CN108627475A - Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms - Google Patents
Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms Download PDFInfo
- Publication number
- CN108627475A CN108627475A CN201810224431.4A CN201810224431A CN108627475A CN 108627475 A CN108627475 A CN 108627475A CN 201810224431 A CN201810224431 A CN 201810224431A CN 108627475 A CN108627475 A CN 108627475A
- Authority
- CN
- China
- Prior art keywords
- spectrum
- spectroscopic data
- sample
- image
- line checking
- 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
- 238000001228 spectrum Methods 0.000 title claims abstract description 25
- 241000287828 Gallus gallus Species 0.000 title claims abstract description 14
- 244000005700 microbiome Species 0.000 title claims abstract description 13
- 238000005516 engineering process Methods 0.000 title claims abstract description 8
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 20
- 230000003595 spectral effect Effects 0.000 claims abstract description 7
- 210000000481 breast Anatomy 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000002310 reflectometry Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 239000003153 chemical reaction reagent Substances 0.000 abstract description 2
- 238000002474 experimental method Methods 0.000 abstract description 2
- 235000013330 chicken meat Nutrition 0.000 description 13
- 238000000034 method Methods 0.000 description 11
- 235000013372 meat Nutrition 0.000 description 7
- 238000001514 detection method Methods 0.000 description 4
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 241000272201 Columbiformes Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000000038 chest Anatomy 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 235000004213 low-fat Nutrition 0.000 description 1
- 235000013622 meat product Nutrition 0.000 description 1
- 230000000813 microbial effect Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
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 applications in high light spectrum image-forming technology on-line checking chicken content of microorganisms.The present invention only needs to obtain the spectroscopic data of sample, then directly the reflectance value under most optimum wavelengths is brought in the higher prediction model of built precision into the content that can be obtained microorganism in sample, the cultivation cycle of microorganism is substantially reduced, it is saves time and effort；Any chemical reagents are not used during experiment, i.e., it is environmentally friendly and cost-effective；Sample need not be pre-processed, non-contacting spectral scan is directly carried out, have the characteristics that expense destroys the on-line checking, it can be achieved that microorganism to sample.
Description
Technical field
The present invention relates to Food Quality and Safety detection fields, and in particular to a kind of micro- life of quick nondestructive on-line checking chicken
The method of object content.
Background technology
Now, chicken is because having many advantages, such as high protein, low fat, low cholesterol and absorption easy to digest, and increasingly by state
The favor of people.The consumption pattern of China's chicken is mainly cold fresh meat at present, but chicken in cold storage procedure easily by endogenous and
The pollution of inoculating microbe, with the aggravation of microbial contamination, color, smell and the appearance of chicken can also run down, these
Meat is once eaten by mistake by consumer, it will directly damages consumer health.According to the relevant regulations in national standard, meat and meat products
In content of microorganisms will be less than 106.When generally being examined to meat, the inspection of content of microorganisms is essential one of journey
Sequence, national standard has GB 4789.2-2016 to the detection method of total plate count in food (TVC) at present, but the method operation is numerous
Trivial, the period is long, costly and have the shortcomings that breakage to sample, is not suitable for the large-scale on-line checking of meat, can not meet and work as
Modern meat industry is to quick, lossless and automation extensive online detection requirements.
Invention content
The present invention is to make up the defects of prior art operation is cumbersome, and the period is long and costly, and provide one kind and be easy to grasp
Make, the total plate count in chicken is detected with this without pretreatment, detection speed fast high light spectrum image-forming technology.
The technical scheme is that：Provide answering in high light spectrum image-forming technology on-line checking chicken content of microorganisms
With.
Further improvement of the present invention includes：
The application acquires the high spectrum image of sample using near-infrared Hyperspectral imager, to the bloom of acquisition
Spectrogram picture carries out black and white board correction, and to obtain the reflectance value of spectrum, is pre-processed to the spectroscopic data of acquisition, by spectrum number
According to substitution following formula：
YTVC=30.762+317.544X903.845nm-213.711X908.787nm-83.41X917.022nm-120.315X931.844nm
+100.056X 945.017nm+83.501X954.896nm-60.374X1000.985nm+42.225X1037.187nm+56.921X1068.446nm-
81.112X1109.572nm+76.338X1137.536nm-57.781X1163.856nm+75.853X1302.073nm+51.835X1405.841nm-
60.909X1630.464nm-51. 644X1665.252nm+125.476X1690.121nm, wherein YTVCFor the logarithm of total plate count in Fresh Grade Breast
Value, X903.845、 X908.787nm、X917.022nm、X931.844nm、X945.017nm、X954.896nm、X1000.985nm、X1037.187nm、X1068.446nm、
X1109.572nm、X1137.536nm、X1163.856nm、X1302.073nm、X1405.841nm、X1630.464nm、X1665.252nm、X1690.121nm, respectively wave
Grow 903.845nm, 908.787nm, 917.022nm, 931.844nm, 945.017nm, 954.896nm, 1000.985nm,
1037.187nm、1068.446nm、1109.572nm、1137.536nm、1163.856nm、1302.073 nm、
Spectral reflectance values above formula related coefficient at 1405.841nm, 1630.464nm, 1665.252nm, 1690.121nm is R=
0.960, root-mean-square error RMSE=0.464.
The application, the spectrum picture, which carries out black and white board correction, to be corrected according to following formula：
Wherein R is the image after correction, R0For original spectrum image；IdFor blackboard image, reflectivity 0%, IwIt is white
Plate image, reflectivity 99.9%.
The pretreatment of spectroscopic data described in the application be to the spectroscopic data of extraction carry out S-G smoothing processings to get
To pretreated spectroscopic data.
The invention has the advantages that：
The present invention only needs to obtain the spectroscopic data of sample, and then directly the reflectance value under most optimum wavelengths is brought into
The content that can be obtained microorganism in sample in the built higher prediction model of precision, substantially reduces the culture of microorganism
It is period, saves time and effort；Any chemical reagents are not used during experiment, i.e., it is environmentally friendly and cost-effective；Not to sample
It is pre-processed, directly carries out non-contacting spectral scan, have the characteristics that expense is destroyed, it can be achieved that microorganism to sample
On-line checking.
Description of the drawings
Fig. 1 is all band spectral signature figure of 84 Fresh Grade Breast samples；
Fig. 2 is regression coefficient method to the extraction Jing Guo the pretreated Fresh Grade Breast most optimum wavelengths of baseline；
Fig. 3 is regression coefficient method to the extraction Jing Guo the pretreated Fresh Grade Breast most optimum wavelengths of S-G；
Fig. 4 is the relationship between Fresh Grade Breast TVC content predictions value and measured value.
Specific implementation mode
It elaborates to the present invention with reference to embodiment.
Embodiment
(1) fresh grade breast in the present embodiment is selected and is not passed through on bubble and meat purchased from the local market of farm produce
Normal fresh dry chest is test sample.All pigeon breasts are divided into 3cm*3cm*1cm's (long * wide * high) is small in laboratory
84, sample is divided into 7 parts again, is placed in the disposable plastic box with lid, is store respectively in 4 DEG C of refrigerator
It hides 0,1,2,3,4,5,6 day, using as tested Fresh Grade Breast sample；
(2) Hyperspectral imager is preheated 30min in advance, while chicken sample also takes out out of refrigerator and waits for its temperature in advance
Degree restores to the acquisition of spectrum picture after room temperature, is carried out, and spectrum picture picking rate is 6.54mm/s, and the time for exposure is
4.65ms；
(3) its total plate count is detected according to GB 4789.2-2016 methods immediately to the sample for acquiring spectrum picture
Content is denoted as CFU/g, and all data are finally converted to log10(CFU/g) pattern, 84 samples according to from small to large
Be ranked sequentially, calibration set total plate count data statistics such as the following table 1：
The total plate count of 1 calibration set sample of table counts
(4) it is carried out black and white board correction according to following formula to obtaining spectrum picture, to obtain the spectral reflectance of chicken sample
Rate value；
(5) identification that area-of-interest is carried out to corrected spectrogram, to extract the full wave spectroscopic data of sample；
As a result such as Fig. 1：
(1) in order to reduce external environment and instrument itself to influence of noise caused by spectroscopic data, therefore to extraction
Spectroscopic data pre-processed, this time use baseline (baseline) and Savitzky-Golay (S-G) smooth treatment,
Obtain pretreated spectroscopic data.
(2) total bacterium of the calibration set chicken meat sample obtained come establishment step (3) using offset minimum binary (PLSR) algorithm
The prediction model between spectroscopic data in the pretreated calibration set all band that several and step (6) is obtained is fallen, correlation is used
Coefficients R and root-mean-square error RMSE evaluate the precision and stability of institute's established model, when R is smaller closer to 1, RMSE
When, the higher the precision of model the more stable.As a result such as table 2：
The PLSR models for the Fresh Grade Breast TVC that 2 all band of table is established
The smooth pretreated spectroscopic datas of S-G are used as can be drawn from Table 3 and use the pretreated spectroscopic data of baseline
The coefficient R for the PLSR models established is respectively 0.978 and 0.977, and root-mean-square error is respectively 0.350 and 0.353,
Institute's established model precision is high and relatively stablizes.So two kinds of preprocess methods are all more satisfactory.
(3) pass through the smooth pretreated spectrum of Savitzky-Golay (S-G) and baseline is pretreated, in 900-
In 1700nm wavelength, share 486 wavelength, wherein there are a large amount of redundancy, these redundancies to the precision of model and
Stability is not contributed, therefore retains useful information to reject redundancy, optimal to extract by regression coefficient method (RC)
Wavelength, to reduce the calculation amount of data, to improve the precision and stability of model.As a result such as Fig. 2 and Fig. 3：
As can be drawn from Figure 2 17 optimal waves are extracted out of by S-G pretreatment all bands using regression coefficient method
It is long, respectively 903.845,908.787,917.022,931.844,945.017,954.896,1000.985,1037.187,
1068.446、1109.572、1137.536、1163.856、1302.073、1405.841、1630.464、1665.252 、
1690.121, and using being extracted 18 most optimum wavelengths in baseline pretreatment all band, respectively 902.198,910.434,
912.081、915.375、925.257、953.25、1002.631、1068.446、1111.217、1124.377、 1135.891、
1300.427、1339.942、1407.49、1599.016、1686.804、1691.78、1696.756。
(4) total plate count of the calibration set chicken meat sample obtained based on step (3) is extracted respectively in connection with step (8)
17 and 18 most optimum wavelengths, the prediction model of new chicken total plate count is established using offset minimum binary (PLSR) method,
As a result such as table 3：
The PLSR models for the prediction Fresh Grade Breast TVC that 3 most optimum wavelengths of table are established
S-G-PLSR models coefficient R=0.960 established using most optimum wavelengths number, root mean square can be obtained from table
Error RMSEC=0.464 is got well than the related coefficient of Baseline-PLSR models and root-mean-square error, so using optimal
The S-G-PLSR models that wavelength is established are more excellent.
(5) the S-G-PLSR calibration models of the most optimum wavelengths obtained are as follows：
YTVC=30.762+317.544X903.845nm-213.711X908.787nm-83.41X917.022nm-120.315X931.844nm
+ 100.056X945.017nm+83.501X954.896nm-60.374X1000.985nm+42.225X1037.187nm+56.921X1068.446nm-
81.112X1109.572nm+76.338X1137.536nm-57.781X1163.856nm+75.853X1302.073nm+51.835X1405.841nm-
60.909X1630.464nm-51.644X1665.252nm+125.476X1690.121nm, wherein YTVCFor the logarithm of total plate count in Fresh Grade Breast
Value, X903.845、X908.787nm、X917.022nm、X931.844nm、X945.017nm、X954.896nm、X1000.985nm、X1037.187nm、X1068.446nm、
X1109.572nm、X1137.536nm、X1163.856nm、X1302.073nm、X1405.841nm、 X1630.464nm、X1665.252nm、X1690.121nm, respectively
Wavelength 903.845nm, 908.787nm, 917.022nm, 931.844nm, 945.017nm, 954.896nm,
1000.985nm、1037.187nm、1068.446nm、1109.572 nm、1137.536nm、1163.856nm、
1302.073nm, 1405.841nm, 1630.464nm, the spectral reflectance values at 1665.252 nm, 1690.121nm.
(6) it tests
1. acquiring the near-infrared high spectrum image of 28 pieces of Fresh Grade Breast samples to be measured, spectrum picture is corrected, it is interested
The identification in region, the extraction of spectroscopic data and to spectroscopic data carry out S-G pretreatments, the spectrum number after being pre-processed
According to.
2. the pretreated spectroscopic data of gained is brought into the S-G-PLSR for the most optimum wavelengths that step (10) is obtained
In calibration model, the logarithm of clump count measured by the logarithm and conventional method of the prediction total plate count of tested Fresh Grade Breast can be obtained
Value is associated, and related coefficient is up to 0.976, root-mean-square error 0.435, between actual value and predicted value it is related very
It is good.As a result such as Fig. 4.Show that the difference very little of the method and actually measured Fresh Grade Breast total plate count of the present invention, the invention have
Prodigious feasibility.
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 (4)
1. the application in high light spectrum image-forming technology on-line checking chicken content of microorganisms.
2. application according to claim 1, which is characterized in that utilize the height of near-infrared Hyperspectral imager acquisition sample
Spectrum picture carries out black and white board correction the high spectrum image of acquisition, to obtain the reflectance value of spectrum, to the spectrum number of acquisition
According to being pre-processed, spectroscopic data is substituted into following formula：
YTVC=30.762+317.544X903.845nm-213.711X908.787nm-83.41X917.022nm-120.315X931.844nm+
100.056X945.017nm+83.501X954.896nm-60.374X1000.985nm+42.225X1037.187nm+56.921X1068.446nm-
81.112X1109.572nm+76.338X1137.536nm-57.781X1163.856nm+75.853X1302.073nm+51.835X1405.841nm-
60.909X1630.464nm-51.644X1665.252nm+125.476X1690.121nm, wherein YTVCFor the logarithm of total plate count in Fresh Grade Breast
Value, X903.845、X908.787nm、X917.022nm、X931.844nm、X945.017nm、X954.896nm、X1000.985nm、X1037.187nm、X1068.446nm、
X1109.572nm、X1137.536nm、X1163.856nm、X1302.073nm、X1405.841nm、X1630.464nm、X1665.252nm、X1690.121nm, respectively wave
Grow 903.845nm, 908.787nm, 917.022nm, 931.844nm, 945.017nm, 954.896nm, 1000.985nm,
1037.187nm、1068.446nm、1109.572nm、1137.536nm、1163.856nm、1302.073nm、1405.841nm、
Spectral reflectance values above formula related coefficient at 1630.464nm, 1665.252nm, 1690.121nm is R=0.960, root mean square
Error RMSE=0.464.
3. application according to claim 2, which is characterized in that the spectrum picture carries out black and white board correction will be according to following
Formula is corrected：
Wherein R is the image after correction, R0For original spectrum image；IdFor blackboard image, reflectivity 0%, IwFor blank figure
Picture, reflectivity 99.9%.
4. application according to claim 2, which is characterized in that the spectroscopic data pretreatment is the spectroscopic data to extraction
S-G smoothing processings are carried out to get to pretreated spectroscopic data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810224431.4A CN108627475A (en) | 2018-03-19 | 2018-03-19 | Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810224431.4A CN108627475A (en) | 2018-03-19 | 2018-03-19 | Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108627475A true CN108627475A (en) | 2018-10-09 |
Family
ID=63706351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810224431.4A Pending CN108627475A (en) | 2018-03-19 | 2018-03-19 | Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108627475A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114252318A (en) * | 2021-12-27 | 2022-03-29 | 浙江大学 | Method and system for detecting staphylococcus aureus in chicken |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564964A (en) * | 2011-12-29 | 2012-07-11 | 南京林业大学 | Spectral image-based meat quality visual non-contact detection method |
| CN106404692A (en) * | 2016-11-09 | 2017-02-15 | 大连工业大学 | Method for detecting freshness grade of instant sea cucumber by using hyperspectral imaging technology |
| CN106525875A (en) * | 2016-12-07 | 2017-03-22 | 江苏大学 | Hyperspectral detection method of color and texture changes in preserved meat salting process |
| CN106596416A (en) * | 2016-11-25 | 2017-04-26 | 华中农业大学 | Chilled fresh meat quality non-destructive testing method based on hyperspectral imaging technology |
| WO2017160382A1 (en) * | 2016-03-17 | 2017-09-21 | Raytheon Company | Ultraviolet led and phosphor based hyperspectral calibrator |
| CN107543801A (en) * | 2017-08-25 | 2018-01-05 | 天津商业大学 | Hardness Prediction method after mango impact injury based on EO-1 hyperion |
-
2018
- 2018-03-19 CN CN201810224431.4A patent/CN108627475A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564964A (en) * | 2011-12-29 | 2012-07-11 | 南京林业大学 | Spectral image-based meat quality visual non-contact detection method |
| WO2017160382A1 (en) * | 2016-03-17 | 2017-09-21 | Raytheon Company | Ultraviolet led and phosphor based hyperspectral calibrator |
| CN106404692A (en) * | 2016-11-09 | 2017-02-15 | 大连工业大学 | Method for detecting freshness grade of instant sea cucumber by using hyperspectral imaging technology |
| CN106596416A (en) * | 2016-11-25 | 2017-04-26 | 华中农业大学 | Chilled fresh meat quality non-destructive testing method based on hyperspectral imaging technology |
| CN106525875A (en) * | 2016-12-07 | 2017-03-22 | 江苏大学 | Hyperspectral detection method of color and texture changes in preserved meat salting process |
| CN107543801A (en) * | 2017-08-25 | 2018-01-05 | 天津商业大学 | Hardness Prediction method after mango impact injury based on EO-1 hyperion |
Non-Patent Citations (2)
| 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》 * |
| YAO-ZE FENG ET AL.: "Determination of total viable count (TVC) in chicken breast fillets by near-infrared hyperspectral imaging and spectroscopic transforms", 《TALANTA》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114252318A (en) * | 2021-12-27 | 2022-03-29 | 浙江大学 | Method and system for detecting staphylococcus aureus in chicken |
| CN114252318B (en) * | 2021-12-27 | 2023-11-17 | 浙江大学 | Method and system for detecting staphylococcus aureus in chicken |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tao et al. | A nondestructive method for prediction of total viable count in pork meat by hyperspectral scattering imaging | |
| Rahman et al. | Quality assessment of beef using Computer Vision Technology | |
| CN104297165B (en) | It is a kind of based on high spectrum image to the method for rot fungi growth prediction | |
| CN103439285A (en) | Fish fillet freshness detection method based on hyperspectral imaging | |
| CN104049068B (en) | The non-destructive determination device of fresh poultry meat freshness and assay method | |
| Urmila et al. | Quantifying of total volatile basic nitrogen (TVB-N) content in chicken using a colorimetric sensor array and nonlinear regression tool | |
| CN204287031U (en) | A kind of online the cannot-harm-detection device of fish freshness based on high light spectrum image-forming technology | |
| Yang et al. | Rapid determination of biogenic amines in cooked beef using hyperspectral imaging with sparse representation algorithm | |
| Yang et al. | Detection of total viable count in spiced beef using hyperspectral imaging combined with wavelet transform and multiway partial least squares algorithm | |
| Yang et al. | Detection of the freshness state of cooked beef during storage using hyperspectral imaging | |
| Wu et al. | Non-destructive techniques for the analysis and evaluation of meat quality and safety: A review | |
| Oyewole et al. | Effect of length of fermentation on the functional characteristics of fermented cassava'fufu' | |
| Rodríguez-Pulido et al. | Research progress in imaging technology for assessing quality in wine grapes and seeds | |
| CN102181514A (en) | Method for rapidly and nondestructively detecting colony count of chilled meat | |
| Zhang et al. | Rapid determination of the oil and moisture contents in Camellia gauchowensis Chang and Camellia semiserrata Chi seeds kernels by near-infrared reflectance spectroscopy | |
| CN104297136A (en) | Hyperspectral image-based method for forecasting growth of pseudomonas aeruginosa | |
| Wang et al. | LW-NIR hyperspectral imaging for rapid prediction of TVC in chicken flesh | |
| Zhang et al. | Intelligent detection of quality deterioration and adulteration of fresh meat products in the supply chain: Research progress and application | |
| CN108627475A (en) | Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms | |
| CN106018292A (en) | Non-destructive testing device for protein conformation in egg white and method of non-destructive testing device | |
| Nagvanshi et al. | Development of a system to measure color in fresh and microwave dried banana slices | |
| CN108645798A (en) | The method of on-line quick detection chicken content of lactic acid bacteria | |
| Xu et al. | Study of monitoring maize leaf nutrition based on image processing and spectral analysis | |
| Zhang et al. | Development of a hyperspectral imaging system for the early detection of apple rottenness caused by P enicillium | |
| CN108872138A (en) | The method of on-line quick detection chicken enterobacteriaceae 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: 20181009 |
|
| WD01 | Invention patent application deemed withdrawn after publication |