CN104062262A - Crop seed variety authenticity identification method based on near infrared spectrum - Google Patents
Crop seed variety authenticity identification method based on near infrared spectrum Download PDFInfo
- Publication number
- CN104062262A CN104062262A CN201410325360.9A CN201410325360A CN104062262A CN 104062262 A CN104062262 A CN 104062262A CN 201410325360 A CN201410325360 A CN 201410325360A CN 104062262 A CN104062262 A CN 104062262A
- Authority
- CN
- China
- Prior art keywords
- near infrared
- infrared spectrum
- crop seed
- data
- modeling
- 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.)
- Pending
Links
Abstract
The invention discloses a crop seed variety authenticity identification method based on near infrared spectrum. The method comprises the following steps of 1, acquiring near infrared spectrum data of crop seed samples, and preprocessing the near infrared spectrum data which is taken as a training sample; 2, selecting the needed spectrum data from the preprocessed near infrared spectrum data, and establishing a qualitative analysis model of the crop seeds by a feature extraction method and a modeling method; and 3, carrying out variety authenticity identification on the spectrum of the crop seeds which are taken as test samples and about to be identified. The crop seed variety authenticity identification method is based on the near infrared spectrum, the general near infrared spectrum qualitative analysis model can be established by a series of operation such as spectrum preprocessing, feature extraction, modeling and identification, and the method is capable of rapidly and accurately identifying the crop seed variety authenticity.
Description
Technical field
The kind that the present invention relates to crop seed is differentiated field, particularly a kind of crop seed variety authenticity discrimination method based near infrared spectrum.
Background technology
China is large agricultural country, and agricultural is the strategic industry of the peace world, the steady popular feelings." state is taking agriculture as this, and agriculture is to plant as first ", planting industry is safely the prerequisite of China's grain security, is one of condition precedent of agricultural safety.But the kind industry market of China allows of no optimist, kind abuse is serious, and the fake and inferior seed harmful farming part of cheating the farmers happens occasionally.Enterprise's right-safeguarding difficulty, lawsuit difficulty, chases after and pays for difficultly, causes many improved seeds to be encroached right, to such an extent as to form breeding not as sell kind, resembling not as doing the strange of operation of making scientific researches.
Currently used variety discriminating method can be divided into following three classes substantially: the one) discrimination method based on morphological character, mainly comprises the methods such as seed morphology discriminating, seedling morphology discriminating, field planting discriminating and computer simulation morphological analysis; Two) discrimination method based on Protocols in Molecular Biology, mainly comprises protein fingerprint pattern and DNA fingerprinting two class discrimination methods; Three) discrimination method based on chemistry, physical characteristics, mainly contains phenol decoration method, NaOH decoration method, potassium hydroxide decoration method, fluorescent scanning Atlas Method etc.
All there is multiple technologies obstacle in above method: (1) discriminating time is long; (2) differentiate that cost is high; (3) process is loaded down with trivial details; (4) identification person needs technical skill knowledge; (5) differentiate and need specific test condition, chemical reagent, equipment etc.Therefore, plant industry market and lack effectively quick on-the-spot authentication technique means and equipment, bring many difficulties to agricultural production, the management enforces the law etc., be difficult to effective guarantee seed safety and grain security.
Near infrared spectrum is a kind of spectral technique to near-infrared spectra district electro-magnetic wave absorption based on material, because near-infrared spectral analysis technology has easy, quick, low cost, pollution-free and do not destroy the advantages such as sample, is therefore widely used in multiple industries.Near infrared qualitative analysis is mainly used in the qualitative discrimination analysis of material, determines the ownership of unknown sample by comparing the spectrum of unknown sample and modeling sample or standard model.
For present situation and many deficiencies of crop seeds variety authentication discrimination method, the present invention proposes a kind of crop seed variety authenticity discrimination method based near infrared spectrum.
Summary of the invention
(1) technical matters that will solve
In view of this, fundamental purpose of the present invention is for a kind of harmless, low cost, easy to operate, the highly reliable crop seed variety authenticity discrimination method based near infrared spectrum are provided, the seed variety authenticity that can realize based near infrared spectrum without professional person differentiates fast, and improved the not high shortcoming of Stability and adaptability of the near infrared qualitative analysis model that existing method sets up.
(2) technical scheme
For achieving the above object, the invention provides a kind of crop seed variety authenticity discrimination method based near infrared spectrum, the method comprises:
Step 1: gather the near infrared spectrum data of crop seed sample as training sample, and these near infrared spectrum data are carried out to pre-service;
Step 2: from selecting required spectroscopic data through pretreated near infrared spectrum data, set up the qualitative analysis model of crop seed by feature extraction and modeling method;
Step 3: utilize the qualitative analysis model of setting up, the spectrum of the crop seed to be identified as test sample book is carried out to variety authentication discriminating.
In such scheme, the near infrared spectrum data described in step 1, its source is near infrared spectrometer.If there are many near infrared spectrometers of same model,, in the time gathering the near infrared spectrum data of crop seed sample, many residing external environment conditions of near infrared spectrometer are identical; To with a crop seed sample, require to measure on different near infrared spectrometers at identical Measuring Time point, obtain many corresponding spectroscopic datas.
In such scheme, described in step 1, near infrared spectrum data is carried out to pre-service, that the preprocess method of employing comprises data normalization processing, derivative method processing, smoothing processing or centralization and standardization in order to remove or to reduce the noise of uncertain background information to spectroscopic data.Described uncertain background information refers to the information that is subject near infrared spectrometer instrument state, condition determination and environmental impact.
In such scheme, described in step 2, from selecting required spectroscopic data through pretreated near infrared spectrum data, refer to from selecting representative modeling sample data through pretreated near infrared spectrum data; Due to the place of production of crop seed, produce the time limit, spectra collection asynchronism(-nization), different these uncertain informations of spectra collection instrument, can impact to qualitative discriminating, therefore these representative modeling sample data are the modeling sample data that can contain these uncertain informations, the accuracy of spectrum being differentiated to reduce the influence of change model of spectrum.
In such scheme, except the impact of described uncertain information, due between different instruments, the difference of different measuring time, in the time selecting modeling sample data, if there are many instruments of same model, for the test sample book data of selected same time point, these representative modeling sample data will comprise the sample data that different instruments gather simultaneously, to realize many instrument associating modelings.According to the difference of sample light spectrometry time, in the time selecting modeling sample data, select suitable spectroscopic data as these representative modeling sample data, to realize prolongation modeling period progressively to increase on the basis of sample that different time measures.
In such scheme, described in step 2, set up the qualitative analysis model of crop seed, comprise that the modeling sample data to selecting carry out dimension-reduction treatment, this dimension-reduction treatment comprises that principal component analysis (PCA) (PCA), partial least square method return (PLS) or linear discriminant analysis (LDA) dimension reduction method.
In such scheme, described in step 2, set up the qualitative analysis model of crop seed, the modeling method adopting adopts different modeling methods according to the difference of the scope of application of model and evaluating objects, comprises bionic pattern recognition methods (BPR), support vector machine (SVM) or nearest Euclidean distance method based on the geometric analysis of higher-dimension image.
In such scheme, described in step 3, utilize the qualitative analysis model of setting up, the spectrum of the crop seed to be identified as test sample book is carried out to variety authentication discriminating, comprise: first obtain the spectroscopic data as the crop seed to be identified of test sample book, then the spectroscopic data of this crop seed to be identified is carried out to pre-service, feature extraction, finally utilize the qualitative analysis model of setting up to differentiate fast, and provide identification result.
In such scheme, the method is in pre-service and feature extraction operation that the near infrared spectrum data gathering is carried out, and the pre-service and the feature extraction operation that use with described qualitative analysis model are identical.
(3) beneficial effect
From technique scheme, can find out, the present invention has following beneficial effect:
(1) the crop seed variety authenticity discrimination method based near infrared spectrum of the present invention, in modeling process, take the sample data that progressively increases different time measurement to set up model, extend modeling period, significantly improved the stability of institute's established model.Secondly, due to the sample data of having selected different instruments and gathering, realize many instrument associating modelings, significantly improved the adaptability of institute's established model.
(2) the crop seed variety authenticity discrimination method based near infrared spectrum of the present invention, in actual applications, between different near infrared spectrometers due to the design of light path, components and parts are selected, the reason such as rigging error and outside environment for use, between the spectral response that makes same sample record, there is certain difference, it is other that this species diversity even may exceed the interspecific difference of article to be identified, cause the discriminating model of setting up on an instrument can not be directly used in the sample spectra analysis of measuring on another instrument, and method provided by the present invention just can address this problem well.
(3) the crop seed variety authenticity discrimination method based near infrared spectrum of the present invention, can make discriminating to the variety authentication of crop seed fast, the discriminating time, few cost was low, and tester is not required to have professional knowledge, application is convenient, can be used for extensive universal.
(4) the crop seed variety authenticity discrimination method based near infrared spectrum of the present invention, the agriculture applications such as the monoploid polyploid that can be applied to crop seeds detects, the detection of hybridization of female parent kind, can also be applied to the aspects such as petrochemical complex, medical pharmacy, bioanalysis research, food security.
Brief description of the drawings
Fig. 1 is the process flow diagram of the crop seed variety authenticity discrimination method based near infrared spectrum provided by the invention.
Fig. 2 is the variation according to the prolongation modeling period model performance of the embodiment of the present invention.
Fig. 3 extends modeling period model performance test result according to the associating modeling of the embodiment of the present invention.
Fig. 4 changes according to the average correct recognition rata of different modeling pattern of the embodiment of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
It should be noted that, the experimental technique that the present invention proposes and operation not represent that the method is confined to agriculture field, all have value at aspects such as petrochemical complex, medical pharmacy, bioanalysis research, food securities.In algorithm, preprocess method, feature extracting method and modeling method are fixing, and experimenter can carry out the each step method of choose reasonable according to different situations and different experiment experiences, and each step algorithm that embodiment uses is not used for limiting the present invention.
As shown in Figure 1, Fig. 1 is the process flow diagram of the crop seed variety authenticity discrimination method based near infrared spectrum provided by the invention, and the method comprises:
Step 1: gather the near infrared spectrum data of crop seed sample as training sample, and these near infrared spectrum data are carried out to pre-service;
Step 2: from selecting required spectroscopic data through pretreated near infrared spectrum data, set up the qualitative analysis model of crop seed by feature extraction and modeling method;
Step 3: utilize the qualitative analysis model of setting up, the spectrum of the crop seed to be identified as test sample book is carried out to variety authentication discriminating.
Wherein, the near infrared spectrum data described in step 1, its source is near infrared spectrometer.If there are many near infrared spectrometers of same model,, in the time gathering the near infrared spectrum data of crop seed sample, many residing external environment conditions of near infrared spectrometer are identical; To with a crop seed sample, require to measure on different near infrared spectrometers at identical Measuring Time point, obtain many corresponding spectroscopic datas.Described near infrared spectrum data is carried out to pre-service, that the preprocess method of employing comprises data normalization processing, derivative method processing, smoothing processing or centralization and standardization in order to remove or to reduce the noise of uncertain background information to spectroscopic data.Described uncertain background information refers to the information that is subject near infrared spectrometer instrument state, condition determination and environmental impact.
Described in step 2, from selecting required spectroscopic data through pretreated near infrared spectrum data, refer to from selecting representative modeling sample data through pretreated near infrared spectrum data; Due to the place of production of crop seed, produce the time limit, spectra collection asynchronism(-nization), different these uncertain informations of spectra collection instrument, can impact to qualitative discriminating, therefore these representative modeling sample data are the modeling sample data that can contain these uncertain informations, the accuracy of spectrum being differentiated to reduce the influence of change model of spectrum.
Except the impact of described uncertain information, due between different instruments, the difference of different measuring time, in the time selecting modeling sample data, if there are many instruments of same model, for the test sample book data of selected same time point, these representative modeling sample data will comprise the sample data that different instruments gather simultaneously, to realize many instrument associating modelings.According to the difference of sample light spectrometry time, in the time selecting modeling sample data, select suitable spectroscopic data as these representative modeling sample data, to realize prolongation modeling period progressively to increase on the basis of sample that different time measures.
Described in step 2, set up the qualitative analysis model of crop seed, comprise that the modeling sample data to selecting carry out dimension-reduction treatment, this dimension-reduction treatment comprises that principal component analysis (PCA) (PCA), partial least square method return (PLS) or linear discriminant analysis (LDA) dimension reduction method.
Described in step 2, set up the qualitative analysis model of crop seed, the modeling method adopting adopts different modeling methods according to the difference of the scope of application of model and evaluating objects, comprises bionic pattern recognition methods (BPR), support vector machine (SVM) or nearest Euclidean distance method based on the geometric analysis of higher-dimension image.
Described in step 3, utilize the qualitative analysis model of setting up, the spectrum of the crop seed to be identified as test sample book is carried out to variety authentication discriminating, comprise: first obtain the spectroscopic data as the crop seed to be identified of test sample book, then the spectroscopic data of this crop seed to be identified is carried out to pre-service, feature extraction, finally utilize the qualitative analysis model of setting up to differentiate fast, and provide identification result.
The method is in pre-service and feature extraction operation that the near infrared spectrum data gathering is carried out, and the pre-service and the feature extraction operation that use with described qualitative analysis model are identical.
Below adopt different modeling methods as different embodiment, and verify this beneficial effect of the invention by experimental result.
Experimental apparatus in the present embodiment adopts the near infrared spectrometer of the SupNIR-2700 series of Hangzhou optically focused scientific & technical corporation (FPI); instrument parameter is as follows: the applicable sample state of instrument is particle or the solid such as Powdered; light source is halogen tungsten lamp; wavelength coverage is 1000～1800nm; effectively light path is 0.2～5mm; wavelength accuracy is 0.2nm, and mensuration form is noncontact diffuse reflection.Experiment is used two instruments, according to being successively demarcated as respectively instrument A, instrument B the date of production.
Experiment specimen in use is corn seed, has 7 kinds, is seed samples, is respectively: collect jade 2102, collect jade 2104, collect jade 2105, collect jade 2106, collect jade 2107, collect jade 2109, collect jade 2110.Sample has carried out cold storing and fresh-keeping processing in non-measuring phases, and measuring phases detects the temperature and humidity of sample experimental situation of living in, keeps constant as far as possible.
(1) collecting sample spectroscopic data
In experimentation, be whole cup sample and measure, at a Measuring Time point, for same increment originally, each survey once on instrument A and instrument B, obtains corresponding two spectrum respectively, and each kind is surveyed 10 on A instrument, correspondence is surveyed 10,7 kinds totally 140 spectrum on B instrument.
Point different time (time span 90 days) repeated acquisition 11 experimental datas, be respectively: the data in 5 days time intervals (4 times, 2013-3-12,3-17,3-22,3-27), the data in 6 days time intervals (3 times, 2013-4-4,4-10,4-16) and the data in 12 days time intervals (4 times, 2013-5-3,5-15,5-27,6-8).All data are numbered to 1～11 according to acquisition time sequencing, be numbered respectively A1～A11 and B1～B11 according to the difference of instrument, the data mixing simultaneously same time being obtained on instrument A and instrument B, forms another group data, is numbered C1～C11.The spectroscopic data of measuring separately in addition 6 groups of different times with instrument A, Measuring Time is respectively 2013-1-4,1-9,1-16,1-21,2-27,3-8, by its in chronological sequence serial number be D1～D6.
Data pre-service adopts digital filtering (Filtering), moving window level and smooth (Smoothing), single order data differentiate (First Derivative, FD) method that, vector normalization (Vector Normalization, VN) combines.The method of digital filtering is for the noise data in filtering spectroscopic data, isolates the spectroscopic data of real useful corn seed.Spectrum is carried out to derivative processing, be baseline correction conventional in near-infrared spectrum analysis and carry high-resolution preprocess method, the Main Function of first order derivative is to eliminate spectral shift.Vector normalization is mainly to eliminate to a certain extent the stochastic error producing in spectral measurement, mainly contains the variation of light path or the impact that the how many variation of dress sample produces spectrum.
(2) set up near infrared qualitative analysis model
Near infrared qualitative analysis is for the qualitative discrimination analysis of material, and the quality of qualitative analysis model performance has determined to differentiate the quality of result, therefore higher to the performance requirement of institute's established model.For the performance of further investigated qualitative analysis model, embodiment tests model performance from the stability and adaptability aspect of model, design two experiments, studied respectively the prolongation modeling period modeling of separate unit instrument and Duo Tai instrument associating modeling to model stability and adaptive impact.
The dimension reduction method adopting in modeling process is: return (PLS) by partial least square method and carry out dimensionality reduction one time, linear discriminant analysis (LDA) carries out secondary dimensionality reduction.
The modeling method adopting in modeling process is: select network forming (modeling) sample point by K-S method, modeling is carried out in bionic pattern recognition methods (BPR).The modeling method of two experiments is herein all based on said method.
The identification thought of bionic pattern identification is different from traditional mode identification (difference of Optimal coverage and optimum division) completely, more approaches the pattern of human knowledge's things.It uses the geometrical body of sealing to cover every class sample, and congener sample covering is compacted, and can effectively refuse to know non-class sample simultaneously.Therefore, use the modeling method of bionic pattern identification can obtain better identification result.
Experiment one: separate unit instrument extends modeling period modeling
Be respectively ma and mb (numbering below criterion in like manner) by pattern number according to the difference of modeling instrument, institute's established model is numbered respectively m1, m2, m3, m4, m5.M1 modeling data used is A5 (B5), m2 modeling data used is A5, A4 (B5, B4), m3 modeling data used is A5～A3 (B5～B3), m4 modeling data used is A5～A2 (B5～B2), and m5 modeling data used is A5～A1 (B5～B1).Therefore, an established model of experiment comprises: ma1～ma5, mb1～mb5.
Experiment two: many instruments extend modeling period associating modeling
Set up 5 models with C1～C5 data set, pattern number is respectively L1～L5, wherein, and L1 C5 modeling, C5, C4 modeling for L2, C5 for L3～C3 modeling, C5 for L4～C2 modeling, C5 for L5～C1 modeling.
(3) variety authentication of discriminating crop seed
In the time that discriminating product profits is planted authenticity, the corresponding method that pre-service, the dimension reduction method etc. that the data of sample to be tested spectrum are used adopts during all with modeling is identical.
Correct recognition rata for test result (Correct Acceptance Rate, CAR) and correct reject rate (Correct Rejection Rate, CRR) represent, formula is as follows:
CAR＝N1/N
CRR＝1-N2/(N3-N)
Wherein, N1 represents to be correctly identified as the sample number of current kind, and N2 represents that other kinds are identified as the sample number of current kind, and N3 represents total test specimens given figure of 7 kinds, and N represents total test specimens given figure of current kind.
Determine test set: A6～A11 and B6～B11 to testing one, and add up correct recognition rata and the correct reject rate of each kind and average; Determine test set: A6～A11 and B6～B11 to testing two, and add up average correct recognition rata and the average correct reject rate of the kind of all participation tests.
(4) experimental result statistics
Experiment one: the test result of separate unit instrument prolongation modeling period modeling as shown in Figure 2.In Fig. 2, ma1～ma5 represents respectively 5 models building with the measured modeling data of instrument A, mb1～mb5 represents respectively 5 models building with the measured modeling data of instrument B, and the modeling period of setting up from m1～m5 model extends gradually, the recognition effect of model is become better and better, the stability of model improves, and makes model aspect the adaptability of interstation instrument, also obtain corresponding improvement simultaneously.
Experiment two: the test result of many instrument prolongation modeling period associating modelings as shown in Figure 3.In Fig. 3, L1～L5 represents respectively 5 models of associating modeling, and extends gradually from the modeling period of L1～L5 model foundation, finds that associating modeling not only can obviously improve the adaptability of model, the stability of model is also had to larger lifting simultaneously, extended the applicable time limit of model.
The average correct recognition rata of the different modeling pattern of Fig. 4 changes.As shown in Figure 4, no matter be to the data on instrument A or instrument B, the model that many days multiple instruments are combined foundation has good recognition effect, and along with the prolongation of modeling period, recognition effect also improves.Experimental results show that, the method of many instrument associating modeling prolongation modeling periods not only can effectively improve the adaptability of model, and can effectively improve the robustness of model, this method set associating modeling and extend the advantage of modeling period method, make model performance more superior.
The present invention has proposed the method for associating modeling in the step of setting up near infrared qualitative analysis model, make qualitative analysis model performance be improved significantly.Associating modeling, with respect to independent modeling, can effectively be shortened the modeling time, reduces and gathers the workload of modeling data and the frequency of image data, has certain practical value.
Therefore, can not extend on the basis of modeling period the method for application associating modeling, the Stability and adaptability of raising model.The method has obtained variety authentication identification result more accurately and reliably with respect to current other modeling methods.
Above-described specific embodiment; object of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any amendment of making, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (12)
1. the crop seed variety authenticity discrimination method based near infrared spectrum, is characterized in that, the method comprises:
Step 1: gather the near infrared spectrum data of crop seed sample as training sample, and these near infrared spectrum data are carried out to pre-service;
Step 2: from selecting required spectroscopic data through pretreated near infrared spectrum data, set up the qualitative analysis model of crop seed by feature extraction and modeling method;
Step 3: utilize the qualitative analysis model of setting up, the spectrum of the crop seed to be identified as test sample book is carried out to variety authentication discriminating.
2. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 1, is characterized in that, the near infrared spectrum data described in step 1, and its source is near infrared spectrometer.
3. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 2, it is characterized in that, if there are many near infrared spectrometers of same model,, in the time gathering the near infrared spectrum data of crop seed sample, many residing external environment conditions of near infrared spectrometer are identical; To with a crop seed sample, require to measure on different near infrared spectrometers at identical Measuring Time point, obtain many corresponding spectroscopic datas.
4. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 1, it is characterized in that, described in step 1, near infrared spectrum data is carried out to pre-service, that the preprocess method of employing comprises data normalization processing, derivative method processing, smoothing processing or centralization and standardization in order to remove or to reduce the noise of uncertain background information to spectroscopic data.
5. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 4, is characterized in that, described uncertain background information refers to the information that is subject near infrared spectrometer instrument state, condition determination and environmental impact.
6. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 1, it is characterized in that, described in step 2, from selecting required spectroscopic data through pretreated near infrared spectrum data, refer to from selecting representative modeling sample data through pretreated near infrared spectrum data; Due to the place of production of crop seed, produce the time limit, spectra collection asynchronism(-nization), different these uncertain informations of spectra collection instrument, can impact to qualitative discriminating, therefore these representative modeling sample data are the modeling sample data that can contain these uncertain informations, the accuracy of spectrum being differentiated to reduce the influence of change model of spectrum.
7. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 6, it is characterized in that, except the impact of described uncertain information, due between different instruments, the difference of different measuring time, in the time selecting modeling sample data, if there are many instruments of same model, for the test sample book data of selected same time point, these representative modeling sample data will comprise the sample data that different instruments gather simultaneously, to realize many instrument associating modelings.
8. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 6, it is characterized in that, according to the difference of sample light spectrometry time, in the time selecting modeling sample data, select suitable spectroscopic data as these representative modeling sample data, to realize prolongation modeling period progressively to increase on the basis of sample that different time measures.
9. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 1, it is characterized in that, described in step 2, set up the qualitative analysis model of crop seed, comprise that the modeling sample data to selecting carry out dimension-reduction treatment, this dimension-reduction treatment comprises that principal component analysis (PCA) (PCA), partial least square method return (PLS) or linear discriminant analysis (LDA) dimension reduction method.
10. the crop seed variety authenticity discrimination method based near infrared spectrum according to claim 1, it is characterized in that, described in step 2, set up the qualitative analysis model of crop seed, the modeling method adopting adopts different modeling methods according to the difference of the scope of application of model and evaluating objects, comprises bionic pattern recognition methods (BPR), support vector machine (SVM) or nearest Euclidean distance method based on the geometric analysis of higher-dimension image.
The 11. crop seed variety authenticity discrimination methods based near infrared spectrum according to claim 1, it is characterized in that, described in step 3, utilize the qualitative analysis model of setting up, the spectrum of the crop seed to be identified as test sample book carried out to variety authentication discriminating, comprising:
First obtain the spectroscopic data as the crop seed to be identified of test sample book, then the spectroscopic data of this crop seed to be identified is carried out to pre-service, feature extraction, finally utilize the qualitative analysis model of setting up to differentiate fast, and provide identification result.
The 12. crop seed variety authenticity discrimination methods based near infrared spectrum according to claim 1, it is characterized in that, the method is in pre-service and feature extraction operation that the near infrared spectrum data gathering is carried out, and the pre-service and the feature extraction operation that use with described qualitative analysis model are identical.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410325360.9A CN104062262A (en) | 2014-07-09 | 2014-07-09 | Crop seed variety authenticity identification method based on near infrared spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410325360.9A CN104062262A (en) | 2014-07-09 | 2014-07-09 | Crop seed variety authenticity identification method based on near infrared spectrum |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104062262A true CN104062262A (en) | 2014-09-24 |
Family
ID=51550077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410325360.9A Pending CN104062262A (en) | 2014-07-09 | 2014-07-09 | Crop seed variety authenticity identification method based on near infrared spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104062262A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104374739A (en) * | 2014-10-30 | 2015-02-25 | 中国科学院半导体研究所 | Identification method for authenticity of varieties of seeds on basis of near-infrared quantitative analysis |
| CN104376325A (en) * | 2014-10-30 | 2015-02-25 | 中国科学院半导体研究所 | Method for building near-infrared qualitative analysis model |
| CN104374737A (en) * | 2014-10-30 | 2015-02-25 | 中国科学院半导体研究所 | Near-infrared quantitative identification method |
| CN104990891A (en) * | 2015-06-24 | 2015-10-21 | 中国农业大学 | Method for establishing seed near infrared spectrum and spectral image qualitative analysis model |
| CN105223164A (en) * | 2015-08-04 | 2016-01-06 | 内蒙古农业大学 | Differentiate the method and system of buckwheat or the adulterated wheat flour of oatmeal |
| CN105424647A (en) * | 2015-11-23 | 2016-03-23 | 中国农业大学 | Construction method of rice seed variety authentication identifying model and application thereof |
| CN105486659A (en) * | 2015-11-23 | 2016-04-13 | 中国农业大学 | Construction method and application of corn seed variety authenticity identifying model |
| CN105699318A (en) * | 2014-11-24 | 2016-06-22 | 严红兵 | Single seed grain nondestructive test method and system thereof |
| CN105866056A (en) * | 2015-03-25 | 2016-08-17 | 山东翰能高科科技有限公司 | Hybrid purity identification method based on near infrared spectroscopy |
| CN104374738B (en) * | 2014-10-30 | 2017-03-08 | 中国科学院半导体研究所 | A kind of method for qualitative analysis improving identification result based on near-infrared |
| CN110163276A (en) * | 2019-05-15 | 2019-08-23 | 浙江中烟工业有限责任公司 | A kind of screening technique of near infrared spectrum modeling sample |
| CN111272668A (en) * | 2020-01-22 | 2020-06-12 | 中国农业科学院农产品加工研究所 | Construction method of wheat variety identification model |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1831515A (en) * | 2006-04-03 | 2006-09-13 | 浙江大学 | Method for nondistructive discriminating crop seed variety using visible light and near-infrared spectrum technology |
| CN101692043A (en) * | 2009-10-13 | 2010-04-07 | 赵景辉 | Method for quickly and non-destructively identifying ginseng seeds by near infrared spectrum |
| CN101738373A (en) * | 2008-11-24 | 2010-06-16 | 中国农业大学 | Method for distinguishing varieties of crop seeds |
| CN101819141A (en) * | 2010-04-28 | 2010-09-01 | 中国科学院半导体研究所 | Maize variety identification method based on near infrared spectrum and information processing |
| CN102768196A (en) * | 2012-08-13 | 2012-11-07 | 中国计量学院 | Method for identifying different transgenic rice |
| CN102841072A (en) * | 2012-08-13 | 2012-12-26 | 中国计量学院 | Method for identifying transgenic rice and non-transgenic rice based on NIR (Near Infrared Spectrum) |
| CN202693464U (en) * | 2012-07-20 | 2013-01-23 | 华中农业大学 | Small particle size seed quality online nondestructive detecting device based on near infrared spectrum |
| CN103344602A (en) * | 2013-07-04 | 2013-10-09 | 中国科学院合肥物质科学研究院 | Nondestructive testing method for rice idioplasm authenticity based on near infrared spectrum |
| CN103743705A (en) * | 2014-01-28 | 2014-04-23 | 盐城工学院 | Rapid detection method for sorghum halepense and similar species |
-
2014
- 2014-07-09 CN CN201410325360.9A patent/CN104062262A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1831515A (en) * | 2006-04-03 | 2006-09-13 | 浙江大学 | Method for nondistructive discriminating crop seed variety using visible light and near-infrared spectrum technology |
| CN101738373A (en) * | 2008-11-24 | 2010-06-16 | 中国农业大学 | Method for distinguishing varieties of crop seeds |
| CN101692043A (en) * | 2009-10-13 | 2010-04-07 | 赵景辉 | Method for quickly and non-destructively identifying ginseng seeds by near infrared spectrum |
| CN101819141A (en) * | 2010-04-28 | 2010-09-01 | 中国科学院半导体研究所 | Maize variety identification method based on near infrared spectrum and information processing |
| CN202693464U (en) * | 2012-07-20 | 2013-01-23 | 华中农业大学 | Small particle size seed quality online nondestructive detecting device based on near infrared spectrum |
| CN102768196A (en) * | 2012-08-13 | 2012-11-07 | 中国计量学院 | Method for identifying different transgenic rice |
| CN102841072A (en) * | 2012-08-13 | 2012-12-26 | 中国计量学院 | Method for identifying transgenic rice and non-transgenic rice based on NIR (Near Infrared Spectrum) |
| CN103344602A (en) * | 2013-07-04 | 2013-10-09 | 中国科学院合肥物质科学研究院 | Nondestructive testing method for rice idioplasm authenticity based on near infrared spectrum |
| CN103743705A (en) * | 2014-01-28 | 2014-04-23 | 盐城工学院 | Rapid detection method for sorghum halepense and similar species |
Non-Patent Citations (1)
| Title |
|---|
| 姚彤炜: "《药物分析》", 31 May 2011 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376325A (en) * | 2014-10-30 | 2015-02-25 | 中国科学院半导体研究所 | Method for building near-infrared qualitative analysis model |
| CN104374737A (en) * | 2014-10-30 | 2015-02-25 | 中国科学院半导体研究所 | Near-infrared quantitative identification method |
| CN104374739A (en) * | 2014-10-30 | 2015-02-25 | 中国科学院半导体研究所 | Identification method for authenticity of varieties of seeds on basis of near-infrared quantitative analysis |
| CN104374738B (en) * | 2014-10-30 | 2017-03-08 | 中国科学院半导体研究所 | A kind of method for qualitative analysis improving identification result based on near-infrared |
| CN105699318A (en) * | 2014-11-24 | 2016-06-22 | 严红兵 | Single seed grain nondestructive test method and system thereof |
| WO2016150130A1 (en) * | 2015-03-25 | 2016-09-29 | 山东翰能高科科技有限公司 | Hybrid purity identification method based on near infrared spectrum |
| CN105866056A (en) * | 2015-03-25 | 2016-08-17 | 山东翰能高科科技有限公司 | Hybrid purity identification method based on near infrared spectroscopy |
| CN104990891A (en) * | 2015-06-24 | 2015-10-21 | 中国农业大学 | Method for establishing seed near infrared spectrum and spectral image qualitative analysis model |
| CN104990891B (en) * | 2015-06-24 | 2017-10-20 | 中国农业大学 | A kind of seed near infrared spectrum and spectrum picture qualitative analysis model method for building up |
| CN105223164A (en) * | 2015-08-04 | 2016-01-06 | 内蒙古农业大学 | Differentiate the method and system of buckwheat or the adulterated wheat flour of oatmeal |
| CN105223164B (en) * | 2015-08-04 | 2017-11-07 | 内蒙古农业大学 | Differentiate the method and system of buckwheat or the adulterated wheat flour of oatmeal |
| CN105486659A (en) * | 2015-11-23 | 2016-04-13 | 中国农业大学 | Construction method and application of corn seed variety authenticity identifying model |
| CN105424647A (en) * | 2015-11-23 | 2016-03-23 | 中国农业大学 | Construction method of rice seed variety authentication identifying model and application thereof |
| CN110163276A (en) * | 2019-05-15 | 2019-08-23 | 浙江中烟工业有限责任公司 | A kind of screening technique of near infrared spectrum modeling sample |
| CN111272668A (en) * | 2020-01-22 | 2020-06-12 | 中国农业科学院农产品加工研究所 | Construction method of wheat variety identification model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104062262A (en) | Crop seed variety authenticity identification method based on near infrared spectrum | |
| CN105866056A (en) | Hybrid purity identification method based on near infrared spectroscopy | |
| CN104374738B (en) | A kind of method for qualitative analysis improving identification result based on near-infrared | |
| CN109142317B (en) | Raman spectrum substance identification method based on random forest model | |
| TW202343352A (en) | Method for reducing false positive identification for spectroscopic classification | |
| CN103411906B (en) | The near infrared spectrum qualitative identification method of pearl powder and oyster shell whiting | |
| CN101692052B (en) | Hyperspectrum image technique-based method and hyperspectrum image technique-based device for identifying true and false famous tea | |
| CN104374739A (en) | Identification method for authenticity of varieties of seeds on basis of near-infrared quantitative analysis | |
| CN103278609A (en) | Meat product freshness detection method based on multisource perceptual information fusion | |
| CN104376325A (en) | Method for building near-infrared qualitative analysis model | |
| CN106706546A (en) | Analysis method for artificial intelligence learning materials on basis of infrared and Raman spectrum data | |
| CN106018332A (en) | Near-infrared-spectrum citrus yellow shoot disease field detection method | |
| EP3222997A1 (en) | Quality evaluation method and quality evaluation device | |
| CN102590129A (en) | Method for detecting content of amino acid in peanuts by near infrared method | |
| CN105136738A (en) | Near-infrared-based method for identifying tree varieties ranging from eucalyptus-category tree varieties to acacia-mangium-category tree varieties | |
| CN107917897A (en) | The method of the special doctor's food multicomponent content of near infrared ray | |
| CN104777143A (en) | Method for similarity identification of expired drugs based on Raman spectroscopy | |
| CN105043998A (en) | Method for identifying corn haploid | |
| CN109444186A (en) | A kind of pearl powder X-ray diffraction differential method | |
| CN101614663A (en) | As seen and near infrared spectrum bee pollen variety discriminating | |
| CN104345045A (en) | Chemical pattern recognition and near infrared spectrum-based similar medicinal material identification method | |
| CN105223140A (en) | The method for quickly identifying of homology material | |
| CN103743705A (en) | Rapid detection method for sorghum halepense and similar species | |
| CN102135496A (en) | Infrared spectrum quantitative analysis method and infrared spectrum quantitative analysis device based on multi-scale regression | |
| CN109975236A (en) | A method of identifying the honeysuckle place of production using near-infrared spectrum technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140924 |