CN116448686B - Anti-counterfeiting detection method for fragile fish feed - Google Patents
Anti-counterfeiting detection method for fragile fish feed Download PDFInfo
- Publication number
- CN116448686B CN116448686B CN202310705482.XA CN202310705482A CN116448686B CN 116448686 B CN116448686 B CN 116448686B CN 202310705482 A CN202310705482 A CN 202310705482A CN 116448686 B CN116448686 B CN 116448686B
- Authority
- CN
- China
- Prior art keywords
- fish
- strong inversion
- corner
- detection
- feed
- 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.)
- Active
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 142
- 238000001514 detection method Methods 0.000 title claims abstract description 84
- 239000011573 trace mineral Substances 0.000 claims abstract description 89
- 235000013619 trace mineral Nutrition 0.000 claims abstract description 89
- 230000008021 deposition Effects 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000012216 screening Methods 0.000 claims abstract description 36
- 210000003205 muscle Anatomy 0.000 claims description 21
- 235000019624 protein content Nutrition 0.000 claims description 19
- 206010018910 Haemolysis Diseases 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 10
- 230000008588 hemolysis Effects 0.000 claims description 8
- 235000019988 mead Nutrition 0.000 claims description 6
- 238000001000 micrograph Methods 0.000 claims description 4
- 238000009360 aquaculture Methods 0.000 claims description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 244000144974 aquaculture Species 0.000 claims description 2
- 238000005406 washing Methods 0.000 claims description 2
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 claims 1
- 210000001519 tissue Anatomy 0.000 description 23
- 238000001228 spectrum Methods 0.000 description 10
- 229910052711 selenium Inorganic materials 0.000 description 9
- 239000011669 selenium Substances 0.000 description 9
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 7
- 238000012360 testing method Methods 0.000 description 7
- 241000276707 Tilapia Species 0.000 description 6
- 241000276701 Oreochromis mossambicus Species 0.000 description 5
- 230000000052 comparative effect Effects 0.000 description 5
- 235000013372 meat Nutrition 0.000 description 5
- 240000006677 Vicia faba Species 0.000 description 4
- 235000010749 Vicia faba Nutrition 0.000 description 4
- 235000002098 Vicia faba var. major Nutrition 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 108010028690 Fish Proteins Proteins 0.000 description 3
- WTDRDQBEARUVNC-LURJTMIESA-N L-DOPA Chemical compound OC(=O)[C@@H](N)CC1=CC=C(O)C(O)=C1 WTDRDQBEARUVNC-LURJTMIESA-N 0.000 description 3
- WTDRDQBEARUVNC-UHFFFAOYSA-N L-Dopa Natural products OC(=O)C(N)CC1=CC=C(O)C(O)=C1 WTDRDQBEARUVNC-UHFFFAOYSA-N 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 3
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000010941 cobalt Substances 0.000 description 3
- 229910017052 cobalt Inorganic materials 0.000 description 3
- GUTLYIVDDKVIGB-UHFFFAOYSA-N cobalt atom Chemical compound [Co] GUTLYIVDDKVIGB-UHFFFAOYSA-N 0.000 description 3
- 230000006378 damage Effects 0.000 description 3
- 208000014674 injury Diseases 0.000 description 3
- 238000002310 reflectometry Methods 0.000 description 3
- 239000011701 zinc Substances 0.000 description 3
- 229910052725 zinc Inorganic materials 0.000 description 3
- 241000252230 Ctenopharyngodon idella Species 0.000 description 2
- 108091005804 Peptidases Proteins 0.000 description 2
- 239000004365 Protease Substances 0.000 description 2
- 102100037486 Reverse transcriptase/ribonuclease H Human genes 0.000 description 2
- 206010070834 Sensitisation Diseases 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 230000002949 hemolytic effect Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 230000004060 metabolic process Effects 0.000 description 2
- 238000000120 microwave digestion Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 210000001087 myotubule Anatomy 0.000 description 2
- 239000002504 physiological saline solution Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 102000004169 proteins and genes Human genes 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 125000003748 selenium group Chemical group *[Se]* 0.000 description 2
- 230000008313 sensitization Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 241000132092 Aster Species 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000003674 animal food additive Substances 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000001479 atomic absorption spectroscopy Methods 0.000 description 1
- 238000001391 atomic fluorescence spectroscopy Methods 0.000 description 1
- 238000001675 atomic spectrum Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000000705 flame atomic absorption spectrometry Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 231100000252 nontoxic Toxicity 0.000 description 1
- 230000003000 nontoxic effect Effects 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000012706 support-vector machine 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/47—Scattering, i.e. diffuse reflection
- G01N21/4738—Diffuse reflection, e.g. also for testing fluids, fibrous materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the technical field of feed anti-counterfeiting, and provides a method for detecting anti-counterfeiting of an embrittled fish feed, which comprises the steps of identifying a strong inversion boundary in a slice microscopic image; calculating strong inversion points according to the deposition areas formed by the strong inversion boundaries, and screening all the deposition areas with the strong inversion points inside as detection areas; acquiring the trace element content of each detection area; if the average content of trace elements in any detection area exceeds a threshold value, the fish is judged to be the embrittled fish fed by the embrittled fish feed, otherwise, the fish is the embrittled fish fed by the adulterated feed. The application improves the characteristics of trace elements, ensures that the trace element content in the fish tissue detection area is uniformly distributed, positions the range of the to-be-detected area with relatively stable gradient difference of the trace elements, ensures the detection accuracy and improves the detection precision.
Description
Technical Field
The application relates to the technical field of feed anti-counterfeiting, in particular to a method for anti-counterfeiting detection of an embrittled fish feed.
Background
To prevent the feed from being counterfeited, some feed manufacturers generally add an appropriate amount of non-toxic and harmless beneficial trace elements (for example, selenium, zinc, cobalt, etc. with a total amount lower than the highest limit specified in the feed and feed additive management regulations) to the feed to calibrate the feed source. However, in the feed for the embrittled fish (the brittle grass carp or the brittle tilapia), since the L-3, 4-dihydroxyphenylalanine-containing sensitizer component such as broad bean is required to promote the embrittlement of the muscle and muscle fiber structure of the fish, the price is higher than that of the general fish feed, and although the embrittled fish fed with the imitated feed with broad bean mixed with the general fish feed can be embrittled, the embrittled fish feed with the embrittled fish feed degree and nutrient components being lower than those of normal is embrittled, so that some feed manufacturers generally add trace elements into the embrittled fish feed, and when the embrittled fish is judged to be true or false after sale, the muscle slices of the embrittled fish are detected by a spectrum analysis method or a trace element analyzer to judge whether the embrittled fish is fed with the embrittled fish feed with the trace elements added, so that the embrittled fish quality and nutrition of the embrittled fish are ensured from the source.
However, in order to prevent the trace elements added in the commercial feed from exceeding the standard, the total amount of the trace elements added in the embrittled fish feed is not very high, but the embrittlement principle of the embrittled fish is that the oxidation resistance protease in the fish body can repair the hemolytic injury caused by the L-3, 4-dihydroxyphenylalanine and other sensitization factors, and the muscle and muscle fiber structure of the fish can be changed under the repeated actions of the protease and the sensitization factors so as to embrittle the meat quality, however, when the fish is subjected to metabolism of repeated hemolytic injury of the embrittled fish, a large amount of trace elements can be metabolized along with the hemolysis of the embrittled fish, so that the trace element content in the embrittled region in the fish is less, the trace element characteristics are not obvious, the trace element content distribution in the fish meat tissue is uneven, and the detection is inaccurate.
Disclosure of Invention
The application aims to provide an anti-counterfeiting detection method for embrittled fish feed, which aims to solve one or more technical problems in the prior art and at least provides a beneficial selection or creation condition.
In order to achieve the above object, according to an aspect of the present application, there is provided a method of tamper-proof detection of an embrittled fish feed, the method comprising the steps of:
s100, feeding the fragile fish with feed to be tested for a period of time, and then obtaining a slice microscopic image of the muscle tissue of the fragile fish;
s200, identifying a strong inversion boundary in the slice microscopic image;
s300, calculating strong inversion points according to the deposition areas formed by the strong inversion boundaries, and screening out all deposition areas with the strong inversion points inside as detection areas;
s400, acquiring the trace element content of each detection area;
s500, if the average content of trace elements in any detection area exceeds a threshold value, judging that the fish is the embrittled fish fed by the embrittled fish feed, otherwise, judging that the fish is the embrittled fish fed by the adulterated feed.
In S500, the threshold value is the average content of trace elements in the tissue of the standard embrittled fish muscle, which is measured in advance.
In S500, the average trace element content refers to an average trace element content at all points in the detection area.
Further, in S100, the specific method for feeding the feed to be tested to the embrittled fish for a period of time includes:
the fish to be embrittled with net weight greater than or equal to 0.5 jin/tail or 1 jin/tail is put in an aquaculture pond of 5 mu, the putting density is less than 2000 jin/mu, the daily feeding amount is 3% -5% of the weight of the fish, the oxygen content of water is greater than 5mg/l, the pH value of the water is 7.8-8.0, the salinity is 0.3-0.4%o, the water temperature is 25-28 ℃, and the feed to be tested is fed for 2-3 months.
Wherein the fish to be embrittled is grass carp with crisp meat or tilapia with crisp meat.
Preferably, the feed to be tested at least comprises L-3, 4-dihydroxyphenylalanine or broad bean products.
Further, in S100, the method for acquiring a microscopic image of a section of the muscle tissue of the embrittled fish includes: obtaining a muscle tissue slice of the embrittled fish, washing the fish in 0.8% physiological saline and sucking the surface moisture; and acquiring hyperspectral images of the fish muscle tissue slices by a microscopic hyperspectral imager to serve as slice microscopic images.
Further, in S100, the slice microscopic image is an image obtained by inverting any one trace element of the selenium element content, the zinc element content, and the cobalt element content of the spectral image by using any one inversion model of a quantitative analysis method, a photon diffusion analysis model (analytical photon diffusion model), an atomic fluorescence spectrometry, an atomic absorption spectrometry, or a least squares support vector machine model of the trace element content in the patent of the application with the patent publication number of CN 114577834B.
Preferably, in S100, it includes: the method for obtaining the trace element content of each pixel point in the section microscopic image comprises the following steps: the content of the trace elements of each pixel point in the slice microscopic image is inverted through the spectrum reflection value of the trace elements provided by any one of the USGS spectrum database, the ASD atomic spectrum database, the JPL standard spectrum database, the ASTER spectrum database, the HIPAS spectrum database and the JHU spectrum database, and the inversion process is based on the Lanbert-beer law, so that the content of the trace elements of each pixel point in the slice microscopic image is obtained.
Wherein the microelements comprise any one of selenium element, zinc element and cobalt element.
Due to the fact that a large amount of trace elements are metabolized along with the hemolysis of the embrittled fish in a large amount during metabolism of repeated hemolysis injury of the embrittled fish, the deposition amount of trace elements in the embrittled fish is small, particularly in the fish meat of the semi-embrittled fish (embrittled fish with low embrittlement degree or embrittled in the primary stage), the spectral reflectivity of trace elements in a large amount of image areas of the corresponding embrittled area, which represent hemolysis or semi-hemolysis positions on a slice microscopic image, is low, and in the embrittled fish slice, a large amount of hemolyzed tissues are staggered with thoroughly embrittled fish tissues and fish tissues incapable of embrittlement, so that the accurate integral content of trace elements in the fish tissues cannot be obtained through normal identification inversion; since the non-hemolytic reaction is not carried out, the deposition amount of trace elements in the fully embrittled fish tissue and the non-embrittled fish tissue area is higher than that in the embrittled fish tissue, and the protein in the fully embrittled fish tissue area is much higher than that in the non-fully embrittled fish tissue, and the protein in the non-embrittled fish tissue area is lower than that in the non-fully embrittled fish tissue, the fully embrittled fish tissue is shown as a gray level relatively higher than that in the non-fully embrittled fish tissue on a gray level map, and the non-embrittled fish tissue is shown as a gray level relatively lower than that in the non-fully embrittled fish tissue on a gray level map, and in order to select the non-embrittled fish tissue area with a large deposition amount and the fully embrittled fish tissue, the following scheme is proposed:
further, in S200, a method of identifying strong inversion boundaries in a slice microscopy image includes:
graying the section microscopic image to obtain a gray image, and calculating the average value of protein content of each pixel point in the section microscopic image to be TU; calculating an average value of each gray value in the gray image as GrayAVE, extracting each edge line in the gray image through a watershed algorithm, and dividing the gray image into a plurality of subareas through the edge lines; selecting a subarea with the maximum value of gray values of all pixels in each subarea smaller than GrayAVE and the average value of protein contents corresponding to all pixels in the subarea smaller than TU as a first screening area; (the first screening area is a fish tissue area that cannot be embrittled);
selecting a subarea with the minimum value of gray values of all pixels in each subarea being larger than GrayAVE, and the average value of protein contents corresponding to all pixels in the subarea being larger than TU as a second screening area; (the second screening area is fish tissue that has been thoroughly embrittled);
marking the first screening area and/or the second screening area as deposition areas;
the edge line of the boundary of the deposition area is taken as a strong inversion boundary.
The protein content of each pixel in the slice microscopic image is analyzed by multiple linear regression to obtain the relation between the protein content and the reflectivity of the pixel in the hyperspectral image, so as to obtain the fish protein content, for example, a fish protein content distribution detection method based on hyperspectral imaging technology in Chinese patent publication No. CN 103630499B.
The deposition area in the strong inversion boundary is an area with more deposition amount of trace elements, but in the actual detection process, the deposition area is often an area with smaller area, and the muscle tissue of the fish is better or worse in local trace element absorption, so that the trace element absorption condition of the whole embrittled fish cannot be represented, and therefore, the range of the to-be-detected area needs to be positioned through the following scheme of the application, so that the detection accuracy is ensured, and the specific method is as follows:
further, in S300, the method for calculating the strong inversion points according to the deposition areas formed by the strong inversion boundaries, and screening all the deposition areas with the strong inversion points inside as the detection areas includes:
performing corner detection on each deposition area to obtain corners, wherein each corner forms a set p, p= { p 0 、p 1 、p 2 …p i …p N }，i=[1,N]N is the total number of corner points;
at i.e. [1, N]Sequentially calculating all corner points p within the range of (2) i Strong inversion point p (p i ): recording corner point p i The corner point with the largest difference of trace element content in the position is pmax and is recorded with the corner point p i The corner with the minimum difference of trace element content in the position is pmin, and each corner is matched with the corner p i The values of the trace element content differences of the set p are arranged into a sequence L (p i ) The method comprises the steps of carrying out a first treatment on the surface of the Pmin is at L (p i ) In (2) is R1, pmax is L (p i ) Wherein the number R2 is represented by L (p i ) All nodes intercepting the sequence number R1 to the sequence number R2 form a close sequence R (p i )，
Calculating the corner point p i Strong inversion point p (p i )；
；
Wherein p is j Is the close sequence R (p i ) The middle sequence numbers are from j=r1 to j=r2 corner points, (note: p if j-1 is 0 j-1 0), j is a sequence number; k1 is p j Is the ratio of the previous content of k2 is p j Is added to the mixture according to the ratio of the post content of (2),；/>；
the content weight ratio k=1-k 1-k2; wherein q j Is the close sequence R (p i ) Trace element content in positions corresponding to corner points from R1 to R2 in the middle sequence number; qL is the close sequence R (p i ) The maximum trace element content in trace elements in positions corresponding to corner points from R1 to R2 in the middle sequence number; qS is the close sequence R (p i ) Minimum trace element content in trace elements in positions corresponding to corner points of the intermediate serial numbers from R1 to R2; (the strong inversion point is the point p with the corner point i The most balanced trace element points corresponding to the positions, namely the trace element gradient differences of all deposition areas around the strong inversion points are small, so that trace element content is uniformly distributed and is the position which is most easily detected, and the strong inversion points are opposite to the corner points p i The position which tends to have smaller gradient difference tends to move, so that strong inversion points are generally not present in the areas with weaker gradient difference and uneven trace element content distribution than trace elements;
all the deposition areas with strong inversion points inside are screened out as detection areas.
Preferably, in order to increase the detection speed, the corner point p i Strong inversion point p (p i ) The method can also be as follows: strong inversion Point p (p) i ) Is the corner point p i The projection points on the connecting line between the corner point pmax and the corner point pmin, but the accuracy of the detection result is reduced.
The detection area obtained by the method has the advantages that due to the rapid blood dissolving reaction of the embrittled fish, the detection area is provided with a relatively large hemolysis area in the detection area on the fish tissue slice of the embrittled fish with relatively low embrittlement degree, so that the uneven distribution of trace element content in the detection area can occur, and the distribution of the trace element content in the detection area is relatively low, so that the detection accuracy is further improved, and the following preferable scheme is provided:
preferably, in S400, screening out all the deposition areas with strong inversion points inside as detection areas includes the following steps:
at i.e. [1, N]Ranges of (2)In turn for each strong inversion point p (p i ) Performing a hemolysis zone operation: obtaining strong inversion points p (p) i ) Included angles between connecting lines of the corner points in the corner point set p; inversion of point p (p i ) The average value of the trace element content difference values of the positions of each corner point in the corner point set p is temM; screening strong inversion points p (p i ) And each corner with the difference value of trace element content of each corner position in the corner set p being greater than or equal to temM, selecting a sum strong inversion point p (p i ) Two corner points PE1 and PE2 of the largest included angle among included angles between connecting lines; calculate the strong inversion point p (p i ) And the average value of the connecting line length of each corner point in the corner point set p is MEAD;
the distance between PE1 and PE2 is denoted LD; judging whether LD is greater than TH times MEAD, if so, adding p (p i ) PE1 and PE2 are connected to each other to form a triangular space, such that p (p i ) The projection point on the edge where PE1 and PE2 are connected is PE3, the edge of the deposition area between the 2 projection points PE4 and PE5 of PE1 and PE2 on the nearest strong inversion boundary is deleted, PE3 and PE4 are connected, and PE3 and PE5 are connected to form a new deposition area; wherein, TH is a preset threshold value, and TH takes on the value [0.7,3 ]]The smaller the TH value, the smaller the deposition area connected, and the higher the detection precision, but the time complexity is high, and the larger the pressure on the detection instrument, the larger the time delay can be generated.
The application also provides a system for detecting the anti-counterfeiting of the fragile fish feed, which comprises: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the method for detecting the anti-counterfeiting of the fragile fish feed when executing the computer program, and the system for detecting the anti-counterfeiting of the fragile fish feed runs in a computing device of a desktop computer, a notebook computer, a palm computer or a cloud data center, and the running system comprises the processor, the memory and a server cluster.
As described above, the method for detecting the anti-counterfeiting of the fragile fish feed has the following beneficial effects: the trace element characteristic is improved, the trace element content in the fish tissue detection area is uniformly distributed, the range of the to-be-detected area with relatively stable gradient difference of the trace element is positioned, the detection accuracy is ensured, and the detection precision is improved.
Drawings
Fig. 1 shows a structural diagram of an anti-counterfeiting detection system for the fragile fish feed.
Detailed Description
The method comprises the steps of stocking tilapia to be embrittled in a test culture pond and a control culture pond with net weight of 1 jin/tail (error interval of 200 g) respectively, wherein the test culture pond and the control culture pond are both aquiculture ponds with 5 mu, stocking density of 2000 tails/mu and daily feeding amount of 5% of the weight of the tilapia. The feeds to be tested which are respectively fed in the test culture pond and the control culture pond are false feeds prepared by compound feeds mixed with broad bean products and aquatic embrittlement feeds containing 0.25mg/kg selenium element which are manufactured by feed manufacturers (the specification of additive use standard in feeds (GB/T22247-2008), and the addition amount of selenium in the aquatic feeds is not more than 0.3 mg/kg). The oxygen content of the water body is 5mg/l, the pH value of the water body is maintained at 7.8-8.0, the salinity is 0.3 per mill, and the water temperature is maintained at 25-28 ℃.
After feeding the feed to be detected for 2 months, respectively obtaining section microscopic images of the muscle tissues of 30 embrittled tilapia mossambica in the test culture pond and the control culture pond, wherein the section microscopic images specifically comprise: respectively obtaining 30 crisp tilapia mossambica in a test culture pond and a control culture pond, obtaining muscle tissue slices of the crisp tilapia, and cleaning and sucking surface moisture in 0.8% physiological saline for fish; and acquiring hyperspectral images of the fish muscle tissue slices by a microscopic hyperspectral imager to serve as slice microscopic images.
The microscopic images of the sections of the muscle tissues of 30 brittle tilapia mossambica are subjected to anti-counterfeiting detection by the anti-counterfeiting detection methods in the following first embodiment, the second embodiment and the comparative embodiment:
embodiment one: identifying a strong inversion boundary in the slice microscopy image; calculating strong inversion points according to the deposition areas formed by the strong inversion boundaries, and screening all the deposition areas with the strong inversion points inside as detection areas; acquiring the trace element content of each detection area; if the average content of trace elements in any detection area exceeds a threshold value, the fragile fish fed by the fragile fish feed is judged, otherwise, the fragile fish fed by the adulterated feed is judged, wherein the threshold value is set to be 0.25mg/kg. Wherein the trace element is selenium.
The method for obtaining the trace element content of each pixel point in the slice microscopic image comprises the following steps: inversion is carried out on the content of the trace elements of each pixel point in the slice microscopic image through the spectrum reflection value of the USGS spectrum database, and the inversion process is based on the Lanbert-beer law, so that the content of the trace elements of each pixel point in the slice microscopic image is obtained.
The method for identifying the strong inversion boundary in the slice microscopic image comprises the following steps:
graying the section microscopic image to obtain a gray image, and calculating the average value of protein content of each pixel point in the section microscopic image to be TU; calculating an average value of each gray value in the gray image as GrayAVE, extracting each edge line in the gray image through a watershed algorithm, and dividing the gray image into a plurality of subareas through the edge lines; selecting a subarea with the maximum value of gray values of all pixels in each subarea smaller than GrayAVE and the average value of protein contents corresponding to all pixels in the subarea smaller than TU as a first screening area; selecting a subarea with the minimum value of gray values of all pixels in each subarea being larger than GrayAVE, and the average value of protein contents corresponding to all pixels in the subarea being larger than TU as a second screening area; the first screening area and the second screening area are marked as deposition areas; the edge line of the boundary of the deposition area is taken as a strong inversion boundary.
Protein content of each pixel point in the section microscopic image is analyzed through multiple linear regression to obtain a relation between the protein content and the reflectivity of the pixel point in the hyperspectral image, and fish protein content is obtained.
Further, the method for calculating the strong inversion points according to the deposition areas formed by the strong inversion boundaries and screening all the deposition areas with the strong inversion points inside as detection areas comprises the following steps:
performing corner detection on each deposition area to obtain corners, wherein each corner forms a set p, p= {p 0 、p 1 、p 2 …p i …p N }，i=[1,N]N is the total number of corner points;
at i.e. [1, N]Sequentially calculating all corner points p within the range of (2) i Strong inversion point p (p i ): recording corner point p i The corner point with the largest difference of trace element content in the position is pmax and is recorded with the corner point p i The corner with the minimum difference of trace element content in the position is pmin, and each corner is matched with the corner p i The values of the trace element content differences of the set p are arranged into a sequence L (p i ) The method comprises the steps of carrying out a first treatment on the surface of the Pmin is at L (p i ) In (2) is R1, pmax is L (p i ) Wherein the number R2 is represented by L (p i ) All nodes intercepting the sequence number R1 to the sequence number R2 form a close sequence R (p i )，
Calculating the corner point p i Strong inversion point p (p i )；
；
Wherein p is j Is the close sequence R (p i ) The middle sequence numbers are from j=r1 to j=r2 corner points, (note: p if j-1 is 0 j-1 0), j is a sequence number; k1 is p j Is the ratio of the previous content of k2 is p j Is added to the mixture according to the ratio of the post content of (2),；/>；
the content weight ratio k=1-k 1-k2; wherein q j Is the close sequence R (p i ) Trace element content in positions corresponding to corner points from R1 to R2 in the middle sequence number; qL is the close sequence R (p i ) The maximum trace element content in trace elements in positions corresponding to corner points from R1 to R2 in the middle sequence number; qS is the close sequence R (p i ) Minimum trace element content in trace elements in positions corresponding to corner points of the intermediate serial numbers from R1 to R2; all the deposition areas with strong inversion points inside are screened out as detection areas.
Embodiment two: identifying a strong inversion boundary in the slice microscopy image; calculating strong inversion points according to the deposition areas formed by the strong inversion boundaries, and screening all the deposition areas with the strong inversion points inside as detection areas; acquiring the trace element content of each detection area; if the average content of trace elements in any detection area exceeds a threshold value, the fragile fish fed by the fragile fish feed is judged, otherwise, the fragile fish fed by the adulterated feed is judged, wherein the threshold value is set to be 0.25mg/kg. Wherein the trace element is selenium.
The method for obtaining the trace element content of each pixel point in the slice microscopic image comprises the following steps: inversion is carried out on the content of the trace elements of each pixel point in the slice microscopic image through the spectrum reflection value of the USGS spectrum database, and the inversion process is based on the Lanbert-beer law, so that the content of the trace elements of each pixel point in the slice microscopic image is obtained.
The method for identifying the strong inversion boundary in the slice microscopic image comprises the following steps:
graying the section microscopic image to obtain a gray image, and calculating the average value of protein content of each pixel point in the section microscopic image to be TU; calculating an average value of each gray value in the gray image as GrayAVE, extracting each edge line in the gray image through a watershed algorithm, and dividing the gray image into a plurality of subareas through the edge lines; selecting a subarea with the maximum value of gray values of all pixels in each subarea smaller than GrayAVE and the average value of protein contents corresponding to all pixels in the subarea smaller than TU as a first screening area; selecting a subarea with the minimum value of gray values of all pixels in each subarea being larger than GrayAVE, and the average value of protein contents corresponding to all pixels in the subarea being larger than TU as a second screening area; the first screening area and the second screening area are marked as deposition areas; the edge line of the boundary of the deposition area is taken as a strong inversion boundary.
Further, the method for calculating the strong inversion points according to the deposition areas formed by the strong inversion boundaries and screening all the deposition areas with the strong inversion points inside as detection areas comprises the following steps: corner points are carried out on each deposition areaDetecting and obtaining angular points, wherein each angular point forms a set p, p= { p 0 、p 1 、p 2 …p i …p N }，i=[1,N]N is the total number of corner points; at i.e. [1, N]Sequentially calculating all corner points p within the range of (2) i Strong inversion point p (p i ): recording corner point p i The corner point with the largest difference of trace element content in the position is pmax and is recorded with the corner point p i The corner point with the minimum difference of trace element content in the position is pmin, and the strong inversion point p (p i ) Is the corner point p i Projection points on connecting lines between the corner points pmax and pmin; all the deposition areas with strong inversion points inside are screened out as detection areas.
In order to improve the detection speed, the accuracy of the detection result is sacrificed, and in order to achieve both the accuracy and the accuracy, the present embodiment improves the detection speed by the following preferred scheme.
Wherein, screening all the deposition areas with strong inversion points inside as detection areas comprises the following steps:
at i.e. [1, N]For each strong inversion point p (p i ) Performing a hemolysis zone operation: obtaining strong inversion points p (p) i ) Included angles between connecting lines of the corner points in the corner point set p; inversion of point p (p i ) The average value of the trace element content difference values of the positions of each corner point in the corner point set p is temM; screening strong inversion points p (p i ) And each corner with the difference value of trace element content of each corner position in the corner set p being greater than or equal to temM, selecting a sum strong inversion point p (p i ) Two corner points PE1 and PE2 of the largest included angle among included angles between connecting lines; calculate the strong inversion point p (p i ) And the average value of the connecting line length of each corner point in the corner point set p is MEAD; the distance between PE1 and PE2 is denoted LD; judging whether LD is greater than TH times MEAD, if so, adding p (p i ) PE1 and PE2 are connected to each other to form a triangular space, such that p (p i ) The projection point on the edge where PE1 and PE2 are connected is PE3, the edge of the deposition area between the 2 projection points PE4 and PE5 of PE1 and PE2 on the nearest strong inversion boundary is deleted, PE3 and PE4 are connected, and PE3 and PE5 are connected to form a new deposition area; wherein,TH is a preset threshold value, and the TH value is 1.
Comparative example: the muscle tissues of 30 brittle tilapia mossambica in the test culture pond and the control culture pond are treated respectively by a microwave digestion method, and the content of selenium is measured by a flame atomic absorption spectrometry. Wherein, the muscle tissue of the tilapia is treated with 5 mL HNO 3 And 1 mL H 2 O 2 After microwave digestion treatment, determining the selenium element content, if the average content of trace elements detected by sampling for any time exceeds a threshold value, determining that the fragile fish is fed by the fragile fish feed, otherwise, setting the threshold value to be 0.25mg/kg for the fragile fish fed by the adulterated feed.
Anti-counterfeiting detection results of muscle tissues of 30 crisp tilapia mossambica in the first embodiment, the second embodiment and the comparative embodiment:
after the method is adopted, the anti-counterfeiting detection result data prepared by the first embodiment, the second embodiment and the comparative example of the application are as follows:
the detection result of the first embodiment is: the fragile fish fed with the 30-tail adulterated feed identified 30 tails, and the fragile fish fed with the 30-tail adulterated feed identified 30 tails.
The detection result of the second embodiment is: the fragile fish fed with the 30-tail adulterated feed identified 29 tails, and the fragile fish fed with the 30-tail adulterated feed identified 30 tails.
The test results of the comparative example are: the fragile fish fed with the 30-tail adulterated feed identified 17 tails and the fragile fish fed with the 30-tail adulterated feed identified 27 tails.
The anti-counterfeiting detection result surface, the identification accuracy of the first embodiment and the second embodiment is remarkably higher than that of the conventional detection comparison example, and the application can accurately identify the embrittled fish fed by the adulterated feed, especially the first embodiment, and the false detection rate of the embrittled fish fed by the adulterated feed is lowest.
The embodiment of the application also provides a system for detecting the anti-counterfeiting of the fragile fish feed, as shown in fig. 1, which is a system structure diagram of the anti-counterfeiting detection of the fragile fish feed, and the system for detecting the anti-counterfeiting of the fragile fish feed of the embodiment comprises: a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the system embodiment of the above-described detection of false-proof of a fragile fish feed when executing the computer program.
The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in units of the following system:
the strong inversion identification unit is used for identifying a strong inversion boundary in the slice microscopic image;
the detection area screening unit is used for calculating strong inversion points according to the deposition areas formed by the strong inversion boundaries and screening out all deposition areas with the strong inversion points inside as detection areas;
the element inversion unit is used for obtaining the trace element content of each detection area;
and the anti-counterfeiting identification unit is used for judging the fragile fish fed by the fragile fish feed if the average content of the trace elements in any detection area exceeds a threshold value, and judging the fragile fish fed by the fragile fish feed if the average content of the trace elements in any detection area exceeds the threshold value, otherwise, judging the fragile fish fed by the adulterated feed.
The system for detecting the anti-counterfeiting of the fragile fish feed can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud data center and the like. The system for detecting the anti-counterfeiting of the fragile fish feed comprises, but is not limited to, a processor and a memory. It will be appreciated by those skilled in the art that the examples are merely examples of a method for tamper-proof detection of an embrittled fish feed and are not limiting of the method for tamper-proof detection of an embrittled fish feed, and may include more or fewer components than examples, or may combine certain components, or different components, e.g., the system for tamper-proof detection of an embrittled fish feed may further include input and output devices, network access devices, buses, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete component gate or transistor logic devices, discrete hardware components, or the like. The general processor can be a microprocessor or any conventional processor, and the processor is a control center of the system for detecting the false proof of the fragile fish feed, and various interfaces and lines are used for connecting various subareas of the whole sentence probability computing system based on the gradient lifting decision tree.
The memory may be used to store the computer program and/or the module, and the processor may implement the various functions of the method for detecting the false proof of the fragile fish feed by running or executing the computer program and/or the module stored in the memory and invoking the data stored in the memory. The memory may include mainly a program area and a data area, where the memory may include a high-speed random access memory, and may include a nonvolatile memory such as a hard disk, a memory, a plug-in type hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid-state storage device.
Although the present application has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the application. Furthermore, the foregoing description of the application has been presented in its embodiments contemplated by the inventors for the purpose of providing a useful description, and for the purposes of providing a non-essential modification of the application that may not be presently contemplated, may represent an equivalent modification of the application.
Claims (5)
1. A method for anti-counterfeiting detection of embrittled fish feed, the method comprising the steps of:
s100, feeding the fragile fish with feed to be tested for a period of time, and then obtaining a slice microscopic image of the muscle tissue of the fragile fish;
s200, identifying a strong inversion boundary in the slice microscopic image;
s300, calculating strong inversion points according to the deposition areas formed by the strong inversion boundaries, and screening out all deposition areas with the strong inversion points inside as detection areas;
s400, acquiring the trace element content of each detection area;
s500, if the average content of trace elements in any detection area exceeds a threshold value, judging that the fragile fish is fed by the fragile fish feed, otherwise, judging that the fragile fish is fed by the adulterated feed;
wherein in S200, the method of identifying strong inversion boundaries in a slice microscopy image comprises: graying the section microscopic image to obtain a gray image, and calculating the average value of protein content of each pixel point in the section microscopic image to be TU; calculating an average value of each gray value in the gray image as GrayAVE, extracting each edge line in the gray image through a watershed algorithm, and dividing the gray image into a plurality of subareas through the edge lines; selecting a subarea with the maximum value of gray values of all pixels in each subarea smaller than GrayAVE and the average value of protein contents corresponding to all pixels in the subarea smaller than TU as a first screening area; selecting a subarea with the minimum value of gray values of all pixels in each subarea being larger than GrayAVE, and the average value of protein contents corresponding to all pixels in the subarea being larger than TU as a second screening area; marking the first screening area and/or the second screening area as deposition areas; taking edge lines of the boundary of the deposition area as strong inversion boundaries;
the method for screening out all the deposition areas with the strong inversion points inside as detection areas comprises the following steps: performing corner detection on each deposition area to obtain corners, wherein each corner forms a set p, p= { p 0 、p 1 、p 2 …p i …p N N+1 is the total number of corner points; at i.e. [1, N]Sequentially calculating all corner points p within the range of (2) i Strong inversion point p (p i ): recording corner point p i Corner point with maximum difference of trace element content in positionLet pmax and point p i The corner point with the minimum difference of trace element content in the position is pmin, and the strong inversion point p (p i ) Is the corner point p i Projection points on connecting lines between the corner points pmax and pmin; screening all deposition areas with strong inversion points inside as detection areas;
wherein, screening all the deposition areas with strong inversion points inside as detection areas comprises the following steps: at i.e. [1, N]For each strong inversion point p (p i ) Performing a hemolysis zone operation: obtaining strong inversion points p (p) i ) Included angles between connecting lines of the corner points in the corner point set p; inversion of point p (p i ) The average value of the trace element content difference values of the positions of each corner point in the corner point set p is temM; screening strong inversion points p (p i ) And each corner with the difference value of trace element content of each corner position in the corner set p being greater than or equal to temM, selecting a sum strong inversion point p (p i ) Two corner points PE1 and PE2 of the largest included angle among included angles between connecting lines; calculate the strong inversion point p (p i ) And the average value of the connecting line length of each corner point in the corner point set p is MEAD; the distance between PE1 and PE2 is denoted LD; judging whether LD is greater than TH times MEAD, if so, adding p (p i ) PE1 and PE2 are connected to each other to form a triangular space, such that p (p i ) The projection point on the edge where PE1 and PE2 are connected is PE3, the edge of the deposition area between the 2 projection points PE4 and PE5 of PE1 and PE2 on the nearest strong inversion boundary is deleted, PE3 and PE4 are connected, and PE3 and PE5 are connected to form a new deposition area; wherein, TH is a preset threshold value, and TH takes on the value [0.7,3 ]]。
2. The method for anti-counterfeiting detection of the feed for the fragile fish according to claim 1, wherein in the step S100, the specific method for feeding the feed to be detected for a period of time to the fragile fish is as follows: the fish to be embrittled is put in an aquaculture pond, the daily feeding amount is 3% -5% of the weight of the fish, the oxygen content of the water body is more than 5mg/l, the pH value of the water body is 7.8-8.0, the salinity is 0.3-0.4%, and the water temperature is 25-28 ℃.
3. The method for anti-counterfeiting detection of the feed for the fragile fish according to claim 1, wherein in S100, the method for acquiring the slice microscopic image of the muscle tissue of the fragile fish comprises the following steps: obtaining a muscle tissue slice of the embrittled fish, washing the fish in normal saline and sucking water on the surface of the fish; and acquiring hyperspectral images of the fish muscle tissue slices by a microscopic hyperspectral imager.
4. The method for anti-counterfeiting detection of an embrittled fish feed according to claim 1, wherein in S500, the threshold value is an average content of trace elements of a predetermined standard embrittled fish muscle tissue.
5. A system for tamper-proof detection of embrittled fish feed, the system comprising: memory, a processor and a computer program stored in the memory and running on the processor, which processor, when executing the computer program, carries out the steps of a method for anti-counterfeit detection of fragile fish feed according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310705482.XA CN116448686B (en) | 2023-06-15 | 2023-06-15 | Anti-counterfeiting detection method for fragile fish feed |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310705482.XA CN116448686B (en) | 2023-06-15 | 2023-06-15 | Anti-counterfeiting detection method for fragile fish feed |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116448686A CN116448686A (en) | 2023-07-18 |
| CN116448686B true CN116448686B (en) | 2023-12-01 |
Family
ID=87130562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310705482.XA Active CN116448686B (en) | 2023-06-15 | 2023-06-15 | Anti-counterfeiting detection method for fragile fish feed |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116448686B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808806B (en) * | 2024-02-29 | 2024-05-03 | 德睦熙睿生物科技(天津)有限公司 | Feed production quality refinement detection method based on image feature analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105901413A (en) * | 2016-04-19 | 2016-08-31 | 通威股份有限公司 | Mixed feed preventing crisp-flesh grass carp over-crispness |
| CN113466232A (en) * | 2021-09-01 | 2021-10-01 | 广东省农业科学院动物科学研究所 | Brittle fish meat rapid detection method and system based on computer image |
| CN114577834A (en) * | 2022-05-06 | 2022-06-03 | 广东省农业科学院动物科学研究所 | Aquatic product quality detection method based on X-ray fluorescence spectrum analysis |
| CN116067964A (en) * | 2023-03-06 | 2023-05-05 | 广东省农业科学院动物科学研究所 | Method and system for promoting fish muscle embrittlement by utilizing condensed tannin |
-
2023
- 2023-06-15 CN CN202310705482.XA patent/CN116448686B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105901413A (en) * | 2016-04-19 | 2016-08-31 | 通威股份有限公司 | Mixed feed preventing crisp-flesh grass carp over-crispness |
| CN113466232A (en) * | 2021-09-01 | 2021-10-01 | 广东省农业科学院动物科学研究所 | Brittle fish meat rapid detection method and system based on computer image |
| CN114577834A (en) * | 2022-05-06 | 2022-06-03 | 广东省农业科学院动物科学研究所 | Aquatic product quality detection method based on X-ray fluorescence spectrum analysis |
| CN116067964A (en) * | 2023-03-06 | 2023-05-05 | 广东省农业科学院动物科学研究所 | Method and system for promoting fish muscle embrittlement by utilizing condensed tannin |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116448686A (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Apple quality identification and classification by image processing based on convolutional neural networks | |
| Kiratiratanapruk et al. | Development of paddy rice seed classification process using machine learning techniques for automatic grading machine | |
| Li et al. | Authentication of fishery and aquaculture products by multi-element and stable isotope analysis | |
| Arakeri | Computer vision based fruit grading system for quality evaluation of tomato in agriculture industry | |
| Xu et al. | Using Deep Convolutional Neural Networks for Image‐Based Diagnosis of Nutrient Deficiencies in Rice | |
| Leng et al. | Fast quantification of total volatile basic nitrogen (TVB-N) content in beef and pork by near-infrared spectroscopy: Comparison of SVR and PLS model | |
| Barbin et al. | Near-infrared hyperspectral imaging for grading and classification of pork | |
| CN116448686B (en) | Anti-counterfeiting detection method for fragile fish feed | |
| Sun et al. | Classification of black beans using visible and near infrared hyperspectral imaging | |
| Zhang et al. | Detection and classification of potato defects using multispectral imaging system based on single shot method | |
| Tsakanikas et al. | High throughput multispectral image processing with applications in food science | |
| CN116067964B (en) | Method and system for promoting fish muscle embrittlement by utilizing condensed tannin | |
| Xu et al. | Spatial‐spectral analysis method using texture features combined with PCA for information extraction in hyperspectral images | |
| Ahmed et al. | Classification of pepper seed quality based on internal structure using X-ray CT imaging | |
| Ruta et al. | Comparable disparity in the appendicular skeleton across the fish–tetrapod transition, and the morphological gap between fish and tetrapod postcrania | |
| Misimi et al. | Quality grading of Atlantic salmon (Salmo salar) by computer vision | |
| Arsalane et al. | The assessment of fresh and spoiled beef meat using a prototype device based on GigE Vision camera and DSP | |
| de Magalhães et al. | Mid-infrared spectroscopic screening of metabolic alterations in stress-exposed gilthead seabream (Sparus aurata) | |
| Davis et al. | Assessing the variability and discriminatory power of elemental fingerprints in whiteleg shrimp Litopenaeus vannamei from major shrimp production countries | |
| Zhang et al. | A novel image detection method for internal cracks in corn seeds in an industrial inspection line | |
| Feng et al. | Detection of Atlantic salmon residues based on computer vision | |
| Zhang et al. | Non-destructive hyperspectral imaging for rapid determination of catalase activity and ageing visualization of wheat stored for different durations | |
| Healy et al. | Aging Pacific cod (Gadus macrocephalus) from otoliths using Fourier‐transformed near‐infrared spectroscopy | |
| Zhang et al. | A transfer learning method for spectral model of moldy apples from different origins | |
| Sun et al. | Research on classification method of eggplant seeds based on machine learning and multispectral imaging classification eggplant seeds |
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 |