CN108896490A - Meat piece affinity verification method and device - Google Patents
Meat piece affinity verification method and device Download PDFInfo
- Publication number
- CN108896490A CN108896490A CN201810574891.XA CN201810574891A CN108896490A CN 108896490 A CN108896490 A CN 108896490A CN 201810574891 A CN201810574891 A CN 201810574891A CN 108896490 A CN108896490 A CN 108896490A
- Authority
- CN
- China
- Prior art keywords
- meat piece
- spectrum
- meat
- region
- affinity
- 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.)
- Granted
Links
- 235000013372 meat Nutrition 0.000 title claims abstract description 373
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000012795 verification Methods 0.000 title claims abstract description 37
- 238000001228 spectrum Methods 0.000 claims abstract description 186
- 230000008569 process Effects 0.000 claims description 17
- 230000002452 interceptive effect Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000012880 independent component analysis Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 3
- 235000013305 food Nutrition 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000004611 spectroscopical analysis Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 241001465754 Metazoa Species 0.000 description 7
- 230000003595 spectral effect Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 230000006641 stabilisation Effects 0.000 description 4
- 238000011105 stabilization Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 235000013622 meat product Nutrition 0.000 description 3
- 235000013594 poultry meat Nutrition 0.000 description 3
- 239000000470 constituent Substances 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000004615 ingredient Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 235000020997 lean meat Nutrition 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000272525 Anas platyrhynchos Species 0.000 description 1
- 241000272814 Anser sp. Species 0.000 description 1
- 241000272173 Calidris Species 0.000 description 1
- 241000287828 Gallus gallus Species 0.000 description 1
- 241000283973 Oryctolagus cuniculus Species 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002574 poison Substances 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 235000015277 pork Nutrition 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002087 whitening effect Effects 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
Abstract
The invention discloses a kind of meat piece affinity verification method and devices, belong to technical field of food detection, and method includes：Obtain the spectrum picture of the first meat piece and the second meat piece that need to carry out affinity verifying；Spectrum picture based on the first meat piece and the second meat piece obtains the region spectrum of the first meat piece and the second meat piece respectively, and calculates the base space of each region spectrum；According to the correlation between the base space of each region spectrum, the affinity of the first meat piece and the second meat piece is verified.The embodiment of the present invention is by verifying consumer meat piece to be purchased and trusts between block meat whether there is affinity, and consumer can effectively be helped to avoid being cheated when buying meat by illegal retailer.
Description
Technical field
The invention belongs to technical field of food detection more particularly to meat piece affinity verification methods and device.
Background technique
Meat is rich in protein and fat, and edible value is very high, deep to be liked by the mankind.Common meat is divided into poultry meat and fowl
Meat.Poultry meat includes ox, sheep, rabbit, pork etc., and poultry includes chicken, duck, goose etc..The ingredient of meat mainly with the type of animal, year
Age, physical feeling, fattening situation have relationship.Different types of meat constituent is different, even same type, Different Individual it
Between meat it is also variant.
As living standard is continuously improved, meat product consuming capacity is continuously increased, and it is raw that meat product has become people
Necessity living, but meat product safety problem also becomes increasingly conspicuous.Some illegal retailers be try to gain individual interest do not stint damage consumption
Person's interests and health are listed after filling the water when butchering animals or butchering the animals to die of illness and are promoted.Government passes through inspection and quarantine department
This malfeasance is carried out and is intervened.The animals meat object of listing is butchered under the supervision of government survey quarantine departments without water filling, disease-free
Poison infection, has generally covered the marking of inspection and quarantine department, can trust edible, this meat is referred to as quality-assured meat.However
Some illegal retailers are largely mixed and are sold using false meat, meat of poor quality, disease meat and quality-assured meat for save the cost,
Looking on meat booth put is the meat piece that trusts for being stamped the marking, and the meat piece that possible consumer takes hand is meat piece inferior, this is
The phenomenon that being frequently run onto supermarket or the market of farm produce.If can fast verification consumer purchase meat piece and trust meat piece whether source
From in the same animal individual, i.e., by the affinity between verifying meat piece, largely can effectively help to disappear
Expense person avoids being cheated by illegal retailer.
Summary of the invention
The purpose of the embodiment of the present application is to provide a kind of meat piece affinity verification method and device, passes through verifying consumer
Meat piece to be purchased and trust between block meat whether there is affinity, effectively to help consumer to avoid when buying meat
It is cheated by illegal retailer.
In order to solve the above technical problems, what the embodiment of the present application was realized in：
In a first aspect, the present invention provides a kind of meat piece affinity verification method, the method includes：
Obtain the spectrum picture of the first meat piece and the second meat piece that need to carry out affinity verifying；
Spectrum picture based on first meat piece and the second meat piece obtains first meat piece and the second meat piece respectively
Region spectrum, and calculate the base space of each region spectrum；
According to the correlation between the base space of each region spectrum, to the homologous of first meat piece and the second meat piece
Relationship is verified.
In some embodiments, it by any one in following operation, realizes described based on first meat piece and the
The spectrum picture of two meat pieces obtains the step of region spectrum of first meat piece and the second meat piece respectively and includes：
Pass through the stabilization that interactive operation selects the spectrum picture of first meat piece and the second meat piece respectively based on user
Region obtains the region spectrum of first meat piece and the second meat piece；Or
The automatic cluster carried out respectively based on the spectrum picture to first meat piece and the second meat piece is handled, described in acquisition
The region spectrum of first meat piece and the second meat piece；Or
Based on the image dividing processing that the spectrum picture to first meat piece and the second meat piece carries out respectively, described in acquisition
The region spectrum of first meat piece and the second meat piece.
In some embodiments, before the base space step for calculating each region spectrum, the method also includes：
The region spectrum of first meat piece and the second meat piece is pre-processed respectively.
In some embodiments, the base space for calculating each region spectrum includes：
Based on independent component analysis method, the base space of each region spectrum is calculated.
In some embodiments, the correlation between the base space according to each region spectrum, to described first
The affinity of meat piece and the second meat piece carries out verifying：
The correlation between the base space of each region spectrum is calculated based on cosine function；
If the value of the correlation is more than preset threshold, it is determined that first meat piece and the second meat piece have homologous pass
System, otherwise, it is determined that first meat piece and the second meat piece do not have affinity.
In some embodiments, the method also includes：
Output is used to indicate whether first meat piece and the second meat piece have the verification result of affinity.
Second aspect, the present invention provides a kind of meat piece affinities to verify device, and described device includes：
First obtains module, for obtaining the spectrogram of the first meat piece and the second meat piece that need to carry out affinity verifying
Picture；
Second obtains module, obtains described first respectively for the spectrum picture based on first meat piece and the second meat piece
The region spectrum of meat piece and the second meat piece；
Computing module, for calculating the base space of each region spectrum；
Authentication module, for the correlation between the base space according to each region spectrum, to first meat piece and
The affinity of second meat piece is verified.
In some embodiments, described second module is obtained specifically for executing any one in following operation：
Pass through the stabilization that interactive operation selects the spectrum picture of first meat piece and the second meat piece respectively based on user
Region obtains the region spectrum of first meat piece and the second meat piece；Or
The automatic cluster carried out respectively based on the spectrum picture to first meat piece and the second meat piece is handled, described in acquisition
The region spectrum of first meat piece and the second meat piece；Or
Based on the image dividing processing that the spectrum picture to first meat piece and the second meat piece carries out respectively, described in acquisition
The region spectrum of first meat piece and the second meat piece.
In some embodiments, described device further includes：
Preprocessing module pre-processes respectively for the region spectrum to first meat piece and the second meat piece.
In some embodiments, the computing module is specifically used for：
Based on independent component analysis method, the base space of each region spectrum is calculated.
In some embodiments, the authentication module is specifically used for：
The correlation between the base space of each region spectrum is calculated based on cosine function；
If the value of the correlation is more than preset threshold, it is determined that first meat piece and the second meat piece have homologous pass
System, otherwise, it is determined that first meat piece and the second meat piece do not have affinity.
In some embodiments, described device further includes output module, and the output module is specifically used for：
Output is used to indicate whether first meat piece and the second meat piece have the verification result of affinity.
The beneficial effect of the embodiment of the present invention is：The present invention is a kind of lossless verification method, by obtaining different meat pieces
Spectrum picture, can fast verification they whether be originated from same individual, meat of poor quality and quality-assured meat are thus mixed in one in retailer
Rise when being sold, consumer can by verify its meat to be purchased and cover the quality restriction qualification marking quality-assured meat whether
From same animal individual, it can be avoided and cheated by illegal retailer；In addition, the present invention passes through the phase based on region spectrum base space
Close property the affinity of first meat piece and the second meat piece is verified, due to calculating be region spectrum base space,
Sensibility when only calculating single pixel spectrum is avoided, thus, it is possible to improve the stability of verification result.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the flow diagram of one embodiment of meat piece affinity verification method provided by the invention；
Fig. 2 is the flow diagram of one embodiment of meat piece affinity verification method provided by the invention；
Fig. 3 is the schematic diagram that spectrum picture provided by the invention is shown on interactive interface；
Fig. 4 is the structural schematic diagram of one embodiment of meat piece affinity verifying device provided by the invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only this
Invention a part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Since meat between animal individual and composition have differences, it is poor that the high-spectral data that correspondence generates can also exist
It is different, and ingredient is approximate between same intraindividual different meat pieces, corresponding high-spectral data can be also more nearly.Based on this,
Both the embodiment of the present invention quickly analyzes whether its similarity approaches by obtaining the spectroscopic data of different meat pieces, judge
Whether there is affinity, effectively helps consumer when supermarket or food market carry out purchase meat to realize, avoid by not
Method retailer deception.Method provided in an embodiment of the present invention can be applied to intelligent terminal, obtain different meat pieces by intelligent terminal
Spectroscopic data, whether and realizing there is affinity to verify different meat pieces, wherein intelligent terminal is preferably intelligent hand
Machine, but intelligent terminal also other, such as personal digital assistant, tablet computer etc., which is not limited by the present invention.
Embodiment one is a kind of meat piece affinity verification method provided in an embodiment of the present invention, and this method can be applied to
In intelligent terminal, referring to Fig. 1, this method be may comprise steps of：
101, the spectrum picture of the first meat piece and the second meat piece that need to carry out affinity verifying is obtained.
Wherein, has quality restriction mark of conformity on one of meat piece in the first meat piece and the second meat piece.The quality
Examine mark of conformity can the form of affixing one's seal be marked.
In the present embodiment, it can use the spectrum that spectrometer acquires the first meat piece and the second meat piece by diffusing reflection mode
Image, and collected spectrum picture is sent to by spectrometer the mobile terminal of consumer by cable network or wireless network
On, which is previously deployed at supermarket or food market, to facilitate consumer to utilize；Spectrometer can use common
Optical spectrum imagers are (such as：Micro-Hyperspec miniature imaging spectrometer) acquisition of meat piece high spectrum image is carried out, acquire spectral regions
Between include visible light and part short wavelength-NIR light.Wave-length coverage is between 400-1000nm, spectral resolution 5nm, image point
Resolution is 1004*1004.In addition, as spectrometer is gradually to the integrated of intelligent terminal, the spectrum of the first meat piece and the second meat piece
Image can also directly be obtained by spectra collection device that is integrated or being loaded on the mobile terminal of consumer, the present invention
This is not construed as limiting.
102, the spectrum picture based on the first meat piece and the second meat piece obtains the region of the first meat piece and the second meat piece respectively
Spectrum.
Specifically, realizing the spectrum picture based on the first meat piece and the second meat piece by any one in following operation
The step of obtaining the region spectrum of the first meat piece and the second meat piece respectively include：
Pass through the stability region that interactive operation selects the spectrum picture of the first meat piece and the second meat piece respectively based on user,
Obtain the region spectrum of the first meat piece and the second meat piece；Or
Based on the automatic cluster processing that the spectrum picture to the first meat piece and the second meat piece carries out respectively, the first meat piece is obtained
With the region spectrum of the second meat piece；Or
Based on the image dividing processing that the spectrum picture to the first meat piece and the second meat piece carries out respectively, the first meat piece is obtained
With the region spectrum of the second meat piece.
103, the base space of each region spectrum is calculated.
Specifically, being based on independent component analysis method, the base space of each region spectrum is calculated.
Optionally, before step 103, method can also include：
The region spectrum of first meat piece and the second meat piece is pre-processed respectively.
104, according to the correlation between the base space of each region spectrum, to the affinity of the first meat piece and the second meat piece
It is verified.
Specifically, the correlation between the base space of each region spectrum is calculated based on cosine function；
If the value of correlation is more than preset threshold, it is determined that the first meat piece and the second meat piece have affinity, otherwise, then
Determine that the first meat piece and the second meat piece do not have affinity.
Wherein, preset threshold customized can be set, for example, if setting preset threshold as 0.8, when the base of each region spectrum
When the value of correlation between space is 0.5, then it can determine that the first meat piece and the second meat piece do not have affinity.
It in one embodiment, can be with defeated after the affinity to the first meat piece and the second meat piece is verified
It is used to indicate whether the first meat piece and the second meat piece have the verification result of affinity out.
Wherein, verification result can export in verifying screen, or the floating layer window that can be popped up above verifying screen
It is exported in mouthful.For example, verifying screen on pop up a floating layer window, and on the window output character content " being verified " or
Person " verifying does not pass through ".
Furthermore it is also possible to meet mark " √ " by output in verifying screen or floating layer window to indicate the first meat piece and the
Two meat pieces have an affinity, and output meets mark "×" to indicate that the first meat piece and the second meat piece do not have affinity, etc.
Deng.
The above-mentioned mode for listing several output verification results, the embodiment of the present invention are not limited to above-mentioned several ways,
Other, which also can be used, can be identified for that the mode of output result is exported.
The embodiment of the invention provides a kind of meat piece affinity verification methods, need to carry out affinity firstly, obtaining
First meat piece of verifying and the spectrum picture of the second meat piece are distinguished based on the spectrum picture of the first meat piece and the second meat piece later
The region spectrum of the first meat piece and the second meat piece is obtained, and calculates the base space of each region spectrum；Then, according to each region spectrum
Base space between correlation, the affinity of the first meat piece and the second meat piece is verified.Thus, it is possible to realize it is lossless,
Whether fast verification difference meat piece is originated from same individual, by obtaining consumer's meat piece to be purchased and covering quality restriction qualification
The marking trusts the respective spectrum picture of meat piece, can fast verification they whether be originated from same individual, thus, it is possible to avoid by
Illegal retailer is mixed meat of poor quality and quality-assured meat by dealer bring deception when selling；In addition, the present invention passes through base
Correlation in region spectrum base space verifies the affinity of first meat piece and the second meat piece, due to calculating
It is the base space of region spectrum, avoids sensibility when only calculating single pixel spectrum, thus, it is possible to improve the stabilization of verification result
Property, and verification process is easy to operate, flexible and convenient.
Embodiment two is a kind of meat piece affinity verification method provided in an embodiment of the present invention, and this method can be applied to
In intelligent terminal, referring to fig. 2, this method be may comprise steps of：
201, the spectrum picture of the first meat piece and the second meat piece that need to carry out affinity verifying is obtained.
Wherein, has quality restriction mark of conformity on one of meat piece in the first meat piece and the second meat piece.The quality
Examine mark of conformity can the form of affixing one's seal be marked.
In embodiment, can use spectrometer by diffusing reflection mode and meanwhile acquire the first meat piece spectrum picture and
The spectrum picture of second meat piece, and collected spectrum picture is sent to by cable network or wireless network by spectrometer and is disappeared
On the mobile terminal of the person of expense, which is previously deployed at supermarket or the market of farm produce, to facilitate consumer to utilize,
In, spectrometer can be using common optical spectrum imagers (such as：Micro-Hyperspec miniature imaging spectrometer) carry out meat piece height
Spectrum picture acquisition, acquisition spectrum range includes visible light and part short wavelength-NIR light, wave-length coverage 400-1000nm it
Between, spectral resolution 5nm, image resolution ratio 1004*1004.In addition, as spectrometer is gradually to the integrated of intelligent terminal, the
The spectrum picture of the spectrum picture of one meat piece and the second meat piece can also be by integrating or being loaded on the intelligent terminal of consumer
Spectra collection device directly obtained, this is not limited by the present invention.
It should be noted that in order to ensure meat piece affinity verification result is more acurrate, in the spectrum picture of acquisition meat piece
Before, can be clean by the first meat piece and the second meat piece surface clean that need to carry out affinity verifying, and be placed on identical
Environment in preset time (for example, 10min), so that meat piece is kept identical temperature humidity.
202, the stabilization that interactive operation selects the spectrum picture of the first meat piece and the second meat piece respectively is passed through based on user
Region obtains the region spectrum of the first meat piece and the second meat piece.
In the embodiment of the present invention, stability region refers to that the constituent of meat piece is stable and consistent, meat in regional area
Pure lean meat or pure fat meat on block belong to meat stability region, and carrying out selection stability region to different meat pieces by user can protect
Demonstrate,prove the consistency of the material composition of different meat pieces.
Specifically, the process may include：
What be will acquire needs to carry out the spectrum picture of the first meat piece of affinity verifying and the spectrogram of the second meat piece
As being simultaneously displayed on user interface, and display reminding selects information, so that user selects information to first according to prompt
The spectrum picture of the spectrum picture of meat piece and the second meat piece carries out regional choice, wherein prompt selection information can wrap containing choosing
Rule is selected, selection rule can serve to indicate that user to the region of different meat pieces selection homogeneity, and here, the region of homogeneity is pointer
The selection of different meat pieces is all lean meat region or is all fat meat region；
Receive the interactive operation of user, wherein interactive operation can be user and pass through the modes of operation needles such as touch or mouse
To the selection that each spectrum picture carries out, interactive operation is also possible to the select tools by providing on interactive interface to each spectrogram
As the selection carried out, which can be dragged on each spectrum picture respectively in a manner of towing, and through user to the selection
Tool is zoomed in and out to select the region on each spectrum picture respectively；
In response to above-mentioned interactive operation, determine user on the spectrum picture of the first meat piece and the spectrum picture of the second meat piece
The stability region selected respectively, and according to the stability region selected respectively, obtain the region spectrum and the second meat piece of the first meat piece
Region spectrum.
Above-mentioned user selected region on each spectrum picture can be the region of same size, be also possible to different big
Small region, wherein region shape can be rectangle or circle or other shapes.Wherein, in order to guarantee subsequent step calculate area
The validity in the base space of domain spectrum at least should include 200 pixels, such as the region that each meat piece is chosen in selected region
Its resolution ratio is the region of 15*20, and for another example, its resolution ratio that each meat piece is chosen is the region of 20x30.
Illustratively, referring to shown in Fig. 3, Fig. 3 is the signal that spectrum picture provided by the invention is shown on interactive interface
Figure, on the interactive interface of intelligent terminal, user can carry out regional choice for each spectrum picture by touch operation mode.
203, the automatic cluster processing carried out respectively based on the spectrum picture to the first meat piece and the second meat piece, obtains first
The region spectrum of meat piece and the second meat piece.
Wherein, Density Clustering method can be used by carrying out automatic cluster processing to spectrum picture, for example use DBSCAN
(Density-Based Spatial Clustering of Applications with Noise)。
Specifically, the process may include step：
(1) one is selected to mark words and phrases for special attention as core point according to neighborhood rule within the scope of spectrum picture, each pair of point answers a light
Modal data；(2) point is randomly selected as seed from core point, find all the points that spectroscopic data density can reach, shape
It is clustered at one；(3) core point set is updated；(4) repeat step (2) to step (3), until core point set be sky, own
Data are clustered.After the completion of cluster, distance d farther out the half of image long side (d be greater than) and maximum two class is as acquisition zone
Domain；(5) pickup area handled based on automatic cluster obtains the region spectrum of the first meat piece and the area light of the second meat piece
Spectrum.
204, the image dividing processing carried out respectively based on the spectrum picture to the first meat piece and the second meat piece obtains first
The region spectrum of meat piece and the second meat piece.
Wherein, the image segmentation based on spectroscopic data can use region growing method, and thought will exactly have similar
The pixel of spectrum connects into region.
Specifically, the process may include：
First look for a pixel as the starting point of growth in the picture, then will be similar with the spectrum of the pixel in surrounding neighbors
Then pixel combination repeats process above for new point as growing point to together, until growth stops being further continued for handling it
The pixel in its region, final image are divided into different zones.Finally, maximum two cut zone will be obtained as acquisition zone
Domain obtains the region spectrum of the first meat piece and the region spectrum of the second meat piece.
It should be noted that step 202 to step 204 is coordination, it in practical applications, can be by step 202
The first meat piece and are obtained respectively to spectrum picture of any one realization based on the first meat piece and the second meat piece in step 204
The region spectrum of two meat pieces.
205, the region spectrum of the first meat piece and the second meat piece is pre-processed respectively.
Specifically, the ash under each wave band in the region spectrum of the second meat piece is neutralized to the first meat piece region spectrum respectively
Degree image is filtered respectively, to remove the noise generated in collection process.
It is assumed that the corresponding area size of meat piece spectrum got is M1xN1, spectral band number is P1, under each wave band
Gray level image be filtered respectively.Preferably, gray level image filtering use 3x3 median filtering, with eliminate spot noise and
Salt-pepper noise.
In the embodiment of the present invention, pre-processed respectively by the region spectrum to the first meat piece and the second meat piece, it can
Further increase the accuracy of subsequent authentication result.
206, it is based on independent component analysis method, the base space of each region spectrum is calculated.
In the present embodiment, for above-mentioned pretreated each region spectrum, by the spectroscopic data of each region spectrum point
Not Zuo Wei observation signal, the base space of each region spectrum is calculated.It is assumed that spectroscopic data is mixed by source signal
, in this way, the base space of region spectrum can be obtained by calculating the independent element of spectroscopic data.It is, assuming source
It is independent from each other between signal, it is mixed to solve using observing in spectroscopic data (each region include m=M1xN1 sample)
Close matrix and source signal.
Specifically, the process may include steps of：
(1) centralization and whitening processing are carried out to spectroscopic data.Centralization is that purpose is to allow institute by subtracting corresponding mean value
Having spectral vector mean value is 0；Albefaction is that independent element is estimated using the method for estimation uncorrelated variables, and common method is meter
The Eigenvalues Decomposition of the covariance matrix for the evidence that counts.Spectral vector after albefaction is incoherent, and its association side with each component
Poor matrix is unit matrix.
(2) with the inverse mapping of stochastic gradient descent method iterative calculation hybrid matrix, then projection calculates source signal, and repeats
For the step until convergence, the space of source signal is exactly the base space of the region spectrum.
It is worth noting that, step 206 is to realize the process in the base space for calculating each region spectrum.In addition to above-mentioned steps
Except mode, it can also realize that the process, the embodiment of the present invention are not limited concrete implementation mode by other means.
207, the correlation between the base space of each region spectrum is calculated based on cosine function, if the value of correlation is super
Cross preset threshold, it is determined that the first meat piece and the second meat piece have affinity.
Specifically, the COS distance between the base space of each region spectrum is calculated based on cosine function, by all bases
The COS distance in space carries out the operation of 2- norm as a vector, obtains relevance values, if the value of correlation is more than default threshold
Value, it is determined that the first meat piece and the second meat piece have affinity.
Wherein, preset threshold can be set according to actual needs, for example, setting preset threshold as 0.8, when each region
When the value of correlation between the base space of spectrum is 0.5, then it can determine that the first meat piece and the second meat piece do not have affinity.
It is worth noting that, step 207 is the correlation between the base space realized according to each region spectrum, to the first meat
The process that the affinity of block and the second meat piece is verified.Other than the mode of above-mentioned steps, its other party can also be passed through
Formula realizes that the process, the embodiment of the present invention are not limited concrete implementation mode.
208, output is used to indicate whether the first meat piece and the second meat piece have the verification result of affinity.
Wherein, verification result can export in verifying screen, or the floating layer window that can be popped up above verifying screen
It is exported in mouthful.For example, verifying screen on pop up a floating layer window, and on the window output character content " being verified " or
Person " verifying does not pass through ".
Furthermore it is also possible to meet mark " √ " by output in verifying screen or floating layer window to indicate the first meat piece and the
Two meat pieces have an affinity, and output meets mark "×" to indicate that the first meat piece and the second meat piece do not have affinity, etc.
Deng.
The embodiment of the invention provides a kind of meat piece affinity verification method, this method can be realized it is lossless, quickly test
Demonstrate,prove whether different meat pieces are originated from same individual, by obtaining consumer's meat piece to be purchased and covering quality restriction mark of conformity
Trust the respective spectrum picture of meat piece, whether they are originated from same individual to energy fast verification, and thus, it is possible to avoid by illegal quotient
Buy to resell bring deception when being sold that meat of poor quality and quality-assured meat mix by dealer；In addition, the present invention is by being based on region
The correlation in spectrum base space verifies the affinity of first meat piece and the second meat piece, and what it is due to calculating is region
The base space of spectrum avoids sensibility when only calculating single pixel spectrum, thus, it is possible to improve the stability of verification result, and tests
Card process is easy to operate, flexible and convenient.
Embodiment three is that a kind of meat piece affinity provided in an embodiment of the present invention verifies device, referring to shown in Fig. 4, the dress
Set including：
First obtains module 41, for obtaining the spectrum of the first meat piece and the second meat piece that need to carry out affinity verifying
Image；
Second obtain module 42, for the spectrum picture based on the first meat piece and the second meat piece obtain respectively the first meat piece and
The region spectrum of second meat piece；
Computing module 43, for the base space of each region spectrum to be calculated；
Authentication module 44, for the correlation between the base space according to each region spectrum, to the first meat piece and the second meat
The affinity of block is verified.
Further, second module 42 is obtained specifically for executing any one in following operation：
Pass through the stability region that interactive operation selects the spectrum picture of the first meat piece and the second meat piece respectively based on user,
Obtain the region spectrum of the first meat piece and the second meat piece；Or
Based on the automatic cluster processing that the spectrum picture to the first meat piece and the second meat piece carries out respectively, the first meat piece is obtained
With the region spectrum of the second meat piece；Or
Based on the image dividing processing that the spectrum picture to the first meat piece and the second meat piece carries out respectively, the first meat piece is obtained
With the region spectrum of the second meat piece.
Further, device further includes：
Preprocessing module 45 pre-processes respectively for the region spectrum to the first meat piece and the second meat piece.
Further, computing module 43 is specifically used for：
Based on independent component analysis method, the base space of each region spectrum is calculated.
Further, authentication module 44 is specifically used for：
The correlation between the base space of each region spectrum is calculated based on cosine function；
If the value of correlation is more than preset threshold, it is determined that the first meat piece and the second meat piece have affinity, otherwise, then
Determine that the first meat piece and the second meat piece do not have affinity.
In some embodiments, device further includes output module 46, and output module 46 is specifically used for：
Output is used to indicate whether the first meat piece and the second meat piece have the verification result of affinity.
The embodiment of the invention provides a kind of meat piece affinity verify device, the device can be realized it is lossless, quickly test
Demonstrate,prove whether different meat pieces are originated from same individual, by obtaining consumer's meat piece to be purchased and covering quality restriction mark of conformity
Trust the respective spectrum picture of meat piece, whether they are originated from same individual to energy fast verification, and thus, it is possible to avoid by illegal quotient
Buy to resell bring deception when being sold that meat of poor quality and quality-assured meat mix by dealer；In addition, the present invention is by being based on region
The correlation in spectrum base space verifies the affinity of first meat piece and the second meat piece, and what it is due to calculating is region
The base space of spectrum avoids sensibility when only calculating single pixel spectrum, thus, it is possible to improve the stability of verification result, and tests
Card process is easy to operate, flexible and convenient.
All the above alternatives can form alternative embodiment of the invention using any combination, herein no longer
It repeats one by one.
It should be noted that：Meat piece affinity verifying device provided by the above embodiment is tested in execution meat piece affinity
When card method, only the example of the division of the above functional modules, in practical application, can according to need and will be above-mentioned
Function distribution is completed by different functional modules, i.e., the internal structure of device is divided into different functional modules, with complete with
The all or part of function of upper description.In addition, above-mentioned meat piece affinity verification method and meat piece affinity verify device
Embodiment belongs to same design, and specific implementation process is detailed in embodiment of the method, and which is not described herein again.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, associated hardware can also be instructed to complete by program, the program can store can in a kind of computer
It reads in storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of meat piece affinity verification method, which is characterized in that the method includes：
Obtain the spectrum picture of the first meat piece and the second meat piece that need to carry out affinity verifying；
Spectrum picture based on first meat piece and the second meat piece obtains the region of first meat piece and the second meat piece respectively
Spectrum, and calculate the base space of each region spectrum；
According to the correlation between the base space of each region spectrum, to the affinity of first meat piece and the second meat piece
It is verified.
2. the method according to claim 1, wherein realizing the base by any one in following operation
The region spectrum of first meat piece and the second meat piece is obtained respectively in the spectrum picture of first meat piece and the second meat piece
Step includes：
Pass through the stability region that interactive operation selects the spectrum picture of first meat piece and the second meat piece respectively based on user,
Obtain the region spectrum of first meat piece and the second meat piece；Or
Based on the automatic cluster processing that the spectrum picture to first meat piece and the second meat piece carries out respectively, described first is obtained
The region spectrum of meat piece and the second meat piece；Or
Based on the image dividing processing that the spectrum picture to first meat piece and the second meat piece carries out respectively, described first is obtained
The region spectrum of meat piece and the second meat piece.
3. the method according to claim 1, wherein the base space step for calculating each region spectrum it
Before, the method also includes：
The region spectrum of first meat piece and the second meat piece is pre-processed respectively.
4. according to claim 1 to method described in 3 any one, which is characterized in that each region spectrum of calculating
Base space includes：
Based on independent component analysis method, the base space of each region spectrum is calculated.
5. the method according to claim 1, wherein between the base space according to each region spectrum
Correlation, carrying out verifying to the affinity of first meat piece and the second meat piece includes：
The correlation between the base space of each region spectrum is calculated based on cosine function；
If the value of the correlation is more than preset threshold, it is determined that first meat piece and the second meat piece have affinity, no
Then, it is determined that first meat piece and the second meat piece do not have affinity.
6. method according to claim 1 or 5, which is characterized in that the method also includes：
Output is used to indicate whether first meat piece and the second meat piece have the verification result of affinity.
7. a kind of meat piece affinity verifies device, which is characterized in that described device includes：
First obtains module, for obtaining the spectrum picture of the first meat piece and the second meat piece that need to carry out affinity verifying；
Second obtains module, obtains first meat piece respectively for the spectrum picture based on first meat piece and the second meat piece
With the region spectrum of the second meat piece；
Computing module, for calculating the base space of each region spectrum；
Authentication module, for the correlation between the base space according to each region spectrum, to first meat piece and second
The affinity of meat piece is verified.
8. device according to claim 7, which is characterized in that described second, which obtains module, is specifically used for executing following operation
In any one：
Pass through the stability region that interactive operation selects the spectrum picture of first meat piece and the second meat piece respectively based on user,
Obtain the region spectrum of first meat piece and the second meat piece；Or
Based on the automatic cluster processing that the spectrum picture to first meat piece and the second meat piece carries out respectively, described first is obtained
The region spectrum of meat piece and the second meat piece；Or
Based on the image dividing processing that the spectrum picture to first meat piece and the second meat piece carries out respectively, described first is obtained
The region spectrum of meat piece and the second meat piece.
9. device according to claim 7, which is characterized in that described device further includes：
Preprocessing module pre-processes respectively for the region spectrum to first meat piece and the second meat piece.
10. according to device described in claim 7 to 9 any one, which is characterized in that the computing module is specifically used for：
Based on independent component analysis method, the base space of each region spectrum is calculated.
11. device according to claim 7, which is characterized in that the authentication module is specifically used for：
The correlation between the base space of each region spectrum is calculated based on cosine function；
If the value of the correlation is more than preset threshold, it is determined that first meat piece and the second meat piece have affinity, no
Then, it is determined that first meat piece and the second meat piece do not have affinity.
12. device according to claim 7 or 11, which is characterized in that described device further includes output module, the output
Module is specifically used for：
Output is used to indicate whether first meat piece and the second meat piece have the verification result of affinity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574891.XA CN108896490B (en) | 2018-06-06 | 2018-06-06 | Meat block homologous relation verification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810574891.XA CN108896490B (en) | 2018-06-06 | 2018-06-06 | Meat block homologous relation verification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108896490A true CN108896490A (en) | 2018-11-27 |
| CN108896490B CN108896490B (en) | 2021-10-01 |
Family
ID=64343962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810574891.XA Active CN108896490B (en) | 2018-06-06 | 2018-06-06 | Meat block homologous relation verification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108896490B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110286094A (en) * | 2019-07-18 | 2019-09-27 | 山东省科学院海洋仪器仪表研究所 | A kind of spectral model transfer method based on clustering |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103019671A (en) * | 2012-10-08 | 2013-04-03 | 中国科学院对地观测与数字地球科学中心 | Data-intensive remote sensing image processing-oriented generic programmed framework programming method |
| CN103805703A (en) * | 2014-02-13 | 2014-05-21 | 向华 | Ingredients of animal origins in meat products identified by using mass spectrometry |
| CN105223140A (en) * | 2015-10-10 | 2016-01-06 | 中国科学院苏州生物医学工程技术研究所 | The method for quickly identifying of homology material |
| CN106056157A (en) * | 2016-06-01 | 2016-10-26 | 西北大学 | Hyperspectral image semi-supervised classification method based on space-spectral information |
| CN107881244A (en) * | 2017-10-31 | 2018-04-06 | 中国食品药品检定研究院 | The probe primer and detection method and purposes of the fluorescence quantitative PCR detection differentiated for the cow-bezoar true and false |
-
2018
- 2018-06-06 CN CN201810574891.XA patent/CN108896490B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103019671A (en) * | 2012-10-08 | 2013-04-03 | 中国科学院对地观测与数字地球科学中心 | Data-intensive remote sensing image processing-oriented generic programmed framework programming method |
| CN103805703A (en) * | 2014-02-13 | 2014-05-21 | 向华 | Ingredients of animal origins in meat products identified by using mass spectrometry |
| CN105223140A (en) * | 2015-10-10 | 2016-01-06 | 中国科学院苏州生物医学工程技术研究所 | The method for quickly identifying of homology material |
| CN106056157A (en) * | 2016-06-01 | 2016-10-26 | 西北大学 | Hyperspectral image semi-supervised classification method based on space-spectral information |
| CN107881244A (en) * | 2017-10-31 | 2018-04-06 | 中国食品药品检定研究院 | The probe primer and detection method and purposes of the fluorescence quantitative PCR detection differentiated for the cow-bezoar true and false |
Non-Patent Citations (2)
| Title |
|---|
| 杨晓忱: "基于高光谱成像技术的不同品种羊肉识别方法研究", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
| 白亚斌 等: "基于高光谱技术的牛肉-猪肉掺假检测", 《海南师范大学学报（自然科学版）》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110286094A (en) * | 2019-07-18 | 2019-09-27 | 山东省科学院海洋仪器仪表研究所 | A kind of spectral model transfer method based on clustering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108896490B (en) | 2021-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Al-Sarayreh et al. | Potential of deep learning and snapshot hyperspectral imaging for classification of species in meat | |
| CN107873101B (en) | Imaging system for object recognition and evaluation | |
| CN107271375B (en) | A kind of high spectral image detecting method of quality of mutton index | |
| Kamal et al. | Object-based approach for multi-scale mangrove composition mapping using multi-resolution image datasets | |
| Coppola et al. | The distribution of oriented contours in the real world | |
| McPhee et al. | Live animal assessments of rump fat and muscle score in Angus cows and steers using 3-dimensional imaging | |
| KR101852511B1 (en) | System Apparatus and Method for Recommending Cosmetics according to User Skin Type | |
| US10852285B2 (en) | Spectroscopic classification of conformance with dietary restrictions | |
| CN103839283A (en) | Area and circumference nondestructive measurement method of small irregular object | |
| Yusuf et al. | Spectral information analysis of image fusion data for remote sensing applications | |
| Zhang et al. | Evaluation of Goddard’s LiDAR, hyperspectral, and thermal data products for mapping urban land-cover types | |
| Przybylak et al. | Marbling classification of lambs carcasses with the artificial neural image analysis | |
| US20220415002A1 (en) | Three-dimensional (3d) image modeling systems and methods for determining respective mid-section dimensions of individuals | |
| Liu et al. | Recognition and localization of actinidia arguta based on image recognition | |
| Huang et al. | Near-Infrared spectral image analysis of pork marbling based on Gabor filter and wide line detector techniques | |
| JP6618631B2 (en) | Computer system, animal diagnosis method and program | |
| CN108896490A (en) | Meat piece affinity verification method and device | |
| Shamsyeh Zahedi et al. | Fractal dimension and the navigational information provided by natural scenes | |
| Yates et al. | Evaluation of synthetic aerial imagery using unconditional generative adversarial networks | |
| Henry | Perceptual indiscernibility, rough sets, descriptively near sets, and image analysis | |
| CN109313802A (en) | Biological object detection | |
| Heitschmidt et al. | Hyperspectral analysis of fecal contamination: a case study of poultry | |
| CN107644679B (en) | Information pushing method and device | |
| Martínez et al. | Improving unsupervised saliency detection by migrating from RGB to multispectral images | |
| Verma et al. | A comparative study of land cover classification techniques for “farmscapes” using very high resolution remotely sensed data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240306 Address after: Room 1179, W Zone, 11th Floor, Building 1, No. 158 Shuanglian Road, Qingpu District, Shanghai, 201702 Patentee after: Shanghai Zhongan Information Technology Service Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee before: ZHONGAN INFORMATION TECHNOLOGY SERVICE Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240415 Address after: Room 1179, W Zone, 11th Floor, Building 1, No. 158 Shuanglian Road, Qingpu District, Shanghai, 201702 Patentee after: Shanghai Zhongan Information Technology Service Co.,Ltd. Country or region after: China Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Patentee before: ZHONGAN INFORMATION TECHNOLOGY SERVICE Co.,Ltd. Country or region before: China |