A method for processing big scale four barbel fish cans

Abstract

The present application belongs to the technical field of intelligent identification, food processing and food industry, and provides a processing method of large-scale four-barbelled fish cans, specifically comprising the following steps: obtaining fish bodies by fishing and cleaning the fish, shooting the fish bodies by image collection instruments and obtaining original images of the fish bodies, pre-processing the original fish body images to form fish body processing images, then analyzing the waxy quality of the fish bodies according to the fish body processing images, and finally excluding fish individuals that do not meet the requirements of can production according to the results of the waxy quality analysis. After ensuring the accuracy of the calculation of the soft waxy characteristics data of the fish scales, further reasonable and effective mathematical support is provided for the screening of fish individuals or fish groups that meet the requirements of fish can production, thereby improving the screening efficiency and accuracy of fish individuals that meet the production requirements in the industrialized and streamlined manufacturing process of large-scale four-barbelled fish cans. The edible experience of the cans is improved, and the product quality and production efficiency of the cans are enhanced.

Description

Technical Field

[0001] This invention belongs to the fields of intelligent identification, food processing and food industry technology, and specifically relates to a processing method for canned large-scaled four-barbel barbs. Background Technology

[0002] The four-barbel barb has a delicate and tender flavor, is rich in protein, healthy fats, and nutrients, and is suitable for various cooking methods. It contains abundant Omega-3 unsaturated fatty acids, which are beneficial for heart health and brain function. Canning the four-barbel barb offers several advantages. Its airtight seal and high-temperature processing extend shelf life, allowing for long-term storage and providing convenient food supply. The ready-to-eat nature of canned fish saves cooking time, making it convenient for busy lifestyles. High-temperature processing sterilizes and improves food safety while preserving the fish's nutrients. The portability of canned fish is suitable for outings and emergencies, and it can also solve seasonal food supply problems. Furthermore, the variety of flavors and tastes increases food diversity.

[0003] One major challenge in making canned fish from the large-scaled barbel (Sinocyclocheilus 'Aureobasidium') is the selection of the fish. Because the scales of the large-scaled barbel have a soft and chewy texture after processing, and are considered a distinctive edible quality, they can be considered an ingredient of equal value to the fish meat and should be packaged in canned fish. However, the soft and chewy nature of the scales is an unstable factor. Depending on the genes of the parent fish or the farmed fish population itself, even within the same batch of large-scaled barbel, some individuals may have insufficiently chewy scales, resulting in scales that are too hard or inedible. Packaging these individuals with insufficiently chewy scales into canned fish would significantly reduce the edible experience, inevitably weakening the product quality and increasing the difficulty of product promotion. Therefore, before canning large-scaled barbel, a method is urgently needed to evaluate and select individuals based on the chewy nature of their scales. Summary of the Invention

[0004] The purpose of this invention is to provide a processing method and system for canned large-scaled four-barbel barbels, in order to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions.

[0005] To achieve the above objectives, according to one aspect of the present invention, a method for processing canned large-scaled four-barbel barbel is provided, the method comprising the following steps:

[0006] S100, catching and cleaning the fish;

[0007] S200 uses an image acquisition instrument to capture images of fish and obtain original images of the fish.

[0008] S300, pre-processing the original fish body image to form a fish body processing image;

[0009] S400, performing waxy quality analysis on the fish body according to the fish body processing image;

[0010] S500, excluding fish individuals that do not meet the requirements of can production according to the result of the waxy quality analysis.

[0011] Further, in step S100, the method of obtaining fish bodies and cleaning the fish is as follows: catching mature fish bodies from a cultured fish pond of Procypris percnosoma, wherein the mature fish bodies are defined as Procypris percnosoma with a feeding time of 6 to 12 months, or the mature fish bodies are defined as Procypris percnosoma with a body weight greater than or equal to 230 g; and cleaning the fish by using a high-pressure water gun or a steam cleaner.

[0012] Further, in step S200, the method of taking pictures of the fish bodies by using an image collection instrument to obtain original fish body images is as follows: the image collection instrument is an industrial CCD camera; the fish bodies are horizontally placed below the image collection instrument; and the side bodies or sides of the fish bodies are taken pictures of, and the obtained images are taken as the original fish body images.

[0013] Further, in step S300, the method of pre-processing the original fish body images to form fish body processing images is as follows: performing image erosion operation on the fish body images; converting the fish body images from an RGB color space to an HSL color space; and extracting the saturation of each pixel in the HSL color space to form an image matrix as the fish body processing image.

[0014] Further, in step S400, the method of performing waxy quality analysis on the fish body according to the fish body processing image is as follows: segmenting the original fish body image into a plurality of regions by using an edge recognition algorithm; taking each region in the original fish body image as a sub-scale domain of the original fish body image; taking the number of the sub-scale domains as Neul; taking the average value of the gray values of each pixel in the sub-scale domain as the average gray value Mavb; defining a pixel as a gray set pixel if the gray value of the pixel is greater than the gray values of each pixel in the eight-neighbor domain and greater than the average gray value; and defining a pixel as a gray edge pixel if the gray value of the pixel is less than the gray values of each pixel in the eight-neighbor domain and less than the average gray value.

[0015] The ratio of the gray value of the gray set pixel to the gray value of the nearest gray edge pixel in the same sub-scale domain is taken as the gray domain characteristic of the gray set pixel; a sequence is constructed by taking the gray domain characteristics of each gray set pixel as elements of the sequence, and the sequence is taken as a gray set sequence Ue_Ls; the number of elements of the gray set sequence is taken as Nech; the geometric mean of each element in the gray set sequence is taken as EUedc; and the waxy scale EVGQ of the original fish body image is calculated.

[0016]

[0017] wherein j1 is an accumulation variable, Ue_Ls(j1) represents the j1th element of the grey set sequence, exp() is an exponential function with base e, ln() is a logarithmic function with base e, ds< > is a range function, and the result of the range function is the difference between the maximum value and the minimum value in the calling sequence, and the waxy scale is taken as the result of waxy quality analysis.

[0018] Since the waxy scale is obtained by combining the grey domain characteristics of the image to be measured, the grey domain characteristics can reflect the characteristic information of the waxy quality related to the fish scales, and effectively quantize the scale waxy characteristics of the high grey value characteristic region in the image to be measured into graphic data. However, this method pays too much attention to the high grey value characteristic region, and the low grey value characteristic region is ignored, which may lead to insufficient quantization and large data waste in the waxy scale analysis. However, the prior art cannot solve the problem of paying too much attention to high characteristic information and ignoring low characteristic information in the application of the waxy scale. In order to make the grey domain characteristics more accurate and the application of the waxy scale more adaptable, the waste of data is reduced. Therefore, a more preferred scheme is provided as follows:

[0019] Preferably, in step S300, the method for analyzing the waxy quality of the fish body according to the fish body processing map is:

[0020] The fish body original image is segmented into a plurality of regions by an edge recognition algorithm, and each region in the image to be measured is taken as a sub-scale domain of the image to be measured. If each pixel of a pixel point and its eight neighbors does not belong to the same sub-scale domain, the pixel is defined as a domain boundary pixel. The median value of the grey values of each pixel point in the sub-scale domain is recorded as the domain grey median value. If the grey values of each pixel of a pixel point and its eight neighbors are all greater than the domain grey median value, the pixel point is defined as an enrichment pixel of the sub-scale domain.

[0021] In a sub-scale domain, the distance between an enrichment pixel and the nearest domain boundary pixel is taken as the point edge distance of the enrichment pixel. A set of pixel points formed by an enrichment pixel and each pixel point in its eight neighbors is taken as the first-order boundary neighborhood of the enrichment pixel. When a plurality of first-order boundary neighborhoods of the enrichment pixel have overlapping parts, the union of the plurality of first-order boundary neighborhoods is taken as a boundary neighborhood.

[0022] The maximum value and the minimum value of the point edge distance of each rich pixel in the boundary neighborhood are recorded as the difference of the boundary neighborhood edge distance GLds of the boundary neighborhood, and the boundary neighborhood edge distances of each boundary neighborhood in the sub-scaled domain are obtained to construct a sequence, which is recorded as a boundary neighborhood edge sequence.

[0023]

[0024] wherein i1 is an accumulation variable, GLds i1 represents the i1th boundary neighborhood edge distance in the boundary neighborhood edge sequence, lg() is a logarithmic function, ER is the standard deviation of the set of the gray values of each pixel in the sub-scaled domain, and Mcgt represents the ratio of the maximum value and the minimum value of the gray values of each pixel point in the sub-scaled domain.

[0025] The average value of the gray values of each pixel point in the sub-scaled domain is defined as the domain gray mean value, the sub-scaled domain with the maximum domain gray mean value in the image to be measured is recorded as an optimal sub-scaled domain, the boundary neighborhood characteristics of each sub-scaled domain are obtained to construct a sequence, which is recorded as a boundary neighborhood characteristic sequence, the boundary neighborhood characteristic of the optimal sub-scaled domain is recorded as EWQES, when a sub-scaled domain satisfies WQES≥EWQES, the sub-scaled domain is defined as a first sub-scaled domain, otherwise, the sub-scaled domain is defined as a second sub-scaled domain.

[0026] The center position of each pixel in a sub-scaled domain is taken as the domain core of the sub-scaled domain, and the distance between the domain cores of any two sub-scaled domains is taken as the core point distance of the two sub-scaled domains; the difference between the boundary neighborhood characteristic of the first sub-scaled domain and the boundary neighborhood characteristic of the second sub-scaled domain with the minimum core point distance is taken as the gelatinization characteristic GTal of the first sub-scaled domain; the gelatinization characteristics of each first sub-scaled domain are obtained to construct a sequence, which is recorded as a gelatinization direction sequence GTLs, the number of elements in the gelatinization direction sequence is recorded as Len.GTLs, and the ratio of the maximum value and the minimum value of each element in the gelatinization direction sequence is recorded as Tcg, and the gelatinization scale EVGQ of the image to be measured is calculated.

[0027]

[0028] wherein i3 is an accumulation variable, mean<> is an arithmetic mean value function, HF<> is a harmonic mean function, ln() is a logarithmic function with the base number e, GTal i3 represents the i2th element in the gelatinization direction sequence, TWQES and BWQES are the maximum value and the minimum value of the boundary neighborhood characteristic sequence, respectively, and the gelatinization scale is taken as the result of the gelatinization quality analysis.

[0029] Beneficial effect: The waxy scale is calculated according to the distribution characteristics of image saturation, so the saturation gradient collapse trend can be accurately marked out, the waxy characteristic defects of fish scales can be effectively identified and weighted, thus the overall identification of the soft waxy characteristics of fish scales can be enhanced, the negative influence of the low correlation pixels of the edge of the scales in the image on the global quantization is avoided, the quantization effect of the image on the highlight area is improved, the accuracy of the calculation of the soft waxy characteristic data of the fish scales is ensured, further reasonable and effective mathematical support is provided for screening fish individuals or fish groups that meet the production of fish cans, and the screening efficiency and accuracy of fish individuals or fish groups that meet the production requirements in the industrialized and streamlined manufacturing process of the Puntius gonionotus fish canner industry are improved.

[0030] Further, in step S500, according to the result of the waxy quality analysis, the method of excluding fish individuals that do not meet the can production requirements is: a pre-set threshold FBEQ, if the waxy scale of a fish individual is less than FBEQ, the fish individual is defined as not meeting the canning standard, otherwise the fish individual is defined as meeting the canning standard.

[0031] Preferably, in step S500, according to the result of the waxy quality analysis, the method of excluding fish individuals that do not meet the can production requirements is: the waxy scales of each fish individual in the same culture pond are constructed into a sequence as a scale sequence, the average value, the upper quartile value and the lower quartile value of the scale sequence are recorded as SBEQ, fq.EVGQ and tq.EVGQ respectively; the group waxy of the culture pond GBEQ is: GBEQ = fq.EVGQ x (tq.EVGQ - fq.EVGQ); the average value of the group waxy of each culture pond in the historical record is recorded as e.GBEQ in the server; if a culture pond meets GBEQ > e.GBEQ, each fish individual in the culture pond is defined as meeting the first production requirement, if a fish individual meets GBEQ > SBEQ, the fish individual is defined as meeting the second production requirement; the fish individual that meets both the first production requirement and the second production requirement is regarded as a fish individual that meets the production of fish cans, otherwise the fish individual is regarded as a fish individual that does not meet the production of fish cans.

[0032] Preferably, in the present application, all undefined variables can be threshold values set by artificial.

[0033] The application further provides a processing system of the canned large-scale four-barbelled fish, 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 processing method of the canned large-scale four-barbelled fish when executing the computer program, and the processing system of the canned large-scale four-barbelled fish can run in a computing device such as a desktop computer, a notebook computer, a palm computer and a cloud data center, and the executable system can comprise, but is not limited to, a processor, a memory, a server cluster, and the processor executes the computer program to run in the following units of the system:

[0034] a fish body catching unit for catching fish bodies and cleaning the fish;

[0035] an image acquisition unit for shooting the fish bodies by an image acquisition instrument and obtaining original images of the fish bodies;

[0036] a preprocessing unit for preprocessing the original fish body images to form fish body processing images;

[0037] a waxy quality analysis unit for analyzing the waxy quality of the fish bodies according to the fish body processing images;

[0038] an individual screening unit for excluding fish individuals that do not meet the production requirements of the canned fish according to the results of the waxy quality analysis.

[0039] The application provides a processing method and system of canned large-scale four-barbelled fish, effectively quantitatively analyzes the waxy characteristics of the scales of the large-scale four-barbelled fish by collecting the saturation information of the scale images of the large-scale four-barbelled fish, further provides reasonable and effective mathematical support for screening fish individuals or fish groups that meet the production requirements of the canned fish after ensuring the accuracy of the calculation of the soft waxy characteristic data of the fish scales, improves the screening efficiency and accuracy of the fish individuals that meet the production requirements in the industrialized and streamlined manufacturing process of the canned large-scale four-barbelled fish, and thus can improve the eating experience of the canned fish and enhance the product quality and production efficiency of the canned fish. BRIEF DESCRIPTION OF DRAWINGS

[0040] The above and other features of the application will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which like elements refer to like elements throughout the description. As best shown in the drawings, the following description describes some embodiments of the application, and other embodiments of the application can be derived from the drawings without paying creative labor, which can be obtained by those skilled in the art. In the drawings:

[0041] Figure 1 a flowchart of a processing method of canned large-scale four-barbelled fish is shown;

[0042] Figure 2 Fig. 1 shows a structural diagram of a processing system of canned Megalobrama phaleres. DETAILED DESCRIPTION

[0043] The concept, specific structure and technical effects of the present application will be described clearly and completely in combination with embodiments and drawings, so as to fully understand the purpose, scheme and effects of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0044] As shown in Figure 1 Fig. 2 shows a flow chart of a processing method of canned Megalobrama phaleres, and the following will describe a processing method of canned Megalobrama phaleres according to an embodiment of the present application in combination with Figure 1 The method comprises the following steps:

[0045] S100, obtaining fish bodies by fishing and cleaning the fish;

[0046] S200, shooting the fish bodies by an image acquisition instrument and obtaining original images of the fish bodies;

[0047] S300, preprocessing the original fish body images to form fish body processing images;

[0048] S400, performing waxy quality analysis on the fish bodies according to the fish body processing images;

[0049] S500, excluding fish individuals that do not meet the requirements of canned production according to the result of the waxy quality analysis.

[0050] Further, in step S100, the method of obtaining fish bodies by fishing and cleaning the fish is: mature fish bodies are fished out from a Megalobrama phaleres breeding fish pond, the mature fish bodies are defined as Megalobrama phaleres with a feeding time of 6 to 12 months, or the mature fish bodies are defined as Megalobrama phaleres with a body weight greater than or equal to 230 grams; the fish are cleaned by a high-pressure water gun or a steam cleaner.

[0051] Further, in step S200, the method of shooting the fish bodies by the image acquisition instrument to obtain the original images of the fish bodies is: the image acquisition instrument is an industrial CCD camera, the fish bodies are horizontally placed below the image acquisition instrument, the side body or side edge of the fish bodies is shot, and the shot image is taken as the original image of the fish bodies.

[0052] Further, in step S300, the method of preprocessing the original fish body images to form fish body processing images is: an image erosion operation is performed on the fish body images, the fish body images are converted from an RGB color space to an HSL color space, the saturation of each pixel in the HSL color space is extracted to form an image matrix, and the image matrix is taken as the fish body processing image.

[0053] Further, in step S400, the method for waxy quality analysis of fish body according to the fish body processing graph is: the fish body original image is segmented into several regions by an edge recognition algorithm, each region in the to-be-tested image is taken as a sub-scale domain of the to-be-tested image, the number of the sub-scale domains is recorded as Neul, the average value of the gray values of each pixel point in the sub-scale domain is recorded as the average gray value Mavb; if the gray value of a pixel point is greater than the gray values of each pixel point in the eight-neighbor domain and greater than the average gray value, the pixel point is defined as a gray set pixel; if the gray value of a pixel point is less than the gray values of each pixel point in the eight-neighbor domain and less than the average gray value, the pixel point is defined as a gray edge pixel;

[0054] The ratio of the gray value of the gray set pixel to the gray value of the nearest gray edge pixel in the same sub-scale domain is taken as the gray domain characteristic of the gray set pixel; a sequence is constructed by acquiring the gray domain characteristics of each gray set pixel as a gray set sequence Ue_Ls, the number of the elements of the gray set sequence is recorded as Nech, the geometric mean value of each element in the gray set sequence is recorded as EUedc, and the waxy scale EVGQ of the to-be-tested image is calculated.

[0055]

[0056] wherein j1 is an accumulation variable, Ue_Ls(j1) represents the j1th element of the gray set sequence, exp() is an exponential function with the base number e, ln() is a logarithmic function with the base number e, ds<> is a range function, the result of the range function is the difference between the maximum value and the minimum value in the called sequence, and the waxy scale is taken as the result of the waxy quality analysis.

[0057] Preferably, in step S300, the method for waxy quality analysis of fish body according to the fish body processing graph is:

[0058] The fish body original image is segmented into several regions by an edge recognition algorithm, each region in the to-be-tested image is taken as a sub-scale domain of the to-be-tested image; if a pixel point and each pixel in the eight-neighbor domain do not satisfy belonging to the same sub-scale domain, the pixel is defined as a domain boundary pixel; the median value of the gray values of each pixel point in the sub-scale domain is recorded as the domain gray median value, and if the gray values of a pixel point and each pixel in the eight-neighbor domain are all greater than the domain gray median value, the pixel point is defined as an enrichment pixel of the sub-scale domain.

[0059] In one sub-scales domain, the distance between the rich pixel and the nearest domain boundary pixel is taken as the point edge distance of the rich pixel; the pixel set composed of the rich pixel and each pixel in the eight-neighbor domain is taken as the first-order boundary neighborhood of the rich pixel, and when several first-order boundary neighborhoods of the rich pixel have overlapping parts, the union of the several first-order boundary neighborhoods is taken as a boundary neighborhood;

[0060] Each boundary neighborhood is obtained by cyclic search in the sub-scales domain, and the number of the boundary neighborhoods is Nen; the difference between the maximum value and the minimum value of the point edge distance of each rich pixel in the boundary neighborhood is taken as the boundary neighborhood edge distance GLds of the boundary neighborhood, and the boundary neighborhood edge distances of each boundary neighborhood in the sub-scales domain are obtained to construct a sequence, which is taken as the boundary neighborhood edge sequence; the average value of each element in the boundary neighborhood edge sequence is defined as e.GLds, and the boundary neighborhood characteristic WQES of the current sub-scales domain is calculated:

[0061]

[0062] Where i1 is an accumulation variable, GLds i1 represents the i1th boundary neighborhood edge distance in the boundary neighborhood edge sequence, lg() is the logarithmic function, ER is the standard deviation of the set composed of the gray values of each pixel in the sub-scales domain, and Mcgt represents the ratio of the maximum value to the minimum value of the gray values of each pixel in the sub-scales domain;

[0063] The average value of the gray values of each pixel in the sub-scales domain is defined as the domain gray mean value, and the sub-scales domain with the maximum domain gray mean value in the image to be measured is taken as the preferred sub-scales domain; the boundary neighborhood characteristics of each sub-scales domain are obtained to construct a sequence, which is taken as the boundary neighborhood characteristic sequence; the boundary neighborhood characteristic of the preferred sub-scales domain is taken as EWQES, and when a sub-scales domain satisfies WQES≥EWQES, the sub-scales domain is defined as the first sub-scales domain, otherwise, the sub-scales domain is defined as the second sub-scales domain,

[0064] The center position of each pixel in one sub-scales domain is taken as the domain core of the sub-scales domain, and the distance between the domain cores of any two sub-scales domains is taken as the core point distance of the two sub-scales domains; the difference between the boundary neighborhood characteristic of the first sub-scales domain and the boundary neighborhood characteristic of the second sub-scales domain with the minimum core point distance is taken as the gelatinization characteristic GTal of the first sub-scales domain; the gelatinization characteristics of each first sub-scales domain are obtained to construct a sequence, which is taken as the gelatinization direction sequence GTLs; the number of elements in the gelatinization direction sequence is taken as Len.GTLs, and the ratio of the maximum value to the minimum value of each element in the gelatinization direction sequence is taken as Tcg; the gelatinization scale EVGQ of the image to be measured is calculated:

[0065]

[0066] where i3 is an accumulated variable, mean< > is an arithmetic mean function, HF< > is a harmonic mean function, ln() is a natural constant e base logarithm function, GTal i3 represents the i2th element in the waxy sequence, TWQES and BWQES are the maximum and minimum values of the adjacent characteristic sequence, respectively, and the waxy scale is taken as the result of waxy quality analysis.

[0067] Further, in step S500, according to the result of waxy quality analysis, the method of excluding fish individuals that do not meet the requirements of can production is: a pre-set threshold FBEQ, if the waxy scale of a fish individual is less than FBEQ, the fish individual is defined as not meeting the can processing standard, otherwise the fish individual is defined as meeting the can processing standard.

[0068] Preferably, in step S500, according to the result of waxy quality analysis, the method of excluding fish individuals that do not meet the requirements of can production is: the waxy scales of each fish individual in the same culture pond are constructed into a sequence as a scale sequence, the average, upper quartile and lower quartile of the scale sequence are denoted as SBEQ, fq.EVGQ and tq.EVGQ, respectively; the population waxy of the culture pond GBEQ is: GBEQ = fq.EVGQ × (tq.EVGQ - fq.EVGQ); the average of the population waxy of each culture pond in the historical record is stored in the server as e.GBEQ; if a culture pond meets GBEQ > e.GBEQ, each fish individual in the culture pond is defined as meeting the first production requirement, if a fish individual meets GBEQ > SBEQ, the fish individual is defined as meeting the second production requirement; the fish individual that meets both the first production requirement and the second production requirement is taken as the fish individual that meets the fish can production, otherwise the fish individual is taken as the fish individual that does not meet the fish can production.

[0069] An embodiment of the present application provides a processing system for big-scale four-barbelled fish cans. Figure 2 As shown in the figure, the processing system for big-scale four-barbelled fish cans provided by the embodiment of the present application comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps in the above-mentioned processing system for big-scale four-barbelled fish cans when executing the computer program.

[0070] The system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor executes the computer program running in the following system units:

[0071] The fish body fishing unit is used for fishing and obtaining fish bodies and washing the fish. The fish body cleaning unit is used for cleaning the fish bodies obtained by the fish body fishing unit. The fish body cutting unit is used for cutting the fish bodies cleaned by the fish body cleaning unit into fish fillets. The fish fillet cleaning unit is used for cleaning the fish fillets cut by the fish body cutting unit. The fish fillet drying unit is used for drying the fish fillets cleaned by the fish fillet cleaning unit. The fish fillet packaging unit is used for packaging the fish fillets dried by the fish fillet drying unit. The fish fillet quality analysis unit is used for analyzing the quality of the fish fillets packaged by the fish fillet packaging unit. The fish individual selection unit is used for selecting fish individuals that meet the fish can production requirements from the fish individuals in the same culture pond according to the result of waxy quality analysis.

[0072] an image acquisition unit, configured to take a fish body by an image acquisition instrument and obtain a raw fish body image;

[0073] a preprocessing unit, configured to preprocess the raw fish body image to form a processed fish body image;

[0074] a waxy quality analysis unit, configured to analyze the waxy quality of the fish body according to the processed fish body image;

[0075] an individual screening unit, configured to exclude fish individuals that do not meet the requirements of can production according to the result of the waxy quality analysis.

[0076] The processing system of the canned large-scale four-barbelled fish can run in a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The processing system of the canned large-scale four-barbelled fish can run in a system that can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the example is only an example of the processing system of the canned large-scale four-barbelled fish and does not constitute a limitation on the processing system of the canned large-scale four-barbelled fish. The processing system of the canned large-scale four-barbelled fish can include more or fewer components, or combine certain components, or different components, for example, the processing system of the canned large-scale four-barbelled fish can also include an input / output device, a network access device, a bus and the like.

[0077] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like. The processor is a control center of the processing system of the canned large-scale four-barbelled fish running system, and connects each part of the processing system of the canned large-scale four-barbelled fish running system by various interfaces and lines.

[0078] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the processing system for canned big-scale four-barbelled carp by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory, and can also include a nonvolatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0079] Although the description of the present application has been quite detailed and particularly described with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present application. Furthermore, the present application is described above in embodiments that the inventors can foresee, and the purpose is to provide a useful description, and non-essential modifications to the present application that have not yet been foreseen can still represent equivalent modifications of the present application.

Claims

1. A processing method for canned large-scaled four-barbel barbel, characterized in that, The method includes the following steps: S100, catching and cleaning the fish; S200 uses an image acquisition instrument to capture images of fish and obtain original images of the fish. S300, preprocesses the original fish image to form a processed fish image; S400, based on the fish body processing diagram, perform glutinous quality analysis on the fish body; S500, based on the results of the glutinous texture quality analysis, fish individuals that do not meet the requirements for canned food production are excluded; The method for performing glutinous quality analysis on the fish body based on the fish body processing image in S400 is as follows: the original image of the fish body is divided into several regions by an edge recognition algorithm. The region corresponding to each region in the image to be tested is taken as the sub-scale region of the image to be tested. The number of sub-scale regions is denoted as Neul. The average gray value of each pixel in the sub-scale region is denoted as the average gray value Mavb. If the gray value of a pixel is greater than the gray values ​​of all pixels in its eight neighboring regions and is greater than the average gray value, then the pixel is defined as a gray set pixel. If the gray value of a pixel is less than the gray values ​​of all pixels in its eight neighboring regions and is less than the average gray value, then the pixel is defined as a gray edge pixel. The ratio of the gray value of a pixel in a gray set to the gray value of the nearest gray edge pixel in the same subscale is taken as the gray-field characteristic of that pixel in the gray set. A sequence is constructed from the gray-field characteristics of each pixel in the gray set as the gray set sequence Ue_Ls. The number of elements in the gray set sequence is denoted as Nech, and the geometric mean of each element in the gray set sequence is denoted as EUedc. The waxy scaling EVGQ of the image under test is then calculated. ； Where j1 is the cumulative variable, Ue_Ls(j1) represents the j1-th element of the gray set sequence, exp() is the exponential function with the natural constant e as the base, ln() is the logarithmic function with the natural constant e as the base, and ds<> is the range function. The result of the range function is the difference between the maximum and minimum values ​​in the call sequence. The waxy scaling is used as the result of waxy quality analysis.

2. The processing method of canned large-scaled four-barbel barbel according to claim 1, characterized in that, In step S100, the method for catching and cleaning the fish is as follows: catching mature fish from the aquaculture pond of the large-scaled barbel, where mature fish are defined as large-scaled barbel that have been raised for 6 to 12 months, or large-scaled barbel that weigh 230 grams or more; and cleaning the fish using a high-pressure water gun or a steam cleaner.

3. The processing method of canned large-scaled four-barbel barbel according to claim 1, characterized in that, In step S200, the method of obtaining the original image of the fish by taking pictures of the fish body with an image acquisition instrument is as follows: the image acquisition instrument is an industrial CCD camera, the fish body is placed horizontally below the image acquisition instrument, and the side or side of the fish body is photographed. The image obtained is used as the original image of the fish body.

4. The processing method of canned large-scaled four-barbel barbel according to claim 1, characterized in that, In step S500, the method for excluding fish individuals that do not meet the requirements for canned food production based on the results of the glutinousness quality analysis is as follows: a pre-set threshold FBEQ is used. If the glutinousness scale of a fish individual is less than FBEQ, then the fish individual is defined as not meeting the canned food processing standard; otherwise, the fish individual is defined as meeting the canned food processing standard.

5. The processing method of canned large-scaled four-barbel barbel according to claim 1, characterized in that, In step S500, the method for excluding fish individuals that do not meet the requirements for canned fish production based on the results of the glutinousness quality analysis is as follows: The glutinousness scaling of each fish individual in the same breeding pond is constructed into a sequence as a scaling sequence. The mean, upper quartile, and lower quartile values ​​of the scaling sequence are denoted as SBEQ, fq.EVGQ, and tq.EVGQ, respectively. Then, the glutinousness GBEQ of the breeding pond is: GBEQ = fq.EVGQ × (tq.EVGQ - fq.EVGQ). The server stores the glutinousness of each breeding pond in historical records, and the average glutinousness of each breeding pond in the server is denoted as e.GBEQ. If a breeding pond meets GBEQ > e.GBEQ, then each fish individual in that breeding pond is defined as meeting the first production requirement; if a fish individual meets GBEQ > SBEQ, then that fish individual is defined as meeting the second production requirement. Fish individuals that simultaneously meet both the first and second production requirements are considered suitable for canned fish production; otherwise, the fish individuals are considered unsuitable for canned fish production.

6. A processing system for canned large-scaled four-barbel barbel, characterized in that, The processing system for canned large-scaled four-barbelly barbel includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the processing method for canned large-scaled four-barbelly barbel according to any one of claims 1-5. The processing system for canned large-scaled four-barbelly barbel operates on a desktop computer, a laptop computer, a handheld computer, or a computing device in a cloud data center.

Images