CN117218455B - Nondestructive rapid identification method for crisp fish - Google Patents
Nondestructive rapid identification method for crisp fish Download PDFInfo
- Publication number
- CN117218455B CN117218455B CN202311464386.7A CN202311464386A CN117218455B CN 117218455 B CN117218455 B CN 117218455B CN 202311464386 A CN202311464386 A CN 202311464386A CN 117218455 B CN117218455 B CN 117218455B
- Authority
- CN
- China
- Prior art keywords
- fish
- embrittlement
- blood vessel
- edge
- inner diameter
- 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 151
- 238000000034 method Methods 0.000 title claims abstract description 56
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 95
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 230000002792 vascular Effects 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 230000017531 blood circulation Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 10
- 241000276707 Tilapia Species 0.000 claims description 8
- 238000003708 edge detection Methods 0.000 claims description 6
- 241000252230 Ctenopharyngodon idella Species 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 235000002566 Capsicum Nutrition 0.000 claims description 3
- 239000006002 Pepper Substances 0.000 claims description 3
- 235000016761 Piper aduncum Nutrition 0.000 claims description 3
- 235000017804 Piper guineense Nutrition 0.000 claims description 3
- 235000008184 Piper nigrum Nutrition 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 150000003839 salts Chemical class 0.000 claims description 3
- 238000002604 ultrasonography Methods 0.000 claims description 3
- 244000203593 Piper nigrum Species 0.000 claims 1
- 206010018910 Haemolysis Diseases 0.000 abstract description 5
- 230000008588 hemolysis Effects 0.000 abstract description 5
- 230000008569 process Effects 0.000 abstract description 5
- 235000013372 meat Nutrition 0.000 description 18
- 230000006870 function Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 210000003205 muscle Anatomy 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000000052 comparative effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 241000722363 Piper Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 206010061218 Inflammation Diseases 0.000 description 1
- 208000025865 Ulcer Diseases 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012669 compression test Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009778 extrusion testing Methods 0.000 description 1
- 238000007542 hardness measurement Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000009864 tensile test Methods 0.000 description 1
- 230000036269 ulceration Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- 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
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention belongs to the field of crisp fish detection, and provides a nondestructive rapid identification method for crisp fish, which is characterized in that a blood vessel region is positioned in an ultrasonic image of the fish; identifying whether the vascular region is an embrittlement-feature-edge or a non-embrittlement-feature-edge; taking the maximum inner diameter of the blood vessel region on the embrittlement characteristic side as a first inner diameter and taking the maximum inner diameter of the blood vessel region on the non-embrittlement characteristic side as a second inner diameter; if all the first inner diameter average values are smaller than all the second inner diameter average values, marking the fish as embrittled fish; otherwise, the marked fish is a common fish, the phenomenon that the edge of the blood vessel wall is uneven due to the embrittlement characteristic shown by hemolysis in the embrittlement process in the blood vessel area can be accurately shown, the line segments screened according to the phenomenon can be accurately used for identifying the embrittlement characteristic, and the embrittlement characteristic edge and the non-embrittlement characteristic edge of the embrittled fish with high embrittlement degree can be more accurately distinguished by the embrittlement viscosity even for the fish with high embrittlement degree.
Description
Technical Field
The invention belongs to the field of detection of crisp fish, and particularly relates to a nondestructive rapid identification method of crisp fish.
Background
For detecting an embrittled fish, the following methods are generally used for detecting an embrittled fish: 1. puncture test: this is a simple method of observing the texture and resistance of fish meat by gently inserting it into the fish meat using a metal probe or knife. 2. Hardness testing: the hardness of fish meat is measured under standard pressure using an instrument such as a durometer or texture analyzer. 3. Elasticity test: the fish meat was subjected to a tensile or compressive test using a tensile or compressive test instrument to evaluate its elasticity and deformability. 4. Appearance inspection: the appearance characteristics of the fish meat such as color, texture, shape and the like are checked through manual observation and comparison. 5. Eating sensory evaluation: the eating sense evaluation of fish meat, including the evaluation of mouthfeel, taste, tenderness, crispness, and the like, is performed by a professional taster or consumer.
However, most of the existing detection of the fragile fish is a destructive detection, and the detection precision is high, for example, the disclosure number is: the Chinese patent of CN113466232A discloses a method and a system for rapidly detecting the embrittled fish based on computer images, which can rapidly screen out the comparison area of tissue slices by acquiring microscopic images of the slices of the fish muscle tissue and marking the types of the fish muscle tissue, intelligently compare the tissue slices with the samples of the fragile fish to identify the embrittled fish, and greatly accelerate the speed of processing the images by a computer, thereby improving the identification efficiency and having high accuracy of identifying the embrittled fish. However, such methods require slicing the fish, cause irreversible damage to the fish, and do not have a high recognition rate of embrittlement unevenness and low embrittlement rate from the slice image.
Disclosure of Invention
The invention aims to provide a nondestructive rapid identification method for crisp fish, 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 invention, there is provided a nondestructive rapid identification method of a brittle fish, the method comprising the steps of:
acquiring an ultrasonic image of the fish, and positioning a blood vessel region in the ultrasonic image;
identifying whether the vascular region is an embrittlement-feature-edge or a non-embrittlement-feature-edge;
taking the maximum inner diameter of the blood vessel region on the embrittlement characteristic side as a first inner diameter and taking the maximum inner diameter of the blood vessel region on the non-embrittlement characteristic side as a second inner diameter;
if all the first inner diameter average values are smaller than all the second inner diameter average values, marking the fish as embrittled fish; otherwise, the marked fish is ordinary fish.
Further, the method for acquiring the ultrasonic image of the fish comprises the steps of scanning the tilapia or the grass carp through Doppler ultrasonic detection to acquire the ultrasonic image, and scanning the tilapia or the grass carp through a B ultrasonic machine for livestock to acquire the ultrasonic image.
Preferably, the fish is tilapia or grass carp embrittled by DB 4420/T13-2022 tilapia embrittlement culture specification.
Further, the method for locating the blood vessel region in the ultrasonic image comprises the following steps:
graying the ultrasonic image, and filtering salt and pepper noise in the ultrasonic image through a Gaussian filter algorithm;
the linear structure in the ultrasonic image is enhanced through the Hessian matrix, and punctiform structures and noise points are filtered; edge detection is carried out through an edge detection operator to obtain edge lines, and a closed interval is formed by the edge lines; carrying out Gaussian blur on each closed interval to obtain a closed-packet interval;
taking the geometric gravity center point of each closure interval as an anchor point, and performing expansion operation on each closure interval by taking each anchor point as a center to obtain a first vessel region; marking a first blood vessel region which is not a closed region in each first blood vessel region as a second blood vessel region;
the corresponding position of each second vessel region on the ultrasound image is taken as the located vessel region.
Since the blood-dissolving degrees caused in the embrittlement process are different between the embrittled fish and the semi-embrittled fish, the blood flow speed in the blood vessel is different, and the edge of the blood vessel region of the fish with higher embrittlement degree and the edge of the fish which is not embrittled yet can appear more obvious embrittlement characteristic edges of blood vessel ulceration and inflammation caused by the embrittlement process, the invention provides the following technical scheme for identifying the edges:
further, the method for identifying whether the blood vessel region is an embrittlement-feature-edge or a non-embrittlement-feature-edge is as follows:
detecting Hough line segments of the blood vessel region, forming a line segment set LS by the detected line segments, and marking the line segments in the line segment set LS as LS i ，LS i For the ith line segment in LS, i e [1, N]N is marked as the total element amount in LS;
within the value range of i, the midpoint of the line segment in LS and the line segment LS are connected i Is less than Max (LS) x LSXRatio and is spaced from the line segment LS i All line segments without intersection points are screened out to form a subset LR1; the complement of the subset LR1 in the line segment set LS is recorded as LR2;
wherein LSXRatio is line segment LS i The distance from the midpoint of the line segment to the midpoint of the line segment with the shortest length value in LS is equal to the line segment LS i The ratio of the midpoint distance between the line segment with the longest length value in LS and the Max (LS) is the length of the line segment with the largest length value in the line segment set LS;
if the number of segments in the subset LR1 is greater than the number of segments in LR2, the vessel region is noted as an embrittlement-feature-edge, otherwise the vessel region is noted as a non-embrittlement-feature-edge.
The LSXRatio shows the ratio of the fold line segment of the vessel wall of the vessel region to the longest side and the shortest side of the vessel region, and the product of the value and the longest side can accurately show the phenomenon that the edge of the vessel wall is uneven due to the embrittlement characteristic shown by hemolysis in the embrittlement process in the vessel region, and the line segment screened according to the phenomenon can accurately be used for identifying the embrittlement characteristic.
On the blood vessel wall of the fish with higher embrittlement degree, the embrittlement characteristic edge width is different and even discontinuous due to the small hemolysis amount in the later embrittlement stage, and the embrittlement characteristic edge and the non-embrittlement characteristic edge of the blood vessel wall are different in the degree of edge adhesion and overlapping, so that the embrittlement characteristic edge and the non-embrittlement characteristic edge of the embrittlement fish with higher embrittlement degree are distinguished more accurately by the following method:
preferably, the method of identifying whether a vascular region is an embrittlement-feature-edge or a non-embrittlement-feature-edge comprises:
the embrittlement viscosity EMB of all the blood vessel regions is calculated respectively, and the calculation method of the EMB is as follows:
let the logarithm of the gray value of the ith pixel point on the edge line of the blood vessel area based on 10 be lg (i), i being the serial number of the ith pixel point on the edge line of the blood vessel area; (the pixel viscosity of the edge of the blood vessel is identified through the slow change amplification of the pixels according to the characteristic that the logarithm can slowly reflect the trend);
in the value range of i, calculating the product of lg (i) and the gray value G (i) of the ith pixel point on the edge line of the vascular region as the embrittlement ratio Glg (i) of the ith pixel point; calculating the arithmetic average value of the embrittlement ratio Glg (i) of pixel points on the edge lines of all the blood vessel areas as EMB;
calculating the arithmetic average value of embrittlement viscosity EMB of edge lines of all blood vessel areas to be EMBMean, marking the blood vessel areas with embrittlement viscosity EMB less than EMBMean as embrittlement characteristic edges, and marking the blood vessel areas with the embrittlement viscosity EMB more than or equal to EMBMean as non-embrittlement characteristic edges.
Further, the method for calculating the maximum inner diameter of the blood vessel region comprises the following steps: and calculating the maximum blood vessel diameter in the blood vessel area point by adopting a maximum inscribed circle algorithm for each blood vessel area to be used as the maximum inner diameter.
Preferably, the method for calculating the maximum inner diameter of the vascular region is as follows:
acquiring the central line of a blood vessel region of an ultrasonic image through a distance transformation algorithm; and calculating the maximum blood vessel diameter point by point on the central line of the blood vessel region by adopting a maximum inscribed circle algorithm to obtain the maximum internal diameter.
Wherein, the distance transformation algorithm is the method in the documents [1], [2], [ 3):
[1] zhang Guodong, han Jiachi skeletal pruning algorithm based on fuzzy distance transformation [ J ]. University of sunk-yang aviation aerospace journal, 2012, 29 (1): 64-69.
[2] GAGVANI N，KENCHAMMANA H D，SILVER D.Volume animation using the skeleton tree[C]. Proceedings of IEEE Volume Visualization， 1998：47-53.
[3] DEY T K， SUN J. Defining and computing curve-skeletons with medial geodesic function[C]. Proceedings of the fourth Eurographics Symposium on Geometry processing， AirelaVille， Switzerland， Eurographics Association，2006：143-152。
Preferably, the method further comprises: marking the fish as an embrittled fish if all the first inner diameter averages are smaller than all the second inner diameter averages; otherwise, the step of marking the fish as normal fish is replaced by:
if all the first inner diameter average values are smaller than all the second inner diameter average values, marking the fish as embrittled fish, wherein the heart blood flow speed of the ultrasonic image is smaller than a preset blood flow speed threshold value; otherwise, the marked fish is ordinary fish.
Note that: the first inner diameter average value is smaller than all the second inner diameter average values, which means that the inner diameter of the fish embrittlement part is more smaller than that of the non-embrittlement part, and the inner diameter of the embrittlement part is reduced, so that the fish is marked as an embrittled fish; with the increase of the embrittlement degree, due to the self-healing phenomenon of the fish after massive hemolysis, the blood flow velocity of the heart is slower than that of the non-embrittled fish or the semi-embrittled fish, and the blood flow velocity threshold is generally set to be the normal blood flow velocity of the non-embrittled fish.
The invention also provides a system for quickly detecting the embrittled fish meat based on the computer image, which 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 blood vessel region acquisition unit is used for acquiring an ultrasonic image of the fish and positioning a blood vessel region in the ultrasonic image;
an embrittlement characteristic recognition unit for recognizing whether the blood vessel region is an embrittlement characteristic edge or a non-embrittlement characteristic edge;
a vessel inner diameter calculation unit configured to set a maximum inner diameter of a vessel region on the embrittlement-feature side as a first inner diameter and a maximum inner diameter of a vessel region on the non-embrittlement-feature side as a second inner diameter;
an embrittlement marking unit for marking the fish as an embrittled fish if all the first inner diameter means are smaller than all the second inner diameter means; otherwise, the marked fish is ordinary fish.
The beneficial effects of the invention are as follows: the invention provides a nondestructive rapid identification method for a crispy fish, which can accurately show the phenomenon that the edge of a blood vessel wall is uneven due to the embrittlement characteristic shown by hemolysis in the embrittlement process in the blood vessel region, the line segment screened according to the phenomenon can be accurately used for identifying the embrittlement characteristic, and the embrittlement characteristic edge and the non-embrittlement characteristic edge of the crispy fish with high embrittlement degree can be distinguished more accurately by the embrittlement viscosity of the fish with high embrittlement degree, so that the nondestructive detection precision of the crispy fish is high.
Drawings
The above and other features of the present invention 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 invention, 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 lossless and rapid identification of crisp fish;
FIG. 2 shows a block diagram of a rapid detection system for the embrittled fish meat based on computer images.
Detailed Description
The conception, specific structure, and technical effects produced by the present invention 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 invention. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
Embodiment one: referring to fig. 1, which is a flowchart illustrating a method for lossless and rapid identification of a crisp fish, a method for lossless and rapid identification of a crisp fish according to an embodiment of the present invention will be described with reference to fig. 1, and the method includes the steps of:
acquiring an ultrasonic image of the fish, and positioning a blood vessel region in the ultrasonic image;
identifying whether the vascular region is an embrittlement-feature-edge or a non-embrittlement-feature-edge;
taking the maximum inner diameter of the blood vessel region on the embrittlement characteristic side as a first inner diameter and taking the maximum inner diameter of the blood vessel region on the non-embrittlement characteristic side as a second inner diameter;
if all the first inner diameter average values are smaller than all the second inner diameter average values, marking the fish as embrittled fish; otherwise, the marked fish is ordinary fish.
Further, the method for acquiring the ultrasonic image of the fish is to scan the tilapia or the grass carp through Doppler ultrasonic detection to acquire the ultrasonic image.
Further, the method for locating the blood vessel region in the ultrasonic image comprises the following steps:
graying the ultrasonic image, and filtering salt and pepper noise in the ultrasonic image through a Gaussian filter algorithm;
the linear structure in the ultrasonic image is enhanced through the Hessian matrix, and punctiform structures and noise points are filtered; edge detection is carried out through an edge detection operator to obtain edge lines, and a closed interval is formed by the edge lines; carrying out Gaussian blur on each closed interval to obtain a closed-packet interval;
taking the geometric gravity center point of each closure interval as an anchor point, and performing expansion operation on each closure interval by taking each anchor point as a center to obtain a first vessel region; marking a first blood vessel region which is not a closed region in each first blood vessel region as a second blood vessel region;
the corresponding position of each second vessel region on the ultrasound image is taken as the located vessel region.
Further, the method for calculating the maximum inner diameter of the blood vessel region comprises the following steps: and calculating the maximum blood vessel diameter in the blood vessel area point by adopting a maximum inscribed circle algorithm for each blood vessel area to be used as the maximum inner diameter.
Further, the method for identifying whether the blood vessel region is an embrittlement-feature-edge or a non-embrittlement-feature-edge is as follows:
detecting Hough line segments of the blood vessel region, forming a line segment set LS by the detected line segments, and marking the line segments in the line segment set LS as LS i ，LS i For the ith line segment in LS, i e [1, N]N is marked as the total element amount in LS;
within the value range of i, the midpoint of the line segment in LS and the line segment LS are connected i Is less than Max (LS) x LSXRatio and is spaced from the line segment LS i All line segments without intersection points are screened out to form a subset LR1; the complement of the subset LR1 in the line segment set LS is recorded as LR2;
wherein LSXRatio is line segment LS i The distance from the midpoint of the line segment to the midpoint of the line segment with the shortest length value in LS is equal to the line segment LS i The ratio of the midpoint distance between the line segment with the longest length value in LS and the Max (LS) is the length of the line segment with the largest length value in the line segment set LS;
if the number of segments in the subset LR1 is greater than the number of segments in LR2, the vessel region is noted as an embrittlement-feature-edge, otherwise the vessel region is noted as a non-embrittlement-feature-edge.
Embodiment two: in a second embodiment, the method of identifying whether the blood vessel region is an embrittlement-feature-edge or a non-embrittlement-feature-edge is replaced with the method of the first embodiment:
the embrittlement viscosity EMB of all the blood vessel regions is calculated respectively, and the calculation method of the EMB is as follows:
let the logarithm of the gray value of the ith pixel point on the edge line of the blood vessel area based on 10 be lg (i), i being the serial number of the ith pixel point on the edge line of the blood vessel area;
in the value range of i, calculating the product of lg (i) and the gray value G (i) of the ith pixel point on the edge line of the vascular region as the embrittlement ratio Glg (i) of the ith pixel point; calculating the arithmetic average value of the embrittlement ratio Glg (i) of pixel points on the edge lines of all the blood vessel areas as EMB;
calculating the arithmetic average value of embrittlement viscosity EMB of edge lines of all blood vessel areas to be EMBMean, marking the blood vessel areas with embrittlement viscosity EMB less than EMBMean as embrittlement characteristic edges, and marking the blood vessel areas with the embrittlement viscosity EMB more than or equal to EMBMean as non-embrittlement characteristic edges.
Further, the method for calculating the maximum inner diameter of the blood vessel region comprises the following steps: and calculating the maximum blood vessel diameter in the blood vessel area point by adopting a maximum inscribed circle algorithm for each blood vessel area to be used as the maximum inner diameter.
Preferably, the method for calculating the maximum inner diameter of the vascular region is as follows:
acquiring the central line of a blood vessel region of an ultrasonic image through a distance transformation algorithm; and calculating the maximum blood vessel diameter point by point on the central line of the blood vessel region by adopting a maximum inscribed circle algorithm to obtain the maximum internal diameter.
Preferably, the method comprises: marking the fish as an embrittled fish if all the first inner diameter averages are smaller than all the second inner diameter averages; otherwise, the step of marking the fish as normal fish is replaced by:
if all the first inner diameter average values are smaller than all the second inner diameter average values, marking the fish as embrittled fish, wherein the heart blood flow speed of the ultrasonic image is smaller than a preset blood flow speed threshold value; otherwise, the marked fish is ordinary fish.
Comparative example: the patent of Chinese invention with publication number CN113466232B discloses a method and a system for quickly detecting embrittled fish meat based on computer images, which are implemented by acquiring microscopic images of sections of fish muscle tissues; graying the slice microscopic image to obtain a gray image, and dividing a plurality of first image areas obtained by roughly dividing the gray image into areas to form a first image set; screening a characteristic image set from the first image set; and comparing each first image area in the characteristic image set with the crisp fish sample image, and identifying and marking the type of the fish muscle tissue.
After the identification and detection of the embrittled fish (living body) are carried out by the methods of the first embodiment, the second embodiment and the comparative embodiment, respectively randomly extracting 50 brittle tilapia (the embrittled tilapia), measuring the hardness of the slice of the embrittled fish and the fish under standard pressure by using a traditional texture analyzer, and carrying out tensile or extrusion test on the fish by using a compression test instrument to evaluate the elasticity and the deformability of the fish so as to confirm whether the embrittled fish is identified and detected by using a confirmation result as the embrittled fish identification and detection result. The embrittlement fish identification detection result data are as follows:
the detection result of the first embodiment is: among the 50 embrittled fish, 47 embrittled fish and 3 non-embrittled fish were identified.
The detection result of the second embodiment is: of the 50 embrittled fish, 49 embrittled fish and 1 non-embrittled fish were identified.
The test results of the comparative example are: among the 50 embrittled fish, 45 embrittled fish and 5 non-embrittled fish were identified.
Therefore, the accuracy of the identification of the embodiment of the application is higher than that of the existing nondestructive detection technology, and particularly, the embodiment is high in accuracy of the identification of the embrittled fish by distinguishing the embrittled characteristic edge and the non-embrittled characteristic edge of the embrittled fish with high embrittlement degree in an improved mode through more accurate embrittlement viscosity.
The embodiment of the invention provides a system for quickly detecting the embrittled fish meat based on a computer image, as shown in fig. 2, which is a structural diagram of the system for quickly detecting the embrittled fish meat based on the computer image, and the system for quickly detecting the embrittled fish meat based on the computer image comprises: the system comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps in the embodiment of the embrittlement fish flesh rapid detection system based on the computer image 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 blood vessel region acquisition unit is used for acquiring an ultrasonic image of the fish and positioning a blood vessel region in the ultrasonic image;
an embrittlement characteristic recognition unit for recognizing whether the blood vessel region is an embrittlement characteristic edge or a non-embrittlement characteristic edge;
a vessel inner diameter calculation unit configured to set a maximum inner diameter of a vessel region on the embrittlement-feature side as a first inner diameter and a maximum inner diameter of a vessel region on the non-embrittlement-feature side as a second inner diameter;
an embrittlement marking unit for marking the fish as an embrittled fish if all the first inner diameter means are smaller than all the second inner diameter means; otherwise, the marked fish is ordinary fish.
The embrittlement fish flesh rapid detection system based on the computer image can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The system for quickly detecting the embrittled fish meat based on the computer image can comprise, but is not limited to, a processor and a memory. It will be appreciated by those skilled in the art that the example is merely an example of a computer image based rapid detection system for fish meat that is not limiting of a computer image based rapid detection system for fish meat that may include more or fewer components than the example, or may combine certain components, or different components, e.g., the computer image based rapid detection system for fish meat 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 system for operating the computer image-based rapid detection system for the fragile fish meat, and various interfaces and lines are used for connecting various parts of the whole system for operating the computer image-based rapid detection system for the fragile fish meat.
The memory may be used to store the computer program and/or the module, and the processor may implement the various functions of the computer image-based rapid detection system by running or executing the computer program and/or the 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 invention 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 invention. Furthermore, the foregoing description of the invention 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 invention that may not be presently contemplated, may represent an equivalent modification of the invention.
Claims (9)
1. A method for the lossless and rapid identification of crisp fish, characterized in that it comprises the following steps:
acquiring an ultrasonic image of the fish, and positioning a blood vessel region in the ultrasonic image;
identifying whether the vascular region is an embrittlement-feature-edge or a non-embrittlement-feature-edge;
taking the maximum inner diameter of the blood vessel region on the embrittlement characteristic side as a first inner diameter and taking the maximum inner diameter of the blood vessel region on the non-embrittlement characteristic side as a second inner diameter;
if all the first inner diameter average values are smaller than all the second inner diameter average values, marking the fish as embrittled fish; otherwise, the marked fish is ordinary fish.
2. The method for nondestructive rapid identification of crisp fish according to claim 1, wherein the method for obtaining ultrasonic images of fish is to scan tilapia or grass carp by doppler ultrasonic detection to obtain ultrasonic images.
3. The method for the nondestructive rapid identification of crisp fish according to claim 1, wherein the method for locating the blood vessel region in the ultrasonic image comprises the following steps:
graying the ultrasonic image, and filtering salt and pepper noise in the ultrasonic image through a Gaussian filter algorithm; the linear structure in the ultrasonic image is enhanced through the Hessian matrix, and punctiform structures and noise points are filtered; edge detection is carried out through an edge detection operator to obtain edge lines, and a closed interval is formed by the edge lines; carrying out Gaussian blur on each closed interval to obtain a closed-packet interval; taking the geometric gravity center point of each closure interval as an anchor point, and performing expansion operation on each closure interval by taking each anchor point as a center to obtain a first vessel region; marking a first blood vessel region which is not a closed region in each first blood vessel region as a second blood vessel region; the corresponding position of each second vessel region on the ultrasound image is taken as the located vessel region.
4. The method for the nondestructive rapid identification of crispy fish according to claim 1, wherein the method for identifying whether the blood vessel area is an embrittlement-feature-edge or a non-embrittlement-feature-edge comprises:
detecting Hough line segments of the blood vessel region, forming a line segment set LS by the detected line segments, and marking the line segments in the line segment set LS as LS i ，LS i For the ith line segment in LS, i e [1, N]N is marked asTotal amount of elements in LS;
within the value range of i, the midpoint of the line segment in LS and the line segment LS are connected i Is less than Max (LS) x LSXRatio and is spaced from the line segment LS i All line segments without intersection points are screened out to form a subset LR1; the complement of the subset LR1 in the line segment set LS is recorded as LR2;
wherein LSXRatio is line segment LS i The distance from the midpoint of the line segment to the midpoint of the line segment with the shortest length value in LS is equal to the line segment LS i The ratio of the midpoint distance between the line segment with the longest length value in LS and the Max (LS) is the length of the line segment with the largest length value in the line segment set LS;
if the number of segments in the subset LR1 is greater than the number of segments in LR2, the vessel region is noted as an embrittlement-feature-edge, otherwise the vessel region is noted as a non-embrittlement-feature-edge.
5. The method for the lossless and rapid identification of a brittle fish according to claim 4, wherein the method for identifying whether the blood vessel region is an embrittlement-feature-edge or a non-embrittlement-feature-edge is replaced with:
the embrittlement viscosity EMB of all the blood vessel regions is calculated respectively, and the calculation method of the EMB is as follows:
let the logarithm of the gray value of the ith pixel point on the edge line of the blood vessel area based on 10 be lg (i), i being the serial number of the ith pixel point on the edge line of the blood vessel area;
in the value range of i, calculating the product of lg (i) and the gray value G (i) of the ith pixel point on the edge line of the vascular region as the embrittlement ratio Glg (i) of the ith pixel point; calculating the arithmetic average value of the embrittlement ratio Glg (i) of pixel points on the edge lines of all the blood vessel areas as EMB;
calculating the arithmetic average value of embrittlement viscosity EMB of edge lines of all blood vessel areas to be EMBMean, marking the blood vessel areas with embrittlement viscosity EMB less than EMBMean as embrittlement characteristic edges, and marking the blood vessel areas with the embrittlement viscosity EMB more than or equal to EMBMean as non-embrittlement characteristic edges.
6. The method for the nondestructive rapid identification of a brittle fish according to claim 1, wherein the method for calculating the maximum inner diameter of the blood vessel region comprises the following steps: and calculating the maximum blood vessel diameter in the blood vessel area point by adopting a maximum inscribed circle algorithm for each blood vessel area to be used as the maximum inner diameter.
7. The method for the nondestructive rapid identification of a brittle fish according to claim 1, wherein the method for calculating the maximum inner diameter of the blood vessel region comprises the following steps: acquiring the central line of a blood vessel region of an ultrasonic image through a distance transformation algorithm; and calculating the maximum blood vessel diameter point by point on the central line of the blood vessel region by adopting a maximum inscribed circle algorithm to obtain the maximum internal diameter.
8. A method for the lossless and rapid identification of crisp fish according to claim 1, characterized in that it further comprises: marking the fish as an embrittled fish if all the first inner diameter averages are smaller than all the second inner diameter averages; otherwise, the step of marking the fish as normal fish is replaced by: if all the first inner diameter average values are smaller than all the second inner diameter average values, marking the fish as embrittled fish, wherein the heart blood flow speed of the ultrasonic image is smaller than a preset blood flow speed threshold value; otherwise, the marked fish is ordinary fish.
9. A system for the lossless and rapid identification of a crisp fish, the system comprising: a processor, a memory and a computer program stored in the memory and executable on the processor, which processor, when executing the computer program, implements the steps of a method for the lossless rapid identification of a brittle fish according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311464386.7A CN117218455B (en) | 2023-11-07 | 2023-11-07 | Nondestructive rapid identification method for crisp fish |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311464386.7A CN117218455B (en) | 2023-11-07 | 2023-11-07 | Nondestructive rapid identification method for crisp fish |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117218455A CN117218455A (en) | 2023-12-12 |
| CN117218455B true CN117218455B (en) | 2024-02-02 |
Family
ID=89042899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311464386.7A Active CN117218455B (en) | 2023-11-07 | 2023-11-07 | Nondestructive rapid identification method for crisp fish |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117218455B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11446660B2 (en) * | 2012-06-18 | 2022-09-20 | Scanlogx, Inc | Organism evaluation system and method of use |
| US10748278B2 (en) * | 2012-06-18 | 2020-08-18 | Sobru Solutions, Inc. | Organism evaluation system and method of use |
-
2023
- 2023-11-07 CN CN202311464386.7A patent/CN117218455B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| 脆化草鱼(Ctenopha...et_V)的病理生理生态学;谭乾开 等;《生态学报》;第2749-2756页 * |
| 鱼类脆化作用机理的研究进展;陈冰 等;《饲料研究》;第140-143页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117218455A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10453191B2 (en) | Automated intravascular plaque classification | |
| Aysal et al. | Rayleigh-maximum-likelihood filtering for speckle reduction of ultrasound images | |
| CN113466232B (en) | Brittle fish meat rapid detection method and system based on computer image | |
| Chawgien et al. | Machine learning techniques for classifying the sweetness of watermelon using acoustic signal and image processing | |
| McDonald et al. | Application of morphological image processing in agriculture | |
| Russ | Image analysis of foods | |
| Ahmed et al. | Classification of pepper seed quality based on internal structure using X-ray CT imaging | |
| Barbosa et al. | Towards automatic quantification of the epicardial fat in non-contrasted CT images | |
| CN108171694A (en) | Nodule detection methods, system and equipment based on convolutional neural networks | |
| CN111742343A (en) | Ultrasonic image processing method, system and computer readable storage medium | |
| Meenakshi et al. | Segmentation and boundary detection of fetal kidney images in second and third trimesters using kernel-based fuzzy clustering | |
| CN116519892B (en) | Fish tenderness quality identification method and system | |
| CN117218455B (en) | Nondestructive rapid identification method for crisp fish | |
| CN115294401B (en) | CT image-based classification method, device, equipment and storage medium | |
| Zhang et al. | Retinal vessel segmentation using Gabor filter and textons | |
| CN116433643A (en) | Fish meat quality identification method and device based on computer vision | |
| Valous et al. | Detecting fractal power-law long-range dependence in pre-sliced cooked pork ham surface intensity patterns using Detrended Fluctuation Analysis | |
| Vicas et al. | Usefulness of textural analysis as a tool for noninvasive liver fibrosis staging | |
| Khoje et al. | A Comprehensive survey of fruit grading systems for tropical fruits of maharashtra | |
| Matsui et al. | Automated detection of internal fruit rot in Hass avocado via deep learning-based semantic segmentation of X-ray images | |
| CN117409245B (en) | Automatic identification method for crisp fish | |
| CN116959036B (en) | Evaluation method for fish embrittlement degree | |
| Shrimali et al. | Medical feature based evaluation of structuring elements for morphological enhancement of ultrasonic images | |
| Aarya et al. | Adaptive Rician denoising with edge preservation for MR images of the articular cartilage | |
| CN115908296B (en) | Medical image class activation mapping evaluation method, device, computer 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 |