CN108593565A - The method of on-line quick detection chicken pseudomonad content - Google Patents
The method of on-line quick detection chicken pseudomonad content Download PDFInfo
- Publication number
- CN108593565A CN108593565A CN201810225151.5A CN201810225151A CN108593565A CN 108593565 A CN108593565 A CN 108593565A CN 201810225151 A CN201810225151 A CN 201810225151A CN 108593565 A CN108593565 A CN 108593565A
- Authority
- CN
- China
- Prior art keywords
- pseudomonad
- content
- chicken
- spectrogram
- sample
- 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
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
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 the method for on-line quick detection chicken pseudomonad content, the high spectrum image of acquisition correction collection chicken meat sample pre-processes the spectrogram of acquisition and carries out the identification of target area and the extraction of spectrogram average spectral data again;The spectroscopic data of extraction is substituted into formula to obtain the final product.In order to reject a large amount of redundancy when the present invention extracts 35 most optimum wavelengths out of 484 all bands, extract useful information, to reduce the calculation amount of data analysis, to improve the precision of partial least square model, to realize the demand of the large-scale online production of meat enterprise.Compared with prior art, the invention has the advantages that:The present invention is not required to pre-process sample, only carries out non-contacting spectral scan and no destructiveness to sample;The present invention does not use any chemical reagents, i.e., green and cost-effective;The present invention is easily operated and saves the time, can realize the extensive on-line checking of chicken pseudomonad content.
Description
Technical field
The present invention relates to and Food Quality and Safety detection field, and in particular to on-line quick detection chicken pseudomonad contains
The method of amount.
Background technology
Chicken is one of the main source of mankind's meat.Compared with pork, beef and mutton, because it is with high protein, low
Fat, the features such as low cholesterol and production cost are low, cheap, and it is more and more favored by consumers.Currently, chilled fresh chicken
It is increasingly becoming the dominant form of China's consumption, but chilled fresh chicken has the characteristics that height is perishable during refrigeration, because false
Monad is a kind of Gram-negative bacteria and the speed of growth at refrigerated temperatures is faster than other polluted bacterias, therefore false unit cell
Bacterium is the main spoilage organisms for causing chilled fresh chicken putrid and deteriorated.General new fresh chicken meat is stored under conditions of 4 DEG C, goods
The frame phase is generally 3-5 days, and putrid and deteriorated chicken can lose its use value to cause the waste of resource, therefore realizes chicken
The quick Clinical significance of detecting of spoilage organisms is great in meat.Currently, the detection method of false pseudomonad is still GB 4789.2- in chicken
2016《Food microbiological examination total plate count measures》Though the method testing result relatively accurately need to locate sample in advance
Reason, and with complex for operation step, detection cycle is long, costly using chemical reagent, destroys sample and can not achieve quickly
Lossless large batch of online detection requirements.By literature search, the fast non-destructive detection method of false pseudomonad is also in chicken at present
It is not developed, but China's meat industry just develops towards the detection technique direction of quick nondestructive.
In recent years, Hyperspectral imager can detect the inside quality and external sort of sample simultaneously, and also have
Quickly, lossless, to sample without pre-process the advantages that, this technology has become the research hotspot of meat field of non destructive testing,
The achievement felt quite pleased is achieved, however the detection report in terms of chicken vacation unit cell is less..
Invention content
In order to solve the deficiencies in the prior art, the present invention provides the sides of on-line quick detection chicken pseudomonad content
Method.
The technical scheme is that:The method of on-line quick detection chicken pseudomonad content, acquisition correction collection chicken
The high spectrum image of sample pre-processes the spectrogram of acquisition identification and the spectrogram average light for carrying out target area again
The extraction of modal data;The spectroscopic data of extraction is substituted into following formula up to YFalse pseudomonad=14.823+42.189X907.14nm-
88.271X912.081nm+164.26X920.316nm-431.331X928.551nm+108.323X936.784nm+222.683X946.664nm+
120.921X951.603nm-147.122X981.2351nm+57.87X1030.605nm+89.061X1101.347nm-34.649X1122.732nm-
80.28X1155.631nm+125.579X1190.356nm-137.566X1216.498nm+118.471X1242.824nm+72.852X1265.862nm-
226.37X1302.073nm-124.863X1318.536nm+64.205X1344.883nm-54.735X1361.354nm+53.882X1377.827nm-
23.651X1386.066nm-54.867X1466.854nm+46.491X1480.054nm+51.849X1501.512nm-29.206X1546.106nm+
18.114X1549.411nm+39.299X1587.437nm-55.824X1590.745nm+35.58X1622.186nm-165.8X1650.339nm+
37.113X1656.966nm+136.824X1680.351nm-123.802X1690.121nm+108.675X1698.415nm, wherein YFalse pseudomonadFor chicken
The content of false pseudomonad, X in brisket907.14nm、X912.081nm、X920.316nm、X928.551nm、X936.784nm、X946.664nm、
X951.603nm、X981.235nm、X1030.605nm、X1101.347nm、X1122.732nm、X1155.631nm、X1190.356、X1216.498nm、X1242.824nm、
X1265.862nm、X1302.073nm、X1318.536nm、X1344.883nm、X1361.354nm、X1377.827nm、X1386.066nm、X1466.854nm、
X1480.054nm、X1501.512nm、X1546.106nm、X1549.411nm、X1587.437nm、X1590.745nm、X1622.186nm、X1650.339nm、
X1656.966nm、X1680.351nm、X1690.121nm、X1698.415nmRespectively wavelength 907.14nm, 912.081nm, 920.316nm,
928.551nm、936.784nm、946.664nm、951.603nm、981.235nm、1030.605nm、1101.347nm、
1122.732nm、1155.631nm、1190.356nm、1216.498nm、1242.824nm、1265.862nm、1302.073nm、
1318.536nm、1344.883nm、1361.354nm、1377.827nm、1386.066nm、1466.854nm、1480.054nm、
1501.512nm、1546.106nm、1549.411nm、1587.437nm、1590.745nm、1622.186nm、1650.339nm、
Spectral reflectance values at 1656.966nm, 1680.351nm, 1690.121nm, 1698.415nm, related coefficient R=
0.976, root-mean-square error RMSE=0.318.
Further improvement of the present invention includes:
I.e. black and white plate correction is pre-processed to the spectrogram of acquisition to carry out according to following formula:
Wherein R is the image after correction, RrFor original spectrum image;IbFor blackboard image, reflectivity 0%, IpIt is white
Plate image, reflectivity 99.9%.
The defects of present invention is that make up prior art operation cumbersome, and cultivation cycle is long, costly and destruction sample, and provide
It is a kind of without pretreatment, non-destructive, low quick, easily operated and expense the features such as high light spectrum image-forming technology detected with this
Enterobacteria number in chicken.
In order to reject a large amount of redundancy when the present invention extracts 35 most optimum wavelengths out of 484 all bands, extraction has
Information, to reduce the calculation amount of data analysis, to improve the precision of partial least square model, to realize that meat enterprise is big
The demand of the online production of scale.Compared with prior art, the invention has the advantages that:The present invention is not to destroying sample
In the case of product, the pseudomonad content that non-contacting spectral scan can be obtained sample only need to be carried out to sample;Experiment process
In reduce the accidental error caused by manual operation;The extensive of Fresh Grade Breast pseudomonad content may be implemented in the present invention
On-line checking.
The invention has the advantages that:The present invention only needs to obtain the spectroscopic data of sample, most acquisition
Spectral reflectance values under excellent wavelength are brought directly to can be obtained enterobacteria in sample in built optimum prediction model
Content greatly improves work efficiency;Any chemical reagents are not used during experiment, that is, are saved money and environmentally friendly;Sample without
It need to be pre-processed, need to only carry out non-contacting spectral scan to the no destructiveness of sample, it can be achieved that the big rule of chicken enterobacteria
Mould on-line checking.
Description of the drawings
Fig. 1 is the spectral reflectance values characteristic pattern of 87 calibration set samples of embodiment.
Fig. 2 is the extraction figure of the Fresh Grade Breast most optimum wavelengths of embodiment.
Correlation between Fig. 3 Fresh Grade Breast vacation pseudomonad predicted value and measured value.
Specific implementation mode
It elaborates to the present invention with reference to embodiment.
Embodiment
A kind of method and step of quick nondestructive on-line checking chicken pseudomonad content of the present embodiment is as follows:
(1) the monoblock fresh grade breast of purchase is divided into the small sample of 3cm*3cm*1cm in laboratory, obtains 87 altogether
Small sample is known as calibration set, then is divided into 7 parts, puts the disposable plastic box with lid into respectively, is finally placed on 4
DEG C refrigerator in refrigerated, at 0,1,2,3,4,5,6 day, each portion that takes out was tested.
(2) before the test, 30min opens Hyperspectral imager preheating in advance, while chicken sample also shifts to an earlier date 30min
It takes out out of refrigerator and is dried the moisture on its surface with blotting paper after its recovery to room temperature, the state of imaging system is adjusted to most
Good i.e. spectrum picture picking rate is 6.54mm/s, when the time for exposure is 4.65ms, then carries out the guarantor of blackboard and whiteboard images
It deposits, finally carries out the acquisition of sample image;The wave-length coverage for the sample that this system can acquire is 900-1700nm.
(3) to acquiring the sample of spectrum picture immediately according to GB 4789.2-2016《Food microbiological examination bacterium colony
Sum measures》Method detects the content data statistics such as table 1 of its false pseudomonad:
The false pseudomonad content of 1 87 calibration set samples of table
(4) it is carried out black and white board correction according to following formula to obtaining spectrum picture;
Wherein R is the image after correction, R0For original spectrum image;RbFor blackboard image, reflectivity 0%, RpIt is white
Plate image, reflectivity 99.9%.
(5) after being corrected to primary light spectrogram, the area-of-interest in image is identified first and spectroscopic data is carried out
The spectroscopic data of extraction, extraction is spectral reflectance values, that is, spectral signature such as Fig. 1 of the 87 calibration set samples obtained:
(6) spectroscopic data and the spectral reflectance in step (3) for carrying out associated steps (4) using Partial Least Squares (PLSR)
All band (484 wavelength) quantitative model between rate Value Data, the i.e. all band of chicken vacation pseudomonad content minimum two partially
Multiply model, when the coefficient R of institute's established model is closer to 1, root-mean-square error RMSE gets over hour and when modeling collection and intersection are tested
Demonstrate,prove collection related coefficient and root-mean-square error closer to when, illustrate modeling collection model precision and stability it is higher, as a result
Such as the following table 2;
The all band PLSR prediction models of 2 calibration set sample vacation pseudomonad content of table
It can show that the coefficient R of modeling collection PLSR models is up to 0.991 from table 2, root-mean-square error 0.199,
The phase relation of middle cross validation collection model and root-mean-square error number also collect all close to modeling, than the result shows that the model that modeling collects
Precision is high and stablizes.
(7) 484 wavelength are shared in all band partial least square model that step (6) is built, and not all wave
It is long that all there is contribution to institute's established model, wherein there are a large amount of redundancy, in order to reduce the calculation amount of data analysis to reach
To the effect of Optimized model, therefore redundancy need to be rejected and retain useful information, optimal wave is extracted by regression coefficient method (RC)
It is long, as a result such as Fig. 2.
(8) 35 most optimum wavelengths are extracted from all band partial least square model using regression coefficient method, respectively
907.14nm、912.081nm、920.316nm、928.551nm、936.784nm、946.664nm、951.603nm、
981.235nm、1030.605nm、1101.347nm、1122.732nm、1155.631nm、1190.176nm、1216.498nm、
1242.824nm、1265.862nm、1302.073nm、1318.536nm、1344.883nm、1361.354nm、1377.827nm、
1386.066nm、1466.854nm、1480.054nm、1501.512nm、1546.106nm、1549.411nm、1587.437nm、
1590.745nm, 1622.186nm, 1650.339nm, 1656.966nm, 1680.171nm, 1690.121nm, 1698.415nm,
The partial least square model of the Fresh Grade Breast vacation pseudomonad content after optimization is established using most optimum wavelengths as input variable, as a result
Such as table 3:
The most optimum wavelengths PLSR prediction models of 3 calibration set sample vacation pseudomonad content of table
It can show that the related coefficient for the modeling collection established using 35 most optimum wavelengths is that 0.976, RMSE is from table 3
0.318, and cross validation collection with modeling collection very close to, therefore use 35 most optimum wavelengths establish chicken vacation pseudomonad
The precision and stabilization of PLSR models are all fine.
(9) the partial least square model i.e. formula of calibration model of the chicken vacation pseudomonad of the most optimum wavelengths obtained
For:YFalse pseudomonad=14.823+42.189X907.14nm-88.271X912.081nm+164.26X920.316nm-431.331X928.551nm+
108.323X936.784nm+222.683X946.664nm+120.921X951.603nm-147.122X981.2351nm+57.102X1030.605nm+
89.061X1101.347nm-34.649X1122.732nm-80.28X1155.631nm+125.579X1190.176nm-137.566X1216.498nm+
118.471X1242.824nm+72.852X1265.862nm-226.37X1302.073nm-124.863X1318.536nm+64.205X1344.883nm-
54.735X1361.354nm+53.882X1377.827nm-23.651X1386.066nm-54.867X1466.854nm+46.491X1480.054nm+
51.849X1501.512nm-29.206X1546.106nm+18.114X1549.411nm+39.299X1587.437nm-55.824X1590.745nm+
17.58X1622.186nm-165.8X1650.339nm+37.113X1656.966nm+136.824X1680.171nm-123.802X1690.121nm+
108.675X1698.415nm, wherein YFalse pseudomonadFor the content of false pseudomonad in Fresh Grade Breast, X907.14nm、X912.081nm、X920.316nm、
X928.551nm、X936.784nm、X946.664nm、X951.603nm、X981.235nm、X1030.605nm、X1101.347nm、X1122.732nm、X1155.631nm、
X1190.176、X1216.498nm、X1242.824nm、X1265.862nm、X1302.073nm、X1318.536nm、X1344.883nm、X1361.354nm、X1377.827nm、
X1386.066nm、X1466.854nm、X1480.054nm、X1501.512nm、X1546.106nm、X1549.411nm、X1587.437nm、X1590.745nm、
X1622.186nm、X1650.339nm、X1656.966nm、X1680.171nm、X1690.121nm、X1698.415nmRespectively wavelength 907.14nm,
912.081nm、920.316nm、928.551nm、936.784nm、946.664nm、951.603nm、981.235nm、
1030.605nm、1101.347nm、1122.732nm、1155.631nm、1190.176nm、1216.498nm、1242.824nm、
1265.862nm、1302.073nm、1318.536nm、1344.883nm、1361.354nm、1377.827nm、1386.066nm、
1466.854nm、1480.054nm、1501.512nm、1546.106nm、1549.411nm、1587.437nm、1590.745nm、
Spectral reflectance at 1622.186nm, 1650.339nm, 1656.966nm, 1680.171nm, 1690.121nm, 1698.415nm
Rate value.The content of Fresh Grade Breast vacation pseudomonad to be measured is detected using this model.
(10) it tests
The high spectrum image for acquiring 29 chicken small samples to be measured, spectral intensity is carried out to the spectrum picture of acquisition respectively
Correction and the extraction of spectral reflectivity Value Data;
By each sample to be tested of acquisition 907.14nm, 912.081nm, 920.316nm, 928.551nm,
936.784nm、946.664nm、951.603nm、981.235nm、1030.605nm、1101.347nm、1122.732nm、
1155.631nm、1190.176nm、1216.498nm、1242.824nm、1265.862nm、1302.073nm、1318.536nm、
1344.883nm、1361.354nm、1377.827nm、1386.066nm、1466.854nm、1480.054nm、1501.512nm、
1546.106nm、1549.411nm、1587.437nm、1590.745nm、1622.186nm、1650.339nm、1656.966nm、
Spectral reflectance values under at 1680.171nm, 1690.121nm, 1698.415nm are input in calibration model, can obtain 29
The content of a Fresh Grade Breast vacation pseudomonad to be measured.The false pseudomonad content for the Fresh Grade Breast that prediction is obtained and use
GB4789.2-2016《Food microbiological examination total plate count measures》False pseudomonad content measured by method carries out linear
Correlation, obtained related coefficient are up to 0.924, root-mean-square error 0.630, the relevant pole between measured value and predicted value
It is good.As a result such as Fig. 3.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (2)
1. the method for on-line quick detection chicken pseudomonad content, which is characterized in that the bloom of acquisition correction collection chicken meat sample
Spectrogram picture pre-processes the spectrogram of acquisition and carries out the identification of target area and proposing for spectrogram average spectral data again
It takes;The spectroscopic data of extraction is substituted into following formula up to YFalse pseudomonad=14.823+42.189X907.14nm-88.271X912.081nm+
164.26X920.316nm-431.331X928.551nm+108.323X936.784nm+222.683X946.664nm+120.921X951.603nm-
147.122X981.2351nm+57.87X1030.605nm+89.061X1101.347nm-34.649X1122.732nm-80.28X1155.631nm+
125.579X1190.356nm-137.566X1216.498nm+118.471X1242.824nm+72.852X1265.862nm-226.37X1302.073nm-
124.863X1318.536nm+64.205X1344.883nm-54.735X1361.354nm+53.882X1377.827nm-23.651X1386.066nm-
54.867X1466.854nm+46.491X1480.054nm+51.849X1501.512nm-29.206X1546.106nm+18.114X1549.411nm+
39.299X1587.437nm-55.824X1590.745nm+35.58X1622.186nm-165.8X1650.339nm+37.113X1656.966nm+
136.824X1680.351nm-123.802X1690.121nm+108.675X1698.415nm, wherein YFalse pseudomonadFor false pseudomonad in Fresh Grade Breast
Content, X907.14nm、X912.081nm、X920.316nm、X928.551nm、X936.784nm、X946.664nm、X951.603nm、X981.235nm、
X1030.605nm、X1101.347nm、X1122.732nm、X1155.631nm、X1190.356、X1216.498nm、X1242.824nm、X1265.862nm、X1302.073nm、
X1318.536nm、X1344.883nm、X1361.354nm、X1377.827nm、X1386.066nm、X1466.854nm、X1480.054nm、X1501.512nm、
X1546.106nm、X1549.411nm、X1587.437nm、X1590.745nm、X1622.186nm、X1650.339nm、X1656.966nm、X1680.351nm、
X1690.121nm、X1698.415nmRespectively wavelength 907.14nm, 912.081nm, 920.316nm, 928.551nm, 936.784nm,
946.664nm、951.603nm、981.235nm、1030.605nm、1101.347nm、1122.732nm、1155.631nm、
1190.356nm、1216.498nm、1242.824nm、1265.862nm、1302.073nm、1318.536nm、1344.883nm、
1361.354nm、1377.827nm、1386.066nm、1466.854nm、1480.054nm、1501.512nm、1546.106nm、
1549.411nm、1587.437nm、1590.745nm、1622.186nm、1650.339nm、1656.966nm、1680.351nm、
Spectral reflectance values at 1690.121nm, 1698.415nm, related coefficient R=0.976, root-mean-square error RMSE=
0.318。
2. the method for on-line quick detection chicken pseudomonad content according to claim 1, which is characterized in that obtaining
Spectrogram pre-processed i.e. black and white plate correction carried out according to following formula:
Wherein R is the image after correction, and R0 is original spectrum image;Rb is blackboard image, and reflectivity 0%, Rp is blank
Image, reflectivity 99.9%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810225151.5A CN108593565A (en) | 2018-03-19 | 2018-03-19 | The method of on-line quick detection chicken pseudomonad content |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810225151.5A CN108593565A (en) | 2018-03-19 | 2018-03-19 | The method of on-line quick detection chicken pseudomonad content |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108593565A true CN108593565A (en) | 2018-09-28 |
Family
ID=63626815
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810225151.5A Pending CN108593565A (en) | 2018-03-19 | 2018-03-19 | The method of on-line quick detection chicken pseudomonad content |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108593565A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103439285A (en) * | 2013-08-19 | 2013-12-11 | 华南理工大学 | Fish fillet freshness detection method based on hyperspectral imaging |
CN104297136A (en) * | 2014-10-28 | 2015-01-21 | 南京农业大学 | Hyperspectral image-based method for forecasting growth of pseudomonas aeruginosa |
CN106383095A (en) * | 2016-11-03 | 2017-02-08 | 宁夏大学 | Device and method for detecting total number of bacteria on surface of cooled mutton |
CN107271375A (en) * | 2017-07-21 | 2017-10-20 | 石河子大学 | A kind of high spectral image detecting method of quality of mutton index |
-
2018
- 2018-03-19 CN CN201810225151.5A patent/CN108593565A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103439285A (en) * | 2013-08-19 | 2013-12-11 | 华南理工大学 | Fish fillet freshness detection method based on hyperspectral imaging |
CN104297136A (en) * | 2014-10-28 | 2015-01-21 | 南京农业大学 | Hyperspectral image-based method for forecasting growth of pseudomonas aeruginosa |
CN106383095A (en) * | 2016-11-03 | 2017-02-08 | 宁夏大学 | Device and method for detecting total number of bacteria on surface of cooled mutton |
CN107271375A (en) * | 2017-07-21 | 2017-10-20 | 石河子大学 | A kind of high spectral image detecting method of quality of mutton index |
Non-Patent Citations (3)
Title |
---|
HONG-JU HE AND DA-WEN SUN: "Toward enhancement in prediction of Pseudomonas counts distribution in salmon fillets using NIR hyperspectral imaging", 《LWT - FOOD SCIENCE AND TECHNOLOGY》 * |
QIAN YANG ET AL.: "Development of simplied models for nondestructive hyperspectral imaging monitoring of TVB-N contents in cured meat during drying process", 《JOURNAL OF FOOD ENGINEERING》 * |
YAO-ZE FENG ET AL.: "Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets", 《FOOD CHEMISTRY》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
He et al. | Hyperspectral imaging technology for rapid detection of various microbial contaminants in agricultural and food products | |
Li et al. | Comparative review and the recent progress in detection technologies of meat product adulteration | |
Hassoun et al. | Food quality 4.0: From traditional approaches to digitalized automated analysis | |
Lee et al. | Determination of the total volatile basic nitrogen (TVB-N) content in pork meat using hyperspectral fluorescence imaging | |
Cheng et al. | Pork biogenic amine index (BAI) determination based on chemometric analysis of hyperspectral imaging data | |
Yu et al. | Nondestructive freshness discriminating of shrimp using visible/near-infrared hyperspectral imaging technique and deep learning algorithm | |
Feng et al. | Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets | |
Alexandrakis et al. | Rapid non-destructive detection of spoilage of intact chicken breast muscle using near-infrared and Fourier transform mid-infrared spectroscopy and multivariate statistics | |
Cheng et al. | Enhancing visible and near-infrared hyperspectral imaging prediction of TVB-N level for fish fillet freshness evaluation by filtering optimal variables | |
Barbin et al. | Non-destructive assessment of microbial contamination in porcine meat using NIR hyperspectral imaging | |
Barbin et al. | Non-destructive determination of chemical composition in intact and minced pork using near-infrared hyperspectral imaging | |
Xu et al. | Rapid Pseudomonas species identification from chicken by integrating colorimetric sensors with near-infrared spectroscopy | |
Kalinowska et al. | Smartphones as tools for equitable food quality assessment | |
CN104049068B (en) | The non-destructive determination device of fresh poultry meat freshness and assay method | |
JP5856741B2 (en) | Aflatoxin quantification method, aflatoxin quantification apparatus, and program | |
Ren et al. | Using Raman spectroscopy and chemometrics to identify the growth phase of Lactobacillus casei Zhang during batch culture at the single-cell level | |
Zhu et al. | Determination of total acid content and moisture content during solid-state fermentation processes using hyperspectral imaging | |
Yoon et al. | Differentiation of big-six non-O157 Shiga-toxin producing Escherichia coli (STEC) on spread plates of mixed cultures using hyperspectral imaging | |
He et al. | Selection of informative spectral wavelength for evaluating and visualising Enterobacteriaceae contamination of salmon flesh | |
CN102181514A (en) | Method for rapidly and nondestructively detecting colony count of chilled meat | |
Lin et al. | A pH-Responsive colourimetric sensor array based on machine learning for real-time monitoring of beef freshness | |
CN104297136A (en) | Hyperspectral image-based method for forecasting growth of pseudomonas aeruginosa | |
Chen et al. | Critical review and recent advances of emerging real-time and non-destructive strategies for meat spoilage monitoring | |
CN108645798A (en) | The method of on-line quick detection chicken content of lactic acid bacteria | |
CN108593565A (en) | The method of on-line quick detection chicken pseudomonad content |
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: 20180928 |
|
WD01 | Invention patent application deemed withdrawn after publication |