A method for quality testing of cigarette sticks and incense threads

Abstract

This invention provides a method for detecting the quality of cigarette smoke thread, comprising: acquiring a CT tomographic image of a cigarette sample and performing three-dimensional reconstruction to obtain a three-dimensional reconstructed image; performing image segmentation processing on the three-dimensional reconstructed image to extract the cigarette filter segment as the region of interest; segmenting the region of interest based on a threshold segmentation method to obtain the filter rod portion and the smoke thread portion; extracting point clouds of the region of interest, the filter rod portion, and the smoke thread portion; determining whether the smoke thread distribution is uniform based on the smoke thread point cloud dataset; determining whether the smoke thread has shifted based on the filter segment point cloud and the smoke thread point cloud dataset; and calculating the length, circumference, and distance from the inhalation end of the smoke thread.

Description

Technical Field

[0001] This invention relates to the field of cigarette product testing technology, and more specifically, to a method for testing the quality of cigarette sticks and incense threads. Background Technology

[0002] Adding flavoring threads to cigarette filters has become an important technological trend for improving the sensory quality and enriching the sensory experience of cigarettes. With the increasing demand from consumers for personalized and diversified cigarette products, the design and application of flavoring threads have become a crucial direction in cigarette research and development. By precisely controlling the release of aroma, flavoring threads can significantly enhance the olfactory and gustatory experience of smoking, satisfying the preferences of different markets and users. A flavoring thread is a thin thread containing flavorings, typically embedded in the cigarette filter. Its main function is to enhance the olfactory and gustatory experience of smoking by controlling the release of flavorings. When smoke passes through the filter, the flavorings within the thread evaporate upon heating, releasing specific aromas. The design of the flavoring thread can complement the aroma of the tobacco itself, creating a richer and more balanced sensory experience. Flavoring threads can impart unique aroma characteristics to different cigarette brands, thereby meeting the needs of different consumers. By adding various flavorings (such as mint, vanilla, citrus, etc.), the flavor of cigarette products can be diversified. Therefore, the quality testing of cigarette flavoring threads has become an inevitable requirement for technological development. As the application of flavoring threads in cigarettes continues to expand, their quality indicators have a direct impact on the sensory effects of the final product. Establishing a scientific and reliable testing system is crucial for ensuring product quality.

[0003] The size and uniformity of the aroma thread directly determine the amount of aroma released in the filter. Uneven distribution of the aroma thread can result in inconsistent aroma intensity, leading to a poor smoking experience. Uneven distribution can also cause some areas to be overly aromatic while others are under-aromatic, resulting in a poor or uncoordinated aroma profile. The diameter and length of the aroma thread directly affect the amount of flavoring it can hold. Too small a size will result in insufficient flavoring, affecting aroma release; too large a size may lead to an overly strong or uneven aroma release. Currently, the detection of the size and uniformity of the aroma thread in cigarettes mainly relies on manual observation or simple optical equipment. This method is highly subjective, depending on the operator's experience and judgment, and is prone to errors, resulting in low detection accuracy.

[0004] Chinese patent (CN116993687A) discloses a method and apparatus for detecting the aroma thread in a cigarette filter stick based on terahertz technology. This patent detects the presence of the aroma thread in the filter stick using terahertz detection, and then accurately and effectively determines whether the aroma thread has shifted by comparing its offset angle with the filter stick's offset angle. However, this patent uses terahertz spectroscopy to measure the aroma thread in the cigarette filter stick and determines the presence of the aroma thread based on a pseudo-color image obtained from the measurement; that is, the computer vision algorithm used in this patent processes a two-dimensional radial image of the aroma thread, and cannot determine the state of the aroma thread in three-dimensional space.

[0005] In order to solve the above problems, people have been seeking an ideal technological solution. Summary of the Invention

[0006] Therefore, it is necessary to provide a method for detecting the quality of cigarette incense threads, addressing the aforementioned technical problems. This method utilizes CT scanning technology to perform a three-dimensional scan of the cigarette sample, acquiring the three-dimensional spatial information of the incense threads. Through three-dimensional point cloud processing technology, the position, size, and quality of the incense threads within the cigarette are detected. This method improves the accuracy of incense thread position and size detection, enhances the precision of incense thread quality detection (whether there is offset or breakage), reduces labor costs, and avoids the health hazards caused by direct exposure to strong light in traditional methods.

[0007] To achieve the above objectives, a first aspect of the present invention provides a method for detecting the quality of cigarette sticks and incense threads, comprising:

[0008] CT tomographic images of cigarette samples were acquired and three-dimensional reconstruction was performed to obtain three-dimensional reconstructed images;

[0009] The three-dimensional reconstructed image is processed by image segmentation, and the cigarette filter segment is extracted as the region of interest;

[0010] The region of interest is segmented using a threshold segmentation method to obtain the filter rod portion and the fragrance thread portion;

[0011] Extract the point cloud of the region of interest, the filter rod portion, and the fragrance thread portion;

[0012] Determine whether the distribution of incense lines is uniform based on the incense line point cloud dataset;

[0013] The system determines whether the fragrance thread has shifted based on the filter tip segment cloud and the fragrance thread segment cloud, and calculates the length, circumference, and distance from the suction end of the fragrance thread.

[0014] To achieve the above objectives, a second aspect of the present invention provides a cigarette thread quality testing device, comprising:

[0015] The acquisition module is configured to acquire CT tomographic images of cigarette samples and perform three-dimensional reconstruction to obtain three-dimensional reconstructed images;

[0016] The image segmentation module is configured to perform image segmentation processing on the three-dimensional reconstructed image, extract the cigarette filter segment as the region of interest, and segment the region of interest based on the threshold segmentation method to obtain the filter rod part and the incense thread part.

[0017] The quality calculation module is configured to extract point clouds of the region of interest, the filter rod section, and the fragrance thread section; determine whether the fragrance thread distribution is uniform based on the fragrance thread point cloud dataset; determine whether the fragrance thread has shifted based on the filter segment point cloud and the fragrance thread point cloud; and calculate the length, circumference, and distance from the suction end of the fragrance thread.

[0018] To achieve the above objectives, a third aspect of the present invention provides a computer device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus.

[0019] Memory, used to store computer programs;

[0020] The processor, when executing a program stored in memory, implements the cigarette thread quality detection method as described in the first aspect.

[0021] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the cigarette wick quality detection method as described in the first aspect.

[0022] To achieve the above objectives, a fifth aspect of the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the cigarette wick quality detection method steps as described in the first aspect.

[0023] The beneficial effects of this invention are as follows:

[0024] This invention utilizes industrial CT technology to scan samples and calculates the length, radius, distance from the puff end, and uniformity of the aroma thread distribution based on the acquired three-dimensional point cloud data of the aroma thread in the cigarette filter. This invention improves the accuracy of aroma thread detection, reduces manual intervention, and lowers the risk of human error. Simultaneously, the three-dimensional data analysis provides more detailed information, helping to accurately determine whether the aroma thread meets standards and even identify minute anomalies, further optimizing production efficiency and cost control. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the method for detecting the quality of cigarette sticks and incense threads described in Embodiment 1 of the present invention.

[0026] Figure 2 This is a schematic diagram of CT scan operation.

[0027] Figure 3 This is a schematic diagram of a CT scan.

[0028] Figure 4 A three-dimensional reconstruction model of the cigarette filter section;

[0029] Figure 5 A three-dimensional reconstruction model of the cigarette incense thread. Detailed Implementation

[0030] To address the aforementioned problems, this invention proposes a method for detecting the quality of cigarette incense threads. This method involves three-dimensional scanning of cigarette samples to obtain the three-dimensional spatial information of the incense threads. Using three-dimensional point cloud processing technology, the position, size, and quality of the incense threads within the cigarette are detected. This method improves the accuracy of incense thread position and size detection, enhances the precision of incense thread quality detection (whether there is offset or breakage), reduces labor costs, and avoids the health hazards caused by direct exposure to strong light in traditional methods.

[0031] The technical solution of the present invention will be further described in detail below through specific embodiments.

[0032] Example 1

[0033] This embodiment provides a method for detecting the quality of cigarette sticks and incense threads, such as... Figure 1 As shown, it includes the following steps:

[0034] S1. Acquire CT tomographic images of cigarette samples and perform three-dimensional reconstruction to obtain three-dimensional reconstructed images.

[0035] Specifically, the detection structure of the CT equipment is as follows: Figure 2 As shown, the specific detection process includes:

[0036] S11, use the clamping device to fix the cigarette sample, and adjust the position of the cigarette sample to ensure that the cigarette sample is perpendicular to the clamping base.

[0037] S12, turn on the CT equipment, place the clamping device into the tray slot inside the CT equipment, and ensure that the clamping device is fixed on the tray to prevent the sample from falling off when the tray rotates.

[0038] S13, set the X-ray source tube voltage to 150kV, X-ray source tube current to 90μA, scanning thickness to 0.004mm, scanning interval to 0.004mm, CT scanning mode to cone-beam scanning, and CT scanning mode to Normal scanning. Move the sample tray on the stage to center the sample within the X-ray scanning range. Control the rotation of the stage to ensure that the cigarette sample is within the X-ray scanning position within a 360° range.

[0039] S14, remove the clamping device, perform air calibration on the CT equipment, place the central axis calibration rod on the tray, and perform central axis calibration.

[0040] S15, place the clamping device on the tray, start the CT scan to scan the inside of the cigarette sample, collect two-dimensional projection data at different angles according to the rotation interval, and transmit the digital signal received by the detector to the computer for storage.

[0041] Specifically, the schematic diagram of a CT scan is as follows: Figure 3 As shown.

[0042] S16, preprocess the acquired CT tomographic images.

[0043] The two-dimensional projection data acquired at each angle during the aforementioned CT scan are weighted to correct the cone-beam distortion. The formula is as follows:

[0044]

[0045] In the formula, P W (β,a,b) is the weighted two-dimensional projection data; P(β,a,b) is the collected two-dimensional projection data. β is the weighting factor; β is the angle of X-ray emission; a, b are the horizontal and vertical coordinates of the pixel to be reconstructed mapped onto the virtual detector.

[0046] S17. Perform one-dimensional filtering on the above-mentioned corrected and weighted projection data along the projection of the flat panel detector perpendicular to the CT equipment. The formula is as follows:

[0047]

[0048] In the formula, is the filtered data; H(a) is the convolution kernel.

[0049] S18, Reconstruct the image by backprojecting the above data.

[0050] One-dimensional filtered projection data along the X-ray direction The back projection calculation is performed using the following formula:

[0051]

[0052] In the formula, R is the distance from the ray source to the rotation center; U is similar to the weighting factor in the two-dimensional equidistant fan beam projection reconstruction algorithm, and its calculation method is: U(x,y,β)=R+xcosβ+ysinβ.

[0053] In the aforementioned back-projection reconstructed image, due to the large spacing along the Z-axis during sampling, interpolation calculations are required along the Z-axis. Bilinear interpolation is used here, and the specific process is as follows:

[0054] Select the four pixels closest to the pixel P(x,y) to be interpolated, and denote them as Q. 11 (x1,y1),Q 12 (x1,y2),Q 21 (x2,y1),Q 22 (x2, y2). First, interpolation is performed in the x-direction, with the following formula:

[0055]

[0056] Next, interpolation is performed in the y-direction, using the following formula:

[0057]

[0058] Thus, the final pixel value of the pixel P to be interpolated is obtained.

[0059] Through the above steps, a three-dimensional reconstruction model of the cigarette inside the cigarette sample can now be constructed, such as... Figure 4 As shown and Figure 5 As shown.

[0060] S2, perform image segmentation processing on the three-dimensional reconstructed image and extract the cigarette filter segment as the region of interest. Specifically, this includes:

[0061] Image processing software such as threshold segmentation, edge detection, or instance segmentation is used to segment the scanned cigarette sample images.

[0062] S3, based on threshold segmentation, segments the region of interest to obtain the filter rod portion and the fragrance thread portion. Specifically, this includes:

[0063] S31. Based on the difference in gray values ​​between the filter rod and the incense thread in a cigarette filter tip in a 2D CT tomographic image, a certain gray value threshold is set, and the region of interest is segmented based on the threshold segmentation method to divide the filter rod and the incense thread and generate two new regions of interest.

[0064] S32, the processed cigarette sample images are extracted into three point cloud datasets. The image of the cigarette filter segment before segmentation is extracted into point cloud dataset D1, the image of the segmented incense thread is extracted into point cloud dataset D2, and the image of the remaining filter rod after segmentation is extracted into point cloud dataset D3.

[0065] S4. Based on the incense line point cloud dataset D2 obtained in S3, determine whether the incense line distribution is uniform. Specifically:

[0066] S41. Define a fixed fitting circle radius \(R\) for each point cloud \(O(x, y, z)\) in the point cloud dataset \(D2\). Calculate the spatial distance \(d\) between this point and each of the remaining points in the point cloud dataset, and use this to calculate the number of point clouds within the fitting circle radius \(R\) of the target point in the point cloud dataset. The specific calculation formula is as follows:

[0067]

[0068] In the formula, \((x1, y1, z1)\) are the three - dimensional spatial coordinates of a point cloud \(P1\) in the incense line point cloud dataset; \((x2, y2, z2)\) are the three - dimensional spatial coordinates of another point cloud \(P2\) in the incense line point cloud dataset.

[0069] Count the number of point clouds within the fitting circle radius \(R\) of point cloud \(P1\) in the point cloud dataset. If \(d < R\), it means that \(P2\) belongs to the neighborhood points of \(P1\); otherwise, it means that \(P2\) does not belong to the neighborhood points of \(P1\).

[0070] Repeat the above calculation steps for all points in the point cloud dataset \(D2\) to obtain the number of neighborhood points \(n\) for each point cloud in the point cloud dataset. i 。

[0071] S42. Based on the number of neighborhood points for each point cloud obtained from the above calculation, set a threshold. When the number of neighborhood points of a certain point cloud exceeds this threshold, it means that the point cloud at that location is sparse, further reflecting that the distribution of the incense line at that location is uneven and there may be breaks.

[0072] S5. Perform point cloud data processing on the filter segment point cloud set \(D1\) and the incense line part point cloud set \(D2\) obtained in S3. Specifically:

[0073] S51. For all points in the point cloud set \(D1\), divide the point cloud set into different point cloud subsets \(D\) based on the \(Z\) value i , where the \(z\) coordinates of the points in each point cloud set are the same value.

[0074] S52. Based on all the point cloud subsets obtained in the first step, perform a fitting circle operation.

[0075] Since all the point clouds in the point cloud set are on the same plane in the \(Z\) - axis direction, only the fitting circle operation on the plane needs to be performed to obtain the fitting circle in three - dimensional space. Let the equation of the circle be:

[0076]

[0077] In the formula, \((x c ,y c ) are the coordinates of the center of the fitting circle; \(r\) is the fitting circle radius of the circle.

[0078] To fit this circle, we need to minimize the following objective function:

[0079]

[0080] The coordinates of the center of the fitted circle for each point cloud set can be obtained using a numerical optimization algorithm (x...). i ,y i ,z i The radius of the fitted circle is r. i .

[0081] S53, repeat the operations of S51 and S52 on the point cloud set of the incense line to obtain the center coordinates of the fitted circle of each point cloud set of the incense line as (x j ,y j ,z j The radius of the fitted circle is r. j .

[0082] S6. Determine if the incense thread has shifted. Specifically:

[0083] S61, based on the filter segment point cloud set obtained in S5, fit the center coordinates (x) of the circle. i ,y i ,z i ) and the coordinates of the center of the circle fitted by the cloud of incense points (x) j ,y j ,z j Calculate the distance between the center coordinates of the fitted circle for the fragrance line and the center coordinates of the fitted circle for the filter tip segment within the same plane. The formula is as follows:

[0084]

[0085] S62, for all d calculated in S61 i Perform statistical analysis and calculate its average value. The formula is as follows:

[0086]

[0087] S63, Set a threshold, when d m If the value exceeds this threshold, it indicates that the incense thread is deviated.

[0088] S7. Calculate the length, circumference, and distance from the suction end of the incense thread. Specifically:

[0089] S71, based on the filter segment cloud obtained in S5, the one with the largest Z value is recorded as z1, which is the z value of the cigarette smoking end.

[0090] S72, based on the incense line point set obtained in S5, the one with the largest Z value is denoted as z2, which is the z value of the top of the incense line.

[0091] S73, calculate the distance from the tip of the incense thread to the suction end. The formula is:

[0092] l=z1-z2

[0093] S74, the radius r of the fitted circle of each fitted circle in the cloud of incense line points obtained in S5. i Statistical analysis is performed to calculate the mean, which represents the overall fitted circle radius of the fragrance line. The formula is as follows:

[0094]

[0095] S75, based on the coordinates (x) of the center of each fitted circle in the cloud of incense line points obtained in S5. j ,y j ,z j The circles with the largest and smallest z-values ​​represent the two ends of the incense thread, respectively. The length of the incense thread can be obtained by calculating the distance between the two end faces. The formula is as follows:

[0096] L=z max -z min

[0097] This invention employs industrial CT technology to perform high-resolution scanning of samples, acquiring three-dimensional point cloud data of the aroma thread in cigarette filters. Through precise analysis of this three-dimensional point cloud data, the length of the aroma thread, the radius of the fitted circle, the distance to the puff end, and the uniformity of the aroma thread's distribution throughout the filter can be calculated. This method not only improves the accuracy of aroma thread detection but also significantly reduces the need for manual intervention, minimizing the risk of human error.

[0098] Furthermore, analysis based on 3D point cloud data can comprehensively capture minute variations in incense threads, including their shape, thickness, and potential defects (such as uneven distribution and breakage). This fine-grained analysis provides richer and more detailed information, enabling accurate assessment of whether incense threads meet industry standards and quality control requirements.

[0099] Furthermore, this invention not only achieves high precision and efficiency in cigarette thread quality inspection, but also enhances quality control capabilities in the production process through advanced three-dimensional data analysis, further promoting the intelligent and automated level of cigarette manufacturing technology.

[0100] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise expressly stated herein, there is no strict order restriction on the execution of these steps; they can be executed in other orders, for example, step S4 can be executed last, or step S4 can be executed simultaneously with steps S5-S7. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the steps or stages of other steps.

[0101] Example 2

[0102] Based on the same inventive concept, this application also provides a cigarette and incense thread quality testing device for implementing the above-mentioned cigarette and incense thread quality testing method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more cigarette and incense thread quality testing device embodiments provided below can be found in the limitations of the cigarette and incense thread quality testing method described above, and will not be repeated here.

[0103] The cigarette stick quality testing device includes:

[0104] The acquisition module is configured to acquire CT tomographic images of cigarette samples and perform three-dimensional reconstruction to obtain three-dimensional reconstructed images;

[0105] The image segmentation module is configured to perform image segmentation processing on the three-dimensional reconstructed image, extract the cigarette filter segment as the region of interest, and segment the region of interest based on the threshold segmentation method to obtain the filter rod part and the incense thread part.

[0106] The quality calculation module is configured to extract point clouds of the region of interest, the filter rod section, and the fragrance thread section; determine whether the fragrance thread distribution is uniform based on the fragrance thread point cloud dataset; determine whether the fragrance thread has shifted based on the filter segment point cloud and the fragrance thread point cloud; and calculate the length, circumference, and distance from the suction end of the fragrance thread.

[0107] Example 3

[0108] This embodiment provides a computer device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0109] Memory, used to store computer programs;

[0110] When the processor executes the program stored in the memory, it implements the cigarette incense thread quality detection method as described in Example 1.

[0111] Example 4

[0112] Based on the above embodiments, this embodiment provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the cigarette and incense thread quality detection method described in Embodiment 1.

[0113] Example 5

[0114] Based on the above embodiments, this embodiment provides a computer program product, including a computer program that, when executed by a processor, implements the cigarette and incense thread quality detection method described in Embodiment 1.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications can still be made to the specific implementation of the present invention or equivalent substitutions can be made to some technical features without departing from the spirit of the technical solutions of the present invention, and all such modifications and substitutions should be covered within the scope of the technical solutions claimed in the present invention.

Claims

1. A method for quality testing of cigarette sticks and incense threads, characterized in that, Including: Obtain the CT tomographic images of the cigarette samples and perform three-dimensional reconstruction to obtain three-dimensional reconstructed images; Perform image segmentation on the three-dimensional reconstructed images and extract the filter section of the cigarette as the region of interest; Based on the threshold segmentation method, segment the region of interest to obtain the filter rod part and the incense line part; Extract the point cloud sets of the region of interest, the filter rod part and the incense line part; Judge whether the distribution of the incense line is uniform based on the incense line point cloud dataset; Judge whether the incense line is offset based on the filter section point cloud set and the incense line point cloud set, and calculate the length, circumference and distance from the suction end of the incense line.

2. The method for quality testing of cigarette sticks and incense threads according to claim 1, characterized in that, Judging whether the distribution of the incense line is uniform based on the incense line point cloud dataset includes: Define a fixed fitting circle radius R for each point cloud in the incense line point cloud dataset, and calculate the spatial distance d between each other point in the incense line point cloud dataset and this point. The calculation formula is as follows: In the formula, (x1, y1, z1) is the three-dimensional spatial coordinates of a point cloud P1 in the incense line point cloud dataset; (x2, y2, z2) is the three-dimensional spatial coordinates of another point cloud P2 in the incense line point cloud dataset; Count the number of point clouds within the fitting circle radius R of the point cloud P1 in the point cloud dataset. If d < R, it is determined that P2 belongs to the neighborhood points of P1; otherwise, it is determined that P2 does not belong to the neighborhood of P1; Repeat the above calculation steps for all point clouds in the incense line point cloud dataset to obtain the number of neighborhood points of each point cloud in the incense line point cloud dataset; Compare the number of neighborhood points of each point cloud in the incense line point cloud dataset with the set point number threshold. If the number of neighborhood points of a certain point cloud exceeds the set point number threshold, it is determined that the distribution of the incense line at this place is uneven; otherwise, it is determined that the distribution of the incense line at this place is uniform.

3. A method for quality testing of cigarette sticks and incense threads according to claim 1 or 2, characterized in that, Before judging whether the incense line is offset based on the filter section point cloud set and the incense line point cloud set, divide the filter section point cloud set and the incense line point cloud set into multiple independent point cloud subsets based on the Z value as the division basis; For all point cloud subsets, use the least squares method to fit a circle to obtain the fitting circle center coordinates and the fitting circle radius.

4. The method for quality testing of cigarette sticks and incense threads according to claim 3, characterized in that, After extracting the point cloud sets of the filter rod part and the incense line part, also execute: Based on the fitting circle center coordinates of each point cloud subset of the filter rod and the fitting circle center coordinates of each point cloud subset of the incense line, calculate the distance between the fitting circle center coordinates of the incense line and the fitting circle center coordinates of the filter section in the same plane; Calculate the mean value of all the distances obtained in the previous step to obtain the average distance; Compare the average distance with the set average distance threshold. When the average distance exceeds the set average distance threshold, it is determined that the incense line is offset; Otherwise, it is determined that the incense line is not offset.

5. The method for quality testing of cigarette sticks and incense threads according to claim 4, characterized in that, Calculating the length, circumference and distance from the suction end of the incense line based on the filter section point cloud set and the incense line point cloud set includes: Record the maximum Z value in the filter section point cloud set as the z value of the cigarette suction end; Record the maximum Z value in the incense line point cloud set as the z value of the top of the incense line; The distance from the tip of the incense stick to the suction end is calculated using the formula: l = z1 - z 2； Among them, z1 is the z value of the cigarette suction end, and z2 is the z value of the top of the incense line; Calculate the mean value of the fitting circle radii of each point cloud subset of the incense line to obtain the average fitting circle radius as the overall fitting circle radius of the incense line; Calculate the distance between the fitting circles with the maximum and minimum z values in the incense line point cloud set as the length of the incense line.

6. The method for quality testing of cigarette sticks and incense threads according to claim 1, characterized in that, Acquire CT tomographic images of cigarette samples and perform 3D reconstruction, including: Use a sample holder to fix the cigarette sample, and adjust the position of the cigarette sample to ensure that the cigarette sample is perpendicular to the sample base. Turn on the CT equipment and place the sample holder into the mounting platform slot inside the CT equipment, ensuring that the sample holder is fixed on the mounting platform; The X-ray source tube voltage is set to 150 kV, the X-ray source tube current to 90 μA, the scanning thickness to 0.004 mm, the scanning interval to 0.004 mm, the CT scanning mode to cone-beam scanning, and the CT scanning mode to Normal scanning. The cigarette sample is positioned in the center of the X-ray scanning range by moving the flat plate detector on the worktable; the rotation of the platform is controlled to ensure that the cigarette sample is in the X-ray scanning position within a 360° range. Remove the sample holder, perform air calibration on the CT equipment, and place the central axis calibration rod on the platform to perform central axis calibration. Place the sample holder on the platform and start the CT scan to scan the inside of the cigarette sample. Collect two-dimensional projection data at different angles according to the rotation interval. The two-dimensional projection data collected at each angle are weighted to correct the cone beam. The corrected and weighted projection data is filtered in one dimension along the projection perpendicular to the flat panel detector. A three-dimensional reconstruction model of the cigarette sample is obtained by back-projecting the one-dimensional filtered data along the X-ray direction.

7. A device for detecting the quality of cigarette sticks and incense threads, characterized in that, include: The acquisition module is configured to acquire CT tomographic images of cigarette samples and perform three-dimensional reconstruction to obtain three-dimensional reconstructed images; The image segmentation module is configured to perform image segmentation processing on the three-dimensional reconstructed image and extract the cigarette filter segment as the region of interest. The region of interest is segmented using a threshold segmentation method to obtain the filter rod portion and the fragrance thread portion; The quality calculation module is configured to extract point clouds of the region of interest, the filter rod section, and the fragrance thread section; determine whether the fragrance thread distribution is uniform based on the fragrance thread point cloud dataset; determine whether the fragrance thread has shifted based on the filter segment point cloud and the fragrance thread point cloud; and calculate the length, circumference, and distance from the suction end of the fragrance thread.

8. A computer device, characterized in that: It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the cigarette thread quality detection method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the cigarette and incense thread quality detection method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the cigarette and incense thread quality detection method according to any one of claims 1 to 6.

Images