Method for determining complete tobacco in-situ combustibility based on image analysis technology

Abstract

The invention discloses a determination method for determining complete tobacco in-situ combustibility based on an image analysis technology, which comprises the following steps: pretreatment of a tobacco sample: removing main veins of the complete tobacco sample, balancing the treated tobacco for 48 hours under the standard conditions that the temperature is 22 + / -1 DEG C and the humidity is 60 + / -2%, and ensuring that the moisture in the sample is uniform and stable; meanwhile, the natural flat state of the tobacco leaves is kept through clamping and pressing of the double-sided grid plate; according to the method, complete tobacco leaves are measured, crushing or destructive treatment is not carried out, the natural state and structural integrity of the tobacco leaves are reserved to the maximum extent, the combustion characteristics of the raw material tobacco leaves in the original state can be reflected more truly, and more real data are provided for quality evaluation of the raw material tobacco leaves; the tobacco in-situ combustibility is quantitatively described, analyzed and evaluated by extracting a plurality of combustion character indexes such as smoldering duration, combustion spot area, combustion spot nearly roundness, combustion ash degree value and the like and integrating the plurality of combustion character indexes.

Description

Technical Field

[0001] This invention relates to the field of tobacco leaf combustibility measurement technology, specifically a method for measuring the in-situ combustibility of intact tobacco leaves based on image analysis technology. Background Technology

[0002] Combustibility of tobacco leaves is a key indicator for evaluating tobacco quality. It directly affects the smoking quality of cigarettes, such as taste, aroma release, and the uniformity and stability of combustion. It is also closely related to many aspects of the cigarette production process, such as adjustments to the rolling process and the application of combustion control technology. Therefore, accurate and comprehensive measurement of tobacco leaf combustibility is crucial for tobacco planting, processing, and cigarette manufacturing industries. Currently, some methods require pulverizing or destructive treatment of the tobacco leaves, such as grinding them into powder before thermogravimetric analysis. While this method can reflect the combustion characteristics of tobacco leaves to some extent, it severely damages the natural state and structural integrity of the leaves. The combustion behavior of tobacco leaves in their intact state may differ significantly from that after pulverization, because the leaf structure, vein distribution, and interactions between different parts of the intact leaf all influence the combustion process. Therefore, traditional destructive methods cannot accurately reflect the combustion performance of tobacco leaves in actual use, leading to discrepancies between the measured results and actual conditions, and failing to provide accurate and reliable data for tobacco quality assessment and cigarette production. Summary of the Invention

[0003] The purpose of this invention is to provide a method for determining the in-situ combustibility of intact tobacco leaves based on image analysis technology, so as to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for determining the in-situ combustibility of intact tobacco leaves based on image analysis technology, comprising the following steps:

[0005] S1. Pretreatment of tobacco leaf samples: Remove the main vein from the whole tobacco leaf sample. The treated tobacco leaf should be equilibrated for 48 hours under standard conditions of temperature 22±1℃ and humidity 60±2% to ensure that the internal moisture of the sample is uniform and stable. At the same time, the tobacco leaf should be kept in a natural flat state by clamping with double-sided grid plates for more than 24 hours.

[0006] S2. Combustion process image acquisition: Under artificial fixed lighting and windless environment, the pretreated tobacco leaf sample is laid flat on a grid plate and heated to a white-hot stable state using an electric heating rod with a standard fixed diameter. This is used as a fire source to vertically contact the surface of the tobacco leaf (avoiding the leaf veins) at the site to be measured. After burning through the leaf, it is immediately removed and allowed to burn naturally in the ignited area to form a combustion spot until it extinguishes naturally. The diffusion process of the combustion spot is recorded throughout the process using an image acquisition device.

[0007] S3. Combustion property data extraction: Using image processing software, extract multiple combustion property indicators from the acquired images during the process of combustion spot ignition, diffusion and extinguishing, including smoldering time, combustion spot area, combustion spot near-circularity and gray value of ash color.

[0008] S4. Comprehensive evaluation of combustibility: Based on the data of multiple indicators extracted above, a comprehensive evaluation model of in-situ combustibility of tobacco leaves is constructed using the multi-index principal component comprehensive evaluation method. The comprehensive combustibility score of each test site (region) on the tobacco leaf is calculated and the regional differences are analyzed.

[0009] Preferably, the image acquisition device includes:

[0010] The sample fixing module, including a double-sided grid plate, a bracket, and a white pad, is used to maintain the natural shape of the intact tobacco leaf;

[0011] The image acquisition module, including a bracket, video recording equipment, a fixed light source, and a white pad, is used to record the entire process of changes in tobacco burning spots.

[0012] The image analysis module, which includes image processing software, is used to extract multiple combustion characteristic indicators from combustion images, such as smoldering time, burning spot area, near-circularity of burning spot, and ash ash value.

[0013] The data analysis module is used to perform principal component analysis on multiple extracted indicators, construct a comprehensive evaluation model for flammability, and output regional difference analysis results.

[0014] Preferably, in the pretreatment of the tobacco leaf samples, only the main vein is removed, while the other parts of the tobacco leaf remain intact, without shearing, crushing, or other destructive treatments.

[0015] Preferably, in the acquisition of combustion process images, symmetrical sites are selected on the left and right sides of the three sections of the tobacco leaf: the tip, middle and base of the leaf, as test sites. An electric heating rod heated to a stable white-hot state is used as the ignition source. The electric heating rod has a diameter of 4 mm and is in perpendicular contact with the surface of the tobacco leaf to burn out circular combustion spots.

[0016] Preferably, in the extraction of combustion characteristic data, the formula for calculating the near-circularity ratio (CR) of the combustion spot is as follows: Where A represents the area of ​​the burning spot and P represents the perimeter of the burning spot; the ash gray value is the gray level of the ash image after tobacco burning, a value in the gray level range of 0-255 (8-bit gray level 256, 0-255 is commonly used in digital images).

[0017] CR can be used to reflect the degree of spatial dispersion. The smaller the value, the greater the curvature of the contour of the measured figure.

[0018] Preferably, the image processing software is ImageJ software, and the extraction of combustion characteristic indicators specifically includes:

[0019] Image length correction: Set a uniform length reference unit;

[0020] Convert an RGB image to an 8-bit grayscale image;

[0021] Set the measurement parameters, including area, average gray value, and shape descriptor;

[0022] Select the area of ​​interest (ROI) for measuring the burning spot, and automatically calculate the measured data of the burning spot.

[0023] Preferably, in the comprehensive evaluation of combustibility, the four combustibility indicators correspond to different combustibility characteristics: smoldering time reflects smoldering intensity, burning spot area reflects combustibility, burning spot sphericity reflects the uniformity of tobacco burning in all directions, and ash ash value reflects complete combustion.

[0024] Preferably, the lighting environment in the image acquisition module is an artificially stable lighting environment, and the video recording device is mounted on a bracket with an adjustable camera lens height to ensure complete capture of the combustion process on the grid plate.

[0025] Preferably, the image analysis module can automatically calculate and export the measurement results of the combustion spots, and supports data accumulation and Excel format export functions.

[0026] Preferably, the data analysis module uses principal component analysis to integrate multiple combustion characteristic indicators into a single score, thereby achieving a quantitative evaluation of regional differences in the combustibility of tobacco leaves.

[0027] Compared with existing technologies, the beneficial effects of this invention are as follows: This method measures whole tobacco leaves without shearing, crushing, or other destructive treatments, preserving the natural state and structural integrity of the tobacco leaves to the greatest extent. This allows for a more realistic reflection of the combustion characteristics of raw tobacco leaves in their original state, providing more accurate data for raw tobacco leaf quality assessment. By extracting multiple combustion characteristic indicators such as smoldering time, burning spot area, near-circularity of burning spot, and ash ash value, the in-situ combustibility of tobacco leaves is characterized comprehensively. Smoldering time reflects smoldering intensity, burning spot area reflects combustibility, near-circularity of burning spot reflects the uniformity of combustion in all directions, and ash ash value reflects complete combustion. Symmetrical sites are selected on both sides of the leaf tip, middle, and base as test sites for multi-point testing. This allows for full consideration of the differences in combustion characteristics of different parts of the tobacco leaf, providing a more comprehensive understanding of the overall combustion performance of the tobacco leaf and offering rich data for in-depth analysis of regional differences in tobacco leaf combustibility. Attached Figure Description

[0028] Figure 1 This is a schematic diagram of the sample fixing module of the present invention;

[0029] Figure 2 This is a diagram showing the division of the tobacco leaf tip (t), leaf middle (m), and leaf base (b) according to the present invention.

[0030] In the picture: 1. White pad; 2. Double-sided mesh panel; 3. Bracket; 4. Video recorder; 5. Bracket. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0032] Please see Figures 1-2 This invention provides a technical solution: a method for determining the in-situ combustibility of intact tobacco leaves based on image analysis technology, comprising the following steps:

[0033] S1. Pretreatment of tobacco leaf samples: Remove the main vein from the whole tobacco leaf sample. The treated tobacco leaf should be equilibrated for 48 hours under standard conditions of temperature 22±1℃ and humidity 60±2% to ensure that the internal moisture of the sample is uniform and stable. At the same time, the tobacco leaf should be kept in a natural flat state by clamping with double-sided grid plates for more than 24 hours.

[0034] S2. Combustion process image acquisition: Under artificial fixed lighting and windless environment, the pretreated tobacco leaf sample is laid flat on a grid plate and heated to a stable white-hot state using a standard fixed-diameter electric heating rod. This heating rod is used as the ignition source and is used to make vertical contact with the tobacco leaf surface (avoiding the leaf veins) at the test site. After burning through the leaf, the sample is immediately removed and allowed to burn naturally in the ignited area to form a burn spot until it extinguishes naturally. The diffusion process of the burn spot is recorded throughout the process using an image acquisition device. In the combustion process image acquisition, symmetrical sites are selected on both sides of the three sections of the tobacco leaf: the tip, middle, and base. A 4mm diameter electric heating rod is used as the ignition source and is used to make vertical contact with the tobacco leaf surface to burn a circular burn spot.

[0035] Image acquisition equipment includes:

[0036] The sample fixing module, including a double-sided grid plate, a bracket, and a white pad, is used to maintain the natural shape of the intact tobacco leaf;

[0037] The image acquisition module, including a bracket, video recording equipment, a fixed light source, and a white pad, is used to record the entire process of changes in tobacco burning spots.

[0038] The image analysis module, which includes image processing software, is used to extract multiple combustion characteristic indicators from combustion images, such as smoldering time, burning spot area, near-circularity of burning spot, and ash ash value.

[0039] The data analysis module is used to perform principal component analysis on multiple extracted indicators, construct a comprehensive evaluation model for flammability, and output regional difference analysis results.

[0040] The image processing software used is ImageJ. The extraction of combustion characteristic indicators specifically includes: image length correction, setting a uniform length reference unit; converting the RGB image to an 8-bit grayscale image; setting measurement parameters, including area, average grayscale value, and shape descriptor; selecting the combustion spot measurement area (ROI); and automatically calculating the combustion spot measurement data. The lighting environment in the image acquisition module is an artificially stabilized lighting environment. The recording equipment is mounted on a bracket, and the camera lens height is adjustable to ensure complete capture of the combustion process on the grid plate.

[0041] The image analysis module can automatically calculate and export the measurement results of combustion spots, supporting data accumulation and Excel format export. The data analysis module uses principal component analysis to integrate multiple combustion characteristic indicators into a single score, enabling a quantitative evaluation of the regional differences in the combustibility of tobacco leaf surfaces.

[0042] S3. Combustion Characteristic Data Extraction: Using image processing software, multiple combustion characteristic indicators of the combustion spot during the ignition, diffusion, and extinguishing process are extracted from the acquired images. These indicators include smoldering time, combustion spot area, combustion spot sphericity, and grayscale values ​​of ash color. The formula for calculating the combustion spot sphericity (CR) in the combustion characteristic data extraction is as follows: Where A represents the area of ​​the burning spot and P represents the perimeter of the burning spot; the ash gray value is the gray level of the ash image after tobacco combustion, a value in the gray range of 0-255 (8-bit gray level 256, 0-255 is commonly used in digital images); CR can be used to reflect the degree of spatial dispersion. The smaller the value, the greater the curvature of the contour of the measured figure.

[0043] S4. Comprehensive evaluation of combustibility: Based on the data of multiple indicators extracted above, a comprehensive evaluation model of in-situ combustibility of tobacco leaves is constructed using the multi-index principal component comprehensive evaluation method. The comprehensive combustibility score of each test site (region) on the tobacco leaf is calculated and the regional differences are analyzed. In the comprehensive evaluation of combustibility, the four combustibility indicators correspond to different combustion characteristics: smoldering time reflects smoldering intensity, burning spot area reflects combustibility, burning spot near-circularity reflects the combustion uniformity of the tobacco leaf in all directions, and ash ash value reflects combustion completeness.

[0044] Example 1:

[0045] S1. Pretreatment of tobacco leaf samples:

[0046] Select intact tobacco leaf samples free from pests and diseases, and carefully remove the main veins to minimize their impact on combustion uniformity. Place the vein-removed tobacco leaves flat in a dedicated sample holder, applying slight pressure to maintain their natural flatness and prevent wrinkles or curling that could affect observation and recording of the combustion process. The pretreated tobacco leaves should be equilibrated for 48 hours under standard conditions of 22±1℃ and 60±2% humidity to ensure uniform and stable internal moisture content.

[0047] S2. Image acquisition of the combustion process:

[0048] Image acquisition is conducted under artificially created stable lighting conditions to avoid interference from natural light variations on image color and contrast. The acquisition device is set up on a flat operating table: first, a sturdy support frame is assembled, upon which a 70cm x 50cm stainless steel double-sided grid plate 2 is placed. A white pad 1 is placed underneath the grid plate 2 to create a uniform background. A video recorder (such as a high-definition digital camcorder) is fixed to the support frame 3. The height of the support frame 3 and the angle of the video recorder 4 are adjusted. A light source is fixedly installed on the support frame 3 near the video recorder 4, ensuring that the lens of the video recorder 4 completely covers the area of ​​the stainless steel grid plate 2 and that the focal plane is parallel to the surface of the tobacco leaves to guarantee a clear and undistorted image of the combustion spots.

[0049] In the three typical sections of the tobacco leaf—the tip (t), the middle (m), and the base (b)—as follows: Figure 2 As shown, symmetrical test points were selected on both the left and right sides. A heating rod with a diameter of approximately 4mm was used as the standard ignition source. The heating rod, heated to a stable white-hot state, was gently touched perpendicularly to the surface of the tobacco leaf. After creating an initial circular burning spot with a diameter similar to the heating rod, the ignition source was immediately removed. A smoldering heating rod was then inserted perpendicularly into the tobacco leaf, creating a circular burning spot with the same diameter as the heating rod. The ignition source was immediately removed, allowing the burning spot to burn freely and spread outwards until it extinguished naturally. A video recording device was activated to record the entire process of the burning spot smoldering, spreading, and extinguishing naturally.

[0050] S3. Extraction of combustion property data:

[0051] The acquired images were analyzed using ImageJ image processing software, and the following key combustion characteristic indicators were extracted:

[0052] Smoldering time: The time interval (in seconds) from the moment the fire source is removed and the tobacco leaves enter a flameless smoldering state until the last spark is completely extinguished. This indicator directly reflects the tobacco leaves' ability to sustain smoldering and must be at least 2 seconds; otherwise, it is considered extinguished smoke.

[0053] Burning Spot Area: Select a keyframe in the image before the burning spot has stabilized or extinguished, use ImageJ's measurement tools to select the burning spot area, and the software will automatically calculate its projected area (unit: mm). 2 This index characterizes the combustibility of tobacco leaves under fixed conditions. The burning spot area refers to the area of ​​the pores formed on the surface of the tobacco leaf at the burning point under fixed conditions.

[0054] Near-circularity ratio (CR) of combustion spots: The formula for calculating the near-circularity ratio is as follows: Where A represents the area of ​​the burning spot and P represents the perimeter of the burning spot; the ash gray value is the gray level of the ash image after tobacco combustion, a value in the gray level range of 0-255 (8-bit gray level 256, 0-255 is commonly used in digital images);

[0055] Ash value: The average value of the image of the ash formed after tobacco leaves have burned completely, measured on a grayscale scale from 0 (pure black) to 255 (pure white). The higher the gray value, the whiter the ash and the more complete the combustion.

[0056] The specific steps of image processing are as follows:

[0057] (1) Image length correction: Open Image J, click File-Open Samples-Leaf, select the length scale in the Leaf model to specify the image length, and then click Analyze-Set Scale. At this time, the Distance in pixels is displayed as 59.5005. Set the Known distance to 10, change the Unit of length to mm, and click Global to make all imported images use a uniform length reference scale unit.

[0058] (2) Image import and conversion: Images of the tobacco burning process were imported sequentially according to the experimental groups. The initial images were in RGB color mode, and were converted to 8-bit grayscale images through menu operation (Image>Type>8-bit) to facilitate subsequent grayscale analysis.

[0059] (3) Set measurement parameters: Under the Analyze menu, select Set Measurements, check the parameters to be measured, including Area, Mean gray value, and Shape descriptors (which include Circularity).

[0060] (4) Index Extraction and Data Recording: Use the software's selection tools (such as free selection or rectangular / elliptical selection tools) to precisely delineate the area of ​​the combustion spot or ash (ROI, Region of Interest). Press Ctrl+M (or select Analyze>Measure), and the software will automatically calculate and display the area, average gray value, and near-circularity of the region. All measurement results will be accumulated in the Results window and can be exported to an Excel file for subsequent statistical analysis. The smoldering time is obtained by playing back the video and recording the time difference from ignition to the extinguishing of the last fire point.

[0061] S4. Comprehensive evaluation of tobacco leaf combustibility:

[0062] Based on the four indicators extracted above—smoldering time (evaluating smoldering flaming power), burning spot area (evaluating combustibility), near-circularity of burning spot (evaluating combustion uniformity), and ash ash value (evaluating combustion completeness)—a comprehensive evaluation model for the in-situ combustibility of tobacco leaves is constructed using the multi-indicator principal component comprehensive evaluation method.

[0063] After standardizing the data of four indicators measured at the leaf tip, middle, and base sites of each group of tobacco leaves, principal component analysis (PCA) was performed. The weights of each principal component were determined based on the variance contribution rate, and the overall combustibility score of each sample was calculated. This model can not only quantitatively rank the overall combustibility of a single tobacco leaf, but also precisely compare the differences in combustibility of different regions (leaf tip, middle, and base) of the same tobacco leaf, providing a scientific basis for tobacco quality assessment, industrial grading, and formulation design.

[0064] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for determining the in-situ combustibility of intact tobacco leaves based on image analysis technology, characterized in that, Includes the following steps: S1. Pretreatment of tobacco leaf samples: Remove the main vein from the whole tobacco leaf sample. The treated tobacco leaf should be equilibrated for 48 hours under standard conditions of temperature 22±1℃ and humidity 60±2% to ensure that the internal moisture of the sample is uniform and stable. At the same time, the tobacco leaf is kept in a natural flat state by clamping it with a double-sided grid plate. S2. Combustion process image acquisition: Under artificial fixed lighting and windless environment, the pretreated tobacco leaf sample is laid flat on a grid plate and heated to a white-hot stable state using an electric heating rod with a standard fixed diameter. This is used as a fire source to vertically contact the surface of the tobacco leaf (avoiding the leaf veins) at the site to be measured. After burning through the leaf, it is immediately removed and allowed to burn naturally in the ignited area to form a combustion spot until it extinguishes naturally. The diffusion process of the combustion spot is recorded throughout the process using an image acquisition device. S3. Combustion property data extraction: Using image processing software, extract multiple combustion property indicators from the acquired images during the process of combustion spot ignition, diffusion and extinguishing, including smoldering time, combustion spot area, combustion spot near-circularity and gray value of ash color. S4. Comprehensive evaluation of combustibility: Based on the data of multiple indicators extracted above, a comprehensive evaluation model of in-situ combustibility of tobacco leaves is constructed using the multi-index principal component comprehensive evaluation method. The comprehensive combustibility score of each test site (region) on the tobacco leaf is calculated and regional differences are analyzed.

2. The method according to claim 1, characterized in that, The image acquisition device includes: The sample fixing module, including a double-sided grid plate, a bracket, and a white pad, is used to maintain the natural shape of the intact tobacco leaf; The image acquisition module, including a bracket, video recording equipment, and a fixed light source, is used to record the entire process of changes in tobacco burning spots. The image analysis module, which includes image processing software, is used to extract multiple combustion characteristic indicators from combustion images, such as smoldering time, burning spot area, near-circularity of burning spot, and ash ash value. The data analysis module is used to perform principal component analysis on multiple extracted indicators, construct a comprehensive evaluation model for flammability, and output regional difference analysis results.

3. The method according to claim 1, characterized in that, In the pretreatment of the tobacco leaf samples, only the main vein is removed, while the other parts of the tobacco leaf remain intact. No cutting, crushing or other destructive treatments are performed.

4. The method according to claim 1, characterized in that, In the image acquisition of the combustion process, symmetrical sites are selected on both sides of the three sections of the tobacco leaf: the tip, middle and base of the leaf, as test sites. An electric heating rod heated to a stable white-hot state is used as the ignition source and is used to burn circular combustion spots in perpendicular contact with the surface of the tobacco leaf.

5. The method according to claim 1, characterized in that, In the extraction of combustion characteristic data, the formula for calculating the near-circularity ratio (CR) of combustion spots is as follows: Where A represents the area of ​​the burning spot and P represents the perimeter of the burning spot; the ash gray value is the gray level of the ash image after tobacco burning, a value in the gray level range of 0-255 (8-bit gray level 256, 0-255 is commonly used in digital images). CR can be used to reflect the degree of spatial dispersion. The smaller the value, the greater the curvature of the contour of the measured figure.

6. The method according to claim 1, characterized in that, The image processing software is ImageJ software, and the specific extraction of combustion characteristic indicators includes: Image length correction: Set a uniform length reference unit; Convert an RGB image to an 8-bit grayscale image; Set the measurement parameters, including area, average gray value, and shape descriptor; Select the area of ​​origin (ROI) for measuring the burning spots and calculate the measured values ​​of the burning spots.

7. The method according to claim 1, characterized in that, In the comprehensive evaluation of combustibility, the four combustibility indicators correspond to different combustion characteristics: smoldering time reflects smoldering intensity, burning spot area reflects combustibility, burning spot sphericity reflects the uniformity of tobacco burning in all directions, and ash ash value reflects complete combustion.

8. The method according to claim 2, characterized in that, The lighting environment in the image acquisition module is an artificially stable lighting environment. The video recording device is mounted on a bracket, and the camera lens height is adjustable to ensure that the combustion process on the grid plate can be completely captured.

9. The method according to claim 2, characterized in that, The image analysis module can automatically calculate and export the measurement results of the combustion spots, and supports data accumulation and Excel format export functions.

10. The system according to claim 2, characterized in that, The data analysis module uses principal component analysis to integrate multiple combustion characteristic indicators into a single score, thereby achieving a quantitative evaluation of regional differences in the combustibility of tobacco leaves.

Images