CN108398391A - A kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated - Google Patents
A kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated Download PDFInfo
- Publication number
- CN108398391A CN108398391A CN201810062042.6A CN201810062042A CN108398391A CN 108398391 A CN108398391 A CN 108398391A CN 201810062042 A CN201810062042 A CN 201810062042A CN 108398391 A CN108398391 A CN 108398391A
- Authority
- CN
- China
- Prior art keywords
- olive oil
- sample
- adulterated
- spectrum image
- spectrum
- 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
- 239000004006 olive oil Substances 0.000 title claims abstract description 74
- 235000008390 olive oil Nutrition 0.000 title claims abstract description 74
- 238000001228 spectrum Methods 0.000 title claims abstract description 69
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 238000005516 engineering process Methods 0.000 title claims abstract description 21
- 238000012417 linear regression Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 15
- 239000002285 corn oil Substances 0.000 claims description 9
- 235000005687 corn oil Nutrition 0.000 claims description 9
- 238000002310 reflectometry Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 230000003595 spectral effect Effects 0.000 claims description 8
- 238000003384 imaging method Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 abstract description 5
- 239000011159 matrix material Substances 0.000 description 13
- 230000008569 process Effects 0.000 description 5
- 238000012512 characterization method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000008157 edible vegetable oil Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000004519 grease Substances 0.000 description 2
- 239000003921 oil Substances 0.000 description 2
- 235000019198 oils Nutrition 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- FPIPGXGPPPQFEQ-UHFFFAOYSA-N 13-cis retinol Natural products OCC=C(C)C=CC=C(C)C=CC1=C(C)CCCC1(C)C FPIPGXGPPPQFEQ-UHFFFAOYSA-N 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 206010020961 Hypocholesterolaemia Diseases 0.000 description 1
- 240000008415 Lactuca sativa Species 0.000 description 1
- 240000007817 Olea europaea Species 0.000 description 1
- FPIPGXGPPPQFEQ-BOOMUCAASA-N Vitamin A Natural products OC/C=C(/C)\C=C\C=C(\C)/C=C/C1=C(C)CCCC1(C)C FPIPGXGPPPQFEQ-BOOMUCAASA-N 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- FPIPGXGPPPQFEQ-OVSJKPMPSA-N all-trans-retinol Chemical compound OC\C=C(/C)\C=C\C=C(/C)\C=C\C1=C(C)CCCC1(C)C FPIPGXGPPPQFEQ-OVSJKPMPSA-N 0.000 description 1
- 230000001093 anti-cancer Effects 0.000 description 1
- 230000003110 anti-inflammatory effect Effects 0.000 description 1
- 230000000845 anti-microbial effect Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000021022 fresh fruits Nutrition 0.000 description 1
- 230000007407 health benefit Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 235000009973 maize Nutrition 0.000 description 1
- 238000001819 mass spectrum Methods 0.000 description 1
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 description 1
- 229910052753 mercury Inorganic materials 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 239000010461 other edible oil Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000985 reflectance spectrum Methods 0.000 description 1
- 235000012045 salad Nutrition 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 235000021122 unsaturated fatty acids Nutrition 0.000 description 1
- 150000004670 unsaturated fatty acids Chemical class 0.000 description 1
- 235000019155 vitamin A Nutrition 0.000 description 1
- 239000011719 vitamin A Substances 0.000 description 1
- 229940045997 vitamin a Drugs 0.000 description 1
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
-
- 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
- G01N21/55—Specular reflectivity
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of detection methods that the olive oil based on high light spectrum image-forming technology is adulterated, it includes pure olive oil and according to the adulterated olive oil sample of preset ratio to obtain first, high spectrum image acquisition is carried out to the olive oil sample of acquisition, extract the averaged spectrum of area-of-interest, eight characteristic wavelengths are gone out using successive projection algorithms selection, to establish multiple linear regression model.Unknown sample can be detected by the multiple linear regression model of foundation, judges whether detected unknown sample is adulterated.The present invention detection method, have many advantages, such as without damage, it is pollution-free, automate, rapidly and efficiently.
Description
Technical field
The invention belongs to technical field of food detection more particularly to a kind of olive oil based on high light spectrum image-forming technology are adulterated
Detection method, be used for olive oil non-destructive testing.
Background technology
Olive oil is that ripe olive fresh fruit is directly cold-pressed the grease produced compared with other plant edible oil to contain
There are an abundant unsaturated fatty acid, and vitamin A, D, E, the Multiple components such as F, K and carrotene are easily digested.
Since olive oil is not chemically treated in processing extraction process, natural nutrient is not corrupted, and is so far in grease
It is most suitable for the edible oil of human body.It is considered as " liquid golden " due to its health benefits, it is antimicrobial including anticancer,
Hypocholesterolemia, anti-hypertension and anti-inflammatory effect.
Olive oil is in trend of selling well in international market at present, in addition price high for a long time so that olive oil
With more wide market development space.Because it is expensive, adulteration repeated.
The method that olive oil authentication technique uses at present is mostly the methods of chromatography, mass spectrum, chemometrics method, these
Although method accuracy of detection is high, detection process is sufficiently complex, and time-consuming, relies on a large amount of chemical reagent, and belongs to and have
Damage detection, waste is big, is unfavorable for promoting.
Therefore, adulterated quick, the lossless detection technique of olive oil will be of great practical significance.
Invention content
The object of the present invention is to provide a kind of detection methods that the olive oil based on high light spectrum image-forming technology is adulterated, to solve
Prior art detection method detection process is complicated, time-consuming, and belongs to and damage detection, wastes big problem.
To achieve the goals above, technical solution of the present invention is as follows:
A kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated, it is described based on high light spectrum image-forming technology
The adulterated detection method of olive oil, including:
It includes pure olive oil and according to the adulterated olive oil sample of preset ratio to obtain;
High spectrum image acquisition is carried out to the olive oil sample of acquisition, obtains the high spectrum image of sample, and carry out black and white
Correction;
The area-of-interest of the high spectrum image of sample is extracted, the spectral reflectivity of all pixels in area-of-interest is calculated
Averaged spectrum of the average value as each sample;
The averaged spectrum of each sample is pre-processed, eight characteristic wavelengths are gone out using successive projection algorithms selection, point
It Wei not 471.27nm, 503.22nm, 524.39nm, 564.70nm, 617.04nm, 722.89nm, 837.13nm, 927.49nm;
According to the averaged spectrum of the characteristic wave bands of selection and sample, establishing multiple linear regression model is:
Y=β0+β1R471.27nm+β2R503.22nm+β3R524.39nm+β4R564.70nm+β5R617.04nm+β6R722.89nm+β7R837.13nm+
β8R927.49nm;
Wherein y is olive oil concentration prediction value, R471.27nm、R503.22nm、R524.39nm、R564.70nm、R617.04nm、R722.89nm、
R837.13nm、R927.49nmFor characteristic wavelength 471.27nm, 503.22nm, 524.39nm, 564.70nm, 617.04nm,
Averaged spectrum reflectivity at 722.89nm, 837.13nm, 927.49nm, β0For constant term, β1、β2…β8For regression coefficient;
The olive oil of acquisition is detected using the multiple linear regression model of foundation.
Further, described to obtain the high spectrum image of sample, and black and white correction is carried out, using following formula:
Wherein:R is image after correction, R0It is original sample image, W is whiteboard images, and B is dark background image.
Further, the averaged spectrum to each sample pre-processes, including:
By using standard, just too the averaged spectrum of olive oil sample is being standardized by variable;
It is filtered again by Savitzky-Golay methods.
Further, the olive oil sample includes:Olive oil and corn oil 10:First group of sample that 1 ratio is mixed
This, olive oil and corn oil 5:First group of sample that 1 ratio is mixed, olive oil and corn oil 3:What 1 ratio was mixed
The 4th group of sample of third group sample and pure olive oil.
Further, the multiple linear regression model of establishing is:
Y=0.718-7.46R471.27nm+0.13R503.22nm+0.274R524.39nm+3.46R564.70nm-2.26R617.04nm+
0.5R722.89nm-1.27R837.13nm+0.82R927.49nm;
Wherein y is olive oil concentration prediction value, R471.27nm、R503.22nm、R524.39nm、R564.70nm、R617.04nm、R722.89nm、
R837.13nm、R927.49nmFor characteristic wavelength 471.27nm, 503.22nm, 524.39nm, 564.70nm, 617.04nm,
Averaged spectrum reflectivity at 722.89nm, 837.13nm, 927.49nm.
The present invention proposes a kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated, using EO-1 hyperion at
As technology, high spectrum image has the advantages that collection of illustrative plates, combines traditional two-dimensional imaging technique and spectral technique, has nothing
Damage, it is pollution-free, automation, rapidly and efficiently the advantages that.Characteristic wavelength is obtained using successive projection algorithm, and establishes multiple linear
Regression model improves the precision of detection.
Description of the drawings
Fig. 1 is a kind of detection method flow chart that the olive oil based on high light spectrum image-forming technology is adulterated of the present invention.
Specific implementation mode
Technical solution of the present invention is described in further details with reference to the accompanying drawings and examples, following embodiment is not constituted
Limitation of the invention.
The technical program is based on high light spectrum image-forming technology, and high light spectrum image-forming technology is in the ultraviolet of electromagnetic spectrum, visible light, close
Infrared and mid infrared region is imaged target area with tens of to hundreds of continuous and subdivision spectral band simultaneously, acquisition
Image has the advantages that image is combined with spectrum.The technical program carries out the adulterated inspection of olive oil using high light spectrum image-forming technology
Survey, have many advantages, such as without damage, it is pollution-free, automate, rapidly and efficiently.
As shown in Figure 1, a kind of embodiment of the technical program, a kind of olive oil based on high light spectrum image-forming technology is adulterated
Detection method includes the following steps:
Step S1, it includes pure olive oil and according to the adulterated olive oil sample of preset ratio to obtain.
The present embodiment tests used sample and eats olive oil using the extra virgin of supermarket's purchase, is not limited to the product of product
Board, it is assumed that it is pure olive oil that the extra virgin bought, which eats olive oil,.By the pure olive oil in part according to certain ratio
Example mixes other edible oils, such as maize germ oil or salad oil etc., artificially produces adulterated olive oil sample.This implementation
The sample that example obtains includes four groups:Olive oil and corn oil 10:First group of sample that 1 ratio is mixed, olive oil and corn
Oil 5:First group of sample that 1 ratio is mixed, olive oil and corn oil 3:The third group sample that 1 ratio is mixed, and
The 4th group of sample of pure olive oil.
It should be noted that the present embodiment is not limited to the group number of sample, it is also not necessarily limited to mixed ratio, such as can also take
8:The sample of 1 ratio mixing forms one group.Every group of the present embodiment takes 40 samples, totally 160 samples.The quantity of sample is more,
It is more accurate for subsequent model,.
Step S2, high spectrum image acquisition is carried out to the olive oil sample of acquisition, obtains the high spectrum image of sample, goes forward side by side
Row black and white corrects.
The present embodiment carries out high spectrum image acquisition using Hyperspectral imager to the sample of acquisition, such as is used
Hyperspectral imager be Image- λ-V10E-PS hyperspectral imagers system (Sichuan Shuan Lihepu Science and Technology Ltd.s) its
Chief component is light source, imaging spectrometer, electronic control translation stage, translational controller and computer composition.Imaging spectrometer
Model Imperx IPX-2M30, spectral region 383.70-1032.70nm, spectral resolution 2.73nm.High spectrum image
Data acquisition is completed using SpecView softwares.Entire gatherer process carries out in camera bellows, and stray light in environment is avoided to bring
It influences.High spectrum image acquisition parameter is set:Time for exposure 20ms, translation stage movement speed 1.2cm/s, 4 mercury lamps and translation
The angle of platform is 53 degree.Hyper-spectral data gathering is carried out to all olive oil samples successively by group.
Blank preferably, is also placed on and carries out blank number with olive oil same distance and lighting position by the present embodiment simultaneously
According to acquisition, it is then shut off lens cap in light source cover and carries out dark background data acquisition.According to the black white image of acquisition, to collected
Sample high spectrum image does black and white correction, to reduce the noise of light source generation.
Black and white updating formula is:
Wherein:R is image after correction, R0It is original sample image, W is whiteboard images, and B is blackboard image.
Step S3, the area-of-interest of the high spectrum image of extraction sample, calculates the light of all pixels in area-of-interest
Compose averaged spectrum of the average value of reflectivity as each sample.
The present embodiment uniformly chooses the square area of 60 pixel * of center of a sample region, 60 pixels as area-of-interest
(ROI), the range of area-of-interest is set according to actual spectrum picture.
The average value of the spectral reflectivity of all pixels point in the square area-of-interest is calculated as each sample
Averaged spectrum, to obtain the averaged spectrum of each sample.
Step S4, the averaged spectrum of each sample is pre-processed, eight features is gone out using successive projection algorithms selection
Wavelength, respectively 471.27nm, 503.22nm, 524.39nm, 564.70nm, 617.04nm, 722.89nm, 837.13nm,
927.49nm。
The present embodiment pre-processes the averaged spectrum of each sample, first pass through using standard just too variable (SNV) will
The averaged spectrum of olive oil sample is standardized, and is then carried out again to it by Savitzky-Golay (SG filtering) method
Filter.
For pretreated spectrum, the present embodiment uses successive projection algorithm (Successive projections
Algorithm, SPA) to select it can most reflect the true and false characteristic wavelength of olive oil.
Specifically, successive projection algorithm SPA is arbitrarily to select a wave to cycle specificity wavelength selection algorithm before one kind
It is long, its projection to residual vector is calculated, the corresponding wavelength of maximal projection vector is put into wavelength set of variables, cycle is until last
One variable terminates.
If Xn×mFor spectrum matrix, wherein n is number of samples, and m is spectral wavelength number, N be need selection variable number (
To the characteristic wave bands number in requisition for selection in the present embodiment).The present embodiment successive projection algorithm SPA includes:
1, first, the spectrum matrix X of arbitrary j row is selectedj, it is denoted as Xk(0);
2, remaining spectroscopic data is placed in S,
3, X is calculated separatelyjTo remaining columns vector projection;
4, note k (n)=arg [max (| | Pxj| |), j ∈ s], with season Xj=Pxj, j ∈ s;
5, n=n+1 is enabled, if n ﹤ N, then 2 is jumped to and is calculated again, the characteristic wavelength of final choice is { Xk(0)...,
Xk(N-1)}。
The present embodiment has been selected by the above method can most reflect the true and false characteristic wavelength of olive oil, pass through above-mentioned sample
This, obtained characteristic wavelength be respectively 471.27nm, 503.22nm, 524.39nm, 564.70nm, 617.04nm, 722.89nm,
837.13nm、927.49nm。
It should be noted that selection characteristic wavelength, can also use principal component analysis (Principal Component
Analysis, PCA) principal component analysis is carried out to sample spectrum data, obtain characteristic wave bands.PCA is a kind of mathematics dimension-reduction algorithm,
It is that original multiple variables are changed into another group of incoherent variable to obtain the way of a small amount of irrelevant variable using linear transformation
Diameter.One group of new mutually independent variable is finally obtained, it can farthest express all information of former variable.PCA
The purpose of dimensionality reduction has not been only reached, and achieves the effect of denoising.Data redundancy while utmostly is reduced in order to reach
The purpose of retention data information, it is 10 to choose number of principal components, and contribution rate of accumulative total reaches 99.41% at this time.
Step S5, according to the averaged spectrum of the characteristic wave bands of selection and sample, multiple linear regression model is established.
The present embodiment is as follows using the multiple linear regression model that multiple linear regression method is established:
Y=β0+β1R471.27nm+β2R503.22nm+β3R524.39nm+β4R564.70nm+β5R617.04nm+β6R722.89nm+β7R837.13nm+
β8R927.49nm;
Wherein y is olive oil concentration of specimens predicted value, β0For constant term, β1、β2…β8For regression coefficient, wherein β1For
R503.22nm、R524.39nm、R564.70nm、R617.04nm、R722.89nm、R837.13nm、R927.49nmWhen fixed, R471.27nmOften increase a list
Position is to the effect of y, i.e. R471.27nmTo the partial regression coefficient of y;Similarly β2For R471.27nm、R524.39nm、R564.70nm、R617.04nm、
R722.89nm、R837.13nm、R927.49nmWhen fixed, R503.22nmOften increase a unit to the effect of y, i.e. R503.22nmY is biased back to
Return coefficient, and so on.
Wherein, R471.27nm、R503.22nm、R524.39nm、R564.70nm、R617.04nm、R722.89nm、R837.13nm、R927.49nmFor each spy
Levy the corresponding averaged spectrum reflectivity of wavelength.
In the present embodiment, it is obtained above-mentioned more after carrying out model training by above-mentioned sample according to selected characteristic wavelength
First linear regression model (LRM) indicates as follows:
Y=0.718-7.46R471.27nm+0.13R503.22nm+0.274R524.39nm+3.46R564.70nm-2.26R617.04nm+
0.5R722.89nm-1.27R837.13nm+0.82R927.49nm。
In addition, the technical program can also be detected the olive oil of acquisition using partial least square model, i.e., will
The averaged spectrum of each sample extracted is stored in matrix X, and each row of matrix represent the reflectance spectrum at a wavelength points
Value represents a sample per a line.
Wherein the concentration matrix (physical and chemical parameter matrix) of spectrum is Y, then has:
X=TP+E;
Y=UQ+F;
Wherein, T is the characterization factor matrix of X, and U is the characterization factor matrix of Y;P is X loading matrixs, and Q is Y loading matrixs;
E is the residual matrix of X, and F is the residual matrix of Y.
By establishing the linear regression model (LRM) of characterization factor matrix U sum, as shown in formula (1):
U=TB+Ed (1);
Wherein, Ed is error matrix, and B is regression coefficient matrix, shown in the solution such as formula (2) of B:
B=(T ' T)-1T′U (2);
Using the least square model of foundation, shown in the predictor formula such as formula (3) to the olive oil (unknown sample) of acquisition:
Y=x (U ' X) ' BQ (3);
Wherein, x is the spectrum of unknown sample, and y is the concentration prediction value of unknown sample.
Step S6, the olive oil of acquisition is detected using the multiple linear regression model of foundation.
Position sample is obtained after carrying out step S2, step S3 and pretreatment for the olive oil unknown sample that needs detect
This averaged spectrum, is inputted multiple linear regression model, and prediction obtains the concentration prediction value of unknown sample.
According to the concentration prediction value being calculated, it can be determined that whether the olive oil unknown sample acquired is adulterated.
The experimental result of the present embodiment is as shown in table 1:
Table 1
Wherein SPA-PLSR indicates to use successive projection algorithm SPA, and the experimental result under partial least square model;
SPA-MLR indicates to use successive projection algorithm SPA, and the experimental result under multiple linear regression model.
As a result show that the residual prediction deviation RPD of SPA-MLR is 4.91, mean square error RMSEV is 0.15, the essence of training set
Degree reaches 96.33%, and the precision of forecast set is 95.47%, and model reaches good estimated performance, than the knot of other model predictions
Fruit is more preferable.
The above embodiments are merely illustrative of the technical solutions of the present invention rather than is limited, without departing substantially from essence of the invention
In the case of refreshing and its essence, those skilled in the art make various corresponding changes and change in accordance with the present invention
Shape, but these corresponding change and deformations should all belong to the protection domain of appended claims of the invention.
Claims (5)
1. a kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated, which is characterized in that described to be based on EO-1 hyperion
The adulterated detection method of the olive oil of imaging technique, including:
It includes pure olive oil and according to the adulterated olive oil sample of preset ratio to obtain;
High spectrum image acquisition is carried out to the olive oil sample of acquisition, obtains the high spectrum image of sample, and carry out black and white correction;
The area-of-interest of the high spectrum image of sample is extracted, the flat of the spectral reflectivity of all pixels in area-of-interest is calculated
Averaged spectrum of the mean value as each sample;
The averaged spectrum of each sample is pre-processed, eight characteristic wavelengths are gone out using successive projection algorithms selection, respectively
471.27nm、503.22nm、524.39nm、564.70nm、617.04nm、722.89nm、837.13nm、927.49nm;
According to the averaged spectrum of the characteristic wave bands of selection and sample, establishing multiple linear regression model is:
Y=β0+β1R471.27nm+β2R503.22nm+β3R524.39nm+β4R564.70nm+β5R617.04nm+β6R722.89nm+β7R837.13nm+β8R927.49nm;
Wherein y is olive oil concentration prediction value, R471.27nm、R503.22nm、R524.39nm、R564.70nm、R617.04nm、R722.89nm、
R837.13nm、R927.49nmFor characteristic wavelength 471.27nm, 503.22nm, 524.39nm, 564.70nm, 617.04nm,
Averaged spectrum reflectivity at 722.89nm, 837.13nm, 927.49nm, β0For constant term, β1、β2…β8For regression coefficient;
The olive oil of acquisition is detected using the multiple linear regression model of foundation.
2. the adulterated detection method of the olive oil based on high light spectrum image-forming technology as described in claim 1, which is characterized in that institute
The high spectrum image for obtaining sample is stated, and carries out black and white correction, using following formula:
Wherein:R is image after correction, R0It is original sample image, W is whiteboard images, and B is dark background image.
3. the adulterated detection method of the olive oil based on high light spectrum image-forming technology as described in claim 1, which is characterized in that institute
It states and the averaged spectrum of each sample is pre-processed, including:
By using standard, just too the averaged spectrum of olive oil sample is being standardized by variable;
It is filtered again by Savitzky-Golay methods.
4. the adulterated detection method of the olive oil based on high light spectrum image-forming technology as described in claim 1, which is characterized in that institute
Stating olive oil sample includes:Olive oil and corn oil 10:First group of sample that 1 ratio is mixed, olive oil and corn oil 5:1
First group of sample that ratio is mixed, olive oil and corn oil 3:Third group sample that 1 ratio is mixed and pure
The 4th group of sample of olive oil.
5. the adulterated detection method of the olive oil based on high light spectrum image-forming technology as claimed in claim 4, which is characterized in that institute
It states and establishes multiple linear regression model and be:
Y=0.718-7.46R471.27nm+0.13R503.22nm+0.274R524.39nm+3.46R564.70nm-2.26R617.04nm+
0.5R722.89nm-1.27R837.13nm+0.82R927.49nm;
Wherein y is olive oil concentration prediction value, R471.27nm、R503.22nm、R524.39nm、R564.70nm、R617.04nm、R722.89nm、
R837.13nm、R927.49nmFor characteristic wavelength 471.27nm, 503.22nm, 524.39nm, 564.70nm, 617.04nm,
Averaged spectrum reflectivity at 722.89nm, 837.13nm, 927.49nm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810062042.6A CN108398391A (en) | 2018-01-23 | 2018-01-23 | A kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810062042.6A CN108398391A (en) | 2018-01-23 | 2018-01-23 | A kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108398391A true CN108398391A (en) | 2018-08-14 |
Family
ID=63094740
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810062042.6A Pending CN108398391A (en) | 2018-01-23 | 2018-01-23 | A kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108398391A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516668A (en) * | 2019-08-16 | 2019-11-29 | 浙江理工大学 | A kind of honey adulteration detection method and device based on high light spectrum image-forming technology |
CN111310571A (en) * | 2020-01-17 | 2020-06-19 | 中国科学院长春光学精密机械与物理研究所 | Hyperspectral image classification method and device based on spatial-spectral-dimensional filtering |
CN111398238A (en) * | 2020-05-13 | 2020-07-10 | 安徽理工大学 | Laser-induced fluorescence spectrum identification method for edible oil doped with castor oil |
CN112819062A (en) * | 2021-01-26 | 2021-05-18 | 淮阴工学院 | Fluorescence spectrum quadratic characteristic selection method based on mixed particle swarm and continuous projection |
CN113655072A (en) * | 2021-08-20 | 2021-11-16 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a surface of a sample |
CN113959961A (en) * | 2021-12-22 | 2022-01-21 | 广东省农业科学院动物科学研究所 | Hyperspectral image-based tannin additive anti-counterfeiting detection method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101995392A (en) * | 2010-11-15 | 2011-03-30 | 中华人民共和国上海出入境检验检疫局 | Method for rapidly detecting adulteration of olive oil |
CN102735642A (en) * | 2012-07-12 | 2012-10-17 | 河北大学 | Method for quickly and losslessly identifying virgin olive oil and olive-residue oil |
CN104677854A (en) * | 2015-02-13 | 2015-06-03 | 王利兵 | Method for near infrared rapid recognition of olive oil and rapeseed oil doped in olive oil |
CN104880427A (en) * | 2015-05-29 | 2015-09-02 | 华南理工大学 | Rapid pork product moisture content detection method |
-
2018
- 2018-01-23 CN CN201810062042.6A patent/CN108398391A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101995392A (en) * | 2010-11-15 | 2011-03-30 | 中华人民共和国上海出入境检验检疫局 | Method for rapidly detecting adulteration of olive oil |
CN102735642A (en) * | 2012-07-12 | 2012-10-17 | 河北大学 | Method for quickly and losslessly identifying virgin olive oil and olive-residue oil |
CN104677854A (en) * | 2015-02-13 | 2015-06-03 | 王利兵 | Method for near infrared rapid recognition of olive oil and rapeseed oil doped in olive oil |
CN104880427A (en) * | 2015-05-29 | 2015-09-02 | 华南理工大学 | Rapid pork product moisture content detection method |
Non-Patent Citations (5)
Title |
---|
D.M. MARTÍNEZ GILA等: "On-line system based on hyperspectral information to estimate acidity,moisture and peroxides in olive oil samples", 《COMPUTERS AND ELECTRONICS IN AGRICULTURE》 * |
原喆等: "基于光电磁及感官信号的实用植物油真实性快速鉴别方法研究进展", 《食品安全质量检测学报》 * |
周瑶等: "高光谱无损检测辣椒粉中苏丹红浓度", 《光电工程》 * |
庄晓丽等: "近红外光谱和化学计量学方法用于橄榄油品质分析与掺杂量检测", 《光谱学与光谱分析》 * |
汞东军等: "基于近红外光谱的橄榄油中玉米油掺杂量检测", 《食品工业科技》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110516668A (en) * | 2019-08-16 | 2019-11-29 | 浙江理工大学 | A kind of honey adulteration detection method and device based on high light spectrum image-forming technology |
CN111310571A (en) * | 2020-01-17 | 2020-06-19 | 中国科学院长春光学精密机械与物理研究所 | Hyperspectral image classification method and device based on spatial-spectral-dimensional filtering |
CN111398238A (en) * | 2020-05-13 | 2020-07-10 | 安徽理工大学 | Laser-induced fluorescence spectrum identification method for edible oil doped with castor oil |
CN112819062A (en) * | 2021-01-26 | 2021-05-18 | 淮阴工学院 | Fluorescence spectrum quadratic characteristic selection method based on mixed particle swarm and continuous projection |
CN113655072A (en) * | 2021-08-20 | 2021-11-16 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a surface of a sample |
CN113655072B (en) * | 2021-08-20 | 2023-12-26 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a sample surface |
CN113959961A (en) * | 2021-12-22 | 2022-01-21 | 广东省农业科学院动物科学研究所 | Hyperspectral image-based tannin additive anti-counterfeiting detection method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108398391A (en) | A kind of detection method that the olive oil based on high light spectrum image-forming technology is adulterated | |
Zhang et al. | A reliable methodology for determining seed viability by using hyperspectral data from two sides of wheat seeds | |
Yang et al. | Spectral and image integrated analysis of hyperspectral data for waxy corn seed variety classification | |
Tahmasbian et al. | Comparison of hyperspectral imaging and near-infrared spectroscopy to determine nitrogen and carbon concentrations in wheat | |
Temiz et al. | A review of recent studies employing hyperspectral imaging for the determination of food adulteration | |
Helfer et al. | Multispectral cameras and machine learning integrated into portable devices as clay prediction technology | |
Xu et al. | Estimation of leaf nitrogen content in rice using vegetation indices and feature variable optimization with information fusion of multiple-sensor images from UAV | |
Zhang et al. | Identification of hybrid okra seeds based on near-infrared hyperspectral imaging technology | |
Navarro Soto et al. | Fast and reliable determination of virgin olive oil quality by fruit inspection using computer vision | |
Xiao et al. | Application of machine vision system in food detection | |
Yuan et al. | A Novel strategy of clustering informative variables for quantitative analysis of potential toxics element in Tegillarca granosa using laser-induced breakdown spectroscopy | |
Przybył et al. | Neural image analysis and electron microscopy to detect and describe selected quality factors of fruit and vegetable spray-dried powders—Case study: Chokeberry powder | |
CN110516668A (en) | A kind of honey adulteration detection method and device based on high light spectrum image-forming technology | |
Kandpal et al. | Development of a low-cost multi-waveband LED illumination imaging technique for rapid evaluation of fresh meat quality | |
Zhou et al. | Machine learning modeling and prediction of peanut protein content based on spectral images and stoichiometry | |
Sun et al. | Identification of eggs from different production systems based on hyperspectra and CS-SVM | |
Li et al. | Hyperspectral imaging with machine learning approaches for assessing soluble solids content of tribute citru | |
Noguera et al. | New, low-cost, hand-held multispectral device for in-field fruit-ripening assessment | |
Mu et al. | Non‐destructive detection of blueberry skin pigments and intrinsic fruit qualities based on deep learning | |
Przybył et al. | Application of machine learning to assess the quality of food products—case study: Coffee bean | |
Weng et al. | Reflectance spectroscopy with operator difference for determination of behenic acid in edible vegetable oils by using convolutional neural network and polynomial correction | |
Jiang et al. | Variety identification of Chinese Walnuts using hyperspectral imaging combined with chemometrics | |
Gallo et al. | Self-Supervised Convolutional Neural Network Learning in a Hybrid Approach Framework to Estimate Chlorophyll and Nitrogen Content of Maize from Hyperspectral Images | |
Adesokan et al. | A review of the use of Near-Infrared Hyperspectral Imaging (NIR-HSI) techniques for the non-destructive quality assessment of root and tuber crops | |
Fei et al. | The rapid non-destructive detection of the protein and fat contents of sorghum based on hyperspectral imaging |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180814 |
|
WD01 | Invention patent application deemed withdrawn after publication |