A cigarette appearance inspection system and method based on image processing

Abstract

The application provides a cigarette appearance inspection system and method based on image processing, and belongs to the technical field of cigarette detection. The system comprises: a sampling module which sequentially grabs cigarette samples from a conveying bridge according to a sampling quantity and a sampling period; a weighing module which weighs the sampled cigarettes and provides the weighed cigarettes to a main control module; a whole appearance inspection module which photographs the sampled cigarettes and provides whole cigarette images to the main control module; a tipping paper appearance inspection module which cuts tipping paper of the sampled cigarettes, photographs the tipping paper to obtain tipping paper images, and provides the tipping paper images to the main control module; and the main control module controls starting of the sampling module, the weighing module, the whole appearance inspection module and the tipping paper inspection module, processes the whole cigarette images and the tipping paper images, and then combines the weighing results to evaluate appearance quality of the sampled cigarettes. The application realizes automatic sampling in a cigarette production process, performs comprehensive appearance inspection, improves appearance quality of the cigarettes, reduces waste of auxiliary materials, and saves labor cost.

Description

Technical Field

[0001] This invention belongs to the field of cigarette inspection technology, specifically relating to a cigarette appearance inspection system and method based on image processing. Background Technology

[0002] The cigarette rolling and packaging equipment in the cigarette production workshop mainly uses ultra-high-speed units. While these machines operate quickly, some have been in use for a long time, resulting in inconsistent cigarette quality. Currently, cigarette appearance inspection relies on operators and inspectors manually checking quality at specified times. However, manual inspection is prone to incomplete checks, misjudgments, and delays, easily leading to potential quality issues in cigarette production. If substandard cigarettes are found, the rolling and packaging equipment needs to rework them quickly. This rework wastes resources such as cartons, individual boxes, inner lining paper, aluminum rods, tipping paper, and roll paper, and requires significant manpower and resources, impacting the cleanliness of the workshop. More seriously, if substandard cigarettes with appearance defects enter the market, it negatively impacts consumer experience and may even lead to consumer complaints.

[0003] In summary, due to the long service life of existing cigarette rolling and packaging equipment, the quality of cigarettes is unstable, resulting in an increase in the number of cigarettes with substandard appearance. However, the existing manual inspection method is prone to false detections, missed detections, and untimely inspections, which is not conducive to the quality control of cigarette appearance. If rework is required, it will result in a waste of resources, materials, and manpower. If the cigarettes enter the market, it will affect the consumer experience.

[0004] This is a shortcoming of the existing technology. Therefore, it is very necessary to provide a cigarette appearance inspection system and method based on image processing to address the above-mentioned defects in the existing technology. Summary of the Invention

[0005] In view of the above-mentioned problems in the existing cigarette rolling and packaging equipment, which suffers from unstable cigarette quality due to long machine age and an increase in the number of cigarettes with substandard appearance, and the shortcomings of the existing manual inspection method, such as false detection, missed detection and untimely inspection, which are not conducive to the control of cigarette appearance quality, the present invention provides a cigarette appearance inspection system and method based on image processing to solve the above-mentioned technical problems.

[0006] In a first aspect, the present invention provides a cigarette appearance inspection system based on image processing, including a sampling module, a weighing module, an overall appearance inspection module, a cutting inspection module, and a main control module.

[0007] The sampling module is used to sequentially grab cigarettes from the conveyor bridge line from rolling to packaging for sampling according to the sampling quantity and sampling cycle;

[0008] The weighing module is used to weigh the sampled cigarettes and provide the weighing results to the main control module;

[0009] The overall appearance inspection module is used to take pictures of the sampled cigarettes to obtain an overall image of the cigarettes and provide it to the main control module.

[0010] The tipping paper appearance inspection module is used to cut the tipping paper of the sampled cigarettes, take pictures of the cut tipping paper to obtain images of the tipping paper and provide them to the main control module;

[0011] The main control module controls the startup of the sampling module, weighing module, overall appearance inspection module, and tipping paper inspection module, processes the overall image of the cigarette and the tipping paper image, and then evaluates the appearance quality of the sampled cigarettes in combination with the weighing results.

[0012] Furthermore, it also includes inspecting the equipment housing;

[0013] The sampling module includes a cigarette gripping mechanism and a cigarette conveying mechanism; both the cigarette gripping mechanism and the cigarette conveying mechanism are connected to the main control module.

[0014] The cigarette grabbing mechanism is located outside the housing of the testing equipment and above the conveyor bridge. It receives control from the main control module to grab a set number of cigarettes according to a set sampling cycle.

[0015] The cigarette conveying mechanism receives control from the main control module and works in conjunction with the cigarette grabbing mechanism to deliver the grabbed cigarettes to the sampling inlet of the testing equipment housing.

[0016] Furthermore, the weighing module includes a balance and a first tilting mechanism;

[0017] The balance and the first flipping mechanism are both connected to the main control module;

[0018] The first flipping mechanism is located at the bottom of the balance.

[0019] The balance receives the sampled cigarettes entering from the sampling inlet, obtains the weight of the cigarettes, and provides the weight of the cigarettes to the main control module.

[0020] The main control module controls the first flipping mechanism to flip the balance, allowing the cigarette to enter the overall appearance inspection module. Furthermore, the overall appearance inspection module includes a rotatable suction cup, a first camera, and an infrared detection unit; the first camera is located on the side of the rotatable suction cup, and the infrared detection unit is located on the top of the rotatable suction cup, and the rotatable suction cup, the first camera, and the infrared detection unit are all connected to the main control module.

[0021] The rotatable suction cup vertically adsorbs the weighed cigarette, keeping the cigarette filter at the bottom;

[0022] The first camera receives control from the main control module to take pictures of the cigarette stick adsorbed by the rotatable suction cup and obtain an overall image of the first cigarette stick.

[0023] The main control module controls the rotatable suction cup to rotate 180 degrees, and then controls the first camera to take pictures of the cigarette sticks adsorbed by the rotatable suction cup, thereby obtaining an overall image of the second cigarette stick.

[0024] The infrared detection unit receives control from the main control module to detect the upper surface of the cigarette and determines whether the cigarette is empty or has a contact point based on the feedback light information.

[0025] Furthermore, the tipping paper appearance inspection module includes a cigarette turning mechanism, a cigarette pushing mechanism, a cigarette fixing mechanism, a cutting mechanism, a filter adsorption mechanism, a tipping paper clamping mechanism, and a second camera;

[0026] The cigarette turning mechanism, cigarette fixing mechanism, cigarette pushing mechanism, cutting mechanism, filter adsorption mechanism, tipping paper clamping mechanism, and second camera are all connected to the main control module;

[0027] The cigarette turning structure receives control from the main control module, turns the cigarette from vertical to horizontal after the overall appearance inspection, and then pushes the cigarette out through the cigarette pushing mechanism 13 and provides it to the cigarette fixing mechanism.

[0028] The cigarette fixing mechanism receives control from the main control module and uses weights to press down on the opposite side of the filter of the horizontal cigarette to fix the cigarette.

[0029] The cutting mechanism receives control from the main control module and performs longitudinal cutting on the tipping paper of the fixed cigarette stick;

[0030] The tipping paper clamping mechanism receives control from the main control module and pulls open and fixes the cut tipping paper on both sides of the cigarette; the filter adsorption mechanism receives control from the main control module, adsorbs and peels off the filter through negative pressure, records the adsorption pressure, and provides it to the main control module.

[0031] The second camera receives control from the main control module and takes pictures of the tipping paper after the filter tip is removed, thus acquiring an image of the tipping paper.

[0032] Furthermore, the main control module includes:

[0033] The sampling parameter configuration unit is used to receive pre-configured sample quantity and cigarette brand for each group of tests;

[0034] The quality evaluation unit is used to obtain the weight of the cigarette from the weighing module, sum the weights of each cigarette sampled in each group, and then compare the cigarette weight with the pre-saved standard weight to obtain the first score of the cigarette; the image processing unit is used to obtain the overall image of the cigarette from the overall appearance inspection module and the tipping paper image from the cutting inspection module, and to perform grayscale calculation, filtering, and feature extraction on the overall cigarette image and the tipping paper image.

[0035] The cigarette overall appearance evaluation unit is used to identify the overall appearance parameters of the cigarette from the overall image of the cigarette after image processing, calculate the length of the tipping paper, and detect the end face of the cigarette through infrared detection. It also compares and identifies the cigarette appearance defects with the pre-saved cigarette appearance defects, and then classifies and summarizes the defects to obtain the second score of the cigarette.

[0036] The tipping paper appearance evaluation unit is used to determine the tipping paper range from the image-processed tipping paper image, identify the hole parameters, and compare them with the pre-set standard hole parameters of the corresponding brand to obtain the third score of the cigarette.

[0037] The cigarette evaluation summary unit is used to summarize the first score, second score, and third score of the cigarette to obtain the overall score of the cigarette, and compare it with the set score threshold to determine whether the sampled cigarette is qualified.

[0038] Furthermore, the image processing unit includes:

[0039] The image filtering subunit is used to take the overall image of the cigarette and the image of the tipping paper as the source image, calculate the image gray value, and perform noise filtering on the image gray value to eliminate interference;

[0040] The feature extraction subunit is used to extract and enhance cigarette features from the filtered image.

[0041] Furthermore, the overall evaluation unit for the appearance of cigarettes includes:

[0042] The overall appearance evaluation subunit is used to analyze the overall image of the processed cigarette, obtain the length and diameter of the cigarette through edge detection, and compare the length and diameter of the cigarette with the standard length and diameter of the corresponding brand of cigarettes that are saved in advance.

[0043] The tipping paper length evaluation subunit is used to identify pattern information in the overall image of the cigarette, locate the overall cigarette based on the pattern information, distinguish the cigarette paper area and tipping paper area, calculate the tipping paper length, and then compare the tipping paper length with the standard tipping paper length of the corresponding brand that was previously saved.

[0044] The first sub-unit for evaluating the appearance defects of cigarettes is used to compare the overall image of the cigarette with the grayscale threshold of the corresponding brand in advance to identify the grayscale difference. Then, the grayscale difference is compared with the pre-saved appearance defects of cigarettes such as misplaced cigarettes, broken cigarettes, cigarette dust, cigarette wrinkles, stains, punctures and steel stamps to identify whether there are related appearance defects. Finally, the appearance defects are classified and summarized to obtain the overall defect area of ​​the cigarette.

[0045] The second cigarette appearance defect evaluation subunit is used to acquire the infrared detection results of the cigarette end face, identify the light feedback information, and compare it with the pre-defined hollow or contact defects to determine whether the corresponding defects exist. The cigarette appearance evaluation summary subunit is used to score the comparison results of the overall parameters of the cigarette, the comparison results of the tipping paper length, the overall defect area of ​​the cigarette, and the hollow and contact defects using the scoring rules.

[0046] Furthermore, the appearance evaluation unit for cork paper includes:

[0047] The tipping paper range determination subunit is used to analyze the processed tipping paper image and obtain the tipping paper range through edge detection;

[0048] The hole identification and defect judgment subunit is used to identify holes within the tipping paper area according to the preset hole grayscale threshold, identify the number of holes, the number of punch rows, the punch position, and whether the holes are connected, and then compare them with the preset standard hole parameters of the corresponding brand to identify hole defects.

[0049] The cork paper appearance evaluation subunit is used to score the identified hole defects using an integral rule.

[0050] Furthermore, the cigarette evaluation summary unit includes:

[0051] The cigarette first scoring processing unit is used to compare the cigarette first score with the standard weight score, calculate the weight deduction, and send the weight deduction to the display device.

[0052] The second cigarette scoring processing unit is used to compare the second cigarette score with the standard overall appearance score, calculate the overall appearance deduction, and send the overall appearance deduction to the display device.

[0053] The cigarette third scoring processing unit is used to compare the cigarette third score with the standard tipping value appearance score, calculate the tipping paper appearance deduction score, and send the tipping paper appearance deduction score to the display device.

[0054] The overall scoring summary processing unit is used to summarize the weight deductions, overall appearance scores, and tipping paper appearance scores to obtain the total deductions. Then, it calculates the difference between the standard full score and the total deductions to obtain the total score. The total score is sent to the display recognition system, and if the total score is less than a score threshold, it notifies the display device to issue an alarm. Secondly, this invention provides an automatic sampling method for inspecting the appearance of cigarettes based on image processing, including the following steps:

[0055] S1. The main control module receives the pre-configured number of samples and cigarette brand for each group of tests, and controls the sampling module, overall appearance inspection module, and cutting inspection module to start.

[0056] S2. The main control module obtains the cigarette weight from the weighing module, sums the weights of each cigarette sampled in each group, and then compares the cigarette weights with the pre-saved standard weights to obtain the first score of the cigarette.

[0057] S3. The main control module obtains the overall image of the cigarette from the overall appearance inspection module and the tipping paper image from the cutting inspection module, and performs grayscale calculation, filtering, and feature extraction on the overall cigarette image and the tipping paper image respectively.

[0058] S4. The main control module identifies the overall appearance parameters of the cigarette from the overall image of the cigarette after image processing, calculates the length of the tipping paper, and detects the end face of the cigarette through infrared detection. It then compares and identifies the cigarette appearance defects with the pre-saved cigarette appearance defects, classifies and summarizes the identified defects, and obtains the second score of the cigarette.

[0059] S5. The main control module determines the tipping paper range from the image of the tipping paper after image processing, identifies the hole parameters, and compares them with the pre-set standard hole parameters of the corresponding brand to obtain the third score of the cigarette.

[0060] S6. The main control module summarizes the first score, second score, and third score of the cigarette to obtain the overall score of the cigarette, and compares it with the preset scoring threshold to determine whether the sampled cigarette is qualified.

[0061] Furthermore, the specific steps of step S3 are as follows:

[0062] S31. The main control module uses the overall image of the cigarette and the image of the tipping paper as source images, calculates the image grayscale value, and performs noise reduction filtering on the image grayscale value to eliminate interference;

[0063] S32. The main control module extracts cigarette features from the filtered image and then enhances the extracted cigarette features. Further, step S4 is detailed as follows:

[0064] S41. The main control module analyzes the overall image of the processed cigarette, obtains the length and diameter of the cigarette through edge detection, and compares the length and diameter of the cigarette with the standard length and diameter of the corresponding brand of cigarettes that are saved in advance.

[0065] S42. The main control module identifies the pattern information in the overall image of the cigarette and locates the overall cigarette based on the pattern information. It distinguishes the cigarette paper area and the tipping paper area, calculates the tipping paper length, and then compares the tipping paper length with the standard tipping paper length of the corresponding brand that has been saved in advance.

[0066] S43. The main control module compares the overall image of the cigarette with the grayscale threshold of the corresponding brand in advance to identify the grayscale difference. Then, it compares the grayscale difference with the pre-saved cigarette defects such as misplaced cigarettes, broken cigarettes, cigarette dust, cigarette wrinkles, stains, punctures, and steel stamp appearance defects to identify whether there are related appearance defects. Finally, it classifies and summarizes the identified appearance defects to obtain the overall defect area of ​​the cigarette.

[0067] S44. The main control module acquires the detection results of infrared light on the end face of the cigarette stick, identifies the light feedback information, compares it with the pre-saved empty head or contact defects, and determines whether there is a corresponding defect.

[0068] S45. The main control module uses the scoring rules to score the overall parameters of the cigarette, the length of the tipping paper, the overall defect area of ​​the cigarette, and the defects of the hollow contact, and obtains the second score of the cigarette.

[0069] The specific steps of step S5 are as follows:

[0070] S51. The main control module analyzes the processed tipping paper image and obtains the tipping paper range through edge detection.

[0071] S52. The main control module identifies holes within the tipping paper area based on the preset hole grayscale threshold, identifying the number of holes, the number of punch rows, the punch position, and whether the holes are connected. Then, it compares the hole defects with the preset standard hole parameters of the corresponding brand.

[0072] S53. The main control module scores the identified holes and defects using an integral rule to obtain the third score of the cigarette. Further, step S6 is as follows:

[0073] S61. The main control module compares the first score of the cigarette with the standard weight score, calculates the weight deduction, and sends the weight deduction to the display device;

[0074] S62. The main control module compares the second score of the cigarette with the standard overall appearance score, calculates the overall appearance deduction, and sends it to the display device;

[0075] S63. The main control module compares the third score of the cigarette with the standard tipping value appearance score, calculates the tipping paper appearance deduction, and sends it to the display device;

[0076] S64. The main control module summarizes the weight deduction, overall appearance score, and cork paper appearance score to obtain the total deduction. Then, it calculates the difference between the standard full score and the total deduction to obtain the total score. The total score is sent to the display device, and when the total score is less than the score threshold, the display device is notified to issue an alarm.

[0077] The beneficial effects of this invention are as follows:

[0078] The image processing-based cigarette appearance inspection system and method provided by this invention realizes automatic cigarette picking in the transmission bridge line and comprehensively checks the appearance quality of the cigarettes according to the inspection items. It solves the problems of false detection, missed detection and untimely inspection in manual inspection, thereby improving the appearance quality of cigarettes in the production process, reducing waste of auxiliary materials and saving manual inspection costs.

[0079] Furthermore, the design principle of this invention is reliable, the structure is simple, and it has a very wide range of application prospects.

[0080] Therefore, it is evident that the present invention has outstanding substantive features and significant progress compared with the prior art, and the beneficial effects of its implementation are also obvious. Attached Figure Description

[0081] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0082] Figure 1 This is a schematic diagram of the control of the cigarette appearance inspection system based on image processing according to the present invention.

[0083] Figure 2 This is a schematic diagram of the equipment housing location of the cigarette appearance inspection system based on image processing according to the present invention.

[0084] Figure 3 This is a schematic diagram of the internal structure of the cigarette appearance inspection system based on image processing according to the present invention.

[0085] Figure 4 This is an enlarged schematic diagram of the appearance inspection area of ​​the cork paper of the present invention.

[0086] Figure 5 This is a flowchart illustrating an embodiment of the cigarette appearance inspection method based on image processing of the present invention.

[0087] Figure 6 This is a flowchart illustrating another embodiment of the cigarette appearance inspection method based on image processing of the present invention.

[0088] Explanation of main figure symbols

[0089] 1. Inspection equipment housing; 2. Rolling and splicing equipment; 3. Packaging equipment; 4. Cigarette gripping mechanism; 5. Cigarette conveying mechanism; 6. Balance; 7. First arc-shaped flipping structure; 8. First vertical slide; 9. Rotatable suction cup; 10. First camera; 11. Infrared detection unit; 12. Cigarette turning mechanism; 13. Cigarette pushing mechanism; 14. Cigarette fixing mechanism; 15. Cutting mechanism; 16. Filter adsorption mechanism; 17. Tipping paper clamping mechanism; 18. Second camera; 19. Second arc-shaped flipping structure. Detailed Implementation

[0090] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0091] like Figure 1 As shown, the present invention provides a cigarette appearance inspection system based on image processing, including a sampling module, a weighing module, an overall appearance inspection module, a cutting inspection module, and a main control module;

[0092] The sampling module is used to sequentially grab cigarettes from the conveyor bridge line from rolling to packaging for sampling according to the sampling quantity and sampling cycle;

[0093] The weighing module is used to weigh the sampled cigarettes and provide the weighing results to the main control module;

[0094] The overall appearance inspection module is used to take pictures of the sampled cigarettes to obtain an overall image of the cigarettes and provide it to the main control module.

[0095] The tipping paper appearance inspection module is used to cut the tipping paper of the sampled cigarettes, take pictures of the cut tipping paper to obtain images of the tipping paper and provide them to the main control module;

[0096] The main control module controls the startup of the sampling module, weighing module, overall appearance inspection module, and tipping paper inspection module, processes the overall image of the cigarette and the tipping paper image, and then evaluates the appearance quality of the sampled cigarettes in combination with the weighing results.

[0097] Example 2:

[0098] like Figure 1 As shown, the present invention provides a cigarette appearance inspection system based on image processing, including a sampling module, a weighing module, an overall appearance inspection module, a cutting inspection module, and a main control module;

[0099] The sampling module is used to sequentially grab cigarettes from the conveyor bridge line from rolling to packaging for sampling according to the sampling quantity and sampling cycle;

[0100] The weighing module is used to weigh the sampled cigarettes and provide the weighing results to the main control module;

[0101] The overall appearance inspection module is used to take pictures of the sampled cigarettes to obtain an overall image of the cigarettes and provide it to the main control module.

[0102] The tipping paper appearance inspection module is used to cut the tipping paper of the sampled cigarettes, take pictures of the cut tipping paper to obtain images of the tipping paper and provide them to the main control module;

[0103] The main control module controls the startup of the sampling module, weighing module, overall appearance inspection module and tipping paper inspection module, processes the overall image of the cigarette and the tipping paper image, and then evaluates the appearance quality of the sampled cigarette by combining the weighing results.

[0104] The main control module includes:

[0105] The sampling parameter configuration unit is used to receive pre-configured sample quantity and cigarette brand for each group of tests;

[0106] The quality evaluation unit is used to obtain the cigarette weight from the weighing module, sum the weights of each cigarette sampled in each group, and then compare the sum of the cigarette weights with the pre-saved standard weights to obtain the first score of the cigarette; the image processing unit is used to obtain the overall image of the cigarette from the overall appearance inspection module and the tipping paper image from the cutting inspection module, and to perform grayscale calculation, filtering, and feature extraction on the overall cigarette image and the tipping paper image; the image processing unit includes:

[0107] The image filtering subunit is used to take the overall image of the cigarette and the image of the tipping paper as the source image, calculate the image gray value, and perform noise filtering on the image gray value to eliminate interference;

[0108] The feature extraction subunit is used to extract and enhance cigarette features in the filtered image;

[0109] The overall cigarette appearance evaluation unit is used to identify the overall appearance parameters of the cigarette from the image-processed overall cigarette image, calculate the tipping paper length, and detect the cigarette end face through infrared detection. This information is then compared with pre-saved cigarette appearance defects for identification, and the defects are categorized and statistically summarized to obtain the second score of the cigarette. The overall cigarette appearance evaluation unit includes:

[0110] The overall appearance evaluation subunit is used to analyze the overall image of the processed cigarette, obtain the length and diameter of the cigarette through edge detection, and compare the length and diameter of the cigarette with the standard length and diameter of the corresponding brand of cigarettes that are saved in advance.

[0111] The tipping paper length evaluation subunit is used to identify pattern information in the overall image of the cigarette, locate the overall cigarette based on the pattern information, distinguish the cigarette paper area and tipping paper area, calculate the tipping paper length, and then compare the tipping paper length with the standard tipping paper length of the corresponding brand that was previously saved.

[0112] The first sub-unit for evaluating the appearance defects of cigarettes is used to compare the overall image of the cigarette with the grayscale threshold of the corresponding brand in advance to identify the grayscale difference. Then, the grayscale difference is compared with the pre-saved appearance defects of cigarettes such as misplaced cigarettes, broken cigarettes, cigarette dust, cigarette wrinkles, stains, punctures and steel stamps to identify whether there are related appearance defects. Finally, the appearance defects are classified and summarized to obtain the overall defect area of ​​the cigarette.

[0113] The second cigarette appearance defect evaluation subunit is used to acquire the detection results of infrared light on the cigarette end face, identify the light feedback information, and compare it with the pre-defined hollow or contact defects to determine whether the corresponding defects exist; the cigarette appearance evaluation summary subunit is used to score the comparison results of the overall parameters of the cigarette, the comparison results of the tipping paper length, the overall defect area of ​​the cigarette, and the hollow and contact defects using the scoring rules.

[0114] The tipping paper appearance evaluation unit is used to determine the tipping paper area from the image-processed tipping paper image, identify the hole parameters, and compare them with the pre-set standard hole parameters for the corresponding brand to obtain the third score of the cigarette; the tipping paper appearance evaluation unit includes:

[0115] The tipping paper range determination subunit is used to analyze the processed tipping paper image and obtain the tipping paper range through edge detection;

[0116] The hole identification and defect judgment subunit is used to identify holes within the tipping paper area according to the preset hole grayscale threshold, identify the number of holes, the number of punch rows, the punch position, and whether the holes are connected, and then compare them with the preset standard hole parameters of the corresponding brand to identify hole defects.

[0117] The cork paper appearance evaluation subunit is used to score the identified hole defects using an integral rule;

[0118] The cigarette evaluation summary unit is used to summarize the first, second, and third scores of the cigarettes to obtain an overall score, which is then compared with a set scoring threshold to determine whether the sampled cigarettes are qualified. The cigarette evaluation summary unit includes:

[0119] The cigarette first scoring processing unit is used to compare the cigarette first score with the standard weight score, calculate the weight deduction, and send the weight deduction to the display device.

[0120] The second cigarette scoring processing unit is used to compare the second cigarette score with the standard overall appearance score, calculate the overall appearance deduction, and send the overall appearance deduction to the display device.

[0121] The cigarette third scoring processing unit is used to compare the cigarette third score with the standard tipping value appearance score, calculate the tipping paper appearance deduction score, and send the tipping paper appearance deduction score to the display device.

[0122] The overall score summary processing unit is used to summarize the weight deduction, overall appearance score, and tipping paper appearance score to obtain the total deduction. Then, it calculates the difference between the standard full score and the total deduction to obtain the total score. The total score is sent to the display recognition, and when the total score is less than the score threshold, it notifies the display device to issue an alarm.

[0123] Example 3:

[0124] like Figure 1 As shown, the present invention provides a cigarette appearance inspection system based on image processing, including a sampling module, a weighing module, an overall appearance inspection module, a cutting inspection module, and a main control module;

[0125] The sampling module is used to sequentially grab cigarettes from the conveyor bridge line from rolling to packaging for sampling according to the sampling quantity and sampling cycle;

[0126] The weighing module is used to weigh the sampled cigarettes and provide the weighing results to the main control module;

[0127] The overall appearance inspection module is used to take pictures of the sampled cigarettes to obtain an overall image of the cigarettes and provide it to the main control module.

[0128] The tipping paper appearance inspection module is used to cut the tipping paper of the sampled cigarettes, take pictures of the cut tipping paper to obtain images of the tipping paper and provide them to the main control module;

[0129] The main control module controls the startup of the sampling module, weighing module, overall appearance inspection module and tipping paper inspection module, processes the overall image of the cigarette and the tipping paper image, and then evaluates the appearance quality of the sampled cigarette by combining the weighing results.

[0130] like Figure 2 As shown, the image processing-based cigarette appearance inspection system also includes an inspection equipment housing 1, which is located in the middle of the conveyor bridge line from the cigarette rolling equipment 2 to the packaging equipment 3.

[0131] like Figure 3 As shown, the inside of the inspection equipment housing 1 is provided with a weighing area, an overall appearance inspection area, and a tipping paper appearance inspection area;

[0132] The sampling module includes a cigarette gripping mechanism 4 and a cigarette conveying mechanism 5; both the cigarette gripping mechanism 4 and the cigarette conveying mechanism 5 are connected to the main control module.

[0133] The cigarette grabbing mechanism 4 is located outside the housing 1 of the testing equipment and above the conveyor bridge line. It receives control from the main control module to grab a set number of cigarettes according to the set sampling cycle.

[0134] The cigarette conveying mechanism 5 receives control from the main control module and works in conjunction with the cigarette grabbing mechanism to convey the grabbed cigarettes to the sampling inlet of the testing equipment housing 1. The cigarette conveying mechanism 5 includes a hopper and a slide rail. After the hopper receives the cigarettes sampled by the cigarette grabbing mechanism, it slides along the slide rail to the sampling inlet of the testing equipment housing 1. The main control module controls the tilting cylinder to tilt the hopper, thereby pouring the sampled cigarettes from the sampling inlet into the weighing area inside the testing equipment housing 1.

[0135] The weighing module includes a balance 6 and a first tilting mechanism;

[0136] The balance 6 and the first flipping mechanism are both connected to the main control module;

[0137] The first flipping mechanism is located at the bottom of the balance 6;

[0138] Balance 6 receives the sampled cigarettes entering from the sampling inlet, obtains the weight of the cigarettes, and provides the weight of the cigarettes to the main control module;

[0139] The main control module controls the first flipping mechanism to flip the balance 6, so that the cigarette enters the overall appearance inspection module; it should be noted that after the cigarette is flipped from the balance 6, it falls into the overall appearance inspection area along the first arc-shaped flipping structure 7 and the first vertical slide 8.

[0140] The overall appearance inspection module includes a rotatable suction cup 9, a first camera 10, and an infrared detection unit 11;

[0141] The first camera 10 is located on the side of the rotatable suction cup 9, and the infrared detection unit 11 is located on the top of the rotatable suction cup 9. The rotatable suction cup 9, the first camera 10, and the infrared detection unit 11 are all connected to the main control module. The rotatable suction cup 9 vertically adsorbs the weighed cigarette and makes the cigarette filter tip at the bottom. The rotatable suction cup 9 adsorbs the cigarette by negative pressure.

[0142] The first camera 10 receives control from the main control module to take pictures of the cigarette stick adsorbed by the rotatable suction cup 9 and obtain an overall image of the first cigarette stick.

[0143] The main control module controls the rotatable suction cup to rotate 180 degrees, and then controls the first camera 10 to take pictures of the cigarette stick adsorbed by the rotatable suction cup 9 to obtain the overall image of the second cigarette stick; for example, the first camera 10 transmits the overall image of the first cigarette stick and the overall image of the second cigarette stick to the main control module for storage through a PCI image acquisition card.

[0144] The infrared detection unit 11 receives control from the main control module to detect the upper surface of the cigarette and determines whether the cigarette is empty or has a contact point based on the feedback light information.

[0145] Once the overall appearance of the cigarette is inspected, the main control module disconnects the negative pressure of the rotatable suction cup 9, and the cigarette falls into the tipping paper appearance inspection area.

[0146] like Figure 4 As shown, the tipping paper appearance inspection module includes a cigarette turning mechanism 12, a cigarette pushing mechanism 13, a cigarette fixing mechanism 14, a cutting mechanism 15, a filter adsorption mechanism 16, a tipping paper clamping mechanism 17, and a second camera 18.

[0147] The cigarette turning mechanism 12, cigarette pushing mechanism 13, cigarette fixing mechanism 14, cutting mechanism 15, filter adsorption mechanism 16, tipping paper clamping mechanism 17, and second camera 18 are all connected to the main control module.

[0148] The cigarette enters the vertical cigarette turning mechanism 12 along the second arc-shaped flipping structure 19;

[0149] The cigarette turning structure 12 receives control from the main control module, turns the cigarette after overall appearance inspection from vertical to horizontal, and then pushes the cigarette out through the cigarette pushing mechanism 13 and provides it to the cigarette fixing mechanism 14.

[0150] The cigarette turning mechanism 12 includes a hollow barrel-shaped shell with a longitudinal opening smaller than the outer diameter of the cigarette. After the main control module controls the barrel-shaped shell to drive the cigarette horizontally, the cigarette pushing mechanism 13 slides horizontally and pushes the cigarette out of the barrel-shaped shell along the opening through the push block, so that it enters the support plate of the cigarette fixing mechanism 14.

[0151] The cigarette fixing mechanism 14 receives control from the main control module and uses a weight to press down on the side opposite the filter of the horizontal cigarette to complete the cigarette fixing; for example, the cigarette fixing mechanism 14 uses a 200g weight to press down the cigarette.

[0152] The cutting mechanism 15 receives control from the main control module and performs longitudinal cutting on the tipping paper of the fixed cigarette stick;

[0153] The tipping paper clamping mechanism 17 receives control from the main control module and pulls open and fixes the cut tipping paper on both sides of the cigarette stick;

[0154] The filter adsorption mechanism 16 receives control from the main control module, adsorbs and peels off the filter through negative pressure, records the adsorption pressure, and provides it to the main control module.

[0155] It should be noted that the adsorption pressure can be used to determine whether there is air leakage at the interface between the cigarette paper and the tipping paper. If air leakage occurs, the adsorption pressure will be lower than the standard pressure.

[0156] The second camera 18 receives control from the main control module to take pictures of the tipping paper after the filter tip is removed, and acquires images of the tipping paper.

[0157] For example, the first camera 10 transmits the U-shaped image of the cork paper to the main control module for storage via a PCI image acquisition card;

[0158] The main control module includes:

[0159] The sampling parameter configuration unit is used to receive pre-configured sample quantity and cigarette brand for each group of tests;

[0160] The quality evaluation unit is used to obtain the cigarette weight from the weighing module, sum the weights of each cigarette sampled in each group, and then compare the sum of the cigarette weights with the pre-saved standard weights to obtain the first score of the cigarette; the image processing unit is used to obtain the overall image of the cigarette from the overall appearance inspection module and the tipping paper image from the cutting inspection module, and to perform grayscale calculation, filtering, and feature extraction on the overall cigarette image and the tipping paper image; the image processing unit includes:

[0161] The image filtering subunit is used to take the overall image of the cigarette and the image of the tipping paper as the source image, calculate the image gray value, and perform noise filtering on the image gray value to eliminate interference;

[0162] The feature extraction subunit is used to extract and enhance cigarette features in the filtered image;

[0163] The overall cigarette appearance evaluation unit is used to identify the overall appearance parameters of the cigarette from the image-processed overall cigarette image, calculate the tipping paper length, and detect the cigarette end face through infrared detection. This information is then compared with pre-saved cigarette appearance defects for identification, and the defects are categorized and statistically summarized to obtain the second score of the cigarette. The overall cigarette appearance evaluation unit includes:

[0164] The overall appearance evaluation subunit is used to analyze the overall image of the processed cigarette, obtain the length and diameter of the cigarette through edge detection, and compare the length and diameter of the cigarette with the standard length and diameter of the corresponding brand of cigarettes that are saved in advance.

[0165] The tipping paper length evaluation subunit is used to identify pattern information in the overall image of the cigarette, locate the overall cigarette based on the pattern information, distinguish the cigarette paper area and tipping paper area, calculate the tipping paper length, and then compare the tipping paper length with the standard tipping paper length of the corresponding brand that was previously saved.

[0166] The first sub-unit for evaluating the appearance defects of cigarettes is used to compare the overall image of the cigarette with the grayscale threshold of the corresponding brand in advance to identify the grayscale difference. Then, the grayscale difference is compared with the pre-saved appearance defects of cigarettes such as misplaced cigarettes, broken cigarettes, cigarette dust, cigarette wrinkles, stains, punctures and steel stamps to identify whether there are related appearance defects. Finally, the appearance defects are classified and summarized to obtain the overall defect area of ​​the cigarette.

[0167] The second cigarette appearance defect evaluation subunit is used to acquire the detection results of infrared light on the cigarette end face, identify the light feedback information, and compare it with the pre-defined hollow or contact defects to determine whether the corresponding defects exist; the cigarette appearance evaluation summary subunit is used to score the comparison results of the overall parameters of the cigarette, the comparison results of the tipping paper length, the overall defect area of ​​the cigarette, and the hollow and contact defects using the scoring rules.

[0168] The tipping paper appearance evaluation unit is used to determine the tipping paper area from the image-processed tipping paper image, identify the hole parameters, and compare them with the pre-set standard hole parameters for the corresponding brand to obtain the third score of the cigarette; the tipping paper appearance evaluation unit includes:

[0169] The tipping paper range determination subunit is used to analyze the processed tipping paper image and obtain the tipping paper range through edge detection;

[0170] The hole identification and defect judgment subunit is used to identify holes within the tipping paper area according to the preset hole grayscale threshold, identify the number of holes, the number of punch rows, the punch position, and whether the holes are connected, and then compare them with the preset standard hole parameters of the corresponding brand to identify hole defects.

[0171] The cork paper appearance evaluation subunit is used to score the identified hole defects using an integral rule;

[0172] The cigarette evaluation summary unit is used to summarize the first, second, and third scores of the cigarettes to obtain an overall score, which is then compared with a set scoring threshold to determine whether the sampled cigarettes are qualified. The cigarette evaluation summary unit includes:

[0173] The cigarette first scoring processing unit is used to compare the cigarette first score with the standard weight score, calculate the weight deduction, and send the weight deduction to the display device.

[0174] The second cigarette scoring processing unit is used to compare the second cigarette score with the standard overall appearance score, calculate the overall appearance deduction, and send the overall appearance deduction to the display device.

[0175] The cigarette third scoring processing unit is used to compare the cigarette third score with the standard tipping value appearance score, calculate the tipping paper appearance deduction score, and send the tipping paper appearance deduction score to the display device.

[0176] The overall score summary processing unit is used to summarize the weight deduction, overall appearance score, and tipping paper appearance score to obtain the total deduction. Then, it calculates the difference between the standard full score and the total deduction to obtain the total score. The total score is sent to the display recognition, and when the total score is less than the score threshold, it notifies the display device to issue an alarm.

[0177] Example 4:

[0178] like Figure 5 As shown, the present invention provides an automatic sampling method for inspecting the appearance of cigarettes based on image processing, comprising the following steps:

[0179] S1. The main control module receives the pre-configured number of samples and cigarette brand for each group of tests, and controls the sampling module, overall appearance inspection module, and cutting inspection module to start.

[0180] S2. The main control module obtains the cigarette weight from the weighing module, sums the weights of each cigarette sampled in each group, and then compares the cigarette weights with the pre-saved standard weights to obtain the first score of the cigarette.

[0181] S3. The main control module obtains the overall image of the cigarette from the overall appearance inspection module and the tipping paper image from the cutting inspection module, and performs grayscale calculation, filtering, and feature extraction on the overall cigarette image and the tipping paper image respectively.

[0182] S4. The main control module identifies the overall appearance parameters of the cigarette from the overall image of the cigarette after image processing, calculates the length of the tipping paper, and detects the end face of the cigarette through infrared detection. It then compares and identifies the cigarette appearance defects with the pre-saved cigarette appearance defects, classifies and summarizes the identified defects, and obtains the second score of the cigarette.

[0183] S5. The main control module determines the tipping paper range from the image of the tipping paper after image processing, identifies the hole parameters, and compares them with the pre-set standard hole parameters of the corresponding brand to obtain the third score of the cigarette.

[0184] S6. The main control module summarizes the first score, second score, and third score of the cigarette to obtain the overall score of the cigarette, and compares it with the preset scoring threshold to determine whether the sampled cigarette is qualified.

[0185] Example 4:

[0186] like Figure 6 As shown, the present invention provides an automatic sampling method for inspecting the appearance of cigarettes based on image processing, comprising the following steps:

[0187] S1. The main control module receives the pre-configured number of samples and cigarette brands for each group of tests, and controls the starting of the sampling module, overall appearance inspection module, and cutting inspection module; for example, it can be set to test 20 cigarettes per group, and a certain time such as 10 minutes can be designed after each group of tests before the next group of samples is taken;

[0188] S2. The main control module obtains the cigarette weight from the weighing module, sums the weights of each cigarette sampled in each group, and then compares the cigarette weights with the pre-saved standard weights to obtain the first score of the cigarette.

[0189] S3. The main control module obtains the overall image of the cigarette from the overall appearance inspection module and the tipping paper image from the cutting inspection module, and performs grayscale calculation, filtering, and feature extraction on the overall cigarette image and the tipping paper image respectively; the specific steps of step S3 are as follows:

[0190] S31. The main control module uses the overall image of the cigarette and the image of the tipping paper as source images, calculates the image grayscale value, and performs noise reduction filtering on the image grayscale value to eliminate interference;

[0191] S32. The main control module extracts cigarette features from the filtered image and then enhances the extracted cigarette features; S4. The main control module identifies the overall appearance parameters of the cigarette from the overall image of the processed cigarette, calculates the tipping paper length, and detects the cigarette end face using infrared detection. This is then compared with pre-saved cigarette appearance defects, and the identified defects are categorized and statistically summarized to obtain the second score of the cigarette; the specific steps of step S4 are as follows:

[0192] S41. The main control module analyzes the overall image of the processed cigarette, obtains the length and diameter of the cigarette through edge detection, and compares the length and diameter of the cigarette with the standard length and diameter of the corresponding brand of cigarettes that are saved in advance.

[0193] S42. The main control module identifies the pattern information in the overall image of the cigarette and locates the overall cigarette based on the pattern information. It distinguishes the cigarette paper area and the tipping paper area, calculates the tipping paper length, and then compares the tipping paper length with the standard tipping paper length of the corresponding brand that has been saved in advance.

[0194] S43. The main control module compares the overall image of the cigarette with the grayscale threshold of the corresponding brand in advance to identify the grayscale difference. Then, it compares the grayscale difference with the pre-saved cigarette defects such as misplaced cigarettes, broken cigarettes, cigarette dust, cigarette wrinkles, stains, punctures, and steel stamp appearance defects to identify whether there are related appearance defects. Finally, it classifies and summarizes the identified appearance defects to obtain the overall defect area of ​​the cigarette.

[0195] S44. The main control module acquires the detection results of infrared light on the end face of the cigarette stick, identifies the light feedback information, compares it with the pre-saved empty head or contact defects, and determines whether there is a corresponding defect.

[0196] S45. The main control module uses the scoring rules to score the overall parameters of the cigarette, the length of the tipping paper, the overall defect area of ​​the cigarette, and the defects of the hollow contact, and obtains the second score of the cigarette.

[0197] S5. The main control module determines the tipping paper area from the image-processed tipping paper image, identifies the hole parameters, and compares them with the pre-set standard hole parameters for the corresponding brand to obtain the third score of the cigarette; the specific steps of step S5 are as follows:

[0198] S51. The main control module analyzes the processed tipping paper image and obtains the tipping paper range through edge detection.

[0199] S52. The main control module identifies holes within the tipping paper area based on the preset hole grayscale threshold, identifying the number of holes, the number of punch rows, the punch position, and whether the holes are connected. Then, it compares the hole defects with the preset standard hole parameters of the corresponding brand.

[0200] S53. The main control module scores the identified hole defects using an integral rule to obtain the third score of the cigarette; S6. The main control module summarizes the first, second, and third scores of the cigarette to obtain the overall score of the cigarette, and compares it with the preset scoring threshold to determine whether the sampled cigarette is qualified; The specific steps of step S6 are as follows:

[0201] S61. The main control module compares the first score of the cigarette with the standard weight score, calculates the weight deduction, and sends it to the display device;

[0202] S62. The main control module compares the second score of the cigarette with the standard overall appearance score, calculates the overall appearance deduction, and sends it to the display device;

[0203] S63. The main control module compares the third score of the cigarette with the standard tipping value appearance score, calculates the tipping paper appearance deduction, and sends it to the display device;

[0204] S64. The main control module summarizes the weight deduction, overall appearance score, and cork paper appearance score to obtain the total deduction. Then, it calculates the difference between the standard full score and the total deduction to obtain the total score. The total score is sent to the display device, and when the total score is less than the score threshold, the display device is notified to issue an alarm.

[0205] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A cigarette appearance inspection system based on image processing, characterized in that, It includes a sampling module, a weighing module, an overall appearance inspection module, a cutting inspection module, and a main control module; The sampling module is used to sequentially grab cigarettes from the conveyor bridge line from rolling to packaging for sampling according to the sampling quantity and sampling cycle; The weighing module is used to weigh the sampled cigarettes and provide the weighing results to the main control module; The overall appearance inspection module is used to take pictures of the sampled cigarettes to obtain an overall image of the cigarettes and provide it to the main control module. The cutting inspection module is used to cut the tipping paper of the sampled cigarettes. The cut tipping paper is pulled apart and fixed on both sides of the cigarette, the filter is adsorbed and peeled off, and the tipping paper after peeling off the filter is photographed to obtain the tipping paper image and provided to the main control module. The main control module controls the startup of the sampling module, weighing module, overall appearance inspection module and cutting inspection module, processes the overall image of the cigarette and the tipping paper image, and then evaluates the appearance quality of the sampled cigarette by combining the weighing results. The main control module includes: The sampling parameter configuration unit is used to receive pre-configured sample quantity and cigarette brand for each group of tests; The quality evaluation unit is used to obtain the weight of the cigarette from the weighing module, sum the weights of each cigarette sampled in each group, and then compare the cigarette weights with the pre-saved standard weights to obtain the first score of the cigarette. The image processing unit is used to obtain an overall image of the cigarette from the overall appearance inspection module and an image of the tipping paper from the cutting inspection module, and to perform image processing on the overall cigarette image and the tipping paper image, including grayscale calculation, filtering, and feature extraction. The cigarette overall appearance evaluation unit is used to identify the overall appearance parameters of the cigarette from the overall image of the cigarette after image processing, calculate the length of the tipping paper, obtain the defect area of ​​the cigarette as a whole, and detect the end face of the cigarette through infrared detection, compare and identify it with the pre-saved cigarette appearance defects, and then classify and summarize the defects to obtain the second score of the cigarette. The tipping paper appearance evaluation unit is used to determine the tipping paper range from the image-processed tipping paper image, identify the hole parameters, and compare them with the pre-set standard hole parameters of the corresponding brand to obtain the third score of the cigarette. The cigarette evaluation summary unit is used to summarize the first score, second score, and third score of the cigarette to obtain the overall score of the cigarette, and compare it with the set score threshold to determine whether the sampled cigarette is qualified.

2. The image processing-based cigarette appearance inspection system as described in claim 1, characterized in that, The image processing unit includes: The image filtering subunit is used to take the overall image of the cigarette and the image of the tipping paper as the source image, calculate the image gray value, and perform noise filtering on the image gray value to eliminate interference; The feature extraction subunit is used to extract and enhance cigarette features from the filtered image.

3. The image processing-based cigarette appearance inspection system as described in claim 1, characterized in that, The overall appearance evaluation unit for cigarettes includes: The overall appearance evaluation subunit is used to analyze the overall image of the processed cigarette, obtain the length and diameter of the cigarette through edge detection, and compare the length and diameter of the cigarette with the standard length and diameter of the corresponding brand of cigarettes that are saved in advance. The tipping paper length evaluation subunit is used to identify pattern information in the overall image of the cigarette, locate the overall cigarette based on the pattern information, distinguish the cigarette paper area and tipping paper area, calculate the tipping paper length, and then compare the tipping paper length with the standard tipping paper length of the corresponding brand that was previously saved. The first sub-unit for evaluating the appearance defects of cigarettes is used to compare the overall image of the cigarette with the grayscale threshold of the corresponding brand in advance to identify the grayscale difference. Then, the grayscale difference is compared with the pre-saved appearance defects of cigarettes such as misplaced cigarettes, broken cigarettes, cigarette dust, cigarette wrinkles, stains, punctures and steel stamps to identify whether there are related appearance defects. Finally, the appearance defects are classified and summarized to obtain the overall defect area of ​​the cigarette. The second appearance defect evaluation subunit of the cigarette is used to obtain the detection results of infrared light on the end face of the cigarette, identify the light feedback information, compare it with the pre-defined empty head or contact defects, and determine whether the corresponding defects exist. The cigarette appearance evaluation summary sub-unit is used to score the overall appearance parameters of the cigarette, the length of the tipping paper, the overall defect area of ​​the cigarette, and the defects of the hollow contact point using the scoring rules.

4. The image processing-based cigarette appearance inspection system as described in claim 1, characterized in that, The appearance evaluation unit for tipping paper includes: The tipping paper range determination subunit is used to analyze the processed tipping paper image and obtain the tipping paper range through edge detection; The hole identification and defect judgment subunit is used to identify holes within the tipping paper area according to the preset hole grayscale threshold, identify the number of holes, the number of punch rows, the punch position, and whether the holes are connected, and then compare them with the preset standard hole parameters of the corresponding brand to identify hole defects. The cork paper appearance evaluation subunit is used to score the identified hole defects using an integral rule.

5. The image processing-based cigarette appearance inspection system as described in claim 1, characterized in that, The cigarette evaluation summary unit includes: The cigarette first scoring processing unit is used to compare the cigarette first score with the standard weight score, calculate the weight deduction, and send the weight deduction to the display device. The second cigarette scoring processing unit is used to compare the second cigarette score with the standard overall appearance score, calculate the overall appearance deduction, and send the overall appearance deduction to the display device. The cigarette third scoring processing unit is used to compare the cigarette third score with the standard tipping paper appearance score, calculate the tipping paper appearance deduction, and send the tipping paper appearance deduction to the display device. The overall scoring summary processing unit is used to summarize the weight deduction, overall appearance deduction, and tipping paper appearance deduction to obtain the total number of deductions. Then, it calculates the difference between the standard full score and the total number of deductions to obtain the total score. The total score is sent to the display recognition, and when the total score is less than the score threshold, it notifies the display device to issue an alarm.

6. A method for inspecting the appearance of cigarettes based on image processing and automatic sampling using the image processing-based cigarette appearance inspection system according to any one of claims 1-5, characterized in that, Includes the following steps: S1. The main control module receives the pre-configured number of samples and cigarette brand for each group of tests, and controls the sampling module, overall appearance inspection module, and cutting inspection module to start. S2. The main control module obtains the cigarette weight from the weighing module, sums the weights of each cigarette sampled in each group, and then compares the cigarette weights with the pre-saved standard weights to obtain the first score of the cigarette. S3. The main control module obtains the overall image of the cigarette from the overall appearance inspection module and the tipping paper image from the cutting inspection module, and performs image processing on the overall cigarette image and tipping paper image respectively, including grayscale calculation, filtering and feature extraction. S4. The main control module identifies the overall appearance parameters of the cigarette from the overall image of the cigarette after image processing, calculates the length of the tipping paper, obtains the overall defect area of ​​the cigarette, and detects the end face of the cigarette through infrared detection, compares and identifies it with the pre-saved cigarette appearance defects, and then classifies and summarizes the identified defects to obtain the second score of the cigarette. S5. The main control module determines the tipping paper range from the image of the tipping paper after image processing, identifies the hole parameters, and compares them with the pre-set standard hole parameters of the corresponding brand to obtain the third score of the cigarette. S6. The main control module summarizes the first score, second score, and third score of the cigarette to obtain the overall score of the cigarette, and compares it with the preset scoring threshold to determine whether the sampled cigarette is qualified.

7. The method for automatic sampling and cigarette appearance inspection based on image processing as described in claim 6, characterized in that, The specific steps of step S3 are as follows: S31. The main control module uses the overall image of the cigarette and the image of the tipping paper as source images, calculates the image grayscale value, and performs noise reduction filtering on the image grayscale value to eliminate interference; S32. The main control module extracts cigarette features from the filtered image and then enhances the extracted cigarette features.

8. The method for automatic sampling and cigarette appearance inspection based on image processing as described in claim 6, characterized in that, The specific steps of step S4 are as follows: S41. The main control module analyzes the overall image of the processed cigarette, obtains the length and diameter of the cigarette through edge detection, and compares the length and diameter of the cigarette with the standard length and diameter of the corresponding brand of cigarettes that are saved in advance. S42. The main control module identifies the pattern information in the overall image of the cigarette and locates the overall cigarette based on the pattern information. It distinguishes the cigarette paper area and the tipping paper area, calculates the tipping paper length, and then compares the tipping paper length with the standard tipping paper length of the corresponding brand that has been saved in advance. S43. The main control module compares the overall image of the cigarette with the grayscale threshold of the corresponding brand in advance to identify the grayscale difference. Then, it compares the grayscale difference with the pre-saved cigarette defects such as misplaced cigarettes, broken cigarettes, cigarette dust, cigarette wrinkles, stains, punctures, and steel stamp appearance defects to identify whether there are related appearance defects. Finally, it classifies and summarizes the identified appearance defects to obtain the overall defect area of ​​the cigarette. S44. The main control module acquires the detection results of infrared light on the end face of the cigarette stick, identifies the light feedback information, compares it with the pre-saved empty head or contact defects, and determines whether there is a corresponding defect. S45. The main control module uses the scoring rules to score the cigarette based on the comparison results of the overall appearance parameters of the cigarette, the comparison results of the tipping paper length, the overall defect area of ​​the cigarette, and the defect of the hollow contact, and obtains the second score of the cigarette. The specific steps of step S5 are as follows: S51. The main control module analyzes the processed tipping paper image and obtains the tipping paper range through edge detection. S52. The main control module identifies holes within the tipping paper area based on the preset hole grayscale threshold, identifying the number of holes, the number of punch rows, the punch position, and whether the holes are connected. Then, it compares the hole defects with the preset standard hole parameters of the corresponding brand. S53. The main control module uses an integral rule to score the identified hole defects and obtains the third score of the cigarette.

9. The method for automatic sampling of cigarette appearance inspection based on image processing as described in claim 6, characterized in that, The specific steps of step S6 are as follows: S61. The main control module compares the first score of the cigarette with the standard weight score, calculates the weight deduction, and sends it to the display device; S62. The main control module compares the second score of the cigarette with the standard overall appearance score, calculates the overall appearance deduction, and sends it to the display device; S63. The main control module compares the third score of the cigarette with the standard tipping paper appearance score, calculates the tipping paper appearance deduction, and sends it to the display device; S64. The main control module summarizes the weight deduction, overall appearance deduction, and tipping paper appearance deduction to obtain the total deduction. Then, it calculates the difference between the standard full score and the total deduction to obtain the total score. The total score is sent to the display device, and when the total score is less than the score threshold, the display device is notified to issue an alarm.

Images