Method and system for identifying processed products and origin of Fructus Aurantii Immaturus based on hyperspectral imaging

Abstract

The present invention relates to a method and system for identifying processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging, the method comprising: acquiring hyperspectral data of processed Fructus Aurantii Immaturus samples; extracting regions of interest after correction of the collected hyperspectral data, obtaining average reflectance spectral data of processed Fructus Aurantii Immaturus samples as original spectral data; preprocessing the original spectral data; performing first-order derivative processing on the preprocessed original spectral data, screening characteristic bands of processed Fructus Aurantii Immaturus spectral data according to the first-order derivative to construct a characteristic index, and obtaining a processed Fructus Aurantii Immaturus product identification index PFAI; using a random forest modeling method, using PFAI data to construct a processed Fructus Aurantii Immaturus product identification model to identify processed Fructus Aurantii Immaturus products and their origins. The present invention can realize rapid, non-destructive, and low-cost identification of different processed products.

Description

Technical Field

[0001] The present invention relates to a method and system for identifying processed products and origin of Citrus aurantium based on hyperspectral imaging, and relates to the technical field of Citrus aurantium identification and authentication. Background Art

[0002] Citrus aurantium mainly comes from the dried immature fruit of the Rutaceae plant Citrus aurantium L. and its cultivated varieties. It is usually harvested in July every year when the peel is still green, cut into two halves from the middle, and dried in the sun or at low temperature. It is suitable for chest and diaphragm fullness and other symptoms.

[0003] Due to the different processing methods, the medicinal efficacy and quality of the produced Citrus aurantium have great differences. This difference requires very experienced people and very professional methods to distinguish the difference. The modern processing of Citrus aurantium is mainly fried with bran, but each place also has its own unique processing method. As a local medicinal material in Jiangxi, Citrus aurantium has unique processing methods.

[0004] At present, there have been studies on the differences in chemical components of processed Fructus Aurantii Immaturus, which provide a reference for the identification of processed Fructus Aurantii Immaturus. However, the existing methods are costly and require destructive treatment of samples. Summary of the invention

[0005] In view of the above problems, the object of the present invention is to provide a method, system, equipment and storage medium for rapid and non-destructive detection of processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for identifying processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging, comprising:

[0008] Obtaining hyperspectral data of processed samples of Fructus Aurantii Immaturus;

[0009] After correcting the collected hyperspectral data, the region of interest is extracted to obtain the average reflectance spectral data of the processed Fructus Aurantii Immaturus samples as the original spectral data;

[0010] Preprocess the raw spectral data;

[0011] The first-order derivative processing was performed on the original spectral data after preprocessing, and the characteristic bands of the spectral data of processed Fructus Aurantii Immaturus were screened according to the first-order derivative to construct a characteristic index, and the processed Fructus Aurantii Immaturus Identification Index (PFAI) was obtained.

[0012] The random forest modeling method was used to construct an identification model for processed Fructus Aurantii Immaturus products using PFAI data to identify processed Fructus Aurantii Immaturus products and their origins.

[0013] Furthermore, the hyperspectral data of the processed samples of Fructus Aurantii Immaturus were obtained, including:

[0014] A hyperspectral imaging spectrometer was used to collect full-band hyperspectral data of processed Citrus aurantium samples at 410-990nm and 950-2500nm.

[0015] Furthermore, the collected hyperspectral data is corrected, including: the hyperspectral data is corrected by RAD correction and black and white plate correction.

[0016] Furthermore, ENVI5.5.3 software was used to extract the region of interest from the corrected hyperspectral image.

[0017] Furthermore, the raw spectral data were preprocessed using multivariate scatter correction.

[0018] Furthermore, the processed Fructus Aurantii Immaturus product identification index PFAI was constructed by screening out the characteristic bands of the spectral data of processed Fructus Aurantii Immaturus according to the peak-valley values ​​of the original spectral data and the peak-valley values ​​of the first-order derivative curve.

[0019] Furthermore, based on 410-990nm and 950-2500nm, the origin of Fructus Aurantii Immaturus was identified. Among the 336 hyperspectral bands, the 20 first-order derivatives PFAIⅡ of 21 bands, including "band31, band 38, band 44, band 48, band 52, band67, band76, band 79, band 81, band 88, band 96, band 130, band 169, band 176, band 181, band195, band 202, band 214, band 233, band 238, and band 266", were used to construct the RF model:

[0020] RandomForestClassifier(n_estimators=151, max_depth=10, min_samples_split=10, rand om_state=90).

[0021] In a second aspect, the present invention also provides a system for identifying processed Fructus Aurantii Immaturus products and origins based on hyperspectral imaging, the system comprising:

[0022] A data acquisition unit is configured to acquire hyperspectral data of a processed sample of Fructus Aurantii Immaturus;

[0023] The correction and extraction unit is configured to extract the region of interest after correction of the collected hyperspectral data, and obtain the average reflectance spectral data of the processed Fructus Aurantii Immaturus sample as the original spectral data;

[0024] A preprocessing unit is configured to preprocess the raw spectral data;

[0025] The PFAI construction unit is configured to perform first-order derivative processing on the pre-processed original spectral data, screen the characteristic bands of the spectral data of the processed Fructus Aurantii Immaturus according to the first-order derivative to construct a characteristic index, and obtain the processed Fructus Aurantii Immaturus ...

[0026] The identification unit is configured to use a random forest modeling method to construct an identification model for processed Fructus Aurantii Immaturus products using PFAI data to identify processed Fructus Aurantii Immaturus products and their origins.

[0027] In a third aspect, the present invention further provides an electronic device, which includes at least a processor and a memory, wherein a computer program is stored in the memory, and when the processor runs the computer program, the computer program is executed to implement the method described.

[0028] In a fourth aspect, the present invention also provides a computer storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions can be executed by a processor to implement the described method.

[0029] Due to the adoption of the above technical solution, the present invention has the following advantages: the present invention can simultaneously obtain the image and spectral information of the research object through hyperspectral imaging, which can provide an important reference for the identification and prediction of the research object. Compared with traditional identification methods, hyperspectral imaging technology, as a non-destructive testing technology, has been widely used in research directions such as drug quality control, and can realize rapid, non-destructive and low-cost identification of different processed products. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Throughout the accompanying drawings, the same reference numerals are used to represent the same components. In the accompanying drawings:

[0031] Figure 1 (a) is the average spectrum curve at 410-990nm of the embodiment of the present invention;

[0032] Figure 1 (b) is the average spectrum curve at 950-2500nm of the embodiment of the present invention;

[0033] Figure 2 (a) is the first-order derivative curve at 410-990 nm of an embodiment of the present invention;

[0034] Figure 2 (b) is the first-order derivative curve at 950-2500 nm of the embodiment of the present invention. DETAILED DESCRIPTION

[0035] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0036] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0037] Although the terms first, second, third, etc. can be used in the text to describe multiple elements, components, regions, layers and / or sections, these elements, components, regions, layers and / or sections should not be limited by these terms. These terms can only be used to distinguish an element, component, region, layer or section from another region, layer or section. Unless the context clearly indicates, terms such as "first", "second" and other numerical terms do not imply order or sequence when used in the text. Therefore, the first element, component, region, layer or section discussed below can be referred to as the second element, component, region, layer or section without departing from the teaching of the example embodiments.

[0038] For ease of description, spatially relative terms may be used herein to describe the relationship of one element or feature relative to another element or feature as shown in the figures, such as "inside", "outside", "inner side", "outer side", "below", "above", etc. Such spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation depicted in the figures.

[0039] Embodiment 1: The method for identifying processed products and origins of Citrus aurantium based on hyperspectral imaging provided in this embodiment uses hyperspectral imaging technology to quickly identify different processed products and origins of Citrus aurantium of the traditional Chinese medicine. The identification process includes:

[0040] S1. Obtaining hyperspectral data of processed samples of Fructus Aurantii Immaturus

[0041] Specifically, a hyperspectral imaging spectrometer was used to collect full-band hyperspectral data of the processed Fructus Aurantii Immaturus samples at 410-990nm and 950-2500nm.

[0042] S2. Perform RAD correction and black and white plate correction on the collected hyperspectral data, extract the region of interest, and obtain the average reflectance spectral data of the processed Fructus Aurantii Immaturus samples as the original spectral data.

[0043] In some implementations, before extracting the area of ​​interest, in order to eliminate the influence of environmental light sources and other factors on the noise generated by the image, the collected hyperspectral data is subjected to RAD correction and black and white plate correction. The RAD correction software provided by the hyperspectral instrument can be used to correct the original hyperspectral data and then perform black and white plate correction.

[0044] Specifically, ENVI5.5.3 software was used to extract the region of interest from the corrected hyperspectral image, and the average reflectance was calculated as the original spectral data.

[0045] S3. Preprocessing of raw spectral data using multivariate scatter correction (MSC)

[0046] Specifically, in order to eliminate the influence of factors such as the sample itself, the environment and the instrument on the spectral data, the original spectral data can be preprocessed by using Multiplicative Scatter Correction (MSC).

[0047] S4. Perform first-order derivative processing on the pre-processed original spectral data, and select the characteristic bands of the spectral data of processed Fructus Aurantii according to the first-order derivative to construct a characteristic index to obtain the processed products of Fructus Aurantii recognition index PFAI

[0048] Specifically, the characteristic bands of the spectral data of the processed Fructus Aurantii Immaturus can be screened out according to the peak-valley values ​​of the original spectral data and the peak-valley values ​​of the curve after the first-order derivative, and a characteristic index can be constructed to obtain the processed Fructus Aurantii Immaturus identification index PFAI. This embodiment constructs PFAIⅠ in the range of 410 to 990 nm and PFAIⅡ in the range of 950 to 2500 nm.

[0049] S5. Use the random forest (RF) modeling method to build a processing model for identifying Fructus Aurantii Immaturus products using PFAI data to identify Fructus Aurantii Immaturus processed products and their origins

[0050] RF is an ensemble learning method with good generalization and anti-overfitting capabilities. It generates a highly accurate classifier by integrating multiple decision trees and can process input samples with high-dimensional features without dimensionality reduction.

[0051] Specifically, a random forest (RF) algorithm can be used to construct a processed Fructus Aurantii Immaturus identification model for the data in the full band range and under PFAI. The random forest RF algorithm uses a simple cross-validation method to construct a processed Fructus Aurantii Immaturus identification model for the data in the full band and under PFAI. The specific process includes: (1) modeling and observing the performance of the model on the data set; (2) adjusting the parameter n_estimators to determine the number of trees in the forest, and then adjusting the parameters one by one through GridSearchCV. By adjusting max_depth, min_samples_leaf, min_samples_split, max_features, and criterion, the model accuracy is continuously improved; (3) finally determining the best parameter combination based on the actual situation. The above random forest algorithm is used as the existing technology and will not be elaborated on.

[0052] The identification process of the processed Fructus Aurantii Immaturus product and the method for identifying the origin based on hyperspectral imaging of the present invention is described in detail below through specific embodiments.

[0053] This embodiment takes the processed Fructus Aurantii Immaturus of the traditional Chinese medicine as the object, and uses the hyperspectral imaging technology to establish a more accurate recognition model for the processed Fructus Aurantii Immaturus of the traditional Chinese medicine.

[0054] The processed Fructus Aurantii Immaturus used in the experiment of this embodiment is from four origins (Jiangxi, Hunan, Zhejiang and Sichuan), and each origin has four processed products (fried Fructus Aurantii Immaturus with bran, roasted Fructus Aurantii Immaturus with honey, camphor (tree) method and Jianchang method). All samples were processed and provided by Jiangxi Tongshantang Chinese Medicine Pieces Co., Ltd., totaling 48 batches, 15 samples were selected from each batch, totaling 720 processed Fructus Aurantii Immaturus.

[0055] 1. Hyperspectral data collection

[0056] The instrument used in this experiment is a hyperspectral imaging device, the HySpex series hyperspectral imaging spectrometer, which is mainly composed of two halogen tungsten lamps, a CCD detector and two lenses. The instrument comes with a computer and built-in related processing software.

[0057] This embodiment uses SN0605VNIR lens (410-990nm) and N3124SWIR lens (950-2500nm) to obtain hyperspectral data, with a spectral resolution of 6nm and spectral band numbers of 108 and 288, respectively. Before acquisition, adjust the system parameters, keep the external environment consistent as much as possible, place the Citrus aurantium samples on the mobile platform and scan them in sequence to obtain the original hyperspectral image.

[0058] In order to eliminate the influence of the instrument on the data, the original hyperspectral data was corrected using the instrument's own RAD correction software and then the black and white plate correction was performed to eliminate the influence of environmental light sources and other factors on the noise generated by the image. The calculation formula is as follows:

[0059]

[0060] In the formula, R represents the corrected image, I R represents the original image, I W represents the whiteboard image, I B Represents a blackboard image.

[0061] 2. Spectral data preprocessing

[0062] 2.1. Selection of Region of Interest

[0063] ENVI5.5.3 software was used to extract the region of interest from the corrected hyperspectral image and calculate the average reflectance, and the average reflectance data of 720 samples were obtained as the original spectral data.

[0064] 2.2 Spectral data preprocessing

[0065] Multivariate scatter correction (MSC) was used to preprocess the raw spectral data.

[0066] 3. Construction of characteristic index

[0067] In order to simplify the complexity of the modeling process and improve the accuracy of the model, this embodiment combines the change characteristics of the spectral curve of the object under study, performs first-order derivative processing on the original spectral data, and screens out the characteristic bands of the spectral data of the processed Fructus Aurantii Immaturus according to the peak-valley values ​​of the original spectral data and the peak-valley values ​​of the curve after the first-order derivative, and constructs a characteristic index to obtain the processed Fructus Aurantii Immaturus Immaturus Identification Index PFAI.

[0068] 4. Use RF to build a recognition model for processed Fructus Aurantii Immaturus to identify processed Fructus Aurantii Immaturus and its origin

[0069] 5. Results and Discussion

[0070] 5.1 Spectral curve analysis

[0071] The average reflectance of all samples of four kinds of processed products (720 samples, 48 ​​batches) from four production areas were averaged to obtain 16 groups of average spectral curves.

[0072] like Figure 1As shown in the figure, from 410 to 990 nm, the spectral curves of the processed products in Hunan and Zhejiang have similar changing trends and are generally rising; the spectral curves of the processed products in Jiangxi and Sichuan have mostly the same changing trends, and the curves fluctuate between 648.79 nm (band45) and 686.71 nm (band52). The changes in the spectral curve can reflect the composition structure and content of the substances contained in it. The reflectivity of green plants increases greatly between 670 and 760 nm. This phenomenon is called the "red edge effect". The red edge is the point where the reflectivity increases fastest in this interval, and it is also the inflection point of the first-order derivative of the spectrum in this interval, which is 686.71 nm (band52). From 950 to 2500 nm, the spectral curve fluctuates significantly. In 1204.89 nm (band48) to 1308.44 nm (band67) and 1902.53 nm (band176) to 2109.65 nm (band214), the differences between the curves of each category are relatively obvious.

[0073] 5.2. PFAI construction results

[0074] Taking the mean spectrum curve as an example, Figure 2 for Figure 1 Finally, 20 characteristic bands were selected from 410 to 990 nm, and 21 characteristic bands were selected from 950 to 2500 nm, and characteristic indexes PFAI were constructed respectively. 19 PFAIⅠ were obtained from 410 to 990 nm, and 20 PFAIⅡ were obtained from 950 to 2500 nm (Rn is the reflectivity value, n is the number of bands). The characteristic index calculation formula is the difference between the reflectivity of adjacent characteristic bands divided by the sum of the reflectivity of adjacent characteristic bands, as shown in Table 1:

[0075] Table 1 Identification index of processed Fructus Aurantii Ii and PFAI II

[0076]

[0077] 5.3. Using the RF method and simple cross-validation method, a drug identification model was constructed for the data under full band and PFAI respectively.

[0078] The identification of processed Fructus Aurantii Immaturus from various origins is as follows: processed products from Zhejiang and Hunan have relatively higher identification accuracy, among which processed products from Zhejiang have the best identification, with an average identification accuracy of 89% for processed products from Zhejiang at 410-990nm and 96% for processed products from Zhejiang at 950-2500nm. Although the identification rate of processed products from Jiangxi and Sichuan is relatively low in the full band, the identification accuracy under the characteristic index PFAI is significantly improved. The identification accuracy of processed Fructus Aurantii Immaturus from various origins is 94% on average. The origin identification of processed Fructus Aurantii Immaturus from various origins is as follows: Jianchang Bangfa Fructus Aurantii Immaturus and glutinous fried Fructus Aurantii Immaturus have relatively better origin identification rates. At 410-990nm, the origin recognition rate of the fried Citrus aurantium with bran was the highest, averaging 90%; at 950-2500nm, the origin recognition rate of the Citrus aurantium processed by Jianchang Bang method was the highest, averaging 97%. The accuracy rate of origin recognition in various Citrus aurantium processed products was 88% on average. Finally, among the 336 hyperspectral bands, it was determined to use "band31 (572.93nm, 1112.22nm), band 38 (610.86nm, 1150.38nm), band 44 (643.36nm, 1183.08nm), band 48 (665.03nm, 1204.885742nm), band 52 (686.70nm, 1226.68nm), band 67 (767.97nm, 1308.44nm), band 76 (816.73nm, 1357.49nm), band 79 (832.98nm, 1373.84nm), band 81 (843.82nm, 1384.74nm), band 88 (881.74nm, 1422.90nm), band Band 96 (925.08nm, 1466.50nm), band 130 (1651.81nm), band 169 (1864.37nm), band 176 (1902.53nm), band 181 (1929.78nm), band 195 (2006.08nm), band 202 (2044.24nm), band 214 (2109.64nm), band233 (2213.20nm), band 238 (2240.45nm), band 266 (2393.06nm)" bands, a total of 21 bands of 20 first-order derivatives PFAIⅡ, to build the RF model:

[0079] RandomForestClassifier(n_estimators=151,max_depth=10,min_samples_split=10,random_state=90) can realize the identification of different processing and origin of Citrus aurantium, and provide a fast and lossless identification method for the identification of Citrus aurantium processed products.

[0080] Embodiment 2: Embodiment 1 above provides a method for identifying processed Fructus Aurantii Immaturus products based on hyperspectral imaging. Correspondingly, this embodiment provides a system for identifying processed Fructus Aurantii Immaturus products based on hyperspectral imaging. The system provided in this embodiment can implement the method for identifying processed Fructus Aurantii Immaturus products based on hyperspectral imaging of Embodiment 1, and the system can be implemented by software, hardware, or a combination of software and hardware. For the convenience of description, this embodiment is described in various units according to their functions. Of course, the functions of each unit can be implemented in the same or more software and / or hardware during implementation. For example, the system may include integrated or separate functional modules or functional units to perform the corresponding steps in each method of Embodiment 1. Since the system of this embodiment is basically similar to the method embodiment, the description process of this embodiment is relatively simple, and the relevant parts can refer to the partial description of Embodiment 1. The embodiment of the system for identifying processed Fructus Aurantii Immaturus products based on hyperspectral imaging provided by the present invention is only schematic.

[0081] This embodiment provides a system for identifying processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging, characterized in that the system comprises:

[0082] A data acquisition unit is configured to acquire hyperspectral data of a processed sample of Fructus Aurantii Immaturus;

[0083] The correction and extraction unit is configured to extract the region of interest after correction of the collected hyperspectral data, and obtain the average reflectance spectral data of the processed Fructus Aurantii Immaturus sample as the original spectral data;

[0084] A preprocessing unit is configured to preprocess the raw spectral data;

[0085] The PFAI construction unit is configured to perform first-order derivative processing on the pre-processed original spectral data, screen the characteristic bands of the spectral data of the processed Fructus Aurantii Immaturus according to the first-order derivative to construct a characteristic index, and obtain the processed Fructus Aurantii Immaturus ...

[0086] The identification unit is configured to use a random forest modeling method to construct an identification model for processed Fructus Aurantii Immaturus products using PFAI data to identify processed Fructus Aurantii Immaturus products and their origins.

[0087] Embodiment 3: This embodiment provides an electronic device corresponding to the method for identifying processed Fructus Aurantii Immaturus products based on hyperspectral imaging provided in Embodiment 1. The electronic device may be an electronic device for a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the method of Embodiment 1.

[0088] The electronic device includes a processor, a memory, a communication interface and a bus, and the processor, the memory and the communication interface are connected through the bus to complete the communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Component (EISA) bus, etc. The memory stores a computer program that can be run on the processor, and the processor executes the method for identifying the processed Fructus Aurantii Immaturus products based on hyperspectral imaging provided in the first embodiment.

[0089] In some implementations, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), optical disk and other media that can store program codes.

[0090] In some other implementations, the processor may be a central processing unit (CPU), a digital signal processor (DSP), or other general-purpose processors of various types, which are not limited herein.

[0091] Embodiment 4: The method for identifying processed Fructus Aurantii Immaturus products based on hyperspectral imaging of the embodiment 1 may be specifically implemented as a computer program product, which may include a computer-readable storage medium carrying computer-readable program instructions for executing the method for identifying processed Fructus Aurantii Immaturus products based on hyperspectral imaging described in the embodiment 1.

[0092] Computer readable storage media can be tangible devices that hold and store instructions used by instruction execution devices. Computer readable storage media can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any combination thereof.

[0093] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some implementations", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging, characterized in that: include: Obtaining hyperspectral data of processed samples of Fructus Aurantii Immaturus; After correcting the collected hyperspectral data, the region of interest is extracted to obtain the average reflectance spectral data of the processed Fructus Aurantii Immaturus samples as the original spectral data; Preprocess the raw spectral data; According to the peak-valley values ​​of the original spectral data and the peak-valley values ​​of the first-order derivative curve, the characteristic bands of the spectral data of the processed Fructus Aurantii Immaturus were screened out to construct the identification index PFAI of the processed Fructus Aurantii Immaturus ... The random forest modeling method was used to construct an identification model for processed Fructus Aurantii Immaturus products using PFAI data to identify processed Fructus Aurantii Immaturus products and their origins.

2. The method for identifying processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging according to claim 1, characterized in that: Obtain hyperspectral data of processed samples of Fructus Aurantii Immaturus, including: A hyperspectral imaging spectrometer was used to collect full-band hyperspectral data of processed Fructus Aurantii Immaturus samples at 410~990nm and 950~2500nm.

3. The method for identifying processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging according to claim 1, characterized in that: The collected hyperspectral data are corrected, including: the hyperspectral data are corrected by RAD correction and black and white plate correction.

4. The method for identifying processed Fructus Aurantii Immaturus products and origins based on hyperspectral imaging according to claim 1, characterized in that: ENVI5.5.3 software was used to extract the region of interest from the corrected hyperspectral image.

5. The method for identifying processed Fructus Aurantii Immaturus products and origins based on hyperspectral imaging according to claim 1, characterized in that: Multivariate scattering correction was used to preprocess the raw spectral data.

6. The method for identifying processed Fructus Aurantii Immaturus products and origins based on hyperspectral imaging according to claim 1, characterized in that: Based on 410-990nm and 950-2500nm, the origin of Fructus Aurantii Immaturus was identified. Among the 336 hyperspectral bands, the bands "band31, band 38, band 44, band 48, band 52, band 67, band 76, band 79, band81, band 88, band 96, band 130, band 169, band 176, band 181, band 195, band 202, band214, band 233, band 238, band 266" were determined, and the RF model was constructed using 20 first-order derivatives PFAIⅡ of 21 bands: RandomForestClassifier(n_estimators=151,max_depth=10,min_samples_split=10,random_state=90).

7. A system for identifying processed Fructus Aurantii Immaturus products and their origins based on hyperspectral imaging, characterized in that: A data acquisition unit is configured to acquire hyperspectral data of a processed sample of Fructus Aurantii Immaturus; The correction and extraction unit is configured to extract the region of interest after correcting the collected hyperspectral data, and obtain the average reflectance spectral data of the processed Fructus Aurantii Immaturus sample as the original spectral data; A preprocessing unit is configured to preprocess the raw spectral data; The PFAI construction unit is configured to select characteristic bands of the spectral data of the processed Fructus Aurantii Immaturus according to the peak-valley values ​​of the original spectral data and the peak-valley values ​​of the first-order derivative curve to construct the processed Fructus Aurantii Immaturus ... The identification unit is configured to use a random forest modeling method to construct an identification model for processed Fructus Aurantii Immaturus products using PFAI data to identify processed Fructus Aurantii Immaturus products and their origins.

8. An electronic device, comprising at least a processor and a memory, wherein a computer program is stored in the memory, wherein: When the processor runs the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer storage medium, characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement the method according to any one of claims 1 to 6.

Images