Method for detecting stem content of tobacco based on hyperspectrum

Abstract

The invention provides a method for detecting the stem content of tobacco leaves based on hyperspectrum, which comprises the following steps: S1, collecting tobacco leaf raw materials, and establishing a tobacco leaf and tobacco stem map database to obtain standard maps of tobacco leaves and tobacco stems; s2, acquiring maps of tobacco leaves and tobacco stems in tobacco leaf raw materials on a production line in real time; s3, comparing the atlas of the tobacco leaves and the tobacco stems obtained in real time with a standard atlas in a tobacco leaf and tobacco stem database to obtain the content of the tobacco leaves and the content of the tobacco stems respectively; and S4, calculating the stem content of the tobacco leaves in real time according to the contents of the tobacco leaves and the tobacco stems. According to the method, the stem content of the tobacco leaves can be automatically detected on line, the tobacco stems in the tobacco leaves do not need to be manually detected, so that the detection efficiency of the stem content of the tobacco leaves can be effectively improved, and the labor intensity of detection personnel is reduced.

Description

Technical Field

[0001] This invention belongs to the field of tobacco leaf testing technology, specifically relating to a method for detecting the stem content of tobacco leaves based on hyperspectral imaging. Background Technology

[0002] As tobacco companies increasingly demand higher standards for raw materials and automation in production, the requirements for stem content in tobacco leaves are becoming more stringent. A high stem content, coupled with inadequate stem removal during processing, can alter the flavor of cigarettes and cause small stems to puncture the cigarette paper, resulting in substandard cigarettes. Currently, stems larger than 1.5mm are manually inspected, which introduces significant human variation, is inefficient, and places a high workload on inspectors.

[0003] Therefore, how to design a hyperspectral-based method for detecting the stem content of tobacco leaves to improve the detection efficiency of tobacco stems and reduce the labor intensity of testing personnel has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a method for detecting the stem content of tobacco leaves based on hyperspectral imaging, so as to solve the above-mentioned technical problems in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A method for detecting the stem content of tobacco leaves based on hyperspectral imaging, comprising the following steps:

[0007] Step S1: Collect tobacco raw materials, establish a tobacco leaf and stem atlas database, and obtain standard atlases of tobacco leaves and stems;

[0008] Step S2: Real-time acquisition of graphs of tobacco leaves and stems in the raw tobacco materials on the production line;

[0009] Step S3: Compare the real-time acquired images of tobacco leaves and stems with the standard images in the tobacco leaf and stem database to obtain the content of tobacco leaves and stems respectively.

[0010] Step S4: Calculate the stem content of the tobacco leaves in real time based on the content of tobacco leaves and stems.

[0011] Preferably, the specific content of collecting tobacco raw materials in step S1 is: collecting tobacco raw materials from different producing areas.

[0012] Preferably, the different production areas include the Southwest production area, the Southeast production area, the middle and upper reaches of the Yangtze River production area, the Huanghuai production area, and the Northern production area.

[0013] Preferably, different parts of tobacco leaves from the same production area are collected as raw tobacco leaves.

[0014] Preferably, the different parts include upper tobacco leaves, middle tobacco leaves, and lower tobacco leaves.

[0015] Preferably, in step S2, hyperspectral imaging of tobacco leaves and stems in the tobacco raw materials on the production line is obtained in real time using hyperspectral technology.

[0016] Preferably, near-infrared spectroscopy is used to scan the tobacco raw materials on the production line to obtain real-time images of tobacco leaves and stems.

[0017] Preferably, after obtaining the chromatograms of tobacco leaves and stems in the raw tobacco materials on the production line, the chromatograms are corrected to make them clear.

[0018] The beneficial effects of this invention are as follows:

[0019] The present invention provides a hyperspectral-based method for detecting the stem content of tobacco leaves, which can automatically detect the stem content of tobacco leaves online without the need for manual detection of tobacco stems, thereby effectively improving the detection efficiency of the stem content of tobacco leaves and reducing the labor intensity of detection personnel. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly described below, and the specific embodiments of the present invention will be further described in detail with reference to the drawings, wherein...

[0021] Figure 1 A flowchart of a method for detecting the stem content of tobacco leaves based on hyperspectral imaging, provided in an embodiment of the present invention. Detailed Implementation

[0022] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention.

[0023] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use.

[0024] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0025] In all the examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0026] like Figure 1As shown, this embodiment of the invention provides a method for detecting the stem content of tobacco leaves based on hyperspectral imaging, which includes the following steps:

[0027] Step S1: Collect tobacco raw materials, establish a tobacco leaf and stem atlas database, and obtain standard atlases of tobacco leaves and stems;

[0028] Step S2: Real-time acquisition of graphs of tobacco leaves and stems in the raw tobacco materials on the production line;

[0029] Step S3: Compare the real-time acquired images of tobacco leaves and stems with the standard images in the tobacco leaf and stem database to obtain the content of tobacco leaves and stems respectively.

[0030] Step S4: Calculate the stem content of the tobacco leaves in real time based on the content of tobacco leaves and stems.

[0031] The hyperspectral-based method for detecting the stem content of tobacco leaves provided in this invention can automatically detect the stem content of tobacco leaves online without the need for manual detection of tobacco stems, thereby effectively improving the detection efficiency of the stem content of tobacco leaves and reducing the labor intensity of detection personnel.

[0032] Furthermore, the specific content of collecting tobacco raw materials in step S1 is as follows: collecting tobacco raw materials from different producing areas, including the Southwest producing area, the Southeast producing area, the middle and upper reaches of the Yangtze River producing area, the Huanghuai producing area, and the Northern producing area. At the same time, collecting different parts of tobacco leaves from the same producing area as tobacco raw materials, including upper tobacco leaves, middle tobacco leaves, and lower tobacco leaves.

[0033] This approach enables the collection of tobacco raw materials from different production areas and different parts of the tobacco leaves. This allows for the acquisition of standard spectra of tobacco leaves and stems from various regions and parts, ensuring that these standard spectra cover tobacco raw materials from different production areas and parts. This makes them more suitable for detecting the stem content of tobacco leaves from different regions and parts, thus improving detection accuracy. It is understandable that because tobacco leaves and stems from different parts of different production areas differ, their spectra will also differ. By obtaining their standard spectra through hyperspectral technology, they can be detected separately for each type of tobacco raw material on the production line.

[0034] Specifically, in step S2, hyperspectral technology is used to acquire in real time the spectra of tobacco leaves and stems in the tobacco raw materials on the production line.

[0035] Preferably, near-infrared spectroscopy can be used to scan the raw tobacco leaves on the production line to obtain real-time images of the tobacco leaves and stems. It is understood that near-infrared spectroscopy is a type of hyperspectral imaging; the principle of obtaining images through near-infrared spectroscopy scanning is existing technology and will not be elaborated upon here.

[0036] Specifically, after obtaining the graphs of tobacco leaves and stems from the raw tobacco materials on the production line, the graphs are corrected to make them clearer, thus making the obtained graph data more accurate, and consequently, the obtained stem content of the tobacco leaves more accurate. It is understood that the correction process for the graphs can use existing correction methods; the percentage of stem content divided by the tobacco leaf content is the stem content of the tobacco leaves.

[0037] This invention applies hyperspectral technology to the identification of tobacco raw materials. Since there are significant differences in the spectral signatures of tobacco leaves and stems, a database of tobacco leaf and stem spectral signatures is established. Hyperspectral technology is then used to detect the stem content in tobacco leaves online, replacing the traditional methods of manual sampling and separation. This invention has a high effective identification rate for tobacco stems, improving the detection efficiency and significantly enhancing the purity of cigarette raw materials, thereby improving cigarette quality.

[0038] While specific embodiments of the invention have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of the invention. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims

1. A method for detecting the stem content of tobacco leaves based on hyperspectral imaging, characterized in that, It includes the following steps: Step S1: Collect tobacco raw materials, establish a tobacco leaf and stem atlas database, and obtain standard atlases of tobacco leaves and stems; Step S2: Real-time acquisition of graphs of tobacco leaves and stems in the raw tobacco materials on the production line; Step S3: Compare the real-time acquired images of tobacco leaves and stems with the standard images in the tobacco leaf and stem database to obtain the content of tobacco leaves and stems respectively. Step S4: Calculate the stem content of the tobacco leaves in real time based on the content of tobacco leaves and stems.

2. The method for detecting the stem content of tobacco leaves based on hyperspectral imaging according to claim 1, characterized in that, The specific content of collecting tobacco raw materials in step S1 is: collecting tobacco raw materials from different producing areas.

3. The method for detecting the stem content of tobacco leaves based on hyperspectral imaging according to claim 2, characterized in that, These different production areas include the Southwest Production Area, the Southeast Production Area, the Middle and Upper Reaches of the Yangtze River Production Area, the Yellow River and Huai River Production Area, and the Northern Production Area.

4. The method for detecting the stem content of tobacco leaves based on hyperspectral imaging according to claim 2, characterized in that, Different parts of tobacco leaves from the same production area are collected as raw materials for tobacco.

5. The method for detecting the stem content of tobacco leaves based on hyperspectral imaging according to claim 4, characterized in that, These different parts include the upper tobacco leaves, the middle tobacco leaves, and the lower tobacco leaves.

6. The method for detecting the stem content of tobacco leaves based on hyperspectral imaging according to any one of claims 1 to 5, characterized in that, In step S2, hyperspectral imaging of tobacco leaves and stems in the raw tobacco materials on the production line is acquired in real time using hyperspectral technology.

7. The method for detecting the stem content of tobacco leaves based on hyperspectral imaging according to claim 6, characterized in that, Near-infrared spectroscopy is used to scan the raw tobacco leaves on the production line to obtain real-time images of tobacco leaves and stems.

8. The method for detecting the stem content of tobacco leaves based on hyperspectral imaging according to claim 6, characterized in that, After obtaining the chromatograms of tobacco leaves and stems from the raw tobacco materials on the production line, the chromatograms are corrected to make them clear.

Images