A method for evaluating tobacco leaf grades

Abstract

The present invention proposes a tobacco leaf grade evaluation method, which belongs to the technical field of cigarette production. The original spectral image of the tobacco leaf to be evaluated is collected, the green tobacco area of ​​the tobacco leaf to be evaluated is obtained through the original spectral image, the green tobacco distribution ratio of the tobacco leaf to be evaluated is calculated based on the green tobacco area, and the grade of the tobacco leaf to be evaluated is determined according to the green tobacco distribution ratio. The appearance quality of tobacco leaves in tobacco leaves can be accurately and quickly identified, and the grade of tobacco leaves can be accurately and quickly evaluated online, thereby avoiding losses caused by human factors, and at the same time greatly solving the personnel consumption, increasing the selective use width of the industry and reducing the difficulty of industrial formulation.

Description

Technical Field

[0001] The invention relates to the technical field of cigarette production, and in particular to a tobacco leaf grade evaluation method. Background Art

[0002] In tobacco leaf production, in order to distinguish tobacco leaves of different qualities and make each grade of tobacco leaves have relatively consistent quality for subsequent cigarette production, it is necessary to grade tobacco leaves. Among them, the appearance quality factor is an important grading factor for measuring tobacco leaf grades.

[0003] In the prior art, the evaluation of tobacco leaf appearance quality is mainly done manually, that is, the grade and quality of tobacco leaves are determined by touch and visual inspection. In tobacco leaf grading, the color of tobacco leaves is an important evaluation indicator of their quality grade. Among them, the basic colors of tobacco leaves include lemon yellow, orange yellow, and red brown; the non-basic colors of tobacco leaves include green-yellow, slightly green, and variegated colors. The accurate identification of the above colors requires a high level of quality from the evaluation experts, and is easily interfered by various external factors in practical applications.

[0004] In view of this, the inventor has designed a tobacco grade evaluation method based on many years of production design experience in this field and related fields and through repeated experiments, in order to solve the problems existing in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a tobacco leaf grade evaluation method, which can accurately and quickly identify the appearance quality of tobacco leaves and realize accurate and rapid grading of tobacco leaves.

[0006] To achieve the above-mentioned purpose, the present invention proposes a tobacco leaf grade evaluation method, wherein the original spectral image of the tobacco leaf to be evaluated is collected, the green smoke area of ​​the tobacco leaf to be evaluated is obtained through the original spectral image, the green smoke distribution ratio of the tobacco leaf to be evaluated is calculated based on the green smoke area, and the grade of the tobacco leaf to be evaluated is determined according to the green smoke distribution ratio.

[0007] Compared with the prior art, the tobacco grade evaluation method proposed by the present invention has the following characteristics and advantages:

[0008] The tobacco leaf grade evaluation method proposed in the present invention can accurately and quickly identify the appearance quality of tobacco leaves in tobacco leaves, and realize accurate and rapid online evaluation of tobacco leaf grades, thereby avoiding losses caused by human factors, while greatly solving personnel consumption, increasing the breadth of industrial selective use and reducing the difficulty of industrial formulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The accompanying drawings described herein are only for explanation purposes and are not intended to limit the scope of the present invention in any way. In addition, the shapes and proportional dimensions of the various components in the figures are only schematic, used to help understand the present invention, and are not specifically limited to the shapes and proportional dimensions of the various components of the present invention. Those skilled in the art can select various possible shapes and proportional dimensions to implement the present invention according to the teachings of the present invention.

[0010] Figure 1 The present invention provides a flowchart of the tobacco leaf grade evaluation method.

[0011] Figure 2 is an original spectral image of a tobacco leaf to be evaluated in one embodiment of the present invention;

[0012] Figure 3 An image of a green tobacco region of a tobacco leaf to be evaluated in one embodiment of the present invention;

[0013] Figure 4 is an original spectral image of a tobacco leaf to be evaluated in another embodiment of the present invention;

[0014] Figure 5 This is an image of the green tobacco region of a tobacco leaf to be evaluated in another embodiment of the present invention. DETAILED DESCRIPTION

[0015] The details of the present invention can be more clearly understood with reference to the accompanying drawings and the description of the specific embodiments of the present invention. However, the specific embodiments of the present invention described herein are only used for the purpose of explaining the present invention and cannot be understood as limiting the present invention in any way. Under the guidance of the present invention, technicians can conceive of any possible variations based on the present invention, which should all be considered to belong to the scope of the present invention.

[0016] The present invention proposes a tobacco grade evaluation method, such as Figure 1 As shown, the original spectral image of the tobacco leaf to be evaluated is collected, the green smoke area of ​​the tobacco leaf to be evaluated is obtained through the original spectral image, the green smoke distribution ratio of the tobacco leaf to be evaluated is calculated based on the green smoke area, and the grade of the tobacco leaf to be evaluated is determined according to the green smoke distribution ratio.

[0017] The tobacco leaf grade evaluation method proposed in the present invention can accurately and quickly identify the appearance quality of tobacco leaves, thereby avoiding losses caused by human factors, while greatly solving the problem of personnel consumption, increasing the breadth of industrial selective use and reducing the difficulty of industrial formulation.

[0018] The tobacco leaf grade evaluation method proposed in the present invention utilizes the original spectral image of the tobacco leaf to be evaluated to quickly identify the appearance of the tobacco leaf, thereby realizing online accurate and rapid evaluation of the tobacco leaf grade and improving the cigarette production efficiency.

[0019] In an optional embodiment of the present invention, the original spectral image (such as Figure 2 , Figure 4 The spectral information after preprocessing is obtained by preprocessing the spectral information, and the spectral curve of each pixel (pixel point) on the leaf surface of the tobacco leaf to be evaluated is obtained through the spectral information, and the curvature radius of the spectral curve of each pixel is calculated. The corresponding pixel (pixel point) is extracted according to the curvature radius and displayed as a green tobacco area (as shown in FIG. Figure 3 , Figure 5 By calculating the curvature radius of the spectral curve of each pixel (pixel point) on the leaf surface in the tobacco leaf spectral image, the green tobacco area distribution is extracted according to the curvature radius of each pixel (pixel point).

[0020] In an optional example of this embodiment, the original spectral image of the tobacco leaf to be evaluated is collected by a hyperspectral imager.

[0021] In an optional example, when a hyperspectral imager is used to collect original spectral images of tobacco leaves, the tobacco leaves are placed in an unfolded state on the stage of the hyperspectral imager, and the spectral information of the front and back sides of the tobacco leaves need to be collected separately, and saved in a preprocessing unit or a computing unit according to the digital numbering.

[0022] In an optional embodiment of the present invention, the preprocessing process includes using a standard black and white plate correction formula to perform data correction on the original atlas information.

[0023] The standard black and white plate correction formula is:

[0024]

[0025] In the formula, the standard white calibration plate obtains the all-white calibration image W; the all-black calibration image B is obtained by scanning the built-in blackboard, the original image I is corrected, and the preprocessed atlas data is R.

[0026] In an optional example of this embodiment, obtaining the spectral value of each pixel on the leaf surface of the tobacco leaf to be evaluated through the preprocessed spectral information includes: converting the preprocessed spectral information into single-band spectrum data; segmenting the single-band spectrum data into tobacco leaf information and background information; segmenting the tobacco leaf information into leaf surface information, leaf stem information and wrinkle information, and marking the leaf surface information as a sensing area; correcting the spectrum of the area of ​​interest, intercepting the leaf surface information within a predetermined band range, and calculating the curvature radius of the spectral curve of each pixel in the leaf surface information one by one.

[0027] In an optional example, the spectrum information at 675.4 nm in the pre-processed spectral information is selected and converted into binary single-band spectrum data.

[0028] In an optional example, a global threshold method may be used to segment tobacco leaves and background information, and then a local threshold method may be used to segment leaf surface, leaf stem, and wrinkle information, and the leaf surface portion may be marked as a region of interest.

[0029] In an optional example of this embodiment, the radius of curvature is calculated using the formula:

[0030]

[0031] In the formula,

[0032] In an optional example, the spectrum of the region of interest is first corrected using a multivariate scattering correction method, and then the 600nm-700nm band is intercepted to calculate the radius of curvature of the spectrum curve of each pixel one by one.

[0033] In an optional embodiment of the present invention, the process of extracting the blue smoke area according to each curvature radius includes: sorting each pixel from low to high according to the curvature radius, then normalizing the curvature radius, and using the quantile as an indicator to set a heat map to display the blue smoke distribution on the leaf surface.

[0034] In an optional example of this implementation, the quantile method is used to divide the curvature radius of each sorted pixel into four equal parts, and 10%, 20%, and 30% of the curvature radius are used as quantile points for blue cigarette identification according to the numerical values.

[0035] In an optional embodiment of the present invention, the tobacco leaves to be evaluated need to be placed in an environment with a relative humidity of 70% and a temperature of 25° C. for 48 hours to form a stable state.

[0036] In an optional embodiment of the present invention, the green tobacco distribution ratio is the ratio of the number of pixels in the green tobacco area to the number of pixels in the tobacco leaves.

[0037] In the present invention, when the distribution ratio of green smoke is within 10%, it is determined that the tobacco leaf to be evaluated is slightly green; when the distribution ratio of green smoke is between 10% and 30%, it is determined that the tobacco leaf to be evaluated is green-yellow.

[0038] The detailed explanation of the above-mentioned embodiments is only intended to explain the present invention so as to facilitate a better understanding of the present invention. However, these descriptions cannot be interpreted as limitations on the present invention for any reason. In particular, the various features described in different embodiments may also be arbitrarily combined with each other to form other embodiments. Unless there is a clear description to the contrary, these features should be understood to be applicable to any embodiment and are not limited to the described embodiments.

[0039] The detailed explanation of the above-mentioned embodiments is only intended to explain the present invention so as to facilitate a better understanding of the present invention. However, these descriptions cannot be interpreted as limitations on the present invention for any reason. In particular, the various features described in different embodiments may also be arbitrarily combined with each other to form other embodiments. Unless there is a clear description to the contrary, these features should be understood to be applicable to any embodiment and are not limited to the described embodiments.

Claims

1. A tobacco leaf grade evaluation method, characterized in that: Collecting an original spectral image of the tobacco leaf to be evaluated, obtaining a green smoke region of the tobacco leaf to be evaluated through the original spectral image, calculating a green smoke distribution ratio of the tobacco leaf to be evaluated based on the green smoke region, and determining a grade of the tobacco leaf to be evaluated according to the green smoke distribution ratio; Preprocessing the original spectral image to obtain preprocessed spectral information, obtaining the spectral curve of each pixel on the leaf surface of the tobacco leaf to be evaluated through the preprocessed spectral information, calculating the curvature radius of the spectral curve of each pixel, extracting the pixel of green tobacco according to each curvature radius and displaying it as a green tobacco area; Obtaining the spectral value of each pixel on the leaf surface of the tobacco leaf to be evaluated through the preprocessed spectral information includes: Converting the preprocessed spectral information into single-band spectrum data; segmenting the single-band spectrum data into tobacco leaf information and background information; segmenting the tobacco leaf information into leaf surface information, leaf stem information and wrinkle information, and marking the leaf surface information as a region of interest; correcting the spectrum of the region of interest, intercepting the leaf surface information within a predetermined band, and calculating the curvature radius of the spectral curve of each pixel in the leaf surface information one by one; The radius of curvature is calculated using the formula: (2) In the formula, ; The process of extracting corresponding pixels according to the curvature radius and displaying them as smoke areas includes: The pixels are sorted from low to high according to the radius of curvature, and then the radius of curvature is normalized, and the quantile is used as an indicator to set the heat map to display the blue smoke area of ​​the leaf surface; the process of extracting the corresponding pixels according to each radius of curvature and displaying them as the blue smoke area includes: The pixels are sorted from low to high according to the radius of curvature, and then the radius of curvature is normalized, and the quantile is used as an indicator to set the heat map to display the blue smoke area on the leaf surface.

2. The tobacco leaf grade evaluation method according to claim 1, characterized in that: The preprocessing process includes using a standard black and white plate correction formula to perform data correction on the original atlas information.

3. The tobacco leaf grade evaluation method according to claim 2, characterized in that: The standard black and white plate correction formula: ， （1） In the formula, the standard white calibration plate obtains the all-white calibration image W; the all-black calibration image B is obtained by scanning the built-in blackboard, the original image I is corrected, and the preprocessed atlas data is R.

4. The tobacco leaf grade evaluation method according to claim 1, characterized in that: The quantile method is used to divide the curvature radius of each sorted pixel into four equal parts, and the quantile points for blue cigarette identification are 10%, 20%, and 30% of the curvature radius according to the numerical value.

5. The tobacco leaf grade evaluation method according to claim 1, characterized in that: The green tobacco distribution ratio is the ratio of the number of pixels in the green tobacco area to the number of pixels in the tobacco leaves.

6. The tobacco leaf grade evaluation method according to claim 1, characterized in that: When the distribution ratio of the green smoke is within 10%, it is determined that the tobacco leaf to be evaluated is slightly green; when the distribution ratio of the green smoke is between 10% and 30%, it is determined that the tobacco leaf to be evaluated is green-yellow.

Images