Detection method of tobacco order rate in cigarettes based on CT scanning technology
Through CT scanning technology and three-dimensional reconstruction technology, the order rate of heating cigarette tobacco is detected, which solves the problem of detecting the disorder rate of tobacco in the existing technology, realizes the automatic judgment and distribution law statistics of tobacco in the tobacco branch, and improves the detection Accuracy and reliability.
Patent Information
- Application Number
- CN202210709131.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-21
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2042-06-21
AI Technical Summary
The prior art is difficult to non-destructively detect the order rate of tobacco wires in heating cigarettes, affecting the suction resistance and suction quality, and affecting the density of the sheet wire when the heating body is inserted.
Using the tobacco line order rate detection method based on CT scanning technology, the CT value database of tobacco line, packaging paper, filter rod and rolled paper is pre-established, and the tomography image of the tomography branch structure is obtained using CT scanner, combined with the database segmentation image, and three-dimensional Structural model reconstruction, calculate the number, length, width and spatial distribution of tobacco threads, and then calculate the order rate of tobacco threads.
It realizes rapid non-destructive testing of the orderly rate of tobacco, provides a scientific and reasonable technical foundation, improves the accuracy and reliability of the detection, can automatically judge the distribution rules of tobacco, and reduces the impact on the heating body when inserting.
Smart Images

Figure CN115035079B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of cigarette manufacturing, and in particular to a method for detecting the orderly rate of shredded tobacco in a cigarette based on CT scanning technology. Background Art
[0002] The orderly rate of tobacco contained in heated cigarette products is an important indicator of concern to the tobacco industry and a key indicator of quality control.
[0003] The reason is that heated cigarette products use heating to generate smoke on thin filaments, while the heated cigarettes sold on the market mainly use internal chip-type or cone-shaped heating bodies, which need to be inserted into the cigarette for heating.
[0004] If the tobacco shreds are arranged in a disordered state, when the heater is inserted into the cigarette, it will have a great impact on the density of the thin shreds at different positions of the cigarette, and will squeeze the tobacco shreds at the interface, resulting in changes in the draw resistance and the quality of the draw, affecting the consumer experience. Therefore, the industry is in urgent need of a solution for non-destructive testing of the orderliness of tobacco shreds in cigarettes. Summary of the invention
[0005] In view of the above, the present invention aims to provide a method for detecting the orderly rate of tobacco shreds in cigarettes based on CT scanning technology, so as to fill the gap in the industry for detecting the orderly rate of tobacco shreds in heated cigarettes.
[0006] The technical solution adopted by the present invention is as follows:
[0007] The present invention provides a method for detecting the order rate of tobacco shreds in cigarettes based on CT scanning technology, which includes:
[0008] Pre-establish a database of CT values for tobacco, packaging paper, filter rods and wrapping paper materials;
[0009] Scanning the cigarette to be tested layer by layer using a CT scanner to obtain N two-dimensional structural tomographic images of the cigarette to be tested;
[0010] In combination with the CT value database, the cigarette structure tomographic image is segmented to obtain CT grayscale images of the tobacco, wrapping paper, filter rod and rolling paper regions of the cigarette to be tested;
[0011] Based on the CT grayscale image, boundary information of the tobacco shreds and the cigarette to be tested is obtained, and a three-dimensional structural model is reconstructed;
[0012] According to the reconstruction results of the three-dimensional structure model, the quantity, length, width and spatial distribution of the tobacco shreds inside the tested cigarette are obtained;
[0013] The order rate of tobacco shreds was calculated based on the obtained quantity, length, width and spatial distribution.
[0014] In at least one possible implementation manner, the total order rate of tobacco in the tested cigarette is: the ratio of the sum of the order rates of each tobacco strand to the total number of tobacco strands in the cigarette.
[0015] In at least one possible implementation, the detection method further includes:
[0016] Detect the tobacco order rate data of heated cigarette products of different specifications;
[0017] The tobacco cut order rate data is integrated and statistically analyzed to determine the distribution law of the tobacco cut order rate.
[0018] In at least one possible implementation manner, obtaining the boundary information of the tobacco shreds and the cigarette to be tested includes: using edge detection, circle detection and ROI region growing method to obtain the boundary and volume of the tobacco shreds and the cigarette to be tested from the CT grayscale image.
[0019] In at least one possible implementation, obtaining the quantity, length, width and spatial distribution of tobacco shreds inside the tested cigarette includes:
[0020] According to the boundary information and the pore three-dimensional space model reconstructed from the three-dimensional structure model, a matching grid size is selected for grid division, and the number, length, width and spatial distribution of tobacco shreds inside the tested cigarette are calculated, wherein the grid type is a non-homogeneous grid.
[0021] In at least one possible implementation manner, the calculating the order rate of the shredded tobacco includes: selecting shredded tobacco having an aspect ratio greater than a preset aspect ratio threshold.
[0022] In at least one possible implementation, calculating the order rate of the shredded tobacco includes:
[0023] Select a plane that is tangent to the outer edge of the three-dimensional model of the cigarette to be tested, and the three-dimensional model of the cigarette to be tested is parallel to the plane;
[0024] Arranging a plurality of straight lines on the plane parallel to the central axis of the three-dimensional model of the cigarette to be tested;
[0025] Projecting an image of a tobacco shred in the three-dimensional model of the cigarette to be tested onto the plane;
[0026] Decomposing the projection image of the tobacco into a plurality of projection arc segments, and measuring the acute angle between each projection arc segment and the straight line to obtain a plurality of angle values;
[0027] The percentage of the ratio of the average of all the angle values to 90° is determined as the tobacco cut order rate of a single tobacco cut.
[0028] In at least one possible implementation, calculating the order rate of the shredded tobacco includes:
[0029] Select a first plane tangent to the outer edge of the three-dimensional model of the cigarette to be tested, and construct a second plane perpendicular to the first plane, and the three-dimensional model of the cigarette to be tested is parallel to the first plane and the second plane respectively;
[0030] A plurality of straight lines parallel to the central axis of the three-dimensional model of the cigarette to be tested are arranged on the first plane and the second plane;
[0031] Projecting an image of a tobacco shred in the three-dimensional model of the cigarette to be tested onto the first plane and the second plane respectively;
[0032] Decomposing the projection image of the tobacco into a plurality of projection arc segments, and measuring the acute angle between each projection arc segment and the straight line to obtain a plurality of angle values;
[0033] Compare the maximum angle values of each projected arc in the first plane and the second plane;
[0034] The percentage of the ratio of the difference between 90° and the maximum angle value to 90° is determined as the tobacco cut order rate of a single tobacco cut.
[0035] In at least one possible implementation, calculating the order rate of the shredded tobacco includes:
[0036] The central axis of the three-dimensional model of the cigarette to be tested is used as the intersection of the first plane and the second plane which are perpendicular to each other, and a third plane which is perpendicular to the central axis is constructed;
[0037] A plurality of parallel lines parallel to the central axis of the three-dimensional model of the cigarette to be tested are arranged on the first plane and the second plane, and two mutually perpendicular intersecting lines are arranged on the third plane, and the projection of the central axis on the third plane is the intersection point of the intersecting lines;
[0038] Projecting an image of a tobacco shred in the three-dimensional model of the cigarette to be tested onto the first plane, the second plane, and the third plane respectively;
[0039] Decomposing the projection image of the tobacco into a plurality of projection arc segments, and measuring the acute angles between each projection arc segment and the parallel lines and the intersection lines on the corresponding plane to obtain a plurality of angle values;
[0040] Compare the maximum angle values of the projected arcs in the first plane, the second plane and the third plane;
[0041] The percentage of the ratio of the maximum angle value to 90° is determined as the tobacco order rate of a single tobacco shred.
[0042] The main design concept of the present invention is to use a non-destructive testing mechanism, combined with mature CT scanning technology and three-dimensional reconstruction technology to obtain the overall structure of the cigarette and the details of the component units. Specifically, the pre-established CT value database of the cigarette unit and the CT scan of the cigarette to be tested are used to segment the tobacco and cigarette images and perform three-dimensional reconstruction. The three-dimensional model is used to obtain the number, length and width of the tobacco inside the cigarette to be tested. Finally, the obtained number, length and width of the tobacco are used to obtain the order rate and spatial distribution law of the tobacco. The present invention can obtain the overall structure of the cigarette based on CT scanning technology and three-dimensional reconstruction technology, realize the automatic judgment of the tobacco inside the cigarette and the statistics of the distribution law, thereby realizing the rapid non-destructive detection and determination of the order rate of the tobacco, and providing a scientific and reasonable technical basis for the determination of the order rate of tobacco in the industry. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:
[0044] Figure 1 A flow chart of a method for detecting the orderly rate of tobacco shreds in a cigarette based on CT scanning technology provided in an embodiment of the present invention;
[0045] Figure 2 A schematic diagram of a plane projection of a cigarette provided by an embodiment of the present invention;
[0046] Figure 3 A schematic diagram of measuring the in-plane order rate of tobacco shreds in a cigarette provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0047] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.
[0048] The present invention proposes an embodiment of a method for detecting the order rate of tobacco shreds in a cigarette based on CT scanning technology. Specifically, Figure 1 Indicative, including:
[0049] Step S1, pre-establishing a CT value database of tobacco shreds, packaging paper, filter rods and winding paper materials;
[0050] In actual operation, appropriate amounts of tobacco shreds, wrapping paper, filter rods and rolling paper samples and other component units can be taken, and the samples can come from actual production samples of various tobacco companies. The number of samples of each component unit is not less than 500, and they are placed in a CT scanner (mature CT scanning equipment such as medical CT and industrial CT), scanned, and the CT values of each component unit sample are obtained and statistical analysis is performed. In this way, CT value databases for tobacco shreds, wrapping paper, filter rods and rolling paper can be established respectively, and the CT value range of each structural component can be determined.
[0051] Step S2, using a CT scanner to scan the cigarette to be tested layer by layer to obtain N two-dimensional cigarette structure tomographic images of the cigarette to be tested;
[0052] Specifically, the cigarette samples to be measured can be placed in a CT scanner, and the CT scanner can be used to scan these cigarette samples layer by layer to obtain N two-dimensional tomographic images of the cigarette samples, and the images are stored in an image processor.
[0053] It can be added here that the CT scanner used to measure the cigarettes to be tested can be pre-calibrated and parameterized, mainly to determine parameters such as image size, scanning speed, scanning resolution, scanning thickness, scanning spacing, etc. specifically used for cigarette structure scanning, so as to avoid low measurement accuracy and measurement errors due to different parameter settings.
[0054] Step S3, combining the CT value database, segmenting the cigarette structure tomographic image, and obtaining CT grayscale images of the tobacco, wrapping paper, filter rod and rolling paper regions of the cigarette to be tested;
[0055] In actual operation, neural network, deep learning and other image processing algorithms can be used to perform multi-threshold segmentation on N two-dimensional tomographic images of the tested cigarette according to the CT threshold range of tobacco, wrapping paper, filter rod and winding paper materials in the CT value database, to form CT images of different component units and perform grayscale processing. The present invention does not limit this, but it can be further explained that before the segmentation operation, the image processing technology can be used to pre-process the tomographic image of the cigarette structure to enhance the image features, retain the useful information in the image, eliminate irrelevant information, and facilitate subsequent segmentation, calculation and other processing. For example, color correction, contrast enhancement and brightness enhancement, median denoising filtering, etc., the present invention does not limit this.
[0056] Step S4, based on the CT grayscale image, obtaining the boundary information of the tobacco shreds and the cigarette to be tested, and reconstructing a three-dimensional structure model;
[0057] Specifically, edge detection, circle detection and ROI region growing method can be used to obtain the boundaries and volumes of tobacco and the cigarette to be tested from the CT grayscale image. Then, the CT grayscale image can be used to establish an stl neutral file, and finite element, AVIZO, ABAQUS and other three-dimensional processing software can be used to achieve three-dimensional model reconstruction.
[0058] Step S5: According to the reconstruction result of the three-dimensional structure model, the quantity, length, width and spatial distribution of the tobacco shreds inside the cigarette to be tested are obtained.
[0059] Specifically, according to the boundary information and the three-dimensional spatial model of the pores, a matching grid size can be selected for grid division (the grid type is a non-homogeneous grid, which can be selected based on different object sizes), so that the number, length, width and spatial distribution of tobacco shreds inside the cigarette can be calculated.
[0060] Finally, step S6 is performed to calculate the order rate of the tobacco shreds according to the obtained quantity, length, width and spatial distribution.
[0061] Furthermore, the width of the cut tobacco is generally 0.7-1.1 mm, so the arrangement direction of the tobacco with an aspect ratio lower than a preset threshold (such as 3) has little effect on the heating plate (cone), so when implementing step S6, this part of the tobacco can be excluded from the calculation scope. Based on this, here is a reference for the implementation of step S6:
[0062] A plane tangent to the outer edge of the cigarette is randomly selected, and the cigarette model is parallel to the plane. Several straight lines parallel to the center line of the cigarette are set on the plane. The image of a tobacco shred with an aspect ratio greater than 3 is projected onto the plane. The angle (acute angle) between the projection of the tobacco shred and the parallel lines is detected by the image method, which is the angle of the tobacco shred. The average value of the sum of the angles of all tobacco shreds / 90°×100% is the order rate of the tobacco shreds.
[0063] Furthermore, although the aforementioned embodiment of measuring the order rate of tobacco shreds in cigarettes can effectively reflect the average order rate of tobacco shreds and provide guidance for testing and production, the present invention further believes that since the data is only an average, it cannot fully and accurately reflect the arrangement pattern of tobacco shreds in the cigarette, and thus it is difficult to analyze which tobacco shreds will affect the insertion and quality of the heating body.
[0064] Specifically, based on the above-mentioned concept, it has been found in practice that although the tobacco in the cigarette has an angle with the axis of the cigarette, when the plane where the tobacco and the axis centerline are located is perpendicular to the projection plane, the projection of the tobacco and the projection of the axis centerline on the projection plane coincide with the projection of the axis centerline on the projection plane. When judging, the tobacco will be considered to be ordered, which will cause certain errors in the order rate detection.
[0065] Therefore, the present invention provides the following improvement ideas:
[0066] Choose a plane X that is tangent to the outer edge of the cigarette, and then build a plane Y that is perpendicular to the plane. The cigarette model is parallel to the two planes. Set several straight lines parallel to the center line of the cigarette on the two planes. Project the image of a tobacco with an aspect ratio greater than 3 obtained in the cigarette on the two planes respectively, and decompose the projection image of the tobacco into multiple arcs composed of single arcs. Use the image method to detect the angle (acute angle) between the projection of the tobacco on the two planes and the parallel line (center line). Compare the size of the projection angle of the tobacco in the two planes, and select the maximum angle of the projection arc in the two planes, which is calculated as θ. max , then (90°-θ max ) / 90°×100% is the order rate of the tobacco.
[0067] For example, the entire cigarette is projected in two planes. Figure 2 As shown, taking the projection of a cigarette on the Y plane as an example, a certain tobacco projection (combined with Figure 3 ), decompose the tobacco composed of multiple arcs into single arc lengths, denoted as AB and BC respectively, and construct line segments L with the endpoints of the arcs respectively AB and L BC , the angles (acute angles) between the line segment and the parallel line are α° and β° respectively. Take the larger value of α° and β°. Assuming α°>β°, the order rate of the tobacco in the plane is α° / 90°. Calculate the projection of the tobacco in plane X and plane Y respectively, and take the maximum angle of the projection arc as θ max , (90°-θ max ) / 90°×100% is taken as the order rate of the tobacco shred.
[0068] Heated cigarettes of different specifications were taken and the order rate was detected using the above two methods and steps (further, the total order rate of tobacco in the cigarette was: the sum of the order rates of each tobacco strand divided by the total number of tobacco strands in the cigarette). The results are shown in Table 1, from which it can be seen that the vertical dual-plane projection method has better accuracy than the single-plane projection method, and can more reliably reflect the arrangement state of tobacco strands in the cigarette.
[0069] Table 1 Tobacco order rate test results
[0070]
[0071] Based on the aforementioned embodiments, it has been further discovered through practice that the spatial arrangement of tobacco in a cigarette is actually three-dimensional. Although the projection of a certain tobacco strand on two vertical planes can reflect the angle between the strand and the center line of the cigarette, it cannot fully reflect the accurate angle between the tobacco strand and the cigarette. The angle will be deformed, resulting in certain errors in the order rate detection.
[0072] Based on this, the present invention proposes the following improvements:
[0073] The axial centerline of the cigarette is taken as the intersection of two vertical planes, and another plane perpendicular to the axial centerline of the cigarette is constructed to form a three-dimensional coordinate system. The image of a tobacco with an aspect ratio greater than 3 obtained in the cigarette is projected on the three planes respectively, and the projection image of the tobacco is decomposed into multiple arcs composed of single arcs. The image method is used to detect the angles (acute angles) between the projections of each arc of the tobacco on the three planes and the parallel lines and intersection lines. The sizes of the projection angles of the tobacco in the three planes are compared, and the maximum angle of the projection arcs in the three planes is selected, which is calculated as θ. max , then θ max / 90°×100% is determined as the order rate of the tobacco. It can be understood that this process is similar to single-plane and double-plane projection, except that the mathematical representations of the order rates of the three are different.
[0074] Furthermore, the order rate of heated cigarettes of different specifications can be detected using the above method and steps, and the distribution law of the order rate of tobacco can be determined to be a normal distribution through statistical analysis of the integral calculation of the data.
[0075] Finally, from the hardware perspective, it can be added that the main architecture for realizing the above-mentioned concept of the present invention may include a CT scanner and an image processing server, an offline / online processing system, a memory, and a display, etc. The image processing server is connected and communicated with the CT scanner; the image processing server stores computer instructions, and completes the scanning and detection of the cigarette structure by executing the computer instructions; the offline / online processing system is used to receive information from the image processing server and perform image analysis calculations, three-dimensional reconstruction and other operations; the memory is used to store information such as the order rate of tobacco shreds; the display is used to display information such as the three-dimensional model, structure, and order rate of tobacco shreds of cigarettes.
[0076] In summary, the main design concept of the present invention is to use a non-destructive testing mechanism, combined with mature CT scanning technology and three-dimensional reconstruction technology to obtain the overall structure of the cigarette and the details of the component units. Specifically, the pre-established cigarette unit CT value database and the CT scan image of the cigarette to be tested are used to segment the tobacco and cigarette images and perform three-dimensional reconstruction. The three-dimensional model is used to obtain the number, length and width of the tobacco inside the cigarette to be tested. Finally, the obtained number, length and width of tobacco are used to obtain the order rate and spatial distribution law of the tobacco. The present invention can obtain the overall structure of the cigarette based on CT scanning technology and three-dimensional reconstruction technology, realize the automatic judgment of the tobacco inside the cigarette and the statistics of the distribution law, thereby realizing the rapid non-destructive detection and determination of the order rate of tobacco, and providing a scientific and reasonable technical basis for the determination of the order rate of tobacco in the industry.
[0077] In the embodiments of the present invention, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. A and B may be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c may be single or multiple.
[0078] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings, but the above is only a preferred embodiment of the present invention. It should be noted that the technical features involved in the above embodiments and their preferred methods can be reasonably combined and matched into a variety of equivalent schemes by those skilled in the art without departing from or changing the design ideas and technical effects of the present invention; therefore, the present invention is not limited to the scope of implementation shown in the drawings, and all changes made in accordance with the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the specification and drawings, should be within the protection scope of the present invention.
Claims
1. A method for detecting the order rate of tobacco in cigarettes based on CT scanning technology. It is characterized in that include: Pre-establish a database of CT values for tobacco, packaging paper, filter rods and wrapping paper materials; Scanning the cigarette to be tested layer by layer using a CT scanner to obtain N two-dimensional structural tomographic images of the cigarette to be tested; In combination with the CT value database, the cigarette structure tomographic image is segmented to obtain CT grayscale images of the tobacco, wrapping paper, filter rod and rolling paper regions of the cigarette to be tested; Based on the CT grayscale image, boundary information of the tobacco shreds and the cigarette to be tested is obtained, and a three-dimensional structural model is reconstructed; According to the reconstruction results of the three-dimensional structure model, the quantity, length, width and spatial distribution of the tobacco shreds inside the tested cigarette are obtained; Calculate the order rate of tobacco shreds based on the obtained quantity, length, width and spatial distribution; The calculation of the tobacco cut order rate comprises: Select any plane that is tangent to the outer edge of the three-dimensional model of the cigarette to be tested, and the three-dimensional model of the cigarette to be tested is parallel to the plane; set a plurality of straight lines parallel to the central axis of the three-dimensional model of the cigarette to be tested on the plane; project the image of a tobacco shred in the three-dimensional model of the cigarette to be tested onto the plane; decompose the projected image of the tobacco shred into a plurality of projected arcs, and measure the acute angle between each projected arc and the straight line to obtain a plurality of angle values; determine the percentage of the ratio of the mean of all the angle values to 90° as the tobacco shred order rate of a single tobacco shred; or, Select any first plane that is tangent to the outer edge of the three-dimensional model of the cigarette to be tested, and construct a second plane that is perpendicular to the first plane, and the three-dimensional model of the cigarette to be tested is parallel to the first plane and the second plane respectively; set a plurality of straight lines parallel to the central axis of the three-dimensional model of the cigarette to be tested on the first plane and the second plane; project the image of a tobacco shred in the three-dimensional model of the cigarette to be tested onto the first plane and the second plane respectively; decompose the projected image of the tobacco shred into a plurality of projected arcs, and measure the acute angles between each projected arc and the straight line to obtain a plurality of angle values; compare the maximum angle values of each projected arc in the first plane and the second plane; determine the percentage of the ratio of the difference between 90° and the maximum angle value to 90° as the tobacco shred order rate of a single tobacco shred; or, The central axis of the three-dimensional model of the cigarette to be tested is taken as the intersection line of the first plane and the second plane which are perpendicular to each other, and a third plane perpendicular to the central axis is constructed; a plurality of parallel lines parallel to the central axis of the three-dimensional model of the cigarette to be tested are set on the first plane and the second plane, and two mutually perpendicular intersecting lines are set on the third plane, and the projection of the central axis on the third plane is the intersection point of the intersecting lines; the image of a tobacco shred in the three-dimensional model of the cigarette to be tested is projected on the first plane, the second plane and the third plane respectively; the projected image of the tobacco shred is decomposed into a plurality of projected arcs, and the acute angles between each projected arc and the parallel lines and the intersecting lines on the corresponding planes are measured to obtain a plurality of angle values; the maximum angle values of each projected arc in the first plane, the second plane and the third plane are compared; the percentage of the ratio of the maximum angle value to 90° is determined as the tobacco order rate of a single tobacco shred.
2. The method for detecting the order rate of tobacco shreds in cigarettes based on CT scanning technology according to claim 1, It is characterized in that The total order rate of the tobacco in the tested cigarette is: the ratio of the sum of the order rates of each tobacco to the total number of tobacco in the cigarette.
3. The method for detecting the order rate of tobacco shreds in cigarettes based on CT scanning technology according to claim 1, It is characterized in that The detection method further comprises: Detect the tobacco order rate data of heated cigarette products of different specifications; The tobacco cut order rate data is integrated and statistically analyzed to determine the distribution law of the tobacco cut order rate.
4. The method for detecting the order rate of tobacco shreds in cigarettes based on CT scanning technology according to claim 1, It is characterized in that The obtaining of the boundary information of the tobacco shreds and the cigarette to be tested includes: using edge detection, circle detection and ROI region growing method to obtain the boundary and volume of the tobacco shreds and the cigarette to be tested from the CT grayscale image.
5. The method for detecting the order rate of shredded tobacco in a cigarette based on CT scanning technology according to claim 1, It is characterized in that The method of obtaining the quantity, length, width and spatial distribution of tobacco shreds inside the tested cigarette comprises: According to the boundary information and the pore three-dimensional space model reconstructed from the three-dimensional structure model, a matching grid size is selected for grid division, and the number, length, width and spatial distribution of tobacco shreds inside the tested cigarette are calculated, wherein the grid type is a non-homogeneous grid.
6. The method for detecting the order rate of shredded tobacco in a cigarette based on CT scanning technology according to claim 1, It is characterized in that The calculating of the order rate of the shredded tobacco includes: selecting shredded tobacco whose length-to-width ratio is greater than a preset length-to-width ratio threshold.
Citation Information
Patent Citations
A cigarette image recognition method combining image processing and neural network
CN109241983A
Method for detecting overall pore uniformity of cigarette
CN113702259A
Tobacco shred supply device for improving tobacco shred sorting rate
CN215684751U
Method and apparatus for reorientated resconstruction of computed tomography images of planar objects
US20110007864A1
