Method and equipment for determining position of blast bead in cigarette filter tip

Abstract

The invention relates to a method and equipment for determining the position of a blasting bead in a cigarette filter tip, and the method comprises the steps: collecting data information of a cigarette from different angles in the circumferential direction through CT equipment, and constructing a three-dimensional reconstruction model of the cigarette based on the data information; splitting a filter tip area and a blasting bead area from the three-dimensional reconstruction model according to gray difference, and respectively forming a point cloud data set of the filter tip area and a point cloud data set of the blasting bead area; circle fitting is conducted on the point cloud data of the smoking end of the cigarette in the point cloud data set of the filter tip area, an end face model is obtained, and in the vertical state of the three-dimensional reconstruction model, the smoking end is the highest position or the lowest position in the filter tip area according to the cigarette direction of the three-dimensional reconstruction model; performing sphere fitting on the point cloud data set of the bead blasting area to obtain a sphere center of a fitted sphere; and calculating the distance from the center of sphere to the end face model to obtain the distance from the blasting bead to the suction end, thereby improving the efficiency and accuracy of position determination.

Description

Technical Field

[0001] This invention relates to a method and device for determining the position of the flavor capsule in a cigarette filter, belonging to the field of cigarette product testing technology. Background Technology

[0002] With the continuous improvement of cigarette consumers' demands and the gradual expansion of the tobacco market, the relatively monotonous flavor characteristics of traditional cigarettes can no longer fully satisfy consumers' sensory needs for cigarette products. To increase the sensory richness of cigarette smoking and enhance consumer satisfaction, the cigarette industry has designed and developed cigarette products with added flavor capsules in the filter to meet consumers' diverse smoking needs. These products add different functional or flavored flavor capsules to the filter. Before smoking, consumers squeeze the capsule to burst it, allowing the flavoring to diffuse throughout the filter. During smoking, the flavoring in the capsule makes the cigarette aroma more intense, enriching the consumer's smoking experience. Currently, the market for cigarette products with added flavor capsules is expanding. This product not only brings economic benefits to cigarette companies but also provides consumers with a variety of flavor experiences. Due to its special product design, the capsule needs to be precisely crushed before smoking to ensure that the flavoring diffuses instantly into the filter. Meanwhile, the position of the flavor capsule inside the filter rod directly affects the draw resistance during cigarette smoking, as well as the diffusion of the flavor within the capsule, thus impacting the consumer's smoking experience. Therefore, determining the position of the flavor capsule inside the filter rod (e.g., the distance between the capsule and the inhalation point, the offset of the capsule, etc.) is essential.

[0003] The patent publication CN118602935A discloses a method and device for detecting the position of a cigarette's flavor capsule. The method involves receiving a first image from a camera; receiving a second image from the camera after a preset time; and obtaining the position of the flavor capsule based on the first and second images. Different images are obtained by illuminating the cigarette with different light intensities, and the flavor capsule position is determined based on these images. Specifically, obtaining the flavor capsule position based on a third image includes: obtaining the region with the highest grayscale value in the third image as the flavor capsule region; calculating the center pixel position of the flavor capsule region as the center position of the flavor capsule; obtaining the pixel position of the cigarette's end face based on the first or second image; and calculating the distance between the center position and the end face as the flavor capsule position. Clearly, the images obtained during the position determination process are all two-dimensional images of the cigarette. This means that the distance between the center position and the cigarette's end face is limited to the radial distance within the cigarette filter. However, cigarettes are three-dimensional products, and a two-dimensional distance cannot accurately represent the position of the flavor capsule within the cigarette, thus making it impossible to determine whether the preset smoking experience can be achieved. The position detection results have poor reliability. Summary of the Invention

[0004] The purpose of this invention is to provide a method and device for determining the position of the flavor capsule in a cigarette filter, thereby solving the technical problem of low accuracy in detecting the position of the flavor capsule in the filter.

[0005] To achieve the above objectives, in one aspect, the present invention proposes a method for determining the position of the flavor capsule in a cigarette filter, comprising:

[0006] Data information of cigarettes was collected from different circumferential angles using CT equipment, and a three-dimensional reconstruction model of the cigarettes was constructed based on the data information;

[0007] The filter area and the popping bead area are split from the 3D reconstruction model according to the gray level difference, and point cloud datasets of the filter area and popping bead area are formed respectively.

[0008] The point cloud data of the cigarette suction end in the point cloud dataset of the filter area is fitted with a circle to obtain the end face model. In the vertical state of the three-dimensional reconstruction model, the suction end is the highest or lowest position in the filter area according to the cigarette direction of the three-dimensional reconstruction model.

[0009] A sphere is fitted to the point cloud dataset of the burst bead region to obtain the center of the fitted sphere; the distance from the center of the sphere to the end face model is calculated to obtain the distance between the burst bead and the suction end.

[0010] Furthermore, the center axis of the point cloud dataset of the filter region is fitted to generate a center axis model of the filter region;

[0011] A reference line parallel to the central axis is set on the outer surface of the filter area;

[0012] Calculate the offset angle between the perpendicular line connecting the center of the popping bead to the central axis model and the perpendicular line connecting the reference point on the same plane as the center of the popping bead to the central axis, as well as the offset distance from the center of the popping bead to the central axis. Use the offset angle and offset distance to represent the offset of the popping bead, wherein the reference point is on the reference line.

[0013] Furthermore, the axis of the tipping paper overlap on the outer surface of the filter tip area is used as a reference line.

[0014] Furthermore, the central axis is fitted using the following method:

[0015] The point cloud dataset of the filter area is divided into subsets along the direction perpendicular to the central axis of the filter. Circle fitting is performed on each subset after division to generate several fitted circles.

[0016] By fitting the center axis of all the fitted circles in the filter area, a central axis model is obtained.

[0017] Furthermore, a sphere is fitted to the point cloud dataset of the popping bead region using the following method:

[0018] Select a preset number of data points from the point cloud dataset of the popping bead region, and perform sphere fitting on the selected data points;

[0019] Determine whether the number of interior points of the fitted sphere is equal to the number of interior points in the point cloud dataset of the popping bead region;

[0020] If so, then the fitted sphere of the popping bead region is obtained;

[0021] If not, the iterative algorithm is invoked to continue selecting unfitted data points from the point cloud dataset of the popping bead region for sphere fitting until the number of interior points of the fitted sphere equals the number of interior points in the point cloud dataset of the popping bead region.

[0022] Furthermore, the burst bead region and / or filter region are obtained from the 3D reconstructed model based on grayscale differences using the following method:

[0023] Based on the data information of the cigarette, a training model is generated to segment the menthol capsule region and / or filter region according to the grayscale difference, thereby generating a training model for extracting the menthol capsule region and / or filter region; the training model is then called on the 3D reconstruction model to segment and obtain the menthol capsule region and / or filter region.

[0024] Furthermore, a filtered back projection algorithm is used to process the data information of the cigarette to generate a three-dimensional reconstruction model of the cigarette.

[0025] In another invention, the present invention also provides a device for determining the position of the flavor capsule in a cigarette filter, the device including a processor for executing the above-described method for determining the position of the flavor capsule in a cigarette filter.

[0026] The beneficial effects of this invention are as follows: Data information of cigarettes collected from different circumferential angles using CT equipment is used to construct a three-dimensional reconstruction model of the cigarette based on this data. The filter area and the flavor capsule area are separated from the three-dimensional reconstruction model according to grayscale differences, forming point cloud datasets for the filter area and the flavor capsule area, respectively. A circle fit is performed on the point cloud data of the cigarette's inhalation end within the point cloud dataset of the filter area to obtain an end-face model. In the vertical state of the three-dimensional reconstruction model, the inhalation end is the highest or lowest position in the filter area, depending on the cigarette's orientation within the three-dimensional reconstruction model. The flavor capsule area is further refined. The point cloud dataset of the bead region is used to fit a sphere to obtain the center of the fitted sphere. The distance from the center of the sphere to the end face model is calculated to obtain the distance from the bead to the inhalation end. This not only constructs a three-dimensional reconstruction model of the cigarette, making subsequent data processing based on three-dimensional data and effectively improving the efficiency of position detection, but also ensures that the data processing in calculating the distance is all within the same point cloud dataset, making the data processing process more holistic and representative, improving the accuracy of distance calculation, and avoiding the low accuracy of determination caused by the determination of end face position and sphere center position based on different images or different data in the existing technology. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating a method for determining the position of the flavor capsule in a cigarette filter according to the present invention.

[0028] Figure 2 This is a schematic diagram illustrating the operation of a CT scanner when collecting data from a cigarette, in a practical application scenario, using a method for determining the position of the flavor capsule in a cigarette filter, as proposed in this invention.

[0029] Figure 3 This is a schematic diagram illustrating the principle of a method for determining the position of the flavor capsule in a cigarette filter, as proposed in this invention, during the scanning process of a cigarette using a CT scanner in a practical application scenario.

[0030] Figure 4 This is a schematic diagram of a three-dimensional reconstruction model of a method for determining the position of the flavor capsule in a cigarette filter, as proposed in this invention, in a practical application scenario.

[0031] Figure 5 This is a schematic diagram showing the measurement results of the position of the flavor capsule in a cigarette filter, based on the method for determining the position of the flavor capsule proposed in this invention, in a practical application scenario.

[0032] Figure label:

[0033] 1-X-X-ray source; 2-Platform; 3-Sample base; 4-Sample holder; 5-Detection platform. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0035] The inventive concept of this invention is as follows: using CT equipment to collect data information of cigarettes through X-rays, which not only does not damage the cigarette body, but also constructs a three-dimensional model of the cigarette based on the data information; then dividing the three-dimensional reconstruction model of the cigarette into different regions to form point cloud datasets for each region, and then processing and calculating the point cloud datasets of each region to obtain the distance of the popping pod from the inhalation end and the offset of the popping pod, thereby improving the efficiency and accuracy of position determination.

[0036] Method Example 1:

[0037] like Figure 1 The diagram shown is a flowchart illustrating a method for determining the position of the flavor capsule in a cigarette filter according to the present invention, which includes steps S11-S14, specifically:

[0038] Before step S11, proceed as follows Figure 2 As shown, data on cigarettes is collected, specifically... Figure 2 This is a schematic diagram illustrating the operation of a CT scanner in a practical application scenario when a method for determining the position of the flavor capsule in a cigarette filter, as proposed in this invention, is used to acquire data from a cigarette. The cigarette is fixed using a sample holder 4, and its position is adjusted to ensure it is perpendicular to the sample base 3. The industrial CT scanner is then opened, and the sample base 3 is placed into the bayonet of the platform 2 within the industrial CT scanner, ensuring that the clamping devices (sample base 3 and sample holder 4) are fixed to the platform 2 to prevent the sample from falling off when the platform 2 rotates. The X-ray source 1 is configured with an X-ray source tube voltage of 100 kV, an X-ray source tube current of 70 μA, a scanning thickness of 0.004 mm, a scanning interval of 0.004 mm, and a cone-beam CT scanning mode. Normal scanning mode (T-scan): The worktable moves the platform 2 so that the cigarette to be detected is centered in the X-ray scanning range. By controlling the rotation of the platform 2, it is ensured that the cigarette is in the X-ray scanning position within a 360° range. The held cigarette is removed, and the CT equipment is calibrated with air. Then, the central axis calibration rod is placed on the platform 2 for central axis calibration. The cigarette is then placed back on the platform 2, and the CT scan is started to scan the cigarette. The data information received by the detection platform 5 is transmitted to the computer for storage, completing the acquisition of cigarette data information. This allows for the acquisition of comprehensive cigarette data information without damaging the cigarette, providing a comprehensive and accurate data source for subsequent analysis of cigarette content.

[0039] After collecting data on the cigarette using a CT scanner, step S11 is executed. The CT scanner collects data on the cigarette from different circumferential angles and constructs a three-dimensional reconstruction model of the cigarette based on the data. Here, "different axial angles" means that data on the cigarette is collected at every axial angle around the cigarette to achieve full-angle data acquisition. Based on the comprehensive data, a three-dimensional reconstruction model of the cigarette is constructed, achieving a high degree of fidelity in the three-dimensional reconstruction model.

[0040] It should be noted that in practical applications, the filtered back projection algorithm is used to process the data information of the cigarette to generate a three-dimensional reconstruction model of the cigarette. Specifically, the filtered back projection algorithm (i.e., the FDK algorithm) is used to process the data information through the following steps: First, the acquired data is preprocessed. Images are acquired at a rate of 1° rotation, resulting in 360 cigarette images. The two-dimensional projection data acquired at each angle is weighted to correct the cone beam. Second, the corrected and weighted projection data is filtered in one dimension along a projection perpendicular to the flat panel detector. Third, the data from the second step is back-projected to reconstruct the image. Back-projection calculations are performed along the X-ray direction on the filtered data. Simultaneously, due to the large spacing in the Z-axis direction during sampling, interpolation calculations are required in the Z-axis direction. In this invention, bilinear interpolation is used. After interpolation in both the X-axis and Y-axis directions, a three-dimensional reconstruction model of the cigarette is formed.

[0041] Step S12: The filter region and the flavor capsule region are split from the 3D reconstruction model according to grayscale differences, forming point cloud datasets for the filter region and the flavor capsule region, respectively. Here, the flavor capsule region and / or filter region are obtained from the 3D reconstruction model according to grayscale differences using the following method: Training is performed on the splitting of the flavor capsule region and / or filter region according to grayscale differences based on the cigarette data information, generating a training model for extracting the flavor capsule region and / or filter region; the training model is called on the 3D reconstruction model to split the flavor capsule region and / or filter region. Multiple training sessions are conducted to split the flavor capsule region and filter region according to grayscale differences, forming an accurate splitting model. This improves the accuracy of splitting the flavor capsule region and filter region from the 3D reconstruction model and lays a precise data foundation for subsequent data processing.

[0042] Specifically, the segmentation training is performed using the following method: A computer image processing system is used to segment images containing popping beads from the acquired two-dimensional image sequence. Based on the different grayscale values ​​of the popping beads and the filter, the popping beads and the filter are labeled separately in the three-view interface of the image processing software (to ensure classification accuracy, multiple two-dimensional images need to be labeled during this process). When the popping bead region is segmented in the three-dimensional reconstruction model, a grayscale-based Region of Interest (ROI) is created in the image processing system. The filter region is then separated separately in the obtained three-dimensional reconstruction model, forming a new ROI. Subsequently, a new ROI is formed within the ROI of the filter region to extract the popping bead region; the popping bead region is then segmented from the filter region based on the new ROI.

[0043] Step S13: Perform circle fitting on the point cloud data of the cigarette suction end in the point cloud dataset of the filter area to obtain the end face model. In the vertical state of the three-dimensional reconstruction model, the suction end is the highest or lowest position in the filter area according to the cigarette direction of the three-dimensional reconstruction model. Here, when determining the point cloud data of the cigarette suction end, the selection is combined with the spatial position of the filter area (for example, selecting the point cloud data with the largest z-value from the point cloud dataset of the filter area for circle fitting, or selecting the point cloud data with the smallest z-value for circle fitting, etc., where the direction of the z-value is along the axial direction perpendicular to the filter center). The end face model refers to a model that can represent the characteristics of the end face position, including but not limited to the end face equation model. In a preferred embodiment of the present invention, the preferred end face model is the end face equation. Specifically, three point cloud data points are randomly selected from the fitted circle of the suction end (i.e., the fitted circle obtained by circle fitting the point cloud data of the suction end) to construct the end face equation.

[0044] Step S14: Perform spherical fitting on the point cloud dataset of the burst bead region to obtain the center of the fitted sphere; calculate the distance from the center of the sphere to the end face model to obtain the distance between the burst bead and the suction end; it should be noted that the spherical fitting on the point cloud dataset of the burst bead region is performed as follows: select a preset number of data points from the point cloud dataset of the burst bead region, and perform spherical fitting on the selected data points; determine whether the number of interior points of the fitted sphere is equal to the number of interior points of the point cloud dataset of the burst bead region; if yes, the fitted sphere of the burst bead region is obtained; if not, call the iterative algorithm to continue from the point cloud dataset of the burst bead region. Unfitted data points are selected from the dataset for sphere fitting until the number of interior points of the fitted sphere equals the number of interior points in the point cloud dataset of the menthol region. Here, the preset number of points refers to the preset number of basic data points required when fitting a sphere. In practical applications, the preset number of points will be set according to the requirements of different cigarettes for the menthol. In the preferred embodiment of this application, the preset number of points is preferably 4 data points. The substitution iterative algorithm refers to continuously selecting unfitted data points from the point cloud dataset of the menthol region until the number of interior points of the fitted sphere equals the number of interior points in the point cloud dataset of the menthol region.

[0045] In practical applications, the fitting parameters of the fitted sphere will be calculated. When the fitting parameters of the fitted sphere reach a preset fitting parameter threshold, the optimal sphere model is obtained. The fitting parameter threshold is used to measure whether the optimal sphere model is obtained during the sphere fitting process, ensuring that all interior points contained in the fitted sphere are integrated during each sphere fitting process, avoiding phenomena such as misfitting or unfitted interior points.

[0046] Through steps S11-S14, the point cloud datasets of the filter area and the burst capsule area are processed respectively to accurately obtain the length of the burst capsule center point from the cigarette filter suction end, simplifying the position determination steps, improving determination efficiency, and thus more effectively guiding the production and processing of cigarettes and their internal burst capsules.

[0047] In a preferred embodiment of the present invention, the cigarette A to be tested is placed on the sample holder in a CT scanner. Data information of cigarette A is acquired from various axial angles through X-ray scanning in the CT scanner. Based on the data of cigarette A, a three-dimensional reconstruction model (Model) of cigarette A is constructed using the FDK algorithm. Following a pre-trained model that splits based on grayscale differences, the menthol capsule region and the filter region are separated from the 3D reconstruction model (Model), forming a point cloud dataset M1 for the menthol capsule region and a point cloud dataset M2 for the filter region. Combining the spatial position of the filter region in the Model, the point cloud data with the largest z-value is preferably selected from the point cloud dataset M2 of the filter region for circle fitting, obtaining the end face equation L1. A sphere is fitted to the menthol capsule region's power data dataset M1. When the number of interior points of the fitted sphere is equal to the number of interior points of the menthol capsule region's point cloud dataset M1, the optimal spherical model of the fitted sphere is obtained, and the center R of the fitted sphere is determined. The distance from the center R of the sphere to the end face equation L is calculated using the following formula, thus obtaining the distance L from the inhalation end of the cigarette A to the flavor capsule. The preferred end face equation is L1 = Ax + By + Cz + D; the center R is (x', y', z').

[0048]

[0049] Method Example 2:

[0050] This invention proposes a method for determining the position of the flavor capsule in a cigarette filter, and also determines the offset of the flavor capsule in the filter. Specifically, the method involves fitting a central axis to the point cloud dataset of the filter region to generate a central axis model of the filter region. Here, the central axis fitting is performed by the following method: the point cloud dataset of the filter region is divided into subsets along the direction perpendicular to the central axis of the filter; each subset is fitted with a circle to generate several fitted circles; the centers of all the fitted circles in the filter region are fitted with a central axis to obtain a central axis model. The central axis model refers to a model that can represent the positional characteristics of the central axis, including but not limited to a central axis equation model. In a preferred embodiment of this invention, the preferred central axis model is a central axis equation.

[0051] A reference line parallel to the central axis is set on the outer surface of the filter area; it should be noted that the reference line is the axis used to calculate the initial measurement position of the following offset angle. Typically, the water tipping paper overlap axis on the outer surface of the filter area is used as the reference line.

[0052] Calculate the offset angle between the perpendicular line connecting the center of the popping bead to the central axis model and the perpendicular line connecting the reference point (which is on the same plane as the center of the popping bead) to the central axis, as well as the offset distance from the center of the popping bead to the central axis. Use the offset angle and offset distance to represent the offset of the popping bead. The reference point is on the reference line. Here, the perpendicular line connecting the center of the popping bead to the central axis model refers to the line connecting the center of the fitted circle (which is on the same plane as the center of the popping bead) in the central axis model and the center of the popping bead. The reference point (which is on the same plane as the center of the popping bead) refers to the reference point on the reference line (which is on the same plane as the center of the popping bead). That is, when calculating the offset angle, the center of the popping bead, the reference point, and the center of the fitted circle in the central axis model are all on the same plane.

[0053] Following the above embodiments of the present invention, the point cloud dataset M2 of the filter area is divided into subsets along the Z-axis direction (where the Z-axis direction is perpendicular to the central axis of the filter), resulting in M ​​point cloud subsets. For each point cloud subset, a fitted circle is obtained, resulting in M ​​fitted circles and their center coordinates. The center coordinates of the M fitted circles are then fitted with an axis to obtain the central axis equation l. The axis of the tipping paper overlap on the outer surface of the filter area is set as the baseline l. s The preferred coordinates of the center of the popping bead are R(x', y', z'). Based on the coordinates of the center of the popping bead, the center of the fitted circle is selected as R0(x0, y0, z0) in the central axis equation l. On the baseline l... s Select the reference point S(x) s y s , z s ), where z`=z0=z s Calculate the angle θ between RR0 and SR0, and the length of RR0, where θ is the offset angle and the length is the offset distance.

[0054] In practical applications, the offset of the menthol capsule will be expressed by the following formula:

[0055]

[0056] Method Example 3:

[0057] like Figure 3The diagram illustrates the principle of a CT scanner during cigarette scanning, in a practical application scenario, of the method for determining the position of the flavor capsule in a cigarette filter proposed in this invention. The cigarette to be scanned is positioned at point O. Images are acquired using X-rays at 1° rotation intervals. A virtual detector is used to weight the two-dimensional projection data acquired at each angle to correct the cone beam. A flat panel detector is then used to perform one-dimensional filtering on the corrected and weighted projection data, thereby acquiring cigarette data information from all angles and constructing a three-dimensional reconstruction model of the cigarette.

[0058] Method Example 4:

[0059] like Figure 4 The figure shows a schematic diagram of a three-dimensional reconstruction model of a method for determining the position of the flavor capsule in a cigarette filter, as proposed in this invention, in a practical application scenario. When the above-mentioned position determination method is applied to the three-dimensional reconstruction model, the distance between the flavor capsule and the upper surface of the filter area is 11.917 mm, and the distance between the flavor capsule and the lower surface of the filter area is 12.127 mm.

[0060] Method Example 5:

[0061] like Figure 5 The diagram shows the position measurement results of the flavor capsule in a cigarette filter, as proposed in this invention, in a practical application scenario. When the position determination method is applied, the diameters of the flavor capsule in the four positions are as follows: 2.713 mm (top position); 1.809 mm (bottom position); 1.903 mm (left position); and 2.464 mm (right position). The distance from the flavor capsule to the upper surface of the filter area is 11.917 mm; the distance from the flavor capsule to the lower surface of the filter area is 12.127 mm.

[0062] Equipment Example:

[0063] The present invention also proposes a device for determining the position of the popcorn capsule in a cigarette filter. The device includes a processor for executing the method for determining the position of the popcorn capsule in a cigarette filter as described above. Here, the embodiments of the detection device are referred to in the embodiments (1-5) of the method for determining the position of the popcorn capsule in a cigarette filter, and will not be repeated here.

[0064] In summary, the present invention provides a method for determining the position of a flavor capsule in a cigarette filter. This method utilizes industrial CT technology to scan the cigarette filter containing the flavor capsule, obtaining a three-dimensional reconstructed model of the sample. The cigarette filter portion and the flavor capsule portion are divided based on grayscale values, thereby obtaining point cloud datasets for each portion. By processing the point cloud datasets, the length of the flavor capsule's center point from the inhalation end of the cigarette filter and the distance of the flavor capsule's center point from the central axis are obtained.

[0065] Furthermore, this invention solves the problems of low efficiency and insufficient accuracy in current cigarette flavor capsule position detection processes, improving detection accuracy and efficiency, and bringing greater economic benefits. Moreover, this invention replaces manual labor with mechanical equipment for detection, solving the problem of workers being exposed to strong light for extended periods during flavor capsule position detection, thus reducing health hazards to workers.

Claims

1. A method for determining the position of a flavor capsule in a cigarette filter, characterized in that, include: Data information of cigarettes was collected from different circumferential angles using CT equipment, and a three-dimensional reconstruction model of the cigarettes was constructed based on the data information; The filter area and the popping bead area are split from the 3D reconstruction model according to the gray level difference, and point cloud datasets of the filter area and popping bead area are formed respectively. The point cloud data of the cigarette suction end in the point cloud dataset of the filter area is fitted with a circle to obtain the end face model. In the vertical state of the three-dimensional reconstruction model, the suction end is the highest or lowest position in the filter area according to the cigarette direction of the three-dimensional reconstruction model. A sphere is fitted to the point cloud dataset of the burst bead region to obtain the center of the fitted sphere; the distance from the center of the sphere to the end face model is calculated to obtain the distance between the burst bead and the suction end.

2. The method for determining the position of the flavor capsule in a cigarette filter according to claim 1, characterized in that, The center axis of the point cloud dataset of the filter area is fitted to generate a center axis model of the filter area. A reference line parallel to the central axis is set on the outer surface of the filter area; Calculate the offset angle between the perpendicular line connecting the center of the popping bead to the central axis model and the perpendicular line connecting the reference point on the same plane as the center of the popping bead to the central axis, as well as the offset distance from the center of the popping bead to the central axis. Use the offset angle and offset distance to represent the offset of the popping bead, wherein the reference point is on the reference line.

3. The method for determining the position of the flavor capsule in a cigarette filter according to claim 2, characterized in that, Use the axis of the tipping paper overlap on the outer surface of the filter area as the baseline.

4. The method for determining the position of the flavor capsule in a cigarette filter according to claim 2, characterized in that, The central axis is fitted using the following method: The point cloud dataset of the filter area is divided into subsets along the direction perpendicular to the central axis of the filter. Circle fitting is performed on each subset after division to generate several fitted circles. By fitting the center axis of all the fitted circles in the filter area, a central axis model is obtained.

5. The method for determining the position of the flavor capsule in a cigarette filter according to any one of claims 1-4, characterized in that, The point cloud dataset of the popping bead region was spherically fitted using the following method: Select a preset number of data points from the point cloud dataset of the popping bead region, and perform sphere fitting on the selected data points; Determine whether the number of interior points of the fitted sphere is equal to the number of interior points in the point cloud dataset of the popping bead region; If so, then the fitted sphere of the popping bead region is obtained; If not, the iterative algorithm is invoked to continue selecting unfitted data points from the point cloud dataset of the popping bead region for sphere fitting until the number of interior points of the fitted sphere equals the number of interior points in the point cloud dataset of the popping bead region.

6. The method for determining the position of the flavor capsule in a cigarette filter according to any one of claims 1-4, characterized in that, The burst bead region and / or filter region are obtained from the 3D reconstructed model based on grayscale differences using the following method: Based on the data information of the cigarette, a training model is generated to segment the menthol capsule region and / or filter region according to the grayscale difference, thereby generating a training model for extracting the menthol capsule region and / or filter region; the training model is then called on the 3D reconstruction model to segment and obtain the menthol capsule region and / or filter region.

7. The method for determining the position of the flavor capsule in a cigarette filter according to any one of claims 1-4, characterized in that, The data information of the cigarette is processed using a filtered back projection algorithm to generate a three-dimensional reconstruction model of the cigarette.

8. A device for determining the position of a flavor capsule in a cigarette filter, characterized in that, The device includes a processor for performing the method for determining the position of the flavor capsule in a cigarette filter as described in any one of claims 1-7.

Images