CN101975844A - Multi-sensor fusion technology-based comprehensive detection method for pork quality - Google Patents
Multi-sensor fusion technology-based comprehensive detection method for pork quality Download PDFInfo
- Publication number
- CN101975844A CN101975844A CN2010102587977A CN201010258797A CN101975844A CN 101975844 A CN101975844 A CN 101975844A CN 2010102587977 A CN2010102587977 A CN 2010102587977A CN 201010258797 A CN201010258797 A CN 201010258797A CN 101975844 A CN101975844 A CN 101975844A
- Authority
- CN
- China
- Prior art keywords
- labeled
- value
- class
- pork
- pork 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
Images
Landscapes
- Investigating Or Analyzing Materials By The Use Of Electric Means (AREA)
Abstract
The invention discloses a multi-sensor fusion technology-based comprehensive detection method for pork quality, which comprises the following steps of: S1, detecting over four indexes of effective attenuation coefficient, impedance spectroscopy, sensory score, muscle oxygen saturation, pH value, chromaticity parameter and bacterial colony sum of a pork sample to be classified, and labeling the type; and S2, performing data fusion calculation and classification according to the index parameters of the pork sample labeled with type, and obtaining a quality classification result of the pork sample. The method can accurately, quickly and comprehensively evaluate the pork quality.
Description
Technical field
The present invention relates to meat quality detection technique field in the agrotechnique, particularly a kind of meat quality method for comprehensive detection based on multi-sensor fusion technology.
Background technology
China's meat total production occupies first place in the world.National meat total production was 7,650 ten thousand tons in 2005, and wherein pork output is 4,960 ten thousand tons, and poultry is about 1,352 ten thousand tons.The production run of animal products can be monitored and control to advanced detection technique not only, and can prevent that the product of inferior quality from coming into the market, and so just protected the consumer health, hit the lawless person and played the effect of standard market.
Meat quality definition both at home and abroad and intension have indicated industry and should pay close attention to which key index, and provide suitable detection means.For many years, the publication of international monograph Meat Science weeds out the old and bring forth the new traditional meat notion with all previous international exchanging of conference of meat science and technology.Modern meat notion reduces 5 kinds of attributes by Denmark scholar Anderson (2000): 1) edible quality: color and luster, local flavor, tender degree, succulence; 2) nutritional quality: protein content and amino acid composition, fat content and fatty acid component, vitamin content, mineral matter, moisture; 3) technical qualities: concern is waterpower, pH level, protein denaturation degree etc.; 4) corruption of health quality meat and degree (relating to the evaluation of freshness), various microbiotic and hormone and growth promoter level, persticide residue, concentration of heavy metal ion, the microbiological indicator of becoming sour; 5) how or the like humane quality, the i.e. culture pattern of pig: being that green is raised pigs or raise pigs in the open air, is that the animal welfare formula is raised pigs or imprison formula intensive pig production, butcher mode.
Prior art adopts sense organ, multiple physical and chemical index to estimate meat quality usually.And for fast detecting pork detects and accurately estimate meat quality, prior art also has employing as technical methods such as near-infrared spectrum analysis, Flame Image Process, impedance detection.Yet, single detection technique and sensor only reflect a certain specific indexes, and meat quality information is an overall target, in order to improve the accuracy that meat quality detects, carry out the data fusion of index, need the comprehensive evaluation detection system of design meat quality.
Summary of the invention
(1) technical matters that will solve
The technical problem to be solved in the present invention is: how to realize exactly, objectively meat quality evaluation.
(2) technical scheme
For solving the problems of the technologies described above, the invention provides a kind of meat quality method for comprehensive detection based on multi-sensor fusion technology, may further comprise the steps:
S1, for a pork sample to be classified, detect four above indexs in effective attenuation factor, impedance spectrum, sensory evaluation scores, flesh oxygen saturation, pH value, colorimetric parameter and the total number of bacterial colonies of pork sample, and the mark classification;
S2, according to mark the achievement data of pork sample of classification carry out that data fusion is calculated and classification, and obtain the attribute classification result of pork sample.
Wherein, use following Pulse Coupled Neural Network algorithm to carry out described data fusion calculating and classification:
U
ij(n)=F
ij(n)(1+βL
ij(n))
Wherein, F
IjBe the feedback input matrix; Y
KlBe the output result; L
IjFor connecting input matrix; U
IjBe the internal motivation matrix; Y
IjBe the igniting output matrix; E
IjBe threshold matrix; C is igniting number of times, i.e. matrix Y
IjThe number of middle element 1; S
IjBe the detected achievement data of sensor; M
IjAnd W
IjBe weight matrix; α
F, V
F, α
L, V
L, β, α
E, V
EBe network parameter; N is the network iterations;
At first, utilize above-mentioned six formula to calculate the igniting number of times of all kinds of achievement datas, thereby obtain the igniting number of times eigenwert of all kinds of achievement datas, classify then;
At a minute time-like, adopt Euclidean distance to differentiate as discriminant function:
Wherein m is the classification of being predicted, R
jBe the characteristic value collection of igniting number of times of the achievement data of j class, C
tBe the igniting number of times eigenwert of all kinds of achievement datas, C
jBe R
jIn element.
Wherein, the detection of effective attenuation factor index and labeling method are:
Detect the effective attenuation factor μ of certain wave strong point pork sample with optical means
Eff(λ), calculate total volatile basic nitrogen TVBN value C according to following formula then
TVBN=a μ
Eff(λ)+b, wherein C
TVBNBe the TVBN value, λ is a wavelength, and a, b are the coefficient by following experiment acquisition: to being no less than one group of pork sample of 5, utilize least-squares algorithm to determine a, b, wherein the effective attenuation factor of each sample and TVBN value are known;
The fresh state of the TVBN value mark pork sample that TVBN value that calculates according to following formula or applied chemistry method are measured, if the TVBN value is less than or equal to 15mg/100g, then be labeled as fresh class, if the TVBN value is between 15~25mg/100g, then be labeled as time fresh class, if the TVBN value more than or equal to 25mg/100g, then is labeled as corrupt class.
Wherein, the detection of impedance spectrum index and labeling method are:
The electrical impedance that forms along with the frequency shift spectrum of measuring the pork sample changes, if impedance real part spectrum middle impedance maximal value has single spectrum peak more than or equal to 100 Ω and imaginary impedance spectrum, and the back slope of differentiating is at 0.03-0.005 Ω (kHz)
-1Between, then be labeled as fresh class, if impedance real part spectrum middle impedance maximal value between 90-110 Ω and the imaginary impedance spectrum single spectrum peak is arranged, and the back slope of differentiating is at 0.005-0.002 Ω (kHz)
-1Between then be labeled as time fresh class, if impedance real part spectrum middle impedance maximal value is less than or equal to 100 Ω and the imaginary impedance spectrum does not have the spectrum peak, and the back slope of differentiating is less than or equal to 0.002 Ω (kHz)
-1, then be labeled as corrupt class.
Wherein, the method for obtaining sensory evaluation scores is:
Provide the sensory evaluation scores of pork sample according to the method for standard GB/T5009.44,,,, then be labeled as corrupt class if be less than or equal to 3 if average mark between 3-4, then is labeled as time fresh class if average mark more than or equal to 4, then is labeled as fresh class.
Wherein, the detection of flesh oxygen saturation and labeling method are:
Utilize the pigment content of optical method for measuring pork sample, when its flesh oxygen saturation is more than or equal to 18%, then be labeled as fresh class, when the flesh oxygen saturation between 10-18%, then be labeled as time fresh class, when the flesh oxygen saturation for being less than or equal to 10%, then be labeled as corrupt class, wherein the flesh oxygen saturation is the ratio a/ (a+b) of oxymyoglobin concentration a and oxymyoglobin concentration a and deoxidation myoglobin concentration b sum in the pork.
Wherein, the detection of pH value and labeling method are:
Measure the pH value of pork sample surfaces, when the pH value between 5.8-6.2, then be labeled as fresh class, when pH between 6.3-6.6, then be labeled as inferior fresh class, when pH greater than 6.7, then be labeled as corrupt class.
Wherein, the detection of colorimetric parameter and labeling method are:
With the brightness value L and the yellow value degree b* of colorimeter measurement pork sample surfaces colourity, when L between 57-47, and b* then is labeled as fresh class between 6-8.5; When L between 46.9-41, and b* is between 8.51-9.9, then is labeled as time fresh class; When L less than 41, and b* then is labeled as corrupt class between 9.91-15.
Wherein, the detection of total number of bacterial colonies and labeling method are:
When total number of bacterial colonies is less than or equal to 5*10
4Cfug
-1, then be labeled as fresh class; When total number of bacterial colonies at 5*10
4Cfug
-1~5*10
6Cfug
-1Between, then be labeled as time fresh class; When total number of bacterial colonies greater than 5*10
6Cfug
-1Between, then be labeled as corrupt class.
Wherein, the detection method with effective attenuation factor replaces with: the effective attenuation factor that detects certain wave strong point pork sample
μ
a(λ) be the absorption coefficient of pork sample, μ '
s(λ) be the reduced scattering coefficient of pork sample, λ is a wavelength.
Wherein, described impedance spectrum is meant the curve that the resistance value of pork sample constitutes on each Frequency point in the 10Hz-500kHz frequency range, described pork impedance real part spectrum is meant the curve that the impedance real part value of pork sample constitutes on each Frequency point in the 10Hz-500kHz frequency range, described pork imaginary impedance spectrum is meant the curve that the imaginary impedance value of pork sample constitutes on each Frequency point in the 10Hz-500kHz frequency range, if the resistance value on each Frequency point is Z (f), then value of real part Z
Real(f)=| Z (f)) | cos θ (f), imaginary values Z
Img(f)=| Z (f)) | sin θ (f), wherein f is a frequency.
(3) beneficial effect
Many indexs that the present invention utilizes Pulse Coupled Neural Network algorithm (PCNN) to carry out sensing data merge and classification, can provide the comprehensive evaluation to meat quality objective, exactly; The detection effective attenuation factor that designs among the present invention also utilizes speed (spending several hours) that method speed (spend several seconds) that effective attenuation factor calculates TVBN value measures than applied chemistry method in the prior art soon and be Non-Destructive Testing; Carrying out the branch time-like, adopting Euclidean distance to differentiate as discriminant function, its benefit is that computing velocity is fast.
Description of drawings
Fig. 1 is the meat quality method for comprehensive detection process flow diagram of the embodiment of the invention;
Fig. 2 is the impedance real part spectrum that causes one group of pork sample of freshness variation along with the resting period;
Fig. 3 is the imaginary impedance spectrum that causes one group of pork sample of freshness variation along with the resting period;
Fig. 4 is the process flow diagram of the PCNN data anastomosing algorithm that uses in the method for the embodiment of the invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples are used to illustrate the present invention, but are not used for limiting the scope of the invention.
In order further to improve objectivity, the accuracy of meat quality evaluation, the present invention will utilize multiple index to carry out data fusion, form new index feature, as a kind of evaluation meat quality effective ways more, discern stale pork.
As shown in Figure 1, the meat quality method for comprehensive detection process flow diagram for the embodiment of the invention may further comprise the steps:
Step S101 detects the index more than four kinds in the effective attenuation factor, impedance spectrum, flesh oxygen saturation, sensory evaluation scores, colorimetric parameter (comprising L brightness, b* Huang degree), pH value, total number of bacterial colonies of pork sample to be classified.Fig. 2,3 collection of illustrative plates are the signal effect, and present embodiment does not have these data to be used, and wherein the 1st class is fresh class, and the 2nd class is a time fresh class, and the 3rd class is corrupt class.
Need to prove,,, can detect the effective attenuation factor μ of certain wave strong point pork sample with optical means if detect the effective attenuation factor index for step S101
Eff(λ), set up effective attenuation coefficient mu with following formula then
Eff(λ) with TVBN value C
TVBNBetween relation, this relation can be expressed as C
TVBN=α μ
Eff(λ)+b (1).Wherein, ask the method for coefficient a, b as follows: to get 5 samples, the C of each sample
TVBNμ with 940nm wavelength place
Eff(λ) known, see Table 1, then can obtain a, b, a=-152.8mg (100g) by least-squares algorithm
-1Mm, b=68.2mg (100g)
-1
Table 1
The TVBN value that calculates according to following formula (1) then is again according to the fresh state of TVBN value mark pork sample.Above-mentioned TVBN is on night duty can the applied chemistry method to be measured.But, the above-mentioned detection effective attenuation factor that designs among the present invention also utilizes the method speed of effective attenuation factor calculating TVBN value more faster than the speed of applied chemistry method measurement in the prior art, the former only use takes the time in several seconds, the latter then needs to spend the time of several hrs, and the former is Non-Destructive Testing, and the latter is for diminishing detection.
Step S102 carries out data fusion and classification by user's strobe pulse coupled neural network algorithm, and can be by Internet display result in browser.
In the present embodiment, the Pulse Coupled Neural Network algorithm steps among the step S102 is as follows:
1) in described index, selects 4 indexs, what select in the present embodiment is TVBN, flesh oxygen saturation, pH value and 4 indexs of total number of bacterial colonies, the data that record as four kinds of sensors (other index also can obtain with sensor measurement, also can measure or calculate with other method);
2) with the input data of four kinds of sensing datas, carry out data fusion and classification as the Pulse Coupled Neural Network algorithm:
U
ij(n)=F
ij(n)(1+βL
ij(n))
Wherein, α
L=1.0, α
E=1.0, α
F=0.1, V
F=0.5, V
L=0.2, V
E=100, β=0.1,
Here S
Ij(i=0,1,2; J=0,1,2) be the numerical value of sensor, a in the present embodiment
1Be the numerical value of TVBN, a
2Be flesh oxygen saturation value, a
3Be the numerical value of pH, a
4Being the numerical value of total number of bacterial colonies, is each input matrix S to one group of four sensing data
IjOperation pulsatile once coupled neural network algorithm, iteration N=60 time, the igniting number of times that calculates detected all kinds of achievement datas (is matrix Y
IjThe number of middle element " 1 "), to obtain the igniting number of times eigenwert of all kinds of achievement datas.Its discriminant function adopts Euclidean distance to differentiate:
Wherein, R
jBe the characteristic value collection of igniting number of times of the achievement data of j class, C
tBe the igniting number of times eigenwert of all kinds of achievement datas, C
jBe R
jIn element, m is the classification of being predicted, as net result.Detailed algorithm steps as shown in Figure 4.
The user can select fixed four kinds of indexs from the page by browser (can be Internet Explorer), and utilizes Pulse Coupled Neural Network to provide classification results.
As implementation result, TVBN is 25mg/100g, and the flesh oxygen saturation value is 10%, the numerical value of pH, the numerical value 6*10 of total number of bacterial colonies
7Cfug
-1, after the calculating pork sample being differentiated is corrupt class.
Above embodiment only is used to illustrate the present invention; and be not limitation of the present invention; the those of ordinary skill in relevant technologies field; under the situation that does not break away from the spirit and scope of the present invention; can also make various variations and modification; therefore all technical schemes that are equal to also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.
Claims (11)
1. the meat quality method for comprehensive detection based on multi-sensor fusion technology is characterized in that, may further comprise the steps:
S1, for a pork sample to be classified, detect four above indexs in effective attenuation factor, impedance spectrum, sensory evaluation scores, flesh oxygen saturation, pH value, colorimetric parameter and the total number of bacterial colonies of pork sample, and the mark classification;
S2, according to mark the achievement data of pork sample of classification carry out that data fusion is calculated and classification, and obtain the attribute classification result of pork sample.
2. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that, uses following Pulse Coupled Neural Network algorithm to carry out described data fusion calculating and classification:
U
ij(n)=F
ij(n)(1+βL
ij(n))
Wherein, F
IjBe the feedback input matrix; Y
KlBe the output result; L
IjFor connecting input matrix; U
IjBe the internal motivation matrix; Y
IjBe the igniting output matrix; E
IjBe threshold matrix; C is igniting number of times, i.e. matrix Y
IjThe number of middle element 1; S
IjBe the detected achievement data of sensor; M
IjAnd W
IjBe weight matrix; α
F, V
F, α
L, V
L, β, α
E, V
EBe network parameter; N is the network iterations;
At first, utilize above-mentioned six formula to calculate the igniting number of times of all kinds of achievement datas, thereby obtain the igniting number of times eigenwert of all kinds of achievement datas, classify then;
At a minute time-like, adopt Euclidean distance to differentiate as discriminant function:
Wherein m is the classification of being predicted, R
jBe the characteristic value collection of igniting number of times of the achievement data of j class, C
tBe the igniting number of times eigenwert of all kinds of achievement datas, C
jBe R
jIn element.
3. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that the detection of effective attenuation factor index and labeling method are:
Detect the effective attenuation factor μ of certain wave strong point pork sample with optical means
Eff(λ), calculate total volatile basic nitrogen TVBN value C according to following formula then
TVBN=a μ
Eff(λ)+b, wherein C
TVBNBe the TVBN value, λ is a wavelength, and a, b are the coefficient by following experiment acquisition: to being no less than one group of pork sample of 5, utilize least-squares algorithm to determine a, b, wherein the effective attenuation factor of each sample and TVBN value are known;
The fresh state of the TVBN value mark pork sample that TVBN value that calculates according to following formula or applied chemistry method are measured, if the TVBN value is less than or equal to 15mg/100g, then be labeled as fresh class, if the TVBN value is between 15~25mg/100g, then be labeled as time fresh class, if the TVBN value more than or equal to 25mg/100g, then is labeled as corrupt class.
4. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that the detection of impedance spectrum index and labeling method are:
The electrical impedance that forms along with the frequency shift spectrum of measuring the pork sample changes, if impedance real part spectrum middle impedance maximal value has single spectrum peak more than or equal to 100 Ω and imaginary impedance spectrum, and the back slope of differentiating is at 0.03-0.005 Ω (kHz)
-1Between, then be labeled as fresh class, if impedance real part spectrum middle impedance maximal value between 90-110 Ω and the imaginary impedance spectrum single spectrum peak is arranged, and the back slope of differentiating is at 0.005-0.002 Ω (kHz)
-1Between then be labeled as time fresh class, if impedance real part spectrum middle impedance maximal value is less than or equal to 100 Ω and the imaginary impedance spectrum does not have the spectrum peak, and the back slope of differentiating is less than or equal to 0.002 Ω (kHz)
-1, then be labeled as corrupt class.
5. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that, the method for obtaining sensory evaluation scores is:
Provide the sensory evaluation scores of pork sample according to the method for standard GB/T5009.44,,,, then be labeled as corrupt class if be less than or equal to 3 if average mark between 3-4, then is labeled as time fresh class if average mark more than or equal to 4, then is labeled as fresh class.
6. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that the detection of flesh oxygen saturation and labeling method are:
Utilize the pigment content of optical method for measuring pork sample, when its flesh oxygen saturation is more than or equal to 18%, then be labeled as fresh class, when the flesh oxygen saturation between 10-18%, then be labeled as time fresh class, when the flesh oxygen saturation for being less than or equal to 10%, then be labeled as corrupt class, wherein the flesh oxygen saturation is the ratio a/ (a+b) of oxymyoglobin concentration a and oxymyoglobin concentration a and deoxidation myoglobin concentration b sum in the pork.
7. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that the detection of pH value and labeling method are:
Measure the pH value of pork sample surfaces, when the pH value between 5.8-6.2, then be labeled as fresh class, when pH between 6.3-6.6, then be labeled as inferior fresh class, when pH greater than 6.7, then be labeled as corrupt class.
8. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that the detection of colorimetric parameter and labeling method are:
With the brightness value L and the yellow value degree b* of colorimeter measurement pork sample surfaces colourity, when L between 57-47, and b* then is labeled as fresh class between 6-8.5; When L between 46.%41, and b* is between 8.51-9.9, then is labeled as time fresh class; When L less than 41, and b* then is labeled as corrupt class between 9.91-15.
9. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 1 is characterized in that the detection of total number of bacterial colonies and labeling method are:
When total number of bacterial colonies is less than or equal to 5*10
4Cfug
-1, then be labeled as fresh class; When total number of bacterial colonies at 5*10
4Cfug
-1~5*10
6Cfug
-1Between, then be labeled as time fresh class; When total number of bacterial colonies greater than 5*10
6Cfug
-1Between, then be labeled as corrupt class.
10. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 3 is characterized in that, the detection method of effective attenuation factor is replaced with: the effective attenuation factor that detects certain wave strong point pork sample
μ
a(λ) be the absorption coefficient of pork sample, μ '
s(λ) be the reduced scattering coefficient of pork sample, λ is a wavelength.
11. the meat quality method for comprehensive detection based on multi-sensor fusion technology as claimed in claim 4, it is characterized in that, described impedance spectrum is meant the curve that the resistance value of pork sample constitutes on each Frequency point in the 10Hz-500kHz frequency range, described pork impedance real part spectrum is meant the curve that the impedance real part value of pork sample constitutes on each Frequency point in the 10Hz-500kHz frequency range, described pork imaginary impedance spectrum is meant the curve that the imaginary impedance value of pork sample constitutes on each Frequency point in the 10Hz-500kHz frequency range, if the resistance value on each Frequency point is Z (f), then value of real part Z
Real(f)=| Z (f)) | cos θ (f), imaginary values Z
Img(f)=| Z (f)) | sin θ (f), wherein f is a frequency.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010102587977A CN101975844A (en) | 2010-08-20 | 2010-08-20 | Multi-sensor fusion technology-based comprehensive detection method for pork quality |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010102587977A CN101975844A (en) | 2010-08-20 | 2010-08-20 | Multi-sensor fusion technology-based comprehensive detection method for pork quality |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101975844A true CN101975844A (en) | 2011-02-16 |
Family
ID=43575746
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010102587977A Pending CN101975844A (en) | 2010-08-20 | 2010-08-20 | Multi-sensor fusion technology-based comprehensive detection method for pork quality |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101975844A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102507882A (en) * | 2011-12-19 | 2012-06-20 | 中国农业大学 | Beef quality multi-parameter compressive evaluation method |
CN102607705A (en) * | 2012-03-26 | 2012-07-25 | 南京农业大学 | Color difference meter assessment method for pork color |
CN103439471A (en) * | 2013-08-19 | 2013-12-11 | 华南理工大学 | Freezing-unfreezing circulation-based freshness detection method for freshwater fish slices |
CN103760193A (en) * | 2014-02-13 | 2014-04-30 | 南京农业大学 | Method for quickly identifying freezing-thawing frequency of poultry meat |
CN103439271B (en) * | 2013-08-29 | 2015-10-28 | 华南理工大学 | The visible detection method of the ripe situation of a kind of pork |
CN105866360A (en) * | 2016-03-31 | 2016-08-17 | 中国农业大学 | A method of detecting water holding capacity of meat |
CN106384138A (en) * | 2016-09-23 | 2017-02-08 | 重庆市万盛区渝旺食品有限公司 | Safety monitoring system for live pig slaughter |
CN109239285A (en) * | 2018-09-28 | 2019-01-18 | 南昌大学 | A kind of detector of measurement meat corruption degree |
KR20210004121A (en) * | 2019-07-03 | 2021-01-13 | 강원대학교산학협력단 | Analaysis method and apparatus for measuring freshness of meat |
CN112634274A (en) * | 2021-03-10 | 2021-04-09 | 广东省农业科学院动物科学研究所 | Machine vision-based fattening pork quality evaluation method and system |
-
2010
- 2010-08-20 CN CN2010102587977A patent/CN101975844A/en active Pending
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102507882A (en) * | 2011-12-19 | 2012-06-20 | 中国农业大学 | Beef quality multi-parameter compressive evaluation method |
CN102507882B (en) * | 2011-12-19 | 2015-01-21 | 中国农业大学 | Beef quality multi-parameter compressive evaluation method |
CN102607705A (en) * | 2012-03-26 | 2012-07-25 | 南京农业大学 | Color difference meter assessment method for pork color |
CN103439471A (en) * | 2013-08-19 | 2013-12-11 | 华南理工大学 | Freezing-unfreezing circulation-based freshness detection method for freshwater fish slices |
CN103439271B (en) * | 2013-08-29 | 2015-10-28 | 华南理工大学 | The visible detection method of the ripe situation of a kind of pork |
CN103760193A (en) * | 2014-02-13 | 2014-04-30 | 南京农业大学 | Method for quickly identifying freezing-thawing frequency of poultry meat |
CN103760193B (en) * | 2014-02-13 | 2015-07-01 | 南京农业大学 | Method for quickly identifying freezing-thawing frequency of poultry meat |
CN105866360A (en) * | 2016-03-31 | 2016-08-17 | 中国农业大学 | A method of detecting water holding capacity of meat |
CN106384138A (en) * | 2016-09-23 | 2017-02-08 | 重庆市万盛区渝旺食品有限公司 | Safety monitoring system for live pig slaughter |
CN109239285A (en) * | 2018-09-28 | 2019-01-18 | 南昌大学 | A kind of detector of measurement meat corruption degree |
CN109239285B (en) * | 2018-09-28 | 2020-08-11 | 南昌大学 | Detector for measuring meat corruption degree |
KR20210004121A (en) * | 2019-07-03 | 2021-01-13 | 강원대학교산학협력단 | Analaysis method and apparatus for measuring freshness of meat |
KR102256520B1 (en) | 2019-07-03 | 2021-05-26 | 강원대학교 산학협력단 | Analaysis method and apparatus for measuring freshness of meat |
CN112634274A (en) * | 2021-03-10 | 2021-04-09 | 广东省农业科学院动物科学研究所 | Machine vision-based fattening pork quality evaluation method and system |
CN112634274B (en) * | 2021-03-10 | 2021-06-04 | 广东省农业科学院动物科学研究所 | Machine vision-based fattening pork quality evaluation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101975844A (en) | Multi-sensor fusion technology-based comprehensive detection method for pork quality | |
Prabhakar et al. | A comprehensive review on freshness of fish and assessment: Analytical methods and recent innovations | |
CN103439285B (en) | A kind of fillet Noninvasive Measuring Method of Freshness based on high light spectrum image-forming | |
Olafsdottir et al. | Multisensor for fish quality determination | |
Hong et al. | Discrimination and prediction of multiple beef freshness indexes based on electronic nose | |
CN101382531B (en) | Method for detecting fresh degree of shrimp by electronic nose | |
Zhang et al. | Electronic nose with an air sensor matrix for detecting beef freshness | |
Yancey et al. | Consumer responses for tenderness and overall impression can be predicted by visible and near-infrared spectroscopy, Meullenet–Owens razor shear, and Warner–Bratzler shear force | |
CN104330382A (en) | Safety classification method of fresh beef | |
Wang | Near-infrared spectroscopy for food quality evaluation | |
CN106338517A (en) | Intelligent judgment method for fruit freshness based on coordination of visual information and olfactory information | |
CN103439271A (en) | Visual detecting method for pork maturity condition | |
CN103424374A (en) | Method for quickly detecting freshness level of hairtail by using near-infrared spectrum technology | |
CN104568815A (en) | Method for quickly and nondestructively detecting content of volatile basic nitrogen in fresh beef | |
CN103712948B (en) | The fast non-destructive detection method of TVB-N content in fresh Carnis caprae seu ovis | |
Sørensen et al. | Biogenic amines: a key freshness parameter of animal protein products in the coming circular economy | |
Sun et al. | Estimating freshness of carp based on EIS morphological characteristic | |
CN104965006A (en) | Electronic-tongue-based mutton freshness quick detection method | |
CN109182443A (en) | A method of the transducer production method of monitoring spoilage organisms breeding and quickly detection spoilage organisms | |
CN105527391A (en) | Electric-nose-analysis-based determination method of tuna oil corruption degree in storage process | |
CN103983676A (en) | Quick pork freshness nondestructive testing method based on gas sensor technology | |
Zhang et al. | Real-time and rapid prediction of TVB-N of livestock and poultry meat at three depths for freshness evaluation using a portable fluorescent film sensor | |
CN103575765A (en) | Method for rapidly detecting mutton adulteration | |
Tahsin et al. | A review on the techniques for quality assurance of fish and fish products | |
CN105842410B (en) | A kind of freshness fast non-destructive detection method based on air-flow pulse and laser ranging |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110216 |