CN116519892B - Fish tenderness quality identification method and system - Google Patents
Fish tenderness quality identification method and system Download PDFInfo
- Publication number
- CN116519892B CN116519892B CN202310776590.6A CN202310776590A CN116519892B CN 116519892 B CN116519892 B CN 116519892B CN 202310776590 A CN202310776590 A CN 202310776590A CN 116519892 B CN116519892 B CN 116519892B
- Authority
- CN
- China
- Prior art keywords
- domain
- core
- fish
- lipid
- armature
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 241000251468 Actinopterygii Species 0.000 claims abstract description 98
- 150000002632 lipids Chemical class 0.000 claims abstract description 78
- 229920000742 Cotton Polymers 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 33
- 235000013372 meat Nutrition 0.000 claims abstract description 12
- 238000010586 diagram Methods 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 11
- 238000009941 weaving Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 9
- 210000003205 muscle Anatomy 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 claims 2
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000009940 knitting Methods 0.000 abstract 2
- 238000012797 qualification Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000000704 physical effect Effects 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 102000004506 Blood Proteins Human genes 0.000 description 2
- 108010017384 Blood Proteins Proteins 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 239000002504 physiological saline solution Substances 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013332 fish product Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/02—Food
- G01N33/12—Meat; Fish
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/286—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q involving mechanical work, e.g. chopping, disintegrating, compacting, homogenising
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/286—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q involving mechanical work, e.g. chopping, disintegrating, compacting, homogenising
- G01N2001/2873—Cutting or cleaving
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Multimedia (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Food Science & Technology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Medicinal Chemistry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application belongs to the technical field of graphic processing and intelligent identification, and provides a fish tenderness quality identification method and system, which specifically comprise the following steps: the fish body is sliced to obtain a reference slice, the reference slice is subjected to image shooting through an electron microscope to obtain a slice image, the slice image is preprocessed to form a processing image, the cotton lipid is calculated according to the processing image, the fat-knitting coefficient is obtained by combining the processing image and the cotton lipid, and finally the tenderness and the smoothness of the fish meat are identified according to the fat-knitting coefficient. The quantitative attribute and gray value attribute of the myoid pixels and the lipoid pixels accurately mark and quantify the balance and the heaviness of fat distribution, so that the sparse characteristic of the fat distribution at each position in an image is quantified, the convenience for fish quality monitoring is greatly improved, and reliable and efficient quality identification data is provided for observers.
Description
Technical Field
The application belongs to the technical field of graphic processing and intelligent identification, and particularly relates to a fish tenderness and smoothness quality identification method and system.
Background
The tender and slippery characteristic of the fish meat is an ideal taste and texture of the fish meat, is one of important characteristics of the fish meat, and has important significance for improving the taste and eating feeling of food. The fish products with tender and smooth mouthfeel can increase the competitiveness and the added value of the products, and have high market demands and economic values. However, tenderness of fish is not an exact physical property, but a property based on subjective perception of human beings, and thus the property cannot be directly measured, if quality identification of tenderness of fish is desired, objective physical properties of fish are not separated from extraction analysis, and tenderness of fish is accurately quantified according to the physical properties obtained by the analysis, wherein fat distribution and thickness of fish are closely related to tenderness of fish.
Disclosure of Invention
The application aims to provide a fish tenderness quality identification method and a fish tenderness quality identification system, which are used for solving one or more technical problems in the prior art and at least providing 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 fish tenderness quality identification method comprising the steps of:
s100, slicing the fish body to obtain a reference slice;
s200, performing image shooting on a reference slice through an electron microscope to obtain a slice diagram;
s300, preprocessing the slice diagram to form a processing diagram;
s400, calculating the cotton lipid degree according to the treatment diagram;
s500, combining the treatment graph and the cotton lipid degree calculation to obtain a lipid weaving coefficient;
s600, quality identification is carried out on the tenderness and the smoothness of the fish meat according to the fat-weaving coefficient.
Further, in step S100, the method for obtaining the reference slice by slicing the fish body is as follows: slicing the fish body by a sampling device, wherein the slicing treatment position is the infraxis muscle below the central point of the trunk of the fish body, the slicing thickness requirement of the slicing treatment is 5-15 mu m, and the sampling device can be a fixing device for sampling the live fish muscle with the publication number of CN 205785876U; the slice was washed with physiological saline to remove water on the surface of the slice, and used as a reference slice.
Further, in step S300, the method for preprocessing the slice map to form a processing map is as follows: and carrying out contrast stretching on the slice image, denoising the slice image through a median filter, and finally carrying out graying treatment on the slice image to obtain a treatment image.
Further, in step S400, the method for calculating the cotton lipid according to the processing chart is as follows: performing super-pixel segmentation on the processing diagram, and taking each region obtained by segmentation as a unit domain respectively; classifying each pixel in the treatment graph through the ICM condition iteration model, and classifying each pixel in the treatment graph into a myoid pixel or a lipoid pixel; the number of myoid pixels and lipid pixels in a unit domain is referred to as myoid amount n_zm and lipid amount n_zf, respectively; the arithmetic average value of the gray value of each muscle-like pixel in the treatment chart is named as full-muscle gray gry _ wem, and the arithmetic average value of the gray value of each lipid pixel in the treatment chart is named as full-fat gray gry _ wef; the arithmetic average of the gray values of the individual pixels in a cell field is denoted gry _z, and if a cell field satisfies gry _z e [ gry _ wef, gry _ wem ], the cell field is defined as a single-bit field; calculate the cotton lipid SFD of single-armature domain:
；
where ln () is a logarithmic function whose base is a natural constant e, and rt_zp is a ratio of the median among the gradation values of the respective pixels in the single-phase domain to the maximum value among them.
In the calculation process of the cotton lipid, the calculation source or the data source of the cotton lipid is limited in the unit domain, so that the problem of insufficient sensitivity to adjacent data can be caused by the operation mode, and further, the data acquisition of the lipid content distribution near the single-match domain is lost, so that the accuracy of the next step of calculating the lipid texture coefficient is reduced; however, the problem of insufficient sensitivity of the cotton-padded fat to proximity perception cannot be solved in the prior art, and in order to better solve the problem and eliminate the phenomenon of insufficient sensitivity of the proximity data, the present application proposes a more preferable scheme as follows:
preferably, in step S400, the method for calculating the cotton lipid according to the processing chart is: performing super-pixel segmentation on the processing diagram, and marking each region obtained by segmentation as a unit domain; classifying each pixel in the treatment graph through an ICM condition iteration model, and classifying each pixel in the treatment graph into a myoid pixel and a lipoid pixel; the arithmetic average value of the gray value of each myoid pixel in the processing chart is recorded as the full-muscle gray gry-wem; the arithmetic average of the gray values of each lipid pixel in the treatment map is designated as full-fat gray gry _ wef;
wherein the full-muscle gray scale is larger than the full-fat gray scale, and muscle tissue contains more protein, blood and other tissue components, so that more light can be absorbed, and a higher gray scale value is obtained.
The arithmetic average of the gray values of the individual pixels in a cell field is denoted gry _z, and if a cell field satisfies gry _z e [ gry _ wef, gry _ wem ], the cell field is defined as a single-bit field; in each pixel of one unit domain, if the eight neighborhood of the pixel contains the pixel which does not belong to the unit domain, the pixel is the boundary pixel of the unit domain, the other unit domains which correspond to the pixel which does not belong to the unit domain in the eight neighborhood of the boundary pixel are taken as the neighboring unit domains of the unit domain, and the number of the neighboring unit domains of the unit domain is recorded as a neighborhood number n_nz;
taking pixels with gray values within the range [ gry _ wef, gry _ wem ] in each pixel of a unit domain as the pixels in the unit domain, otherwise, taking the pixels out of the unit domain; taking the ratio of the median of the gray value of each intra-pixel to the median of the gray value of each extra-pixel in the unit domain as the bit rate rt_dp of the unit domain; the number of myoid pixels and lipid pixels in a unit domain is referred to as myoid amount n_zm and lipid amount n_zf, respectively; calculate the cotton lipid SFD of single-armature domain:
；
where i1 is an accumulated variable, n_zm i1 And n_zf i1 Representing the myoid and lipid amounts of the i1 st neighbor of the single-armature domain, respectively, ln () is a logarithmic function with the natural constant e as a base.
The beneficial effects are that: because the cotton lipid is calculated according to the quantity attribute and gray value attribute of the similar muscle pixels and the lipoid pixels obtained by classification, the equilibrium and the thick degree of the distribution of the fat nearby the unit domain can be accurately marked, and thus, the data support and the foundation can be made for improving the next more accurate calculation of the fat tissue coefficient.
Further, in step S500, the method for obtaining the lipid texture coefficient by combining the treatment chart and the cotton lipid degree calculation is as follows: the center point of the unit domain is used as the domain core of the unit domain, the single-armature path of each domain core is calculated, and the method for calculating the single-armature path is as follows: the method comprises the steps of taking a domain core with a single-armature short diameter to be calculated as a current domain core, searching a domain core which is closest to the current domain core and belongs to the single-armature domain as a single-armature short diameter core, and recording the distance between the single-armature short diameter core and the current domain core as a single-armature short diameter szsp of the current domain core; the average value of the single-phase minor diameters of the cores of each domain is recorded as a minor diameter average value Eszsp, and the sub-cotton lipid degree SSFD is calculated for each unit domain respectively:
；
wherein grb (szsp) is a backtracking function, and the cotton lipid SFD corresponding to a single-match domain for determining a single-match short path is obtained through the backtracking function; n_sz is the number of domain kernels of a single match domain which appear in a circular range with the domain kernels as the circle center and the radius of Eszsp; and (3) carrying out corner detection on the processing diagram, taking a unit domain with at least one corner in the unit domain as a key domain, and taking an arithmetic average value of sub-cotton lipid corresponding to each key domain as a cotton lipid SFD.
In the process of calculating the cotton-fat degree SFD, there is a phenomenon that the result of the corner operation is too dependent, which is easy to cause the problem of decreasing the accuracy of the cotton-fat degree when the distribution of the corner points of the image is uneven, however, the prior art cannot effectively optimize or solve the problem of decreasing the accuracy of the cotton-fat degree under the special condition, in order to further improve the accuracy of the cotton-fat degree and calculate and solve the problem, and eliminate the phenomenon that the result of the corner operation is too dependent, so the application proposes a more preferable scheme as follows:
preferably, in step S500, the method for obtaining the lipid texture coefficient by combining the treatment map and the cotton lipid degree calculation is: the number of the single-match domains is recorded as n_ grz, each single-match domain is arranged from large to small according to the corresponding cotton fat SFD to form a domain descending sequence, each single-match domain is subjected to domain-attaching rejection according to the domain descending sequence, and the domain-attaching rejection method comprises the following steps: traversing from the first element of the domain descending sequence, sequentially taking each element as a current single-match domain, taking other single-match domains in each adjacent unit domain of the current single-match domain as auxiliary domains of the current single-match domain, deleting the corresponding elements of each auxiliary domain in the domain descending sequence and forming a new domain descending sequence, ending traversing until the last element in the domain descending sequence is traversed, and taking each element in the finally obtained domain descending sequence as the first single-match domain;
taking the center point of the unit domain as the domain core of the unit domain, wherein the horizontal coordinate and the vertical coordinate of the center point of the unit domain are respectively the average value of the horizontal coordinate and the average value of the vertical coordinate of each pixel in the unit domain, marking the domain core of the first single-match domain as the match domain core, taking the distance between one match domain core and the other match domain core closest to the match domain core as the domain short diameter of the match domain core, respectively obtaining the corresponding domain short diameter zsp by each domain core, and taking the arithmetic average value of the domain short diameters of each match domain core as the field average domain short diameter ezsd;
the distance between one armature domain core and another other armature domain core is referred to as an inter-core diameter len1, and then the inter-core diameter adjustment value len2 of the armature domain core and the other armature domain core is len2=len1-ezsd; the inter-core diameter adjustment values of the armature domain core and each other armature domain core are arranged from small to large, the first inter-core diameter adjustment value conforming to len2 & gt 0 is obtained through sequential screening, and the corresponding inter-core diameter is taken as a domain length diameter zlp of the armature domain core; calculating a fat-weaving coefficient FRCI:
；
where i2 is an accumulated variable, n_zc represents the total number of armature domain cores, zlp i2 And zsp i2 The field major axis and the field minor axis of the i2 nd armature core are respectively represented, SFD i2 Cotton-like fat representing the single armature domain corresponding to the i2 nd armature domain coreDegree.
The beneficial effects are that: through the cotton degree of each point location, the tenderness and the fat distribution of the fish meat in the treatment diagram are effectively combined, and the sparsity of the fat distribution of each position in the image is quantified, so that the convenience for monitoring the fish meat quality can be greatly improved, and reliable and efficient quality identification data can be provided for observers.
Further, in step S600, the method for quality identification of tenderness of fish according to the lipid-tissue coefficient is as follows: obtaining 3-5 reference slices from a fish body, respectively calculating and obtaining the lipid texture coefficients corresponding to each reference slice, and taking the minimum value in each lipid texture coefficient as the real value of the lipid texture coefficient of the fish body; and calculating actual values of the fat-texture coefficients of a plurality of fish bodies, comparing the actual values of the fat-texture coefficients of the fish bodies, taking the fish body corresponding to the actual value of the fat-texture coefficient with the maximum value as a high-quality fish body, sending the serial number corresponding to the high-quality fish body and the actual value of the fat-texture coefficient to a client, and sending the serial number corresponding to the high-quality fish body and the fat-texture coefficients obtained by the high-quality fish body to a server for storage.
Preferably, all undefined variables in the present application, if not explicitly defined, may be thresholds set manually.
The application also provides a fish tenderness quality identification system, which comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the method for identifying tenderness and smoothness of fish when executing the computer program, the system for identifying tenderness and smoothness of fish can be operated in a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud data center, and the like, and the executable system can include, but is not limited to, a processor, a memory, and a server cluster, and the processor executes the computer program to operate in the units of the following systems:
the sampling slice unit is used for carrying out slice processing on the fish body to obtain a reference slice;
the microscopic shooting unit is used for shooting an image of a reference slice through an electron microscope to obtain a slice diagram;
the image preprocessing unit is used for preprocessing the slice images to form processing images;
a cotton lipid measuring and calculating unit for calculating the cotton lipid according to the processing chart;
the fat texture measuring and calculating unit is used for combining the treatment graph and the cotton fat degree to calculate and obtain a fat texture coefficient;
and the quality identification unit is used for carrying out quality identification on the tenderness and the smoothness of the fish meat according to the fat-weaving coefficient.
The beneficial effects of the application are as follows: the application provides a fish tenderness quality identification method and a fish tenderness quality identification system, which accurately marks and quantifies the balance and heaviness of fat distribution through the quantity attribute and gray value attribute of myoid pixels and lipoid pixels, quantifies the sparse characteristic of the fat distribution at each position in an image, greatly improves the convenience provided for fish quality monitoring and provides reliable and efficient quality identification data for observers.
Drawings
The above and other features of the present application will become more apparent from the detailed description of the embodiments thereof given in conjunction with the accompanying drawings, in which like reference characters designate like or similar elements, and it is apparent that the drawings in the following description are merely some examples of the present application, and other drawings may be obtained from these drawings without inventive effort to those of ordinary skill in the art, in which:
FIG. 1 is a flow chart of a method for identifying tenderness and smoothness of fish meat;
FIG. 2 is a diagram showing a structure of a fish tenderness and smoothness quality identification system.
Detailed Description
The conception, specific structure, and technical effects produced by the present application will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present application. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.
Referring to fig. 1, which is a flowchart illustrating a method for identifying tenderness and smoothness of fish, a method for identifying tenderness and smoothness of fish according to an embodiment of the present application will be described with reference to fig. 1, and comprises the following steps:
s100, slicing the fish body to obtain a reference slice;
s200, performing image shooting on a reference slice through an electron microscope to obtain a slice diagram;
s300, preprocessing the slice diagram to form a processing diagram;
s400, calculating the cotton lipid degree according to the treatment diagram;
s500, combining the treatment graph and the cotton lipid degree calculation to obtain a lipid weaving coefficient;
s600, quality identification is carried out on the tenderness and the smoothness of the fish meat according to the fat-weaving coefficient.
Further, in step S100, the method for obtaining the reference slice by slicing the fish body is as follows: slicing the fish body by a sampling device, wherein the slicing treatment position is the infraxis muscle below the central point of the trunk of the fish body, the slicing thickness requirement of the slicing treatment is 5-15 mu m, and the sampling device is a fixing device for sampling the live fish muscle, wherein the publication number of the fixing device is CN 205785876U; the slice was washed with physiological saline to remove water on the surface of the slice, and used as a reference slice.
Further, in step S300, the method for preprocessing the slice map to form a processing map is as follows: and carrying out contrast stretching on the slice image, denoising the slice image through a median filter, and finally carrying out graying treatment on the slice image to obtain a treatment image.
Further, in step S400, the method for calculating the cotton lipid according to the processing chart is as follows: performing super-pixel segmentation on the processing diagram, and taking each region obtained by segmentation as a unit domain respectively; classifying each pixel in the treatment graph through the ICM condition iteration model, and classifying each pixel in the treatment graph into a myoid pixel or a lipoid pixel; the number of myoid pixels and lipid pixels in a unit domain is referred to as myoid amount n_zm and lipid amount n_zf, respectively; the arithmetic average value of the gray value of each muscle-like pixel in the treatment chart is named as full-muscle gray gry _ wem, and the arithmetic average value of the gray value of each lipid pixel in the treatment chart is named as full-fat gray gry _ wef; the arithmetic average of the gray values of the individual pixels in a cell field is denoted gry _z, and if a cell field satisfies gry _z e [ gry _ wef, gry _ wem ], the cell field is defined as a single-bit field; calculate the cotton lipid SFD of single-armature domain:
；
where ln () is a logarithmic function whose base is a natural constant e, and rt_zp is a ratio of the median among the gradation values of the respective pixels in the single-phase domain to the maximum value among them.
Preferably, in step S400, the method for calculating the cotton lipid according to the processing chart is: performing super-pixel segmentation on the processing diagram, and marking each region obtained by segmentation as a unit domain; classifying each pixel in the treatment graph through an ICM condition iteration model, and classifying each pixel in the treatment graph into a myoid pixel and a lipoid pixel; the arithmetic average value of the gray value of each myoid pixel in the processing chart is recorded as the full-muscle gray gry-wem; the arithmetic average of the gray values of each lipid pixel in the treatment map is designated as full-fat gray gry _ wef;
wherein the full-muscle gray scale is larger than the full-fat gray scale, and muscle tissue contains more protein, blood and other tissue components, so that more light can be absorbed, and a higher gray scale value is obtained.
The arithmetic average of the gray values of the individual pixels in a cell field is denoted gry _z, and if a cell field satisfies gry _z e [ gry _ wef, gry _ wem ], the cell field is defined as a single-bit field; in each pixel of one unit domain, if the eight neighborhood of the pixel contains the pixel which does not belong to the unit domain, the pixel is the boundary pixel of the unit domain, the other unit domains which correspond to the pixel which does not belong to the unit domain in the eight neighborhood of the boundary pixel are taken as the neighboring unit domains of the unit domain, and the number of the neighboring unit domains of the unit domain is recorded as a neighborhood number n_nz;
taking pixels with gray values within the range [ gry _ wef, gry _ wem ] in each pixel of a unit domain as the pixels in the unit domain, otherwise, taking the pixels out of the unit domain; taking the ratio of the median of the gray value of each intra-pixel to the median of the gray value of each extra-pixel in the unit domain as the bit rate rt_dp of the unit domain; the number of myoid pixels and lipid pixels in a unit domain is referred to as myoid amount n_zm and lipid amount n_zf, respectively; calculate the cotton lipid SFD of single-armature domain:
；
where i1 is an accumulated variable, n_zm i1 And n_zf i1 Representing the myoid and lipid amounts of the i1 st neighbor of the single-armature domain, respectively, ln () is a logarithmic function with the natural constant e as a base.
Further, in step S500, the method for obtaining the lipid texture coefficient by combining the treatment chart and the cotton lipid degree calculation is as follows: the center point of the unit domain is used as the domain core of the unit domain, the single-armature path of each domain core is calculated, and the method for calculating the single-armature path is as follows: the method comprises the steps of taking a domain core with a single-armature short diameter to be calculated as a current domain core, searching a domain core which is closest to the current domain core and belongs to the single-armature domain as a single-armature short diameter core, and recording the distance between the single-armature short diameter core and the current domain core as a single-armature short diameter szsp of the current domain core; the average value of the single-phase minor diameters of the cores of each domain is recorded as a minor diameter average value Eszsp, and the sub-cotton lipid degree SSFD is calculated for each unit domain respectively:
；
wherein grb (szsp) is a backtracking function, and the cotton lipid SFD corresponding to a single-match domain for determining a single-match short path is obtained through the backtracking function; n_sz is the number of domain kernels of a single match domain which appear in a circular range with the domain kernels as the circle center and the radius of Eszsp; and (3) carrying out corner detection on the processing diagram, taking a unit domain with at least one corner in the unit domain as a key domain, and taking an arithmetic average value of sub-cotton lipid corresponding to each key domain as a cotton lipid SFD.
Preferably, in step S500, the method for obtaining the lipid texture coefficient by combining the treatment map and the cotton lipid degree calculation is:
the number of the single-match domains is recorded as n_ grz, each single-match domain is arranged from large to small according to the corresponding cotton fat SFD to form a domain descending sequence, each single-match domain is subjected to domain-attaching rejection according to the domain descending sequence, and the domain-attaching rejection method comprises the following steps: traversing from the first element of the domain descending sequence, sequentially taking each element as a current single-match domain, taking other single-match domains in each adjacent unit domain of the current single-match domain as auxiliary domains of the current single-match domain, deleting the corresponding elements of each auxiliary domain in the domain descending sequence and forming a new domain descending sequence, ending traversing until the last element in the domain descending sequence is traversed, and taking each element in the finally obtained domain descending sequence as the first single-match domain;
taking the center point of the unit domain as the domain core of the unit domain, wherein the horizontal coordinate and the vertical coordinate of the center point of the unit domain are respectively the average value of the horizontal coordinate and the average value of the vertical coordinate of each pixel in the unit domain, marking the domain core of the first single-match domain as the match domain core, taking the distance between one match domain core and the other match domain core closest to the match domain core as the domain short diameter of the match domain core, respectively obtaining the corresponding domain short diameter zsp by each domain core, and taking the arithmetic average value of the domain short diameters of each match domain core as the field average domain short diameter ezsd;
the distance between one armature domain core and another other armature domain core is referred to as an inter-core diameter len1, and then the inter-core diameter adjustment value len2 of the armature domain core and the other armature domain core is len2=len1-ezsd; the inter-core diameter adjustment values of the armature domain core and each other armature domain core are arranged from small to large, the first inter-core diameter adjustment value conforming to len2 & gt 0 is obtained through sequential screening, and the corresponding inter-core diameter is taken as a domain length diameter zlp of the armature domain core; calculating a fat-weaving coefficient FRCI:
；
where i2 is an accumulated variable, n_zc represents the total number of armature domain cores, zlp i2 And zsp i2 Domains respectively representing the i2 nd armature domain coreLong diameter and domain short diameter, SFD i2 Representing the cotton-like character of the i2 nd fragment core corresponding to the single fragment.
Further, in step S600, the method for quality identification of tenderness of fish according to the lipid-tissue coefficient is as follows: obtaining 5 reference slices from a fish body, respectively calculating and obtaining the lipid texture coefficients corresponding to each reference slice, and taking the minimum value in each lipid texture coefficient as the real value of the lipid texture coefficient of the fish body; and calculating actual values of the fat-texture coefficients of a plurality of fish bodies, comparing the actual values of the fat-texture coefficients of the fish bodies, taking the fish body corresponding to the actual value of the fat-texture coefficient with the maximum value as a high-quality fish body, sending the serial number corresponding to the high-quality fish body and the actual value of the fat-texture coefficient to a client, and sending the serial number corresponding to the high-quality fish body and the fat-texture coefficients obtained by the high-quality fish body to a server for storage.
Fig. 2 shows a block diagram of a tenderness quality identification system for fish according to an embodiment of the present application, where the tenderness quality identification system for fish according to the embodiment of the present application includes: a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of one embodiment of the fish tenderness qualification system described above when the computer program is executed.
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 sampling slice unit is used for carrying out slice processing on the fish body to obtain a reference slice;
the microscopic shooting unit is used for shooting an image of a reference slice through an electron microscope to obtain a slice diagram;
the image preprocessing unit is used for preprocessing the slice images to form processing images;
a cotton lipid measuring and calculating unit for calculating the cotton lipid according to the processing chart;
the fat texture measuring and calculating unit is used for combining the treatment graph and the cotton fat degree to calculate and obtain a fat texture coefficient;
and the quality identification unit is used for carrying out quality identification on the tenderness and the smoothness of the fish meat according to the fat-weaving coefficient.
The fish tenderness and smoothness quality identification system can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The fish tenderness qualification system may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the examples are merely examples of one type of fish tenderness qualification system and are not limiting of one type of fish tenderness qualification system, and may include more or fewer components than examples, or may combine certain components, or different components, e.g., the one type of fish tenderness qualification system 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 gate or transistor logic devices, discrete hardware components, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, and the processor is a control center of the running system of the fish tenderness quality identification system, and various interfaces and lines are used for connecting various parts of the running system of the whole fish tenderness quality identification system.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the fish tenderness qualification system by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, 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 identifying tenderness and smoothness quality of fish meat, which is characterized by comprising the following steps:
s100, slicing the fish body to obtain a reference slice;
s200, performing image shooting on a reference slice through an electron microscope to obtain a slice diagram;
s300, preprocessing the slice diagram to form a processing diagram;
s400, calculating the cotton lipid degree according to the treatment diagram;
s500, combining the treatment graph and the cotton lipid degree calculation to obtain a lipid weaving coefficient;
s600, carrying out quality identification on tenderness of fish according to the fat-weaving coefficient;
in step S400, the method for calculating the cotton lipid according to the processing chart is as follows: performing super-pixel segmentation on the processing diagram, and taking each region obtained by segmentation as a unit domain respectively; classifying each pixel in the treatment graph through the ICM condition iteration model, and classifying each pixel in the treatment graph into a myoid pixel or a lipoid pixel; the number of myoid pixels and lipid pixels in a unit domain is referred to as myoid amount n_zm and lipid amount n_zf, respectively; the arithmetic average value of the gray value of each muscle-like pixel in the treatment chart is named as full-muscle gray gry _ wem, and the arithmetic average value of the gray value of each lipid pixel in the treatment chart is named as full-fat gray gry _ wef; the arithmetic average of the gray values of the individual pixels in a cell field is denoted gry _z, and if a cell field satisfies gry _z e [ gry _ wef, gry _ wem ], the cell field is defined as a single-bit field; calculate the cotton lipid SFD of single-armature domain:
；
where ln () is a logarithmic function with a natural constant e as a base, and rt_zp is a ratio of a median among gray values of the respective pixels in the single-phase domain to a maximum among them;
in step S500, the method for obtaining the lipid fraction by combining the treatment chart and the cotton lipid degree calculation is as follows: the center point of the unit domain is used as the domain core of the unit domain, the single-armature path of each domain core is calculated, and the method for calculating the single-armature path is as follows: the method comprises the steps of taking a domain core with a single-armature short diameter to be calculated as a current domain core, searching a domain core which is closest to the current domain core and belongs to the single-armature domain as a single-armature short diameter core, and recording the distance between the single-armature short diameter core and the current domain core as a single-armature short diameter szsp of the current domain core; the average value of the single-phase minor diameters of the cores of each domain is recorded as a minor diameter average value Eszsp, and the sub-cotton lipid degree SSFD is calculated for each unit domain respectively:
；
wherein grb (szsp) is a backtracking function, and the cotton lipid SFD corresponding to a single-match domain for determining a single-match short path is obtained through the backtracking function; n_sz is the number of domain kernels of a single match domain which appear in a circular range with the domain kernels as the circle center and the radius of Eszsp; performing corner detection on the processing diagram, taking a unit domain with at least one corner in the unit domain as a key domain, and taking an arithmetic average value of sub-cotton lipid corresponding to each key domain as a cotton lipid SFD;
taking the center point of the unit domain as the domain core of the unit domain, wherein the horizontal coordinate and the vertical coordinate of the center point of the unit domain are respectively the average value of the horizontal coordinate and the average value of the vertical coordinate of each pixel in the unit domain, marking the domain core of the first single-match domain as the match domain core, taking the distance between one match domain core and the other match domain core closest to the match domain core as the domain short diameter of the match domain core, respectively obtaining the corresponding domain short diameter zsp by each domain core, and taking the arithmetic average value of the domain short diameters of each match domain core as the field average domain short diameter ezsd;
the distance between one armature domain core and another other armature domain core is referred to as an inter-core diameter len1, and then the inter-core diameter adjustment value len2 of the armature domain core and the other armature domain core is len2=len1-ezsd; the inter-core diameter adjustment values of the armature domain core and each other armature domain core are arranged from small to large, the first inter-core diameter adjustment value conforming to len2 & gt 0 is obtained through sequential screening, and the corresponding inter-core diameter is taken as a domain length diameter zlp of the armature domain core; calculating a fat-weaving coefficient FRCI:
；
where i2 is an accumulated variable, n_zc represents the total number of armature domain cores, zlp i2 And zsp i2 The field major axis and the field minor axis of the i2 nd armature core are respectively represented, SFD i2 The number of single-stranded strands was noted n_ grz, representing the degree of cotton-like character of the i 2-th strand core corresponding to the single strand.
2. The method for identifying tenderness and smoothness of fish according to claim 1, wherein in step S100, the method for slicing fish body to obtain reference slices comprises: slicing the fish body by a sampling device, wherein the slicing position is the axillary muscle below the central point of the trunk of the fish body, the slicing thickness requirement of the slicing treatment is 5-15 mu m, and the slicing is cleaned by normal saline to remove the water on the surface of the slicing to be used as a reference slice.
3. The method for identifying tenderness and smoothness of fish according to claim 1, wherein in step S300, the method for preprocessing the slice map to form a processed map comprises: and carrying out contrast stretching on the slice image, denoising the slice image through a median filter, and finally carrying out graying treatment on the slice image to obtain a treatment image.
4. The method for quality identification of tenderness of fish according to claim 1, wherein in step S600, the method for quality identification of tenderness of fish according to the lipid-tissue coefficient is as follows: obtaining 3-5 reference slices from a fish body, respectively calculating and obtaining the lipid texture coefficients corresponding to each reference slice, and taking the minimum value in each lipid texture coefficient as the real value of the lipid texture coefficient of the fish body; and calculating actual values of the fat-texture coefficients of a plurality of fish bodies, comparing the actual values of the fat-texture coefficients of the fish bodies, taking the fish body corresponding to the actual value of the fat-texture coefficient with the maximum value as a high-quality fish body, sending the serial number corresponding to the high-quality fish body and the actual value of the fat-texture coefficient to a client, and sending the serial number corresponding to the high-quality fish body and the fat-texture coefficients obtained by the high-quality fish body to a server for storage.
5. A fish tenderness quality identification system, characterized in that it comprises: a processor, a memory and a computer program stored in the memory and executable on the processor, the processor implementing the steps in a fish tenderness quality assessment method according to any one of claims 1-4 when the computer program is executed, the fish tenderness quality assessment system being run in a computing device of a desktop computer, a notebook computer, a palm computer and a cloud data center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310776590.6A CN116519892B (en) | 2023-06-29 | 2023-06-29 | Fish tenderness quality identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310776590.6A CN116519892B (en) | 2023-06-29 | 2023-06-29 | Fish tenderness quality identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116519892A CN116519892A (en) | 2023-08-01 |
| CN116519892B true CN116519892B (en) | 2023-08-25 |
Family
ID=87396216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310776590.6A Active CN116519892B (en) | 2023-06-29 | 2023-06-29 | Fish tenderness quality identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116519892B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117409245B (en) * | 2023-10-23 | 2024-04-02 | 广东省农业科学院动物科学研究所 | Automatic identification method for crisp fish |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4413279A (en) * | 1980-12-17 | 1983-11-01 | Pfister Gmbh | Method for contact-free determination of quality features of a test subject of the meat goods class |
| CN101474082A (en) * | 2009-01-16 | 2009-07-08 | 北京工业大学 | Elastic analysis method of vascular wall based on finite element deformation theory |
| EP2018553B1 (en) * | 2006-04-26 | 2014-04-09 | Meat Vision Limited | Evaluation of meat tenderness |
| CN105701805A (en) * | 2016-01-07 | 2016-06-22 | 中国农业大学 | Pork intramuscular fat content nondestructive testing method based on computer vision |
| 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 |
| CN116087195A (en) * | 2023-03-06 | 2023-05-09 | 华南师范大学 | Fish freshness evaluation method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8260005B2 (en) * | 2007-03-30 | 2012-09-04 | Universidad De Santiago De Chile | Portable tool for determining meat quality |
| WO2009005828A1 (en) * | 2007-07-03 | 2009-01-08 | Tenera Technology, Llc | Imaging method for determining meat tenderness |
| US20110128373A1 (en) * | 2009-11-28 | 2011-06-02 | Tenera Technology, Llc | Determining Meat Tenderness |
| WO2015167585A1 (en) * | 2014-05-02 | 2015-11-05 | Empire Technology Development Llc | Meat assessment device |
-
2023
- 2023-06-29 CN CN202310776590.6A patent/CN116519892B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4413279A (en) * | 1980-12-17 | 1983-11-01 | Pfister Gmbh | Method for contact-free determination of quality features of a test subject of the meat goods class |
| EP2018553B1 (en) * | 2006-04-26 | 2014-04-09 | Meat Vision Limited | Evaluation of meat tenderness |
| CN101474082A (en) * | 2009-01-16 | 2009-07-08 | 北京工业大学 | Elastic analysis method of vascular wall based on finite element deformation theory |
| CN105701805A (en) * | 2016-01-07 | 2016-06-22 | 中国农业大学 | Pork intramuscular fat content nondestructive testing method based on computer vision |
| 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 |
| CN116087195A (en) * | 2023-03-06 | 2023-05-09 | 华南师范大学 | Fish freshness evaluation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于高光谱图像纹理特征的牛肉嫩度分布评价;赵娟;彭彦昆;;农业工程学报(第07期);279-286 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116519892A (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109360206B (en) | Method for dividing rice ears in field based on deep learning | |
| CN111161275B (en) | Method and device for segmenting target object in medical image and electronic equipment | |
| US20220092789A1 (en) | Automatic pancreas ct segmentation method based on a saliency-aware densely connected dilated convolutional neural network | |
| CN113466232B (en) | Brittle fish meat rapid detection method and system based on computer image | |
| CN108288271A (en) | Image detecting system and method based on three-dimensional residual error network | |
| CN116519892B (en) | Fish tenderness quality identification method and system | |
| CN116067964B (en) | Method and system for promoting fish muscle embrittlement by utilizing condensed tannin | |
| CN111862044A (en) | Ultrasonic image processing method and device, computer equipment and storage medium | |
| CN110321943B (en) | CT image classification method, system and device based on semi-supervised deep learning | |
| CN110009656B (en) | Target object determination method and device, storage medium and electronic device | |
| Russ | Image analysis of foods | |
| US20210089825A1 (en) | Systems and methods for cleaning data | |
| Barbosa et al. | Towards automatic quantification of the epicardial fat in non-contrasted CT images | |
| Viji et al. | Modified texture based region growing segmentation of MR brain images | |
| CN110570394A (en) | medical image segmentation method, device, equipment and storage medium | |
| Logeswari et al. | Hybrid self organizing map for improved implementation of brain MRI segmentation | |
| CN110874835B (en) | Crop leaf disease resistance identification method and system, electronic equipment and storage medium | |
| CN113256670A (en) | Image processing method and device, and network model training method and device | |
| CN116596879A (en) | Grape downy mildew self-adaptive identification method based on quantiles of boundary samples | |
| CN115797246A (en) | Pathological image quality evaluation and adjustment method and system, electronic device and medium | |
| CN116228753B (en) | Tumor prognosis evaluation method, device, computer equipment and storage medium | |
| CN116433643A (en) | Fish meat quality identification method and device based on computer vision | |
| CN110991408A (en) | Method and device for segmenting white matter high signal based on deep learning method | |
| CN116721113A (en) | Three-dimensional point cloud plane segmentation method and system | |
| CN115294401A (en) | CT image-based classification method, device, equipment and storage medium |
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 |