 6 processes the multi-spectral image data, and when foreign matters are found in the tobacco, the controller 7 controls an air flow nozzle in the foreign matter removing device 5 to spray air flow so as to remove the foreign matters from the tobacco, thereby avoiding the manual removal of the foreign matters in the tobacco, reducing the production cost and improving the production efficiency.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will appreciate that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. The utility model provides a pipe tobacco foreign matter rejection apparatus, its characterized in that, includes and spreads out thin device, conveyor, multispectral camera detection device, light source device, rejects foreign matter device, information processing system and controller, wherein:
the conveying device comprises a conveying belt, an input end and an output end;
the spreading device is arranged above the conveying belt and is positioned at the input end, and a gap is formed between the spreading device and the conveying belt, so that the cut tobacco is spread by a thin layer after passing through the gap;
the multi-spectral camera detection device comprises a multi-spectral camera, the multi-spectral camera is arranged right above the width direction of the conveying belt, a lens surface of the multi-spectral camera faces the conveying belt and is parallel to the length direction of the conveying belt, the multi-spectral camera is in communication connection with the information processing system, and the multi-spectral camera is used for linearly scanning and collecting multi-spectral image data of the tobacco shreds;
the light source device is electrically connected with a power supply, and the light source device surrounds the multispectral camera so as to meet the illumination intensity of the multispectral camera when acquiring the multispectral image data;
the foreign matter removing device is arranged at the output end and comprises an air flow nozzle, the air flow direction sprayed by the air flow nozzle is parallel to the width direction of the conveying belt, and the foreign matter removing device is in communication connection with the controller to remove foreign matters in the tobacco shreds.
2. The tobacco shred foreign matter removing equipment according to claim 1, wherein the light source device is a plurality of halogen lamps, the halogen lamps are divided into two groups, the two groups of halogen lamps are respectively positioned at two sides of the length direction of the conveying belt and at two sides of the multispectral camera, and the power of the halogen lamps is more than 200W.
3. The tobacco shred foreign matter removing device according to claim 2, wherein the vertical distance between the multispectral camera and the conveying belt is 0.8m-1m, and the angle of field of the multispectral camera is 30-40 °.
4. The tobacco foreign matter removing apparatus according to claim 3, wherein the thinning device is one of a star roller type spreading device, a scraper type device, and a vibration conveying thinning device.
5. The tobacco shred foreign matter removing equipment according to claim 4, wherein the multispectral camera is a filter splitting type linear scanning camera, the number of the wave bands is more than 5, the wave bands comprise 475nm wave bands, 590nm wave bands, 758nm wave bands, 805nm wave bands and 990nm wave bands, and the linear scanning frame rate is more than 1000 fps.
6. The tobacco foreign matter removing apparatus according to claim 5, wherein the gap is 2-3cm, and the belt speed is 2-3 m/s.
7. The tobacco shred foreign matter removing device according to claim 6, wherein the information processing system comprises a multispectral information storage module, a multispectral data preprocessing module, a multispectral data analysis module and an image marking module, wherein the multispectral information storage module and the multispectral data preprocessing module are respectively used for storing and processing spectral information to realize smoothing and noise reduction of the multispectral image data; the multispectral data analysis module is used for realizing dimension reduction, feature extraction and spectral data analysis of the multispectral image data and extracting the feature spectrum and position information of the foreign matter; the image marking module is used for marking the position and the shape of the foreign matter so as to analyze and process the multispectral image data collected by the multispectral camera, mark the position where the foreign matter appears in an image, and transmit corresponding abnormal signals and position information to the foreign matter removing device.
8. A tobacco foreign matter removing method is characterized in that tobacco foreign matter removing is carried out by using the tobacco foreign matter removing equipment of any one of claims 1 to 7, and the method comprises the following steps:
turning on the light source device and the multispectral camera, and performing multispectral camera linear scanning on the cut tobacco which is positioned on the input end and passes through the spreading device;
acquiring each single frame of multispectral image data, and simultaneously carrying out anomaly detection on the single frame of multispectral image data;
calculating the similarity between each pixel in the single-frame multispectral image data and the line data as a background, and returning the gray value of each pixel;
performing threshold segmentation on the single-frame multispectral image data, and marking the data position of an abnormal pixel;
when three continuous abnormal pixels appear transversely or longitudinally, position information is transmitted to the information processing system, and the controller controls the foreign matter removing device to remove foreign matters.
9. The tobacco shred foreign matter removing method according to claim 8, wherein abnormality detection is performed on each single frame of multispectral image data collected by a multispectral camera and the abnormal pixel is segmented by a threshold, and when 3 or more abnormal pixels continuously appear in the transverse direction or the longitudinal direction, the image marking module records the center position of the continuously marked abnormal pixel by the following steps:
the first step is as follows: when the multispectral camera linearly scans and acquires multispectral image data of each single frame, all pixels of the row are used as background pixels, the spectral mean mu and the covariance matrix K of P dimensions of the background pixels are calculated, and the method is realized by the following formula:
r represents the row of pixels to be detected;
the second step is that: calculating the likelihood fraction sigma of each pixel of the row and the background is realized by the following formula:
σ＝(r-μ)TK-1(r-μ)
t represents matrix transposition;
the third step: dividing the row of data by using a threshold value, wherein the division threshold value is omega, abnormal pixels are larger than omega, and background cut tobacco is smaller than omega;
the fourth step: when more than three adjacent pixels in each row or each column are marked as abnormal pixels, the information processing system sends the position information of the foreign matters to the foreign matter removing device according to the central position of the adjacent abnormal pixels;
the fifth step: the foreign matter removing device receives a removing instruction of the controller and controls the airflow nozzle to remove the foreign matters at the marked positions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111633976.9A CN114505239A (en) | 2021-12-29 | 2021-12-29 | Tobacco shred foreign matter removing equipment and removing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111633976.9A CN114505239A (en) | 2021-12-29 | 2021-12-29 | Tobacco shred foreign matter removing equipment and removing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114505239A true CN114505239A (en) | 2022-05-17 |
Family
ID=81547728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111633976.9A Pending CN114505239A (en) | 2021-12-29 | 2021-12-29 | Tobacco shred foreign matter removing equipment and removing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114505239A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115104757A (en) * | 2022-06-20 | 2022-09-27 | 河南中烟工业有限责任公司 | Tobacco shred foreign matter control system, electronic equipment and storage medium |
| CN115410077A (en) * | 2022-11-02 | 2022-11-29 | 杭州首域万物互联科技有限公司 | Method for realizing cut tobacco impurity detection and identification based on YOLOV7 target detection algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000028544A (en) * | 1998-07-08 | 2000-01-28 | Japan Tobacco Inc | Near-infrared ray type foreign material inspection device |
| CN103071629A (en) * | 2013-02-07 | 2013-05-01 | 中国烟草总公司郑州烟草研究院 | Process and device for detecting foreign matters and selecting tobacco leaves before redrying tobacco lamina |
| CN205146716U (en) * | 2015-05-11 | 2016-04-13 | 南京文采科技有限责任公司 | Shaker based on timesharing exposure and many spectral imaging |
| CN110501346A (en) * | 2019-09-24 | 2019-11-26 | 江南大学 | Quality detection system based on multi-optical spectrum image collecting technology |
| CN215142340U (en) * | 2021-07-08 | 2021-12-14 | 广东中烟工业有限责任公司 | Automatic identifying and removing device for tobacco shred sundries |
| CN215189387U (en) * | 2021-04-24 | 2021-12-17 | 河南中烟工业有限责任公司 | Tobacco shred foreign matter blowing and removing device |
-
2021
- 2021-12-29 CN CN202111633976.9A patent/CN114505239A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000028544A (en) * | 1998-07-08 | 2000-01-28 | Japan Tobacco Inc | Near-infrared ray type foreign material inspection device |
| CN103071629A (en) * | 2013-02-07 | 2013-05-01 | 中国烟草总公司郑州烟草研究院 | Process and device for detecting foreign matters and selecting tobacco leaves before redrying tobacco lamina |
| CN205146716U (en) * | 2015-05-11 | 2016-04-13 | 南京文采科技有限责任公司 | Shaker based on timesharing exposure and many spectral imaging |
| CN110501346A (en) * | 2019-09-24 | 2019-11-26 | 江南大学 | Quality detection system based on multi-optical spectrum image collecting technology |
| CN215189387U (en) * | 2021-04-24 | 2021-12-17 | 河南中烟工业有限责任公司 | Tobacco shred foreign matter blowing and removing device |
| CN215142340U (en) * | 2021-07-08 | 2021-12-14 | 广东中烟工业有限责任公司 | Automatic identifying and removing device for tobacco shred sundries |
Non-Patent Citations (1)
| Title |
|---|
| 付航;李果;许成;袁兴;朱云霞;闻平;: "基于智能相机的残烟丝异物智能剔除系统的研究", 科技创新导报, no. 09 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115104757A (en) * | 2022-06-20 | 2022-09-27 | 河南中烟工业有限责任公司 | Tobacco shred foreign matter control system, electronic equipment and storage medium |
| CN115410077A (en) * | 2022-11-02 | 2022-11-29 | 杭州首域万物互联科技有限公司 | Method for realizing cut tobacco impurity detection and identification based on YOLOV7 target detection algorithm |
| CN115410077B (en) * | 2022-11-02 | 2023-03-24 | 杭州首域万物互联科技有限公司 | Method for realizing cut tobacco impurity detection based on YOLOV7 target detection algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114505239A (en) | Tobacco shred foreign matter removing equipment and removing method | |
| CN111275679B (en) | Image-based solar cell defect detection system and method | |
| CN108230315B (en) | Mask belt loss detection method based on machine vision | |
| CN113962997B (en) | Strip steel edge crack defect detection method and system based on image processing | |
| CN109697717B (en) | Lining crack identification method based on image automatic search | |
| CN110261391A (en) | A kind of LED chip appearance detection system and method | |
| CN102663760A (en) | Location and segmentation method for windshield area of vehicle in images | |
| CN103177445A (en) | Outdoor tomato identification method based on subsection threshold image segmentation and light spot identification | |
| CN103387123A (en) | Mine adhesive tape tearing intelligent detecting system based on machine vision | |
| CN112560941A (en) | Coal and gangue identification method based on image detection | |
| CN106485696A (en) | A kind of detection method of the explosive dangerous materials stitch defect based on machine vision | |
| CN103175850A (en) | Detection method and system for material surface detects of wide-range high-speed production line | |
| CN106934796A (en) | High-speed belt conveyor rock slag video analytic system and method that rock tunnel(ling) machine is carried | |
| CN107256549B (en) | Bamboo strip defect detection method based on machine vision | |
| CN101770645A (en) | Method and system for quickly segmenting high-resolution color image of cotton foreign fibers | |
| CN106900601A (en) | A kind of fast accurate identification prawn image shrimp head method of the point with shrimp tail point | |
| CN112950602B (en) | Candy defect detection device and classification method based on depth camera and machine learning | |
| Kumuda et al. | Edge based segmentation approach to extract text from scene images | |
| CN115423799A (en) | Method and device for identifying surface cracks of continuous casting billet | |
| Nagarasu et al. | Automatic irrigation and worm detection for peanut field using Raspberry pi with OpenCV | |
| CN115994921A (en) | Mature cherry fruit image segmentation method integrating HSV model and improving Otsu algorithm | |
| CN115358972A (en) | Tobacco leaf grading method and system based on visual feature fusion | |
| CN115358991A (en) | Method and system for identifying seedling leaking quantity and position of seedlings | |
| CN111144513B (en) | Industrial product spraying defect data enhancement method combining generation countermeasure network and traditional image processing technology | |
| CN104574398A (en) | Boxed cigarette filter stick counting system based on line scanning camera |
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 |