Tobacco sheet uniformity quantification method and device

Abstract

The invention provides a tobacco sheet uniformity quantification method and device. The tobacco sheet uniformity quantification method comprises the following steps: S1, obtaining to-be-detected spectral information and reference spectral information of a to-be-detected tobacco sheet; s2, processing the spectral information to be measured based on a chemometrics algorithm to obtain target spectral information; and S3, based on the reference spectral information, performing uniformity quantitative analysis processing on the target spectral information to obtain uniformity quantitative information of the tobacco sheet to be detected.

Description

Technical Field

[0001] The present application belongs to the field of tobacco sheet detection, and specifically relates to a tobacco sheet uniformity quantification method and a tobacco sheet uniformity quantification device. Background Art

[0002] Tobacco flakes, also known as reconstituted tobacco or homogenized tobacco, are made from waste tobacco leaf fragments, tobacco dust, tobacco stems or low-grade tobacco leaves in the cigarette production process. They are processed, adhesives and other additives are added, and then dried and processed to form a sheet product with properties close to or better than natural tobacco leaves. The production of tobacco flakes can make full use of tobacco waste and effectively improve the utilization rate of tobacco materials, thereby reducing the production cost of cigarettes. In addition, tobacco flakes can also effectively reduce the harmful components such as nicotine and tar brought by cigarettes, while retaining the original taste of cigarettes, achieving effective tar reduction without affecting the quality of cigarettes, becoming a more useful way to reduce tar and reduce harm in current cigarettes.

[0003] Traditional technical means of evaluating the uniformity of tobacco sheets, whether they rely on intuitive measurements of physical parameters (such as accurate determination of thickness and density) or analytical methods that rely on complex chemical reactions (such as in-depth profiling by chromatography), have limitations that cannot be ignored. These traditional methods are not only inefficient and costly, but also incapable of fully revealing the delicate characteristics of the distribution of microscopic components in tobacco sheets. More importantly, they often need to be carried out at the expense of sample integrity, which undoubtedly limits the widespread application of these technologies in the field of non-destructive testing.

[0004] At the same time, although conventional near-infrared spectroscopy (NIR) technology has opened up a new way to evaluate the uniformity of tobacco slices with its unique non-destructive detection characteristics, its inherent spatial resolution limitations have become a bottleneck that restricts its effectiveness. Specifically, the spatial resolution of conventional NIR technology is generally higher than 1 mm, and this resolution is difficult to accurately capture the complex and changeable microstructure and composition gradient inside tobacco slices. In addition, the widespread phenomenon of wide spectral peak overlap in the near-infrared spectral region undoubtedly increases the difficulty of data analysis, making the impact of interference information on the test results more significant, thereby affecting the accuracy and credibility of the test results. Summary of the invention

[0005] In view of this, the purpose of this application is to provide a method and device for quantifying the uniformity of tobacco sheets to solve the above problems.

[0006] In order to solve the above technical problems, this application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a method for quantifying the uniformity of tobacco sheet. The method for quantifying the uniformity of tobacco sheet includes: Step S1: Obtain the spectral information to be measured and the reference spectral information of the tobacco sheet to be measured; Step S2: Process the spectral information to be measured based on chemometric algorithms to obtain target spectral information; Step S3: Based on the reference spectral information, perform uniformity quantification analysis on the target spectral information to obtain the uniformity quantification information of the tobacco sheet to be measured.

[0008] Further, Step S1 includes: Step A1: Obtain the tobacco sheet to be measured; Step A2: Perform near-infrared spectral scanning on the tobacco sheet to be measured to obtain the spectral information to be measured, and the spectral information to be measured includes near-infrared spectral image information.

[0009] Further, Step A2 includes: Step A21: Use the scanned gold-plated lens as the background spectrum, and place the tobacco sheet to be measured on the stage; Step A22: Perform diffuse reflectance FT-NIR spectral image scanning on the tobacco sheet to be measured to obtain the spectral information to be measured.

[0010] Further, the reference spectral information includes the visible spectral information of the tobacco sheet to be measured and the near-infrared spectral information of the standard tobacco sheet. Step S1 includes: Step B1: Perform visible spectral image scanning on the tobacco sheet to be measured to obtain the visible spectral information; Step B2: Perform near-infrared spectral scanning on the standard tobacco sheet to obtain the reference spectral image.

[0011] Further, the chemometric algorithms include at least any one of the following: first derivative, second derivative, Savitzky-Golay convolution smoothing, multiplicative scatter correction, and standard normal variate transformation.

[0012] Further, Step S3 includes: Step S31: According to the spectral similarity algorithm, perform spectral similarity measurement analysis on the target spectral information and the reference spectral information to obtain a spectral similarity correlation coefficient map; Step S32: According to a preset uniformity threshold, perform binary image processing on the spectral similarity correlation coefficient map to obtain a binary spectral similarity correlation coefficient map; Step S33: Based on the binary spectral similarity correlation coefficient map, perform qualitative analysis and / or quantitative analysis on the tobacco sheet to be measured to obtain the corresponding uniformity information of the tobacco sheet to be measured.

[0013] In a second aspect, the present application provides a device for quantifying the uniformity of tobacco sheet. The device for quantifying the uniformity of tobacco sheet includes: an acquisition module, a processing module, and a quantification module. The acquisition module is used to obtain the spectral information to be measured and the reference spectral information of the tobacco sheet to be measured; the processing module is used to process the spectral information to be measured based on chemometric algorithms to obtain target spectral information; the quantification module is used to perform uniformity quantification analysis on the target spectral information based on the reference spectral information to obtain the uniformity quantification information of the tobacco sheet to be measured.

[0014] In a third aspect, the present application provides a computer system, which includes a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the tobacco sheet uniformity quantification method according to the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program / instructions are stored. When the computer program / instructions are executed by a processor, the tobacco sheet uniformity quantification method according to the first aspect is implemented.

[0016] In a fifth aspect, the present application provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the tobacco sheet uniformity quantification method according to the first aspect is implemented.

[0017] Spectral imaging technology combines imaging technology and spectral technology to collect the spectra of each point in the space of a sample, and can simultaneously obtain the two-dimensional spatial information and spectral information of the sample, so as to clearly and intuitively characterize the distribution of different components in the sample. According to different imaging methods, the detector can be selected from three types: single point, line array or area array. According to the spectral resolution, it can be divided into multispectral imaging and hyperspectral imaging. Hyperspectral imaging has high resolution, but the detection time is longer. According to different molecular spectral types, it can be divided into near-infrared spectral imaging, mid-infrared spectral imaging, Raman spectral imaging, fluorescence spectral imaging, etc. At present, the application of spectral imaging technology is mainly concentrated in the fields of pharmaceuticals, food, agricultural products, and materials science, and a part of the research belongs to the pure algorithm field.

[0018] Microscopic near-infrared spectral imaging technology collects the near-infrared spectra of each point in a two-dimensional plane, and obtains the distribution information of the substance in the two-dimensional space while obtaining the near-infrared spectral information of the substance. Compared with traditional infrared spectra, microscopic near-infrared spectral imaging retains the characteristics of non-destructive, sensitive, and environmentally friendly, and can additionally obtain the distribution and concentration of inhomogeneous samples in the two-dimensional space, making the analysis and detection more convenient and accurate.

[0019] As can be seen from the above technical solutions, the advantages and positive effects of the tobacco sheet uniformity quantification method and the tobacco sheet uniformity quantification device proposed in the present application are as follows:

[0020] By combining microscopic near-infrared spectral imaging technology with chemometric data processing methods, the present application can greatly improve the spatial resolution of tobacco sheet detection and the utilization rate of infrared spectral information, so as to distinguish the compositional differences in the microscopic regions (such as fiber bundles, filler aggregation regions) of the same tobacco sheet sample, and then be used to guide the improvement of the thin sheet production process.

[0021] It can be understood that there are differences in the structures between traditional ordinary tobacco cuttings and reconstituted tobacco. Different from the relevant algorithms used in other tobacco fields, such as ordinary tobacco cuttings, etc., the microscopic near-infrared spectral imaging combined with chemometric means in this application is particularly applicable to the field of reconstituted tobacco and can extract more effective information of reconstituted tobacco. Among them, chemometrics uses mathematical and statistical methods to design and select the optimal measurement procedures and experimental methods, and obtains the maximum amount of information by interpreting chemical data. Introducing chemometric means in spectral analysis can greatly improve and enhance the analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above content of this application and the following specific embodiments will be better understood when read in conjunction with the accompanying drawings. It should be noted that the drawings are only examples of the claimed technical solutions.

[0023] Figure 1 is a flowchart of the method for quantifying the uniformity of reconstituted tobacco in this application;

[0024] Figure 2 is a visible spectral image of the reconstituted tobacco to be measured;

[0025] Figure 3 is a near-infrared spectrogram of the standard reconstituted tobacco;

[0026] Figure 4 is a reconstructed diagram of the spectral similarity correlation coefficient of the reconstituted tobacco to be measured;

[0027] Figure 5 is a binary image of the spectral similarity correlation coefficient of the reconstituted tobacco to be measured. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The detailed features and advantages of this application are described in detail in the following specific embodiments. The content is sufficient for any person skilled in the art to understand the technical content of this application and implement it accordingly. And based on the specification, claims and drawings disclosed in this specification, those skilled in the art can easily understand the relevant purposes and advantages of this application.

[0029] It should be noted that in this specification, similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0030] In the description of this embodiment, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", "inner", "bottom", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product is usually placed during use. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0031] To make the objectives, technical solutions, and advantages of the present application clearer, the following will further describe the implementation manners of the present application in detail with reference to the drawings.

[0032] Please refer to Figure 1 , the present application provides a method for quantifying the uniformity of tobacco sheet, and the specific steps of this method for quantifying the uniformity of tobacco sheet are as follows:

[0033] Step S1: Obtain the spectral information to be measured and the reference spectral information of the tobacco sheet to be measured.

[0034] Step S2: Process the spectral information to be measured based on chemometric algorithms to obtain the target spectral information.

[0035] Among them, the chemometric algorithms can include at least any one of the following: first derivative, second derivative, Savitzky-Golay convolution smoothing, multiplicative scatter correction, and standard normal variate transformation.

[0036] Step S3: Based on the reference spectral information, perform uniformity quantification analysis on the target spectral information to obtain the uniformity quantification information of the tobacco sheet to be measured.

[0037] It can be understood that the present application combines spectral technology with various chemometric algorithms and applies them to the analysis of the quality uniformity of tobacco sheet. While breaking through the spatial resolution limitation of traditional methods, it can also maximize the extraction of spectral information and achieve a more accurate uniformity quantification effect for tobacco sheet.

[0038] Among them, step S1 of obtaining the spectral information to be measured of the tobacco sheet to be measured can include:

[0039] Step A1: Obtain the tobacco sheet to be measured.

[0040] Step A2: Perform near-infrared spectral scanning on the tobacco sheet to be measured to obtain the spectral information to be measured, and the spectral information to be measured includes near-infrared spectral image information.

[0041] Specifically, step A2 includes:

[0042] Step A21: Use the scanned gold-plated lens as the background spectrum and place the tobacco sheet to be measured on the stage.

[0043] Step A22: Perform diffuse reflectance FT-NIR spectral image scanning on the tobacco slice to be measured to obtain the spectral information to be measured.

[0044] Among them, the reference spectral information includes the visible spectral information of the tobacco slice to be measured and the near-infrared spectral information of the standard tobacco slice. The step S1 of obtaining the reference spectral information of the tobacco slice to be measured may include:

[0045] Step B1: Perform visible spectral image scanning on the tobacco slice to be measured to obtain visible spectral information.

[0046] Step B2: Perform near-infrared spectral scanning on the standard tobacco slice to obtain a reference spectral image.

[0047] Exemplarily, the spectral acquisition device is a Spotlight 400 Fourier transform near-infrared imaging system (PerkinElmer, USA), and the system is equipped with a liquid nitrogen-cooled 2×8 element linear array mercury cadmium telluride (MCT) detector.

[0048] In the image mode of the system, use the scanned gold-plated lens as the background spectrum, and set the resolution parameter to 16 cm -1 , and the number of scans is 15 times.

[0049] Place the tobacco slice sample to be measured on the stage, and randomly select multiple regions with the same size of 10000μm×10000μm through the linear array detector of the system to perform visible spectral image and diffuse reflectance FT-NIR spectral image scanning respectively. The wavelength range is 7800 - 4000 cm -1 , the resolution is 16 cm -1 , the number of scans is 2 times, and the pixel size is 25μm×25μm to obtain the spectral information to be measured including the near-infrared spectral image and the reference spectral information including the visible spectral image.

[0050] The near-infrared spectrum of the standard tobacco slice can be collected in the point mode of an ordinary near-infrared spectrometer or a microscopic near-infrared spectrometer, such as Figure 2 shown in the near-infrared spectrum diagram of the standard tobacco slice as the reference spectrum.

[0051] It can be understood that both the ordinary near-infrared spectrometer and the microscopic near-infrared spectrometer obtain standard near-infrared spectra. Among them, the spatial resolution of the ordinary near-infrared instrument is relatively low, the light spot of the infrared light hitting the sample is larger, and the finally obtained is the average spectrum of the light spot area. Here, the near-infrared spectrum diagram of the standard and uniform tobacco slice sample can be collected as the reference spectrum. Because the sample of the standard tobacco slice is itself uniform, it can be considered that there is no difference in the images obtained by these two methods, and those skilled in the art can choose according to actual needs.

[0052] As Figure 3 shown, it can be understood that the visible spectrum image can be popularly regarded as a "photo", which also has spatial resolution. That is to say, the visible spectrum image of the tobacco slice to be measured can be used as a supplement for judging the uniformity of the tobacco slice.

[0053] Exemplarily, if non-uniformity can be seen anywhere in the visible spectrum image, it can be used as a verification or supplement to the uniformity result corresponding to the tobacco slice to be measured. In addition, if the non-uniformity of the tobacco slice cannot be seen in the visible spectrum image, while the near-infrared spectrum of the standard tobacco slice can determine the non-uniformity of the tobacco slice, it can further reflect the superiority of the comparison with another reference spectrum information (the near-infrared spectrum of the standard tobacco slice).

[0054] It can be understood that applying the microscopic near-infrared spectroscopy imaging technology combined with various chemometric methods to the analysis of the quality uniformity of tobacco slices can break through the spatial resolution limitation of traditional methods while maximizing the extraction of spectral information. In addition, the microscopic near-infrared spectroscopy imaging technology combined with various chemometric methods can also simultaneously realize the qualitative and quantitative analysis of the quality uniformity of tobacco slices, with the results being visualized and intuitive and easy to understand.

[0055] Exemplarily, chemometric algorithms can be used to process the spectral information to be measured through Matlab software. That is, five chemometric algorithms, namely the first derivative, the second derivative, Savitzky-Golay convolution smoothing (S-G smoothing), multiplicative scatter correction (MSC), and standard normal variate transformation (SNV), are respectively used to optimize the near-infrared spectrum image of the tobacco slice to be measured to obtain the target near-infrared spectrum image of the tobacco slice to be measured.

[0056] The first derivative can eliminate the random error caused by the translation of the spectral baseline, improve the resolution of the spectrum, make the characteristic peaks in the spectral image more prominent, and be easy to identify.

[0057] The second derivative can eliminate the rotational error of the spectral baseline and further improve the resolution and clarity of the spectrum. Compared with the first derivative, the second derivative is more sensitive to the subtle changes in the spectrum and can reveal more hidden spectral features.

[0058] S-G smoothing is a spectral smoothing method based on polynomial fitting, which can remove the high-frequency noise in the spectrum while retaining the important features of the spectrum. In near-infrared spectroscopy analysis, S-G smoothing is often used in the preprocessing stage to improve the signal-to-noise ratio of the spectrum and the stability of the data.

[0059] MSC is a method for eliminating spectral differences caused by different scattering levels during spectral measurement. In near-infrared spectroscopy analysis, MSC is often used to process spectral data of solid or slurry samples to eliminate the influence of factors such as uneven particle distribution and particle size on the spectrum. Through MSC processing, the baseline drift and offset phenomena in the spectral image are significantly suppressed, improving the accuracy and consistency of spectral data.

[0060] SNV is a method for eliminating the influence of intensity differences and uneven instrument responses by adjusting the scale of spectral data. In near-infrared spectroscopy analysis, SNV is often used to process spectral data of samples with different concentrations or different physical states. Through SNV processing, the intensity differences in the spectral image are eliminated, making the spectral data between different samples comparable.

[0061] Immediately, the near-infrared spectral image of the tobacco sheet to be measured can be deeply mined by chemometric algorithms to make the unobvious peaks very obvious, while removing the influence of noise and retaining useful signals as much as possible.

[0062] Step S3 specifically includes:

[0063] Step S31: According to the spectral similarity algorithm, perform spectral similarity measurement and analysis on the target spectral information and the reference spectral information to obtain a spectral similarity correlation coefficient map.

[0064] Specifically, through three chemometric spectral similarity algorithms, namely the correlation coefficient method, the Euclidean distance method, and the spectral angle method, perform spectral similarity measurement and analysis on the target near-infrared spectral image of the tobacco sheet to be measured and the standard near-infrared spectrum in the reference spectral information.

[0065] ⑴ Correlation Coefficient Method (CCM)

[0066] The correlation coefficient method analyzes the similarity of two spectra by measuring the correlation coefficient between the reference spectrum and the spectrum of a certain pixel point in the spectral image. The calculation formula of the correlation coefficient method is as follows:

[0067]

[0068] where r x,y is the correlation coefficient between the reference spectrum and the spectrum of the pixel point with spatial position coordinates (x, y), and p and S are the reference spectrum and the spectrum of this pixel point respectively. The closer r is to 1, the stronger the linear relationship between the measured spectrum and the reference spectrum.

[0069] ⑵ Spectral Angle Method (SAM)

[0070] The spectral angle method is a spectral similarity measurement method based on projection. It analyzes the similarity between two spectra by measuring the cosine of the angle between the reference spectrum and the spectrum of a pixel in the spectral image, with the aim of analyzing the similarity between the two spectra.

[66] . Since it only considers the direction of the spectral vector, it is insensitive to the spectral absorption intensity. The calculation formula of the spectral angle method is as follows:

[0071]

[0072] where a x,y is the angle between the reference spectrum and the spectrum of the pixel with spatial position coordinates (x, y). The smaller the spectral angle, the higher the similarity between the spectrum to be measured and the reference spectrum, and the stronger the linear relationship.

[0073] ⑶ Euclidean Distance Method (EDM)

[0074] The Euclidean distance method discriminates similarity by calculating the Euclidean distance between two spectra. The Euclidean distance method considers the difference in absorbance, but it is not sensitive to the difference in spectral shape.

[67] . The calculation formula of the Euclidean distance method is as follows:

[0075]

[0076] where d x,y is the Euclidean distance between the reference spectrum and the spectrum of the pixel with spatial position coordinates (x, y). The smaller the Euclidean distance, the higher the similarity between the spectrum to be measured and the reference spectrum, and the stronger the linear relationship.

[0077] A standard near-infrared spectrum (one) and a microscopic spectrum group (1600 target near-infrared spectral images in one area) are subjected to similarity measurement analysis, and finally a spectral similarity correlation coefficient map is obtained.

[0078] As Figure 4 shown, based on the spectral similarity correlation coefficient map, a reconstructed spectral similarity correlation coefficient map is constructed on a two-dimensional plane. According to the reconstructed spectral similarity correlation coefficient map, the position information of the standard tobacco slice and the tobacco slice to be measured can be made to correspond one by one in the space of the two-dimensional plane.

[0079] That is to say, according to the spectral reconstruction map, it is possible to know which pixel specifically and which position in space it is, and the magnitude of its correlation with the infrared spectral map of the standard tobacco slice, and then it is known which position in the acquisition area of the tobacco slice to be measured is uneven.

[0080] Step S32: According to a preset uniformity threshold, perform binary image processing on the spectral similarity correlation coefficient map to obtain a binary spectral similarity correlation coefficient map.

[0081] Exemplarily, the uniformity threshold is characterized as 1 if it is 100% similar to the standard infrared spectrogram and 0 if it is completely dissimilar, that is, the setting range of the uniformity threshold is between 0 and 1. In practical applications, the qualified range can be set as needed. If the uniformity threshold is set to be above 0.75, it is considered to be uniform.

[0082] As Figure 5 shown, by setting the threshold of the correlation coefficient, the correlation coefficient map of spectral similarity is binarized to construct a binarized map of the correlation coefficient of spectral similarity.

[0083] Step S33: Based on the binarized map of the correlation coefficient of spectral similarity, perform qualitative analysis and / or quantitative analysis on the tobacco sheet to be measured, and obtain the uniformity information corresponding to the tobacco sheet to be measured.

[0084] According to the binarized map of the correlation coefficient of spectral similarity, it can be determined whether the site uniformity of the tobacco sheet to be measured is qualified, and rapid qualitative analysis of the uniformity of the tobacco sheet to be measured can be realized.

[0085] In addition, in combination with the traversal method, all regions of the entire tobacco sheet to be measured can be traversed, and the area with uneven quality can be calculated, so as to realize the quantitative analysis of the uniformity of the tobacco sheet to be measured.

[0086] Based on the same inventive concept, the present application also provides a device for quantifying the uniformity of tobacco sheets, which includes: an acquisition module, a processing module, and a quantification module.

[0087] The acquisition module is used to acquire the spectral information to be measured and the reference spectral information of the tobacco sheet to be measured.

[0088] The processing module is used to process the spectral information to be measured based on chemometric algorithms to obtain target spectral information.

[0089] The quantification module is used to perform uniformity quantification analysis processing on the target spectral information based on the reference spectral information to obtain the uniformity quantification information of the tobacco sheet to be measured.

[0090] Specifically, the acquisition module is further used to acquire the tobacco sheet to be measured; perform near-infrared spectral scanning on the tobacco sheet to be measured to obtain the spectral information to be measured, and the spectral information to be measured includes near-infrared spectral image information.

[0091] The acquisition module is further used to use the scanned gold-plated lens as the background spectrum, place the tobacco sheet to be measured on the stage; perform diffuse reflection FT-NIR spectral image scanning on the tobacco sheet to be measured to obtain the spectral information to be measured.

[0092] The acquisition module is further configured to perform visible spectrum image scanning on the tobacco slice to be measured to obtain visible spectrum information, and perform near-infrared spectrum scanning on the standard tobacco slice to obtain a reference spectrum image.

[0093] The quantization module is further configured to perform spectral similarity measurement analysis on the target spectrum information and the reference spectrum information according to the spectral similarity algorithm to obtain a spectral similarity correlation coefficient map; perform binary image processing on the spectral similarity correlation coefficient map according to a preset uniformity threshold to obtain a binary image of the spectral similarity correlation coefficient; and perform qualitative analysis and / or quantitative analysis on the tobacco slice to be measured based on the binary image of the spectral similarity correlation coefficient to obtain the uniformity information corresponding to the tobacco slice to be measured.

[0094] It can be understood that the tobacco slice uniformity quantization device provided in this application corresponds to the tobacco slice uniformity quantization method provided in this application. For the sake of brevity of the specification, the same or similar parts can refer to the content of the tobacco slice uniformity quantization method section, which will not be elaborated here.

[0095] Each module in the above tobacco slice uniformity quantization device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the server in hardware form or independent of the processor, or stored in the memory in the server in software form, so that the processor can call and execute the operations corresponding to the above modules. The processor can be a central processing unit (CPU), a microprocessor, a single-chip microcomputer, etc.

[0096] The above tobacco slice uniformity quantization method and / or tobacco slice uniformity quantization device can be implemented in the form of a computer-readable instruction, and the computer-readable instruction can run on a computer system.

[0097] An embodiment of this application further provides a computer system, including a memory, a processor, and a computer-readable instruction stored on the memory and executable on the processor. When the processor executes the program, the above tobacco slice uniformity quantization method is implemented.

[0098] The computer system can be a server. The computer system includes a processor, a non-volatile storage medium, an internal memory, an input device, a display screen, and a network interface connected through a system bus. Among them, the non-volatile storage medium of the computer system can store an operating system and a computer-readable instruction. When the computer-readable instruction is executed, the processor can execute a tobacco slice uniformity quantization method in various embodiments of this application. The specific implementation process of this method can refer to Figure 1 the specific content, which will not be elaborated here.

[0099] The processor of the computer system is used to provide computing and control capabilities to support the operation of the entire computer system. Computer-readable instructions can be stored in the internal memory. When the computer-readable instructions are executed by the processor, the processor can execute a method for quantifying the uniformity of tobacco sheets. The input device of the computer system is used for inputting various parameters, the display screen of the computer system is used for display, and the network interface of the computer system is used for network communication.

[0100] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, on which computer-readable instructions are stored. When the program is executed by the processor, the steps in the above method for quantifying the uniformity of tobacco sheets are implemented.

[0101] The memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DR RAM).

[0102] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0103] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context.

[0104] In this application, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0105] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0106] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0107] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0108] In several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical, or other forms.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] In addition, the functional units in each embodiment of this application can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0111] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0112] The terms and expressions used herein are for descriptive purposes only, and this application should not be limited to these terms and expressions. Using these terms and expressions does not mean excluding any equivalent features of the illustration and description (or parts thereof). It should be recognized that various possible modifications should also be included within the scope of the claims. Other modifications, variations, and substitutions may also exist. Correspondingly, the claims should be regarded as covering all such equivalents.

[0113] Similarly, it should be noted that although this application has been described with reference to current specific embodiments, those of ordinary skill in the art should recognize that the above embodiments are only used to illustrate this application. Various equivalent changes or substitutions can be made without departing from the spirit of the invention. Therefore, as long as the changes and variations of the above embodiments are within the scope of the spirit of this application, they will fall within the scope of the claims of this application.

Claims

1. A method for quantifying uniformity of tobacco sheets, characterized in that: The tobacco sheet uniformity measurement method comprises: Step S1: obtaining spectrum information to be tested and reference spectrum information of the tobacco slice to be tested; Step S2: Processing the spectrum information to be measured based on a chemometric algorithm to obtain target spectrum information; Step S3: Based on the reference spectrum information, the target spectrum information is subjected to uniformity quantitative analysis and processing to obtain uniformity quantitative information of the tobacco sheet to be tested.

2. The method for quantifying uniformity of tobacco sheets according to claim 1, characterized in that: The step S1 comprises: Step A1: obtaining the tobacco slice to be tested; Step A2: performing near-infrared spectrum scanning on the tobacco slice to be tested to obtain the spectrum information to be tested, wherein the spectrum information to be tested includes near-infrared spectrum image information.

3. The method for quantifying uniformity of tobacco sheets according to claim 2, characterized in that: The step A2 comprises: Step A21: placing the tobacco slice to be tested on a stage while scanning the gold-coated lens as a background spectrum; Step A22: performing diffuse reflectance FT-NIR spectrum image scanning on the tobacco slice to be tested to obtain the spectrum information to be tested.

4. The method for quantifying uniformity of tobacco sheets according to claim 1, characterized in that: The reference spectrum information includes the visible spectrum information of the tobacco sheet to be tested and the near infrared spectrum information of the standard tobacco sheet, and the step S1 includes: Step B1: scanning the visible spectrum image of the tobacco slice to be tested to obtain the visible spectrum information; Step B2: performing near-infrared spectral scanning on the standard tobacco sheet to obtain the reference spectral image.

5. The method for quantifying uniformity of tobacco sheets according to claim 1, characterized in that: The chemometrics algorithm includes at least any one of the following: first-order derivative, second-order derivative, Savitzky-Golay convolution smoothing, multivariate scattering correction and standard normal variate transformation.

6. The method for quantifying uniformity of tobacco sheets according to claim 1, characterized in that: The step S3 comprises: Step S31: performing spectral similarity measurement analysis on the target spectral information and the reference spectral information according to a spectral similarity algorithm to obtain a spectral similarity correlation coefficient graph; Step S32: performing binarization image processing on the spectral similarity correlation coefficient map according to a preset uniformity threshold value to obtain a spectral similarity correlation coefficient binarization map; Step S33: Based on the spectral similarity correlation coefficient binarization graph, qualitative analysis and / or quantitative analysis is performed on the tobacco slice to be tested to obtain uniformity information corresponding to the tobacco slice to be tested.

7. A tobacco sheet uniformity quantification device, characterized in that: The tobacco sheet uniformity quantification device comprises: an acquisition module, a processing module and a quantification module. The acquisition module is used to acquire the spectrum information to be tested and the reference spectrum information of the tobacco slice to be tested; The processing module is used to process the spectrum information to be measured based on a chemometric algorithm to obtain target spectrum information; The quantification module is used to perform uniformity quantitative analysis on the target spectrum information based on the reference spectrum information to obtain uniformity quantitative information of the tobacco sheet to be tested.

8. A computer system, comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the tobacco sheet uniformity quantification method of claim 1.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: The computer program / instructions implement the tobacco sheet uniformity quantification method of claim 1 when executed by a processor.

10. A computer program product comprising a computer program / instructions, characterized in that The computer program / instructions implement the tobacco sheet uniformity quantification method of claim 1 when executed by a processor.

Images