CN112067578A - Rapid identification system and identification method for corn seeds - Google Patents
Rapid identification system and identification method for corn seeds Download PDFInfo
- Publication number
- CN112067578A CN112067578A CN202010845303.9A CN202010845303A CN112067578A CN 112067578 A CN112067578 A CN 112067578A CN 202010845303 A CN202010845303 A CN 202010845303A CN 112067578 A CN112067578 A CN 112067578A
- Authority
- CN
- China
- Prior art keywords
- infrared spectrum
- corn seeds
- corn
- detected
- near infrared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 240000008042 Zea mays Species 0.000 title claims abstract description 105
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 title claims abstract description 105
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 105
- 235000005822 corn Nutrition 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 66
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 13
- 238000005259 measurement Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000004451 qualitative analysis Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000004611 spectroscopical analysis Methods 0.000 description 2
- 238000004497 NIR spectroscopy Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001962 electrophoresis Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000000103 photoluminescence spectrum Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000000985 reflectance spectrum Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
- G01N2201/1296—Using chemometrical methods using neural networks
Abstract
The invention discloses a rapid identification system and method for corn seeds, which comprises the following steps: the detection unit is used for measuring a standard corn seed by using a near-infrared spectrometer to obtain a near-infrared spectrum of the standard corn seed, performing integral calculation on the near-infrared spectrum of the standard corn seed to obtain an integral signal of the near-infrared spectrum of the standard corn seed, training a base pair neural network by using the execution unit to obtain a base pair neural network structure, measuring the corn seed to be measured by using the near-infrared spectrometer by using the unit to be measured to obtain the near-infrared spectrum of the corn seed to be measured, performing integral calculation to obtain the integral signal of the near-infrared spectrum of the corn seed to be measured, and identifying the corn seed to be measured by using the base pair neural network obtained in the execution unit by using the identification unit to obtain an identification result.
Description
Technical Field
The invention relates to the field of crop seed identification, in particular to a rapid identification system for corn seeds and an identification method thereof.
Background
Crop seed identification is an important problem in current agricultural production, crop breeding and seed testing. Due to the increasing phenomena of counterfeit and shoddy seeds for sale and production, the economic loss caused each year is huge. Meanwhile, because variety identification is difficult, huge economic losses are caused by variety mistake and poor purity every year. Therefore, crop seed identification is increasingly paid attention by seed quality control departments, crop seed breeding research and other units. At present, the common methods for identifying crop seeds at home and abroad mainly comprise a morphological method, a chemical identification method, an electrophoresis identification method, a seedling identification method, a field plot planting identification method, a DNA molecular marking method and the like. However, the above methods for identifying crop seeds have some disadvantages, such as: the precision is not high, the operation process is complicated, the efficiency is low, non-professionals are difficult to perform, and the method is not suitable for batch analysis, nondestructive online detection and the like of samples. Therefore, it is necessary to establish a set of simple, fast, efficient, economic and highly accurate crop seed identification technology.
The spectrum technology is more and more widely applied in various industries due to the characteristics of rapidness, wide coverage and the like, and the development of the spectrum technology provides a new technical means for the identification of the corn seeds. The method for identifying the corn seeds by utilizing the spectrum has the characteristics of high speed, high efficiency, low cost, good test reproducibility, convenience in measurement and the like. At present, the spectral technology is mainly used for identifying corn seeds: visible/near infrared spectra, photoluminescence spectra, diffuse reflectance spectra, hyperspectral imaging techniques, etc. However, these spectroscopic analysis techniques have disadvantages that the recognition rate is to be improved, the data processing is complicated, and the impurities on the surface of the corn seed particles are difficult to recognize, so that the effect of the spectroscopic analysis techniques is greatly reduced.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a rapid identification system and an identification method for corn seeds.
In order to achieve the purpose, the invention adopts the technical scheme that: a rapid identification system for corn seeds comprising: the system comprises a detection unit, an execution unit, a unit to be detected and an identification unit, wherein the detection unit is used for measuring the standard corn seeds by using a near-infrared spectrometer to obtain the near-infrared spectrum of the standard corn seeds, and performing integral calculation on the near-infrared spectrum of the standard corn seeds to obtain integral signals of the near-infrared spectrum of the standard corn seeds; the execution unit is used for taking an integral signal of the near infrared spectrum of the standard corn seed as an input value of the base pair neural network, and training the base pair neural network to obtain a base pair neural network structure; the unit to be detected measures the corn seeds to be detected by using a near-infrared spectrometer to obtain the near-infrared spectrum of the corn seeds to be detected, and performs integral calculation on the near-infrared spectrum of the corn seeds to be detected to obtain integral signals of the near-infrared spectrum of the corn seeds to be detected; the identification unit is used for selecting an integral signal of the near infrared spectrum of the corn seed to be detected in the unit to be detected as an input value of the base pair neural network, and identifying the corn seed to be detected by using the base pair neural network obtained in the execution unit to obtain an identification result.
In a preferred embodiment of the invention, when the near infrared spectrum data of the corn seed sample is collected, the external environments of a plurality of near infrared spectrometers are the same; and (3) measuring the same corn seed sample on different near infrared spectrometers at the same measurement time point to obtain corresponding multiple pieces of spectral data.
In a preferred embodiment of the present invention, the near infrared spectroscopy is used to measure the near infrared spectrum data of any standard corn seed measured at the same point.
In a preferred embodiment of the present invention, the near infrared spectrum data of the corn seeds to be tested measured at the same point are measured for a plurality of times.
In a preferred embodiment of the present invention, the approximate infrared spectrum ranges measured by the standard corn seed and the corn seed to be detected are both 300-1200 nm.
An identification method of a rapid identification system for corn seeds comprises the following steps:
s1: collecting near infrared spectrum data of a corn seed sample as a standard sample, and preprocessing the near infrared spectrum data;
s2: selecting required near infrared spectrum data from the preprocessed near infrared spectrum data, and establishing a qualitative analysis model of the corn seeds by a feature extraction and modeling method;
s3: and performing variety authenticity identification on the near infrared spectrum of the corn seeds to be identified as the test sample.
In a preferred embodiment of the present invention, the preprocessing method used includes data normalization, derivative processing, smoothing, or centering and normalization.
In a preferred embodiment of the invention, representative modeling sample data is selected from the preprocessed near infrared spectral data.
The invention solves the defects in the background technology, and has the following beneficial effects:
(1) according to the method, the integral processing is carried out on the approximate infrared spectrums of the standard corn seeds and the corn seeds to be detected, the processed spectrums are used as input values of the base pair neural network, the constructed base pair neural network is used for identifying the corn seeds, the data processing efficiency and the identification result accuracy can be well considered, particularly, the integral processing is carried out on the wavelengths of the approximate infrared spectrums of the standard corn seeds and the corn seeds to be detected, integral signals of the approximate infrared spectrums of the standard corn seeds and the corn seeds to be detected are respectively obtained, further, useful information for type identification in the approximate infrared spectrums can be extracted, a large amount of interference information is reduced, the corn seed type identification effect is improved, and the corn seed identification work is more efficient and faster.
(2) In the modeling process, the invention adopts the step-by-step increase of sample data measured at different times to establish the model, thereby prolonging the modeling period and obviously improving the stability of the established model. And secondly, as the sample data collected by different instruments is selected, the combined modeling of a plurality of instruments is realized, and the adaptability of the established model is effectively improved.
(3) The representative modeling sample data in the invention simultaneously contains the sample data collected by different instruments, so as to realize the combined modeling of a plurality of instruments. According to different sample spectrum measurement time, when the modeling sample data is selected, proper spectrum data is selected as the representative modeling sample data on the basis of gradually increasing samples measured at different times, so that the modeling period is prolonged.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of the operation of a preferred embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
As shown in fig. 1, a rapid identification system for corn seeds comprises: the system comprises a detection unit, an execution unit, a unit to be detected and an identification unit, wherein the detection unit is used for measuring the standard corn seeds by using a near-infrared spectrometer to obtain the near-infrared spectrum of the standard corn seeds, and performing integral calculation on the near-infrared spectrum of the standard corn seeds to obtain integral signals of the near-infrared spectrum of the standard corn seeds; the execution unit is used for taking an integral signal of the near infrared spectrum of the standard corn seed as an input value of the base pair neural network, and training the base pair neural network to obtain a base pair neural network structure; the unit to be detected measures the corn seeds to be detected by using a near-infrared spectrometer to obtain the near-infrared spectrum of the corn seeds to be detected, and performs integral calculation on the near-infrared spectrum of the corn seeds to be detected to obtain integral signals of the near-infrared spectrum of the corn seeds to be detected; the identification unit is used for selecting an integral signal of the near infrared spectrum of the corn seed to be detected in the unit to be detected as an input value of the base pair neural network, and identifying the corn seed to be detected by using the base pair neural network obtained in the execution unit to obtain an identification result.
In a preferred embodiment of the invention, when the near infrared spectrum data of the corn seed sample is collected, the external environments of a plurality of near infrared spectrometers are the same; the method comprises the steps of measuring the same corn seed sample on different near infrared spectrometers at the same measurement time point to obtain multiple corresponding spectrum data, measuring the near infrared spectrum data measured on the same point of any standard corn seed by using the near infrared spectrometer for multiple times, and measuring the near infrared spectrum data measured on the same point of the corn seed to be measured for multiple times, wherein the approximate infrared spectrum ranges measured by the standard corn seed and the corn seed to be measured are both 300-1200 nm.
An identification method of a rapid identification system for corn seeds comprises the following steps:
s1: collecting near infrared spectrum data of a corn seed sample as a standard sample, and preprocessing the near infrared spectrum data;
s2: selecting required near infrared spectrum data from the preprocessed near infrared spectrum data, and establishing a qualitative analysis model of the corn seeds by a feature extraction and modeling method;
s3: and performing variety authenticity identification on the near infrared spectrum of the corn seeds to be identified as the test sample.
In a preferred embodiment of the present invention, the preprocessing method used includes data normalization, derivative processing, smoothing or centering and normalization, and representative modeling sample data is selected from the preprocessed near infrared spectrum data.
In a preferred embodiment of the invention, the approximate infrared spectrums of the standard corn seeds and the corn seeds to be detected are subjected to integral processing, so that the processed spectrums are used as input values of the base pair neural network, the constructed base pair neural network is used for identifying the corn seeds, the data processing efficiency and the identification result accuracy can be well considered, particularly, the integral processing is carried out on the wavelengths of the approximate infrared spectrums of the standard corn seeds and the corn seeds to be detected, integral signals of the approximate infrared spectrums of the standard corn seeds and the corn seeds to be detected are respectively obtained, further, useful information for type identification in the approximate infrared spectrums can be extracted, a large amount of interference information is reduced, the corn seed type identification effect is improved, and the corn seed identification work is more efficient and faster.
In a preferred embodiment of the invention, the model is built by gradually increasing sample data measured at different times in the modeling process, so that the modeling period is prolonged, and the stability of the built model is obviously improved. And secondly, as the sample data collected by different instruments is selected, the combined modeling of a plurality of instruments is realized, and the adaptability of the established model is effectively improved.
In a preferred embodiment of the invention, representative modeling sample data simultaneously contains sample data acquired by different instruments, so that the combined modeling of multiple instruments is realized. According to different sample spectrum measurement time, when the modeling sample data is selected, proper spectrum data is selected as the representative modeling sample data on the basis of gradually increasing samples measured at different times, so that the modeling period is prolonged.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (8)
1. A rapid identification system for corn seeds comprising: the system comprises a detection unit, an execution unit, a unit to be detected and an identification unit, and is characterized in that the detection unit is used for measuring a standard corn seed by using a near-infrared spectrometer to obtain a near-infrared spectrum of the standard corn seed, and performing integral calculation on the near-infrared spectrum of the standard corn seed to obtain an integral signal of the near-infrared spectrum of the standard corn seed; the execution unit is used for taking an integral signal of the near infrared spectrum of the standard corn seed as an input value of the base pair neural network, and training the base pair neural network to obtain a base pair neural network structure; the unit to be detected measures the corn seeds to be detected by using a near-infrared spectrometer to obtain the near-infrared spectrum of the corn seeds to be detected, and performs integral calculation on the near-infrared spectrum of the corn seeds to be detected to obtain integral signals of the near-infrared spectrum of the corn seeds to be detected; the identification unit is used for selecting an integral signal of the near infrared spectrum of the corn seed to be detected in the unit to be detected as an input value of the base pair neural network, and identifying the corn seed to be detected by using the base pair neural network obtained in the execution unit to obtain an identification result.
2. A rapid identification system for corn seeds as claimed in claim 1, wherein: then, collecting near infrared spectrum data of the corn seed sample, wherein the external environments of the plurality of near infrared spectrometers are the same; and (3) measuring the same corn seed sample on different near infrared spectrometers at the same measurement time point to obtain corresponding multiple pieces of spectral data.
3. A rapid identification system for corn seeds as claimed in claim 1, wherein: and (3) carrying out multiple measurements on the near infrared spectrum data measured on the same point of any standard corn seed by using a near infrared spectrometer.
4. A rapid identification system for corn seeds as claimed in claim 1, wherein: and measuring the near infrared spectrum data of the corn seeds to be measured at the same point for multiple times.
5. A rapid identification system for corn seeds as claimed in claim 1, wherein: the approximate infrared spectrum ranges measured by the standard corn seeds and the corn seeds to be detected are both 300-1200 nm.
6. An identification method of the rapid identification system for corn seeds of claim 1, comprising the steps of:
s1: collecting near infrared spectrum data of a corn seed sample as a standard sample, and preprocessing the near infrared spectrum data;
s2: selecting required near infrared spectrum data from the preprocessed near infrared spectrum data, and establishing a qualitative analysis model of the corn seeds by a feature extraction and modeling method;
s3: and performing variety authenticity identification on the near infrared spectrum of the corn seeds to be identified as the test sample.
7. The method of claim 6, wherein the system comprises: the preprocessing method adopted comprises data normalization processing, derivative method processing, smoothing processing or centralization and standardization processing.
8. The method of claim 6, wherein the system comprises: representative modeling sample data is selected from the preprocessed near infrared spectral data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010845303.9A CN112067578A (en) | 2020-08-20 | 2020-08-20 | Rapid identification system and identification method for corn seeds |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010845303.9A CN112067578A (en) | 2020-08-20 | 2020-08-20 | Rapid identification system and identification method for corn seeds |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112067578A true CN112067578A (en) | 2020-12-11 |
Family
ID=73662208
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010845303.9A Withdrawn CN112067578A (en) | 2020-08-20 | 2020-08-20 | Rapid identification system and identification method for corn seeds |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112067578A (en) |
-
2020
- 2020-08-20 CN CN202010845303.9A patent/CN112067578A/en not_active Withdrawn
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102778442B (en) | Method for rapidly identifying type of balsam material liquid for cigarette | |
CN101059426A (en) | Method for non-destructive measurement for tea polyphenol content of tea based on near infrared spectrum technology | |
CN105866056A (en) | Hybrid purity identification method based on near infrared spectroscopy | |
CN105181678A (en) | Identification method of rice varieties based on laser-induced breakdown spectroscopy (LIBS) | |
CN103134850A (en) | Tea quality rapid detection apparatus and detection method based on characteristic fragrance | |
CN108444924B (en) | Method for discriminating storage period of tea by applying hyperspectral image technology | |
CN105548233A (en) | Method for discriminating acacia honey and rape honey on basis of H-nuclear magnetic resonance | |
CN111965140B (en) | Wavelength point recombination method based on characteristic peak | |
CN103822897A (en) | White spirit appraising and source-tracing method based on infrared spectroscopy | |
CN103411906A (en) | Near infrared spectrum qualitative identification method of pearl powder and shell powder | |
KR20120033649A (en) | Biomarkers for origin discrimination of chinese cabbage | |
CN112098361A (en) | Corn seed identification method based on near infrared spectrum | |
CN110749565A (en) | Method for rapidly identifying storage years of Pu' er tea | |
WO2020248961A1 (en) | Method for selecting spectral wavenumber without reference value | |
CN109187443A (en) | Water body bacterial micro-organism based on multi-wavelength transmitted spectrum accurately identifies method | |
CN107727640A (en) | A kind of method for differentiating essence spice for cigarette using SERS method | |
CN110231328B (en) | Raman spectrum quantitative analysis method based on half-peak height distance method | |
CN106770607A (en) | A kind of method that utilization HS-IMR-MS differentiates genuine-fake cigarette | |
CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
CN108444953A (en) | Rice varieties method for quick identification based on laser induced breakdown spectroscopy differential signal | |
CN111398208B (en) | Method for rapidly identifying jadeite in traditional process by utilizing near infrared technology | |
CN112540971A (en) | Full-information online acquisition system and method based on tobacco leaf characteristics | |
CN111426657B (en) | Identification comparison method of three-dimensional fluorescence spectrogram of soluble organic matter | |
CN112067578A (en) | Rapid identification system and identification method for corn seeds | |
CN108169204B (en) | Raman spectrum preprocessing method based on database |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201211 |
|
WW01 | Invention patent application withdrawn after publication |