Method for identifying structure of heated cigarette based on micro scanning and electronic device

Abstract

The application discloses a kind of based on the structure identification method of heating cigarette of micro scanning and electronic equipment, it is related to heating tobacco detection technical field, the method includes: obtaining the multiple scanning images of heating cigarette cigarette, multiple scanning images are obtained by the X-ray scanning of micro scanning equipment to heating cigarette cigarette;According to multiple scanning images, region of interest three-dimensional model is constructed, and region of interest three-dimensional model is the tobacco core filling space in the wrapping range of heating cigarette paper of heating cigarette cigarette;According to region of interest three-dimensional model, solid phase voxel and gas phase voxel are identified;According to solid phase voxel and gas phase voxel, structure characteristics are calculated.It can be without destroying cigarette, according to the scanning image of micro scanning equipment, region of interest three-dimensional model is constructed, and the accurate identification of tobacco filling area is realized.Based on region of interest three-dimensional model, structure characteristics such as porosity can be accurately identified, and the accuracy of porosity detection is improved.

Description

Technical Field

[0001] This invention relates to the field of heated tobacco detection technology, and in particular to a method and electronic device for structural identification of heated cigarettes based on micro-scanning. Background Technology

[0002] The porosity of tobacco shreds is a parameter that characterizes the proportion of air volume in the internal structure of heated cigarette shreds. It has a direct impact on cigarette weight control, rolling adaptability evaluation, and product quality stability.

[0003] Currently, the analysis of cigarette porosity mainly relies on indirect inference from physical indicators such as cigarette weight and density, or on destructive methods such as cutting and sampling. While these methods can reflect the filling state of the cigarette to some extent, they are difficult to accurately characterize the three-dimensional porosity distribution of the tobacco filling area inside the cigarette while maintaining the integrity of the original sample structure, and it is difficult to accurately identify key structural information such as the overall porosity. Summary of the Invention

[0004] This invention provides a method and electronic device for structural identification of heated cigarettes based on micro-scanning, in order to solve the current problem of not being able to detect the porosity of tobacco inside a cigarette without damaging the cigarette.

[0005] According to one aspect of the present invention, a method for structural identification of heated cigarettes based on micro-scanning is provided, comprising:

[0006] Multiple scanned images of a heated cigarette are acquired, wherein the multiple scanned images are obtained by X-ray scanning of the heated cigarette using a micro-scanning device;

[0007] A three-dimensional model of the region of interest is constructed based on the multiple scanned images. The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick.

[0008] Identify solid-phase voxels and gas-phase voxels based on the three-dimensional model of the region of interest;

[0009] Structural features are calculated based on the solid-phase voxel and the gas-phase voxel.

[0010] According to another aspect of the present invention, a structure recognition device for heated cigarettes based on micro-scanning is provided, comprising:

[0011] The image acquisition module is used to acquire multiple scan images of the heated cigarette stick, which are obtained by X-ray scanning of the heated cigarette stick by a micro-scanning device;

[0012] The model building module is used to construct a three-dimensional model of the region of interest based on the multiple scanned images. The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick.

[0013] A solid-gas identification module is used to identify solid voxels and gas voxels based on the three-dimensional model of the region of interest.

[0014] The structural feature calculation module is used to calculate structural features based on the solid phase voxel and the gas phase voxel.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the micro-scanning-based structure recognition method for heated cigarettes according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the micro-scanning-based structure recognition method for heated cigarettes as described in any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring multiple scanned images of a heated cigarette, obtained by X-ray scanning of the heated cigarette using a micro-scanning device; constructing a three-dimensional model of a region of interest (ROI) based on the scanned images, where the ROI represents the fill space of the cigarette core within the cigarette paper wrapping area; identifying solid and gaseous voxels based on the ROI model; and calculating structural features based on the solid and gaseous voxels. Compared to the current method of physically cutting and weighing to measure porosity, which damages the cigarette, the technical solution provided by this invention can construct a ROI model based on the scanned images acquired by the micro-scanning device without damaging the cigarette, achieving accurate identification of the tobacco fill area. Then, by identifying solid and gaseous voxels and calculating structural features such as porosity using the ROI model, the accuracy of porosity detection is improved without damaging the cigarette.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic flowchart of a method for structural identification of heated cigarettes based on micro-scanning provided in an embodiment of the present invention;

[0024] Figure 2 This is a flowchart illustrating another method for structural identification of heated cigarettes based on micro-scanning provided in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of a structure recognition device for heated cigarettes based on micro-scanning, provided in an embodiment of the present invention.

[0026] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the micro-scanning-based structure recognition method for heated cigarettes according to embodiments of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "comprising" and "having" and any variations thereof in the specification, claims and accompanying drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such processes, methods, products or devices.

[0029] The inventors discovered that the porosity of tobacco shreds is a parameter characterizing the proportion of air volume in the internal tobacco packing state of heated cigarettes, directly impacting cigarette weight control, rolling adaptability evaluation, and product quality stability. Specifically, during the development of heated cigarette technology, the internal structure of the cigarette directly affects product performance. Especially for externally heated cigarettes, the internal filling is not simply about achieving high density, but rather about creating reasonable gaps based on a certain structural stability to allow for effective heat transfer and the formation of a suitable smoke-generating space during heating. From production and R&D practice, a low porosity can lead to an overly tight cigarette, impeded heat conduction, insufficient smoke generation, or excessive draw resistance; a high porosity can lead to an overly loose cigarette, unstable weight, increased air pockets, decreased mechanical integrity, or poor sensory consistency. Therefore, porosity is not a single quality indicator, but a fundamental structural indicator that permeates the formulation, rolling, quality, and sensory performance.

[0030] Currently, the analysis of cigarette porosity mainly relies on indirect inference from physical indicators such as cigarette weight and density, or on destructive methods such as cutting and sampling. While these methods can reflect the filling state of the cigarette to some extent, they are difficult to accurately characterize the three-dimensional porosity distribution of the tobacco filling area inside the cigarette while maintaining the integrity of the original sample structure, and it is difficult to accurately identify key structural information such as the overall porosity.

[0031] Figure 1 This is a flowchart illustrating a method for structural identification of heated cigarettes based on micro-scanning, provided in an embodiment of the present invention. This embodiment is applicable to situations requiring the detection of porosity in heated tobacco shreds. The method can be executed by a micro-scanning-based structural identification device for heated cigarettes, which can be implemented in hardware and / or software, such as... Figure 1 As shown, the method includes:

[0032] Step S110: Obtain multiple scanned images of the heated cigarette stick, wherein the multiple scanned images are obtained by X-ray scanning of the heated cigarette stick by a micro-scanning device.

[0033] Micro-scanning devices (such as micro-CT scanners) can be used to sample and scan a batch of heated cigarettes, producing multiple images of each sample. The micro-CT technology used in these devices is a micrometer-level X-ray computed tomography technique that utilizes X-rays to perform high-resolution, non-destructive scanning of samples and reconstruct their internal three-dimensional structure. This technology can obtain spatial distribution information of different components and pore structures within a sample without damaging its original structure.

[0034] The micro-CT equipment consists of a microfocus X-ray source, a high-resolution flat panel detector, a high-precision motorized rotary stage, a control system computer, and an image analysis workstation. The X-ray source and detector are mounted on opposite sides of the rotary stage, which carries the sample and allows for 360-degree step-by-step rotation. The control system computer connects the X-ray source, detector, and rotary stage, and is responsible for setting scanning parameters and acquiring data. The image analysis workstation is equipped with a graphics processor and a large-capacity memory (greater than 64GB) for subsequent 3D reconstruction and structural feature analysis.

[0035] The sample to be tested is fixed on the rotating stage. After the scanning cavity is closed, the parameters such as the X-ray source voltage, current, and detector exposure time are first set. After the scan is started, the rotating stage moves in preset angle steps (e.g., 0.5° per step). At each angle, the X-ray source emits micron-sized focal spots of X-rays that penetrate the sample. The detector receives the attenuated X-ray signal and generates a two-dimensional scan image.

[0036] The following pretreatment was performed on the samples to be tested: (1) Sample screening: Select cigarette samples that are intact, undamaged and undeformed, and equilibrate them for more than 24 hours in a constant temperature and humidity environment of (22±1)℃ and (40±5)% relative humidity to ensure that the moisture content of the samples is consistent and to avoid the influence of moisture fluctuation on the structural state. (2) Sample fixation: Use non-metallic low-density foam board as the fixing base, and use non-metallic binding straps to horizontally bind and fix the cigarettes to the foam board. Fix 2 cigarettes on each foam board, and the distance between the two cigarettes is ≥3cm to avoid mutual obstruction and artifacts during scanning. The binding force should be uniform and should not cause the cigarettes to deform. No metal parts should be used as fixing materials to avoid introducing metal artifacts. (3) Sample positioning: Place the foam board with the fixed sample in the center of the micro-CT scanning chamber, and record the sample number, batch, formula / process information and scanning date to ensure that the sample information is traceable.

[0037] In addition, before scanning, the scanning parameters of the micro-CT equipment (tube voltage, tube current, exposure time, scan resolution, number of projection frames, etc.) are fixed according to the structural characteristics of heated cigarettes. A full-length continuous tomographic scan is performed on the entire cigarette to obtain high-resolution tomographic images. When testing heated cigarettes from the same batch, all samples used the same scanning parameters. If parameter adjustments are necessary due to sample characteristics, pre-test verification must be completed in advance and recorded separately to ensure comparability between samples.

[0038] Step S120: Construct a three-dimensional model of the region of interest based on the multiple scanned images. The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick.

[0039] Optionally, constructing a 3D model of the region of interest based on the multiple scanned images can be implemented in the following manner:

[0040] 1) Determine the starting layer scan image and the ending layer scan image of the region of interest based on the multiple scan images.

[0041] In this embodiment of the invention, the region of interest (ROI) is the area where the cigarette core is filled. Before determining the ROI, the cigarette core filling area, it is necessary to remove the cigarette paper, filter, and external air background, retaining only the core smoke-generating area when the cigarette is in operation, to ensure the consistency of the calculation area.

[0042] The region of interest (ROI) is a three-dimensional analysis area formed by extracting the core-filling area layer by layer from consecutive scanned images within the selected starting and ending layer scans. Specifically, the ROI on each image layer is the core-filling area within the cigarette paper wrapping area. Multiple consecutive ROIs are superimposed along the cigarette axis to form a three-dimensional volume of interest, which is used for subsequent calculations of porosity, solid volume fraction, and spatial structure parameters.

[0043] 2) Based on the automatic bonding of the outer layer and the comparison of the binary image, the filling area of ​​the cigarette core in the target layer scan image is determined. The target layer scan image is any scan image between the starting layer scan image and the ending layer scan image.

[0044] Optionally, based on the comparison between the automatically bonded outer layer and the binary image, the cigarette core filling area in the target layer scan image can be determined as follows:

[0045] The target layer scan image is converted into a binary image according to a preset grayscale threshold; the outline of the filling region is determined according to the binary image; and a cigarette core filling region that fits the outline of the filling region is generated according to the binary image.

[0046] First, the outer layer of closed cigarette paper in the cross-section is identified. Then, the interior of the cigarette paper is automatically outlined by adhering to the outer layer as the region of interest. The basic principle of the automatic adhering function is based on image grayscale segmentation and boundary recognition. Specifically, the software first converts the original CT image into a binary image according to a set grayscale threshold, distinguishing the target area from the background area in the image. Subsequently, based on the outer contour of the target area in the binary image, the software automatically generates the boundary of the region of interest (i.e., the cigarette core filling area) that conforms to the contour.

[0047] The above process distinguishes different regions based on their grayscale differences in CT images. The operator adjusts the grayscale threshold to clearly display the cross-sectional outline of the cigarette and the boundary of the core-filling area. Based on this, the region of interest is automatically generated by shrinking and fitting the image boundary to the outer edge of the target area.

[0048] The aforementioned automatic bonding system is primarily used to assist in extracting the cigarette core filling area within the cigarette paper wrapping area. Its function is to reduce the workload and human error associated with manual layer-by-layer drawing. This process can be performed by operators who set preset grayscale thresholds according to standardized criteria and check the bonding results.

[0049] The above-described implementation can perform binary image conversion based on a preset grayscale threshold, thereby separating the cigarette from the background. The binary image can accurately peel off the background. Contour fitting based on the binary image can accurately extract the cigarette core filling area, improving the accuracy of cigarette core filling area recognition.

[0050] 3) Perform 3D modeling based on the smoke core filling region in multiple consecutive target layer scan images to obtain the 3D model of the region of interest.

[0051] The above-described implementation can identify the tobacco core filling area from the scanned image by automatically bonding the outer layer and comparing binary images. The three-dimensional model of the region of interest obtained by three-dimensional modeling based on the tobacco core filling area can accurately mark the filling space of the heated tobacco.

[0052] Step S130: Identify solid voxels and gas voxels based on the three-dimensional model of the region of interest.

[0053] Optionally, identifying solid-phase voxels and gas-phase voxels based on the three-dimensional model of the region of interest can be implemented in the following manner:

[0054] Obtain the solid-gas grayscale threshold; obtain the target grayscale value of the target voxel in the 3D model of the region of interest, wherein the target voxel is any spatial voxel in the 3D model of the region of interest.

[0055] If the target gray value is greater than the solid-gas gray value threshold, then the target voxel is a solid phase voxel; if the target gray value is less than or equal to the solid-gas gray value threshold, then the target voxel is a gas phase voxel.

[0056] The above-described embodiments can accurately identify solid voxels and gas voxels based on solid-gas grayscale thresholds, thereby improving the accuracy of solid and gas identification.

[0057] Step S140: Calculate the structural features based on the solid phase voxel and the gas phase voxel.

[0058] Optionally, the structural features can be calculated based on the solid-phase voxel and the gas-phase voxel in the following manner:

[0059] The number of solid-phase voxels and gas-phase voxels in the target space of the region of interest (ROI) 3D model are counted. The solid-phase volume is determined based on the number of solid-phase voxels and the volume per unit voxel; the gas-phase volume is determined based on the number of gas-phase voxels and the volume per unit voxel; the total volume of the target space is determined based on the target space. Gas-phase volume correction is performed based on the solid-phase volume, the gas-phase volume, and the total volume of the target space; the porosity is determined based on the corrected gas-phase volume and the total volume of the target space.

[0060] Since the shape of the gas phase region is not fixed, the gas phase volume can be accumulated in units of voxels. The 3D model of the region of interest is composed of voxels, each with the same and fixed size, also known as the unit voxel volume. Therefore, each voxel corresponds to a fixed volume. After identifying the solid phase voxels and gas phase voxels, the number of gas phase voxels is counted, and the gas phase volume is obtained by multiplying the number of gas phase voxels by the unit voxel volume.

[0061] The calculation method is as follows: gas phase volume = number of gas phase voxels × volume per unit voxel.

[0062] The volume of a single voxel is determined by the scanning resolution 'a'. For example, if the voxel size is a μm × a μm × a μm, then the volume of a single voxel is a³. For instance, the scanning resolution for a cigarette can be 9 μm.

[0063] The above-described embodiments can use the calculated solid phase volume to correct the gas phase volume, and calculate the porosity based on the corrected gas phase volume, thereby improving the accuracy of the porosity.

[0064] In the 3D model of the region of interest, the solid phase and the gas phase are two corresponding regions. Identifying solid phase voxels helps to accurately determine the gas phase boundary, avoiding misclassification of tobacco solids as voids and ensuring accurate porosity calculations. Solid phase voxels can also be used to subsequently calculate structural features such as solid volume fraction, solid volume, and solid-gas ratio, and to verify the reasonableness of the binarized segmentation results.

[0065] Furthermore, before counting the number of solid-phase voxels and gas-phase voxels in the target space of the three-dimensional model of the region of interest, the method further includes: dividing the cigarette into equal segments along the length of the cigarette to obtain multiple segmented spaces, wherein the target space is any combination of one or more of the multiple segmented spaces.

[0066] Accordingly, after determining the porosity based on the corrected gas phase volume and the total volume of the target space, the method further includes: statistically analyzing the porosity of each segment of the space to obtain the porosity distribution of the heated tobacco.

[0067] The above implementation method can spatially divide the three-dimensional model of the region of interest corresponding to the heated tobacco, and analyze the porosity of each segment. This extends the porosity representation to multiple levels, including the overall three-dimensional model of the region of interest, the segmented spaces, and the local regions composed of the connecting segmented spaces, thereby more completely reflecting the tobacco stacking state and structural differences inside the cigarette.

[0068] The above-described embodiments can accurately obtain the porosity distribution of each segment of a cigarette without damaging the cigarette, thus improving the ease of use of porosity detection.

[0069] Furthermore, the calculation of structural features based on the solid-phase voxel and the gas-phase voxel also includes:

[0070] Based on the solid and gaseous voxels of the target space, determine one or more of the following structural features: cross-sectional porosity, proportion of local macropores, axial uniformity, or location and proportion of anomalous void regions. Output the above structural features.

[0071] The system can visualize and digitally output the characterization results of the overall porosity, segmented porosity, axial uniformity, and local abnormal porosity of cigarettes, which can be used to evaluate the uniformity and stability of the tobacco filling structure inside heated cigarettes. These results can serve as an important reference for cigarette weight control, raw material structure adjustment, and cigarette rolling process optimization, thereby shifting from traditional experience-based judgment to a technical evaluation method based on internal structural data analysis.

[0072] The above-described embodiments can calculate and output various structural features based on solid-phase voxels and gas-phase voxels, thereby enabling a more comprehensive detection of heated tobacco in cigarettes and improving the reliability of heated tobacco detection.

[0073] This invention provides a method for structural identification of heated cigarettes based on micro-scanning. The method acquires multiple scanned images of the heated cigarette, obtained by X-ray scanning of the cigarette using a micro-scanning device. A three-dimensional model of the region of interest (ROI) is constructed based on these images. This ROI model represents the fill space of the cigarette core within the cigarette paper wrapping area of ​​the heated cigarette. Solid and gaseous voxels are identified based on the ROI model. Structural features are then calculated based on these voxels. Compared to current methods that physically cut and weigh the cigarette to measure porosity, which damages the cigarette, this method, based on micro-scanning, can construct a ROI model from the scanned images without damaging the cigarette, achieving accurate identification of the tobacco fill area. Then, by identifying solid and gaseous voxels and calculating porosity and other structural features using the ROI model, the method accurately identifies porosity and other structural features without damaging the cigarette, improving the accuracy of porosity detection.

[0074] Figure 2 This is a flowchart illustrating a method for structural identification of heated cigarettes based on micro-scanning, provided by an embodiment of the present invention. As a specific illustration of the above embodiments, the method includes:

[0075] Step S201: Obtain multiple scanned images of the heated cigarette stick, wherein the multiple scanned images are obtained by X-ray scanning of the heated cigarette stick by a micro-scanning device.

[0076] Step S202: Determine the starting layer scan image and the ending layer scan image of the region of interest based on the multiple scan images.

[0077] Step S203: Convert the target layer scan image into a binary image according to a preset grayscale threshold; determine the outline of the filling region according to the binary image; generate a cigarette core filling region that fits the outline of the filling region according to the binary image.

[0078] The target layer scan image is any one of the scan images between the start layer scan image and the end layer scan image.

[0079] Step S204: Perform 3D modeling based on the smoke core filling region in multiple consecutive target layer scan images to obtain a 3D model of the region of interest.

[0080] The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick.

[0081] Step S205: Obtain the solid-gas grayscale threshold; obtain the target grayscale value of the target voxel in the three-dimensional model of the region of interest.

[0082] The target voxel is any spatial voxel in the three-dimensional model of the region of interest.

[0083] Step S206: If the target grayscale value is greater than the solid-gas grayscale threshold, then the target voxel is a solid-phase voxel. If the target grayscale value is less than or equal to the solid-gas grayscale threshold, then the target voxel is a gas-phase voxel.

[0084] Step S207: Divide the cigarette into equal segments along its length to obtain multiple segmented spaces. Count the number of solid-phase voxels and gas-phase voxels in the target space of the region of interest 3D model.

[0085] The target space is any combination of one or more of the plurality of segmented spaces.

[0086] Step S208: Determine the solid phase volume based on the number of solid phase voxels and the volume per unit voxel. Determine the gas phase volume based on the number of gas phase voxels and the volume per unit voxel. Determine the total volume of the target space based on the target space.

[0087] Step S209: Perform gas phase volume correction based on the solid phase volume, the gas phase volume, and the total target space volume. Determine the porosity based on the corrected gas phase volume and the total target space volume.

[0088] Step S210: Calculate the porosity of each segment space, obtain and output the porosity distribution of the heated tobacco.

[0089] Step S211: Determine and output any one or more of the following structural features based on the solid and gaseous voxels of the target space: cross-sectional porosity, proportion of local large pores, axial uniformity, or location and proportion of abnormal void areas.

[0090] The micro-scanning-based structural identification method for heated cigarettes provided in this invention can achieve visualization and digital analysis of the internal void structure of heated cigarettes under non-destructive conditions, improve the accuracy, repeatability and comparability of void ratio detection results, and provide a more direct and reliable structural characterization basis for cigarette weight control, raw material structure optimization and rolling process parameter adjustment.

[0091] The structural identification method for heated cigarettes based on micro-scanning provided in this invention uses micro-CT to scan the entire cigarette without cutting, dissecting, or disassembling the sample. It can acquire internal three-dimensional structural information without disrupting the original packing state. The detection process maintains the integrity of the sample, realistically presenting the internal void state of the cigarette, and supports repeated verification and methodological comparison with similar samples. The detection results closely approximate the actual structural state, exhibiting higher reliability. It can directly perform three-dimensional segmentation of the gas phase space and solid phase filling material inside the cigarette, and the porosity is directly obtained through volume calculation, without relying on empirical inferences based on external indicators such as weight and suction resistance. The detection object focuses on the internal structural body, improving the accuracy and interpretability of porosity evaluation, providing direct basis for R&D and process optimization. It can use the three-dimensional data of the entire cigarette as the analysis object, covering structural information along the entire length, calculating the overall porosity, and simultaneously acquiring the porosity distribution of different sections, local abnormal pore characteristics, and axial uniformity. The full-length multi-dimensional analysis capability can identify structural defects and instability characteristics that are difficult to capture by traditional methods, matching the needs of refined R&D.

[0092] Figure 3 This is a schematic diagram of a structure recognition device for heated cigarettes based on micro-scanning, provided in an embodiment of the present invention. This embodiment is applicable to situations where the porosity of heated tobacco shreds needs to be detected. This structure recognition device for heated cigarettes based on micro-scanning can be implemented in hardware and / or software. Figure 3 As shown, the structure recognition device for heated cigarettes based on micro-scanning includes: a scanned image acquisition module 31, a model building module 32, a solid-gas recognition module 33, and a structure feature calculation module 34.

[0093] The image acquisition module 31 is used to acquire multiple scan images of the heated cigarette stick, wherein the multiple scan images are obtained by X-ray scanning of the heated cigarette stick by a micro-scanning device;

[0094] Model building module 32 is used to build a three-dimensional model of the region of interest based on the multiple scanned images. The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick.

[0095] Solid-gas identification module 33 is used to identify solid voxels and gas voxels based on the three-dimensional model of the region of interest;

[0096] The structural feature calculation module 34 is used to calculate structural features based on the solid phase voxel and the gas phase voxel.

[0097] Based on the above embodiments, optionally, the model building module 32 is used for:

[0098] The starting and ending layer scan images of the region of interest are determined based on the multiple scan images;

[0099] Based on the automatic bonding of the outer layer and the comparison of the binary image, the cigarette core filling area in the target layer scan image is determined. The target layer scan image is any scan image between the start layer scan image and the end layer scan image.

[0100] Three-dimensional modeling of the region of interest is obtained by performing three-dimensional modeling on the smoke core filling region in multiple consecutive target layer scan images.

[0101] Based on the above embodiments, optionally, the model building module 32 is used to determine the cigarette core filling region in the target layer scan image based on the automatic bonding of the outer layer and the comparison of the binary image, including:

[0102] The target layer scan image is converted into a binary image based on a preset grayscale threshold.

[0103] The outline of the filled region is determined based on the binary image;

[0104] Generate a cigarette core filling region that matches the outline of the filling region based on the binary image.

[0105] Based on the above embodiments, optionally, the solid-gas identification module 33 is used for:

[0106] Obtain the solid-gas grayscale threshold;

[0107] Obtain the target grayscale value of the target voxel in the 3D model of the region of interest, wherein the target voxel is any spatial voxel in the 3D model of the region of interest;

[0108] If the target grayscale value is greater than the solid-gas grayscale threshold, then the target voxel is a solid-phase voxel;

[0109] If the target grayscale value is less than or equal to the solid-gas grayscale threshold, then the target voxel is a gas phase voxel.

[0110] Based on the above embodiments, optionally, the structural feature calculation module 34 is used for:

[0111] The number of solid-phase voxels and gas-phase voxels in the target space of the three-dimensional model of the region of interest is counted.

[0112] The solid phase volume is determined based on the number of solid phase voxels and the volume per unit voxel.

[0113] The gas phase volume is determined based on the number of gas phase voxels and the volume per unit voxel.

[0114] Determine the total volume of the target space based on the target space;

[0115] Gas phase volume correction is performed based on the solid phase volume, the gas phase volume, and the total target space volume;

[0116] The porosity is determined based on the corrected gas phase volume and the total target space volume.

[0117] Based on the above embodiments, optionally, the solid-gas identification module 33 is used to perform equidistant segmentation along the length of the cigarette before counting the number of solid phase voxels and gas phase voxels in the target space of the three-dimensional model of the region of interest, to obtain multiple segmented spaces, wherein the target space is any combination of one or more of the multiple segmented spaces.

[0118] Correspondingly, the structural feature calculation module 34 is also used to calculate the porosity of each segment space after determining the porosity based on the corrected gas phase volume and the total volume of the target space, so as to obtain the porosity distribution of the heated tobacco.

[0119] Based on the above embodiments, optionally, the structural feature calculation module 34 is also used for:

[0120] Based on the solid and gaseous voxels of the target space, determine one or more of the following structural features: cross-sectional porosity, proportion of local macropores, axial uniformity, or location and proportion of abnormal void areas.

[0121] The structural identification device for heated cigarettes based on micro-scanning provided in this embodiment of the invention includes: a scanning image acquisition module 31, used to acquire multiple scanning images of the heated cigarette, obtained by X-ray scanning of the heated cigarette by a micro-scanning device; a model construction module 32, used to construct a three-dimensional model of the region of interest based on the multiple scanning images, wherein the three-dimensional model of the region of interest is the tobacco filling space within the cigarette paper wrapping area of ​​the heated cigarette; a solid-gas identification module 33, used to identify solid voxels and gas voxels based on the three-dimensional model of the region of interest; and a structural feature calculation module 34, used to calculate structural features based on the solid voxels and gas voxels. Compared with the current method of physically cutting and weighing to measure porosity, which damages the cigarette, the structural identification device for heated cigarettes based on micro-scanning provided in this embodiment of the invention can construct a three-dimensional model of the region of interest based on the scanning images acquired by the micro-scanning device without damaging the cigarette, thus achieving accurate identification of the tobacco filling area. Then, by using a 3D model of the region of interest, solid-phase voxels and gas-phase voxels are identified and structural features such as porosity are calculated, so as to accurately identify structural features such as porosity without damaging the cigarette and improve the accuracy of porosity detection.

[0122] The micro-scanning-based heated cigarette structure recognition device provided in this embodiment of the invention can execute the micro-scanning-based heated cigarette structure recognition method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0123] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0124] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as a camera, ultrasonic sensor, infrared sensor, etc.; output unit 17, such as various types of speakers, etc.; storage unit 18, such as a disk, solid-state drive, etc.; and communication unit 19, such as a network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0126] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the seismic response monitoring method for a double-arm gate across a dam section.

[0127] In some embodiments, the microscan-based structure recognition method for heated cigarettes can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the microscan-based structure recognition method for heated cigarettes described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the microscan-based structure recognition method for heated cigarettes by any other suitable means (e.g., by means of firmware).

[0128] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs for implementing the micro-scanning-based structural identification method for heated cigarettes of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] This invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a method for structural recognition of heated cigarettes based on micro-scanning, the method comprising:

[0131] Multiple scanned images of a heated cigarette are acquired, wherein the multiple scanned images are obtained by X-ray scanning of the heated cigarette using a micro-scanning device;

[0132] A three-dimensional model of the region of interest is constructed based on the multiple scanned images. The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick.

[0133] Identify solid-phase voxels and gas-phase voxels based on the three-dimensional model of the region of interest;

[0134] Structural features are calculated based on the solid-phase voxel and the gas-phase voxel.

[0135] Based on the above embodiments, optionally, constructing a three-dimensional model of the region of interest based on the multiple scanned images includes:

[0136] The starting and ending layer scan images of the region of interest are determined based on the multiple scan images;

[0137] Based on the automatic bonding of the outer layer and the comparison of the binary image, the cigarette core filling area in the target layer scan image is determined. The target layer scan image is any scan image between the start layer scan image and the end layer scan image.

[0138] Three-dimensional modeling of the region of interest is obtained by performing three-dimensional modeling on the smoke core filling region in multiple consecutive target layer scan images.

[0139] Based on the above embodiments, optionally, the cigarette core filling area in the target layer scan image is determined by comparing the automatically bonded outer layer and the binary image, including:

[0140] The target layer scan image is converted into a binary image based on a preset grayscale threshold.

[0141] The outline of the filled region is determined based on the binary image;

[0142] Generate a cigarette core filling region that matches the outline of the filling region based on the binary image.

[0143] Based on the above embodiments, optionally, identifying solid-phase voxels and gas-phase voxels according to the three-dimensional model of the region of interest includes:

[0144] Obtain the solid-gas grayscale threshold;

[0145] Obtain the target grayscale value of the target voxel in the 3D model of the region of interest, wherein the target voxel is any spatial voxel in the 3D model of the region of interest;

[0146] If the target grayscale value is greater than the solid-gas grayscale threshold, then the target voxel is a solid-phase voxel;

[0147] If the target grayscale value is less than or equal to the solid-gas grayscale threshold, then the target voxel is a gas phase voxel.

[0148] Based on the above embodiments, optionally, the structural features are calculated according to the solid-phase voxel and the gas-phase voxel, including:

[0149] The number of solid-phase voxels and gas-phase voxels in the target space of the three-dimensional model of the region of interest is counted.

[0150] The solid phase volume is determined based on the number of solid phase voxels and the volume per unit voxel.

[0151] The gas phase volume is determined based on the number of gas phase voxels and the volume per unit voxel.

[0152] Determine the total volume of the target space based on the target space;

[0153] Gas phase volume correction is performed based on the solid phase volume, the gas phase volume, and the total target space volume;

[0154] The porosity is determined based on the corrected gas phase volume and the total target space volume.

[0155] Based on the above embodiments, optionally, before counting the number of solid-phase voxels and gas-phase voxels in the target space of the three-dimensional model of the region of interest, the method further includes:

[0156] The cigarette is divided into equal segments along its length to obtain multiple segmented spaces, and the target space is any combination of one or more of the multiple segmented spaces.

[0157] Accordingly, after determining the porosity based on the corrected gas phase volume and the total target space volume, the method further includes:

[0158] The porosity of each segment is statistically analyzed to obtain the porosity distribution of the heated tobacco.

[0159] Based on the above embodiments, optionally, the calculation of structural features based on the solid-phase voxel and the gas-phase voxel also includes:

[0160] Based on the solid and gaseous voxels of the target space, determine one or more of the following structural features: cross-sectional porosity, proportion of local macropores, axial uniformity, or location and proportion of abnormal void areas.

[0161] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0162] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0163] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0164] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0165] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0166] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for structural identification of heated cigarettes based on micro-scanning, characterized in that, include: Multiple scanned images of a heated cigarette are acquired, wherein the multiple scanned images are obtained by X-ray scanning of the heated cigarette using a micro-scanning device; A three-dimensional model of the region of interest is constructed based on the multiple scanned images. The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick. Identify solid-phase voxels and gas-phase voxels based on the three-dimensional model of the region of interest; Structural features are calculated based on the solid-phase voxel and the gas-phase voxel.

2. The method according to claim 1, characterized in that, Constructing a 3D model of the region of interest based on the multiple scanned images includes: The starting and ending layer scan images of the region of interest are determined based on the multiple scan images; Based on the automatic bonding of the outer layer and the comparison of the binary image, the cigarette core filling area in the target layer scan image is determined. The target layer scan image is any scan image between the start layer scan image and the end layer scan image. A 3D model of the region of interest is obtained by performing 3D modeling on the smoke core filling region in multiple consecutive target layer scan images.

3. The method according to claim 2, characterized in that, Based on the automatic bonding of the outer layer and the comparison of the binary image, the core filling region in the target layer scan image is determined, including: The target layer scan image is converted into a binary image based on a preset grayscale threshold. The outline of the filled region is determined based on the binary image; Generate a cigarette core filling region that matches the outline of the filling region based on the binary image.

4. The method according to claim 1, characterized in that, Identifying solid-phase voxels and gas-phase voxels based on the three-dimensional model of the region of interest includes: Obtain the solid-gas grayscale threshold; Obtain the target grayscale value of the target voxel in the 3D model of the region of interest, wherein the target voxel is any spatial voxel in the 3D model of the region of interest; If the target grayscale value is greater than the solid-gas grayscale threshold, then the target voxel is a solid-phase voxel; If the target grayscale value is less than or equal to the solid-gas grayscale threshold, then the target voxel is a gas phase voxel.

5. The method according to claim 4, characterized in that, The structural features are calculated based on the solid-phase voxel and the gas-phase voxel, including: The number of solid-phase voxels and gas-phase voxels in the target space of the three-dimensional model of the region of interest is counted. The solid phase volume is determined based on the number of solid phase voxels and the volume per unit voxel. The gas phase volume is determined based on the number of gas phase voxels and the volume per unit voxel. Determine the total volume of the target space based on the target space; Gas phase volume correction is performed based on the solid phase volume, the gas phase volume, and the total target space volume; The porosity is determined based on the corrected gas phase volume and the total target space volume.

6. The method according to claim 5, characterized in that, Before calculating the number of solid-phase voxels and gas-phase voxels in the target space of the 3D model of the region of interest, the following steps are also included: The cigarette is divided into equal segments along its length to obtain multiple segmented spaces, and the target space is any combination of one or more of the multiple segmented spaces. Accordingly, after determining the porosity based on the corrected gas phase volume and the total target space volume, the method further includes: The porosity of each segment is statistically analyzed to obtain the porosity distribution of the heated tobacco.

7. The method according to claim 4, characterized in that, The calculation of structural features based on the solid-phase voxel and the gas-phase voxel also includes: Based on the solid and gaseous voxels of the target space, determine one or more of the following structural features: cross-sectional porosity, proportion of local macropores, axial uniformity, or location and proportion of abnormal void areas.

8. A structure recognition device for heated cigarettes based on micro-scanning, characterized in that, include: The image acquisition module is used to acquire multiple scan images of the heated cigarette stick, which are obtained by X-ray scanning of the heated cigarette stick by a micro-scanning device; The model building module is used to construct a three-dimensional model of the region of interest based on the multiple scanned images. The three-dimensional model of the region of interest is the filling space of the cigarette core within the area wrapped by the cigarette paper of the heated cigarette stick. A solid-gas identification module is used to identify solid-phase voxels and gas-phase voxels based on the three-dimensional model of the region of interest. The structural feature calculation module is used to calculate structural features based on the solid phase voxel and the gas phase voxel.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the micro-scanning-based structural identification method for heated cigarettes according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the micro-scanning-based structural identification method for heated cigarettes as described in any one of claims 1-7.

Images