Intelligent judgment method and device for grade of butter crabs

Abstract

The invention discloses an intelligent judgment method and device for the grade of a butter crab, and relates to the technical field of image recognition, and the method comprises the steps: obtaining a belly photo and a light-transmitting photo of a to-be-judged crab; calculating the fatness of the to-be-judged crabs; judging the sex and the maturity type of the crab to be judged according to the picture of the abdomen to be detected by utilizing a first YOLO model; judging the fullness type of the to-be-judged crab according to the fullness degree; judging the oiliness type of the to-be-judged crab according to the to-be-detected abdomen picture by utilizing a second YOLO model; the ovary development degree of the to-be-judged crab is judged according to the shape and width of the shadow in the to-be-detected light-transmitting photo by using a third YOLO model; and judging the grade of the to-be-judged crab according to the sex, the mature type, the full type, the oily type and the ovary development degree. According to the method, the to-be-judged crabs are placed in the standard white light shooting device and the accent light shooting device respectively, then photos of different illumination and different parts are obtained, the grade of the butter crabs can be accurately recognized, and the grade of the butter crabs can be recognized in a low-cost, damage-free and dissection-free mode.

Description

A method and device for intelligently determining the grade of butter crabs Technical Field

[0001] This application relates to the field of image recognition technology, and in particular to a method and apparatus for intelligently determining the grade of a yellow croaker. Background Technology

[0002] Butter crabs are an extremely rare and prized delicacy. Female mud crabs, under specific environmental conditions, undergo abnormal ovarian development, causing lipid substances to permeate their entire body, resulting in an orange-yellow color – hence the name "butter crab." Butter crabs are extremely rare in the wild; only two or three out of every thousand mud crabs can transform into butter crabs. Due to their scarcity, their market price is usually much higher than that of ordinary mud crabs. Different grades of butter crabs have significantly different prices; therefore, accurately determining the grade of butter crabs without damaging or dissecting them is crucial for market sales.

[0003] However, existing technologies for identifying butter crabs are not very accurate and are costly. Summary of the Invention

[0004] The main objective of this application is to propose an intelligent method and apparatus for determining the grade of butter crabs, so as to determine the grade of butter crabs in a low-cost and accurate manner.

[0005] To achieve the above objectives, one aspect of this application proposes an intelligent method for judging the grade of yellow crab. The method uses a standard white light imaging device comprising a first light-shielding box and a first light-shielding cover. The first light-shielding cover is placed on top of the first light-shielding box, and a standard white light lamp is connected below the first light-shielding cover. The first light-shielding cover has a first through hole. The method also uses a high-intensity light imaging device comprising a second light-shielding box, a second light-shielding cover, a third light-shielding box, and a high-intensity light lamp. The high-intensity light lamp is placed inside the third light-shielding box. The bottom of the second light-shielding box is connected to the top of the third light-shielding box. The bottom of the second light-shielding box is a transparent plate. The illumination of the high-intensity light lamp is set to shine on the transparent plate, and the light direction is adjustable. The second light-shielding cover has a second through hole. The method includes the following steps: placing the crab to be judged inside the standard white light imaging device, and using a camera to examine it under standard white light through the first light-shielding box... A through-hole is used to photograph the abdomen of the crab to be judged, obtaining a corresponding abdominal photograph. The crab is placed in a high-intensity light imaging device, and a camera is used to photograph both sides of the crab under high intensity light through the second through-hole, obtaining corresponding translucent photographs. The plumpness of the crab is calculated. A pre-trained first YOLO model is used to determine the sex and maturity type of the crab based on the abdominal photograph. The plumpness is compared with a plumpness threshold to determine the fullness type of the crab. A pre-trained second YOLO model is used to determine the oiliness type of the crab based on the abdominal photograph. A pre-trained third YOLO model is used to determine the ovarian development level of the crab based on the shape and width of the shadows in the translucent photograph. The grade of the crab is determined by combining the sex and maturity type, the fullness type, the oiliness type, and the ovarian development level.

[0006] In some embodiments, the step of using a pre-trained third YOLO model to determine the ovarian development level of the crab to be judged based on the shape and width of the shadow in the translucent photograph to be tested, classifying it into immature ovarian crabs, nascent ovarian crabs, and mature ovarian crabs, includes the following steps: if the pre-trained third YOLO model identifies that the shape of the shadow in the translucent photograph to be tested is gradually narrowing from the center to both sides, then the ovarian development level of the crab to be judged is determined to be immature ovarian crabs; if the pre-trained third YOLO model identifies that the width of the shadow in the translucent photograph to be tested is uniform and less than a set width threshold, then the ovarian development level of the crab to be judged is determined to be nascent ovarian crabs; if the pre-trained third YOLO model identifies that the width of the shadow in the translucent photograph to be tested is uniform and reaches the set width threshold, then the ovarian development level of the crab to be judged is determined to be mature ovarian crabs.

[0007] In some embodiments, determining the grade of the crab to be judged based on its sex and maturity type, its plumpness type, its oiliness type, and its ovarian development level includes the following steps: if the sex and maturity type is male, then the crab to be judged is determined to be male; if the sex and maturity type is immature crab, then the crab to be judged is determined to be immature crab; if the sex and maturity type is mature female crab, then the crab to be judged is initially determined to be mature female crab; if the plumpness type of the mature female crab is water crab, then the crab to be judged is determined to be water crab; if the plumpness type of the mature female crab is... If the crab is not a water crab, it is initially determined to be a normal mature female crab; if the normal mature female crab has no oil, it is determined to be a common crab; if the normal mature female crab has oil, it is initially determined to be a yellow butter crab; if the yellow butter crab's ovary development is immature, it is determined to be a full-oil yellow butter crab; if the yellow butter crab's ovary development is early maturity, it is determined to be a head-and-hand yellow butter crab; if the yellow butter crab's ovary development is mature, it is determined to be a roe-oil yellow butter crab.

[0008] In some embodiments, the method further includes the following steps: placing multiple sample crabs in the standard white light imaging device, and using a camera to take a picture of the abdomen of each sample crab through the first through-hole under standard white light to obtain a corresponding sample abdomen photograph; placing each sample crab in the high-intensity light imaging device, and using a camera to take a picture of both sides of each sample crab through the second through-hole under high-intensity light to obtain a corresponding sample translucent photograph; calculating the plumpness of each sample crab; determining the sex, maturity type, plumpness type, oiliness type, and ovarian development degree of each sample crab by measurement and dissection; and using the sample abdomen photographs of each sample crab... The first YOLO model is constructed based on the morphology and color characteristics of the plastron of the crabs, as well as their corresponding sex and maturity type. The plumpness thresholds for water crabs and non-water crabs are determined using the plumpness and corresponding plumpness types of each sample crab. The second YOLO model is constructed using the color of the articular membrane in the abdominal photographs of each sample crab, as well as its corresponding oiliness type. The third YOLO model is constructed using the shape and width of the shadows in the translucent photographs of each sample crab, as well as the corresponding ovarian development level. The first YOLO model, the second YOLO model, and the third YOLO model are then trained.

[0009] In some embodiments, determining the sex, maturity type, fullness type, oiliness type, and ovarian development degree of each sample crab through measurement and dissection includes the following steps: determining the sex and maturity type based on the morphology of the ventral carapace; among them, a long and pointed triangular ventral carapace indicates a male crab, a wide triangular and lighter-colored ventral carapace indicates a young female crab, and a broad and round and darker-colored ventral carapace indicates a mature female crab; determining the oiliness type based on the yellow-blue value b of the swimming leg joint membrane, and a determination of b≥X is made for oiliness, and a determination of b<X is made for non-oiliness; where X is a preset oiliness threshold; determining the fullness type based on the condition of the crab body after dissection, a water crab has more water and less meat, and the opposite is a non-water crab; determining the ovarian development degree based on the ovarian development period and ovarian index; among them, a determination of ovarian immaturity is made when the ovarian development period is stage I–II, individuals with ovarian development reaching stage III or above are weighed for ovarian weight, and the ovarian index is calculated in combination with the body weight, a determination of ovarian initial maturity is made when the ovarian index≤Y, and a determination of ovarian maturity is made when the ovarian index>Y; where the ovarian index = ovarian weight / body weight, and Y is a preset ovarian index threshold.

[0010] In some embodiments, the method further includes the following steps: regularly retraining the first YOLO model using the abdominal photos of the test samples whose sex and maturity type are determined to be correctly classified; regularly retraining the second YOLO model using the abdominal photos of the test samples whose oiliness type is determined to be correctly classified; regularly retraining the third YOLO model using the translucent photos of the test samples whose ovarian development degree is determined to be correctly classified.

[0011] To achieve the above objectives, another aspect of this application proposes an intelligent determination device for the grade of yellow crab. The device includes: a first imaging unit for placing the crab to be determined within a standard white light imaging device and using a camera to capture a corresponding abdominal photograph of the crab under standard white light through a first through-hole; a second imaging unit for placing the crab to be determined within a high-intensity light imaging device and using a camera to capture corresponding translucent photographs of both sides of the crab under high-intensity light through a second through-hole; a plumpness calculation unit for calculating the plumpness of the crab; and a sex and maturity type recognition unit for using a pre-trained first Y... The YOLO model determines the sex and maturity type of the crab based on the abdominal photograph; the plumpness recognition unit determines the plumpness type of the crab based on the plumpness; the oiliness recognition unit uses a pre-trained second YOLO model to determine the oiliness type of the crab based on the abdominal photograph; the ovary recognition unit uses a pre-trained third YOLO model to determine the ovary development level of the crab based on the shape and width of the shadow in the translucent photograph; and the grading unit determines the grade of the crab by combining the sex and maturity type, the plumpness type, the oiliness type, and the ovary development level.

[0012] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0013] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0014] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0015] The embodiments of this application include at least the following beneficial effects: This application provides an intelligent method and apparatus for judging the grade of yellow crab. The solution of this application involves placing the crab to be judged in a standard white light shooting device, using a camera to take a picture of the abdomen of the crab to be judged under standard white light through a first through hole to obtain a corresponding picture of the abdomen to be judged; placing the crab to be judged in a strong light shooting device, using a camera to take pictures of both sides of the crab to be judged under strong light through a second through hole to obtain corresponding pictures of the translucent light to be judged; calculating the plumpness of the crab to be judged; using a pre-trained first YOLO model to determine the sex and maturity type of the crab to be judged based on the picture of the abdomen to be judged; determining the plumpness type of the crab to be judged based on the plumpness; using a pre-trained second YOLO model to determine the oiliness type of the crab to be judged based on the picture of the abdomen to be judged; using a pre-trained third YOLO model to determine the ovarian development degree of the crab to be judged based on the shape and width of the shadow in the picture of the translucent light to be judged; and comprehensively judging the grade of the crab to be judged based on the sex and maturity type, plumpness type, oiliness type, and ovarian development degree. This application obtains photos of crabs under different lighting conditions and different parts by placing them under standard white light and strong light photography devices. Based on the photos under specific lighting conditions, the sex, maturity type, plumpness type, oiliness type, and ovarian development degree of the crabs under test are distinguished, and the grade of the yellow oil crabs is comprehensively classified. The grade of yellow oil crabs can be accurately identified. Moreover, the grade of yellow oil crabs can be identified at low cost, without damage or dissection, by using the photography device and YOLO model. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 is a flowchart illustrating an intelligent method for determining the grade of a yellow crab according to an embodiment of this application; Figure 2 is an example flowchart illustrating an intelligent method for determining the grade of a yellow crab according to an embodiment of this application; Figure 3 is a logic diagram illustrating a comprehensive determination of the grade of a yellow crab according to an embodiment of this application; Figure 4 is an example diagram illustrating an imaging device and an intelligent recognition system according to an embodiment of this application; Figure 5 is a training data diagram of a first YOLO model according to an embodiment of this application; Figure 6 is a recognition result diagram of a first YOLO model according to an embodiment of this application; Figure 7 is a training data diagram of a second YOLO model according to an embodiment of this application; Figure 8 is a recognition result diagram of a second YOLO model according to an embodiment of this application; Figure 9 is a training data diagram of a third YOLO model according to an embodiment of this application; Figure 10 is a recognition result diagram of a third YOLO model according to an embodiment of this application; Figure 11 is an example result diagram of yellow crab grade recognition according to an embodiment of this application; Figure 12 is a structural schematic diagram illustrating an intelligent determination device for the grade of a yellow crab according to an embodiment of this application; Figure 13 is an example diagram illustrating an intelligent determination device for the grade of a yellow crab according to an embodiment of this application; Figure 14 is a hardware structure schematic diagram illustrating an electronic device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before describing the embodiments of this application in detail, some related technologies involved in the embodiments of this application will be described first, as follows: The color of the joint membrane of the yellow roe crab is different from that of the ordinary roe crab. The yellow roe crabs on the market can be divided into three grades according to the degree of ovarian development, from low to high: full yellow roe crab, head and hand yellow roe crab, and roe yellow roe crab.

[0021] According to relevant standards, yellow oil crabs are classified into top-grade, extra-grade, and first-grade, based on the amount of light-transmitting area along the serrated edge of their carapace. Based on extensive sample dissection, the inventors of this application believe that yellow oil crabs should be graded into three categories: fully oily, head-and-hand (with ovaries and roe), and oily with roe. Full-oil yellow oil crabs are those whose ovaries have not yet developed to stage III; head-and-hand yellow oil crabs are those whose ovaries have developed to stage III with an ovarian index ≤5%; and oily with roe yellow oil crabs are those with an ovarian index >5%. The group standard specifies that top-grade yellow oil crabs have a large area of ​​light-transmitting light along the serrated edge of their carapace, extra-grade yellow oil crabs have a partial area of ​​light-transmitting light along the serrated edge of their carapace, and first-grade yellow oil crabs have a small area of ​​light-transmitting light along the serrated edge of their carapace. The inventors of this application discovered through dissection that the shadows of the yellow crab include not only the ovaries but also the hepatopancreas. The translucent parts at the serrated edge of the cephalothorax reflect the number of ovaries and hepatopancreas, but cannot accurately reflect the development of the ovaries. Therefore, this basis cannot distinguish between the full-oil yellow crab and the head-and-hand yellow crab. Moreover, this basis for classifying the head-and-hand yellow crab and the roe-oil yellow crab is highly subjective.

[0022] In the prior art, CN119322028A discloses a method and apparatus for evaluating the quality of Chinese mitten crabs (Eriocheir sinensis) based on spectral information. This method involves using a spectrometer to measure the spectrum of the crab, acquiring spectral data, extracting characteristic parameters from this data, calculating similarity, and selecting the quality grade corresponding to the maximum similarity as the preliminary quality grade of the crab. Grades include top-grade, premium-grade, first-grade, and unqualified. These characteristic parameters are further combined to calculate the yellow-blue value and light transmittance of the crab, while also considering plumpness and ovarian index to form a comprehensive evaluation index. Finally, this evaluation index is compared with a preset quality range, and the determined quality grade is corrected based on the comparison results to ultimately determine the actual quality grade of the crab.

[0023] Current technology has limitations: While acquiring spectral data can provide a precise criterion for classifying ovarian area proportion, it faces challenges such as expensive equipment and radiation risks. Furthermore, the process of extracting feature parameters and using X-ray 3D reconstruction to obtain ovarian volume information is cumbersome, time-consuming, and technically demanding, requiring significant manpower and increasing costs, hindering rapid assessment and widespread adoption. In addition, infrared imaging technology has limited ability to differentiate between the ovaries and hepatopancreas of mud crabs and cannot be used as a basis for classifying them as either fully oily or head-and-hand yellow oil crabs.

[0024] In summary, there is currently no accurate basis for distinguishing between fully oily yellow crabs and top-grade yellow crabs. The distinction between top-grade yellow crabs and roe-rich yellow crabs relies on experience or complex software calculations. Furthermore, there is currently no complete intelligent method to differentiate between common mud crabs, fully oily yellow crabs, top-grade yellow crabs, and roe-rich yellow crabs. Therefore, it is necessary to provide an intelligent method and device for judging the grade of yellow crabs to accurately and objectively determine their quality.

[0025] This application provides a method and apparatus for intelligently determining the grade of yellow crabs, relating to the field of image recognition technology. The method and apparatus provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited thereto; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application implementing an intelligent method for determining the grade of yellow crabs, but is not limited to the above forms.

[0026] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0027] Referring to Figure 1, this application embodiment provides a method for intelligently determining the grade of a yellow crab. The standard white light imaging device used in this method includes a first light-shielding box and a first light-shielding cover. The first light-shielding cover is placed on top of the first light-shielding box, and a standard white light lamp is connected below the first light-shielding cover. The first light-shielding cover has a first through hole. The high-intensity light imaging device used in this method includes a second light-shielding box, a second light-shielding cover, a third light-shielding box, and a high-intensity light lamp. The high-intensity light lamp is placed inside the third light-shielding box. The bottom of the second light-shielding box is connected to the top of the third light-shielding box. The bottom of the second light-shielding box is a transparent plate. The illumination of the high-intensity light lamp is set to illuminate the transparent plate, and the light direction is adjustable. The second light-shielding cover has a second through hole. This method may include, but is not limited to, steps S100 to S160, specifically as follows: S100: The crab to be judged is placed inside the standard white light imaging device, and the camera is used to examine the crab to be judged under standard white light through the first through hole. S110: Take a picture of the abdomen to obtain a corresponding test abdominal photo; S120: Place the crab to be judged in a strong light shooting device, and use a camera to take pictures of both sides of the crab to be judged under the strong light through the second through hole to obtain corresponding test translucent photos; S130: Calculate the plumpness of the crab to be judged; S140: Use a pre-trained first YOLO model to determine the sex and maturity type of the crab to be judged based on the test abdominal photo; S150: Use a pre-trained second YOLO model to determine the oily type of the crab to be judged based on the test abdominal photo; S160: Use a pre-trained third YOLO model to determine the ovarian development degree of the crab to be judged based on the shape and width of the shadow in the test translucent photo; S170: Combine the sex and maturity type, the plump type, the oily type, and the ovarian development degree to determine the grade of the crab to be judged.

[0028] Optionally, the step of using a pre-trained third YOLO model to determine the ovarian development level of the crab to be judged based on the shape and width of the shadow in the translucent photograph to be tested, classifying it into immature ovarian crabs, nascent ovarian crabs, and mature ovarian crabs, includes the following steps: if the pre-trained third YOLO model identifies that the shape of the shadow in the translucent photograph to be tested gradually narrows from the center to both sides, then the ovarian development level of the crab to be judged is determined to be immature ovarian crabs; if the pre-trained third YOLO model identifies that the width of the shadow in the translucent photograph to be tested is uniform and less than a set width threshold, then the ovarian development level of the crab to be judged is determined to be nascent ovarian crabs; if the pre-trained third YOLO model identifies that the width of the shadow in the translucent photograph to be tested is uniform and reaches the set width threshold, then the ovarian development level of the crab to be judged is determined to be mature ovarian crabs.

[0029] Optionally, the step of determining the grade of the crab to be judged based on the sex and maturity type, the plumpness type, the oiliness type, and the degree of ovarian development includes the following steps: if the sex and maturity type is male, then the crab to be judged is determined to be male; if the sex and maturity type is immature crab, then the crab to be judged is determined to be immature crab; if the sex and maturity type is mature female crab, then the crab to be judged is initially determined to be mature female crab; if the plumpness type of the mature female crab is water crab, then the crab to be judged is determined to be water crab; if the plumpness type of the mature female crab is non-water crab... If the crab is classified as a normal mature female crab, it is initially determined that the crab is a normal mature female crab. If the normal mature female crab has no oily substance, it is determined that the crab is a common crab. If the normal mature female crab has oily substance, it is initially determined that the crab is a yellow butter crab. If the yellow butter crab's ovary development is immature, it is determined that the crab is a full-oil yellow butter crab. If the yellow butter crab's ovary development is early-mature, it is determined that the crab is a head-and-hand yellow butter crab. If the yellow butter crab's ovary development is mature, it is determined that the crab is a roe-oil yellow butter crab.

[0030] Optionally, the method further includes the following steps: placing multiple sample crabs in the standard white light imaging device, and using a camera to take pictures of the abdomen of each sample crab through the first through-hole under standard white light to obtain corresponding sample abdominal photographs; placing each sample crab in the high-intensity light imaging device, and using a camera to take pictures of both sides of each sample crab through the second through-hole under high-intensity light to obtain corresponding sample translucent photographs; calculating the plumpness of each sample crab; determining the sex, maturity type, plumpness type, oiliness type, and ovarian development degree of each sample crab by measurement and dissection; and using the abdominal images of each sample crab... The first YOLO model is constructed based on the morphological and color characteristics of the crab shell, as well as the corresponding sex and maturity type. The plumpness thresholds for water crabs and non-water crabs are determined using the plumpness and corresponding fullness type of each sample crab. The second YOLO model is constructed using the color of the articular membrane in the abdominal photographs of each sample crab, as well as the corresponding oiliness type. The third YOLO model is constructed using the shape and width of the shadows in the translucent photographs of each sample crab, as well as the corresponding ovarian development level. The first, second, and third YOLO models are then trained.

[0031] Optionally, determining the gender, maturity type, fullness type, oiliness type, and ovarian development degree of each sample crab through measurement and dissection includes the following steps: determining the gender and maturity type based on the shape of the ventral carapace; among them, a long and pointed triangular ventral carapace indicates a male crab, a wide triangular ventral carapace with a lighter color indicates a young crab, and a broad and round ventral carapace with a darker color indicates a mature female crab; determining the oiliness type based on the yellow-blue value b of the swimming leg joint membrane, where a determination of b≥X indicates oiliness, and a determination of b<X indicates non-oiliness; where X is a preset oiliness threshold; determining the fullness type based on the condition of the crab body after dissection, where a crab with more water and less meat is a watery crab, and vice versa is a non-watery crab; determining the ovarian development degree based on the ovarian development period and ovarian index; among them, a determination of ovarian development stage I–II indicates immature ovaries, individuals with ovarian development reaching stage III and above are weighed for ovarian weight, and the ovarian index is calculated in combination with the body weight. An ovarian index ≤Y indicates initial ovarian maturity, and an ovarian index >Y indicates ovarian maturity; where the ovarian index = ovarian weight / body weight, and Y is a preset ovarian index threshold.

[0032] Optionally, the method further includes the following steps: regularly retraining the first YOLO model using the test abdominal photos whose gender and maturity type are determined to be correctly classified; regularly retraining the second YOLO model using the test abdominal photos whose oiliness type is determined to be correctly classified; regularly retraining the third YOLO model using the test translucent photos whose ovarian development degree is determined to be correctly classified.

[0033] Next, specific application examples will be combined to introduce and illustrate some optional embodiments of the present application in detail.

[0034] Referring to FIG. 2, this embodiment provides a method for intelligent determination of the grade of butter crabs. FIG. 3 is a logic diagram for comprehensive determination of the grade of butter crabs. FIG. 4 is an example diagram of a photographing device and an intelligent recognition system.

[0035] This embodiment may include: 1. Distinguishing the ovarian development degree based on features such as the shape and width of the shadow in the translucent photo of the green crab. When the ovaries are immature, the shadow gradually narrows from the center to both sides. When the ovaries are initially mature, the shadow width is uniform and thin. When the ovaries are mature, the shadow width is uniform and wide; determining the gender and maturity type based on the shape and color of the ventral carapace of the green crab under standard white light; determining the oiliness type based on the color of the joint membrane of the green crab under standard white light. Based on this, three machine vision and deep learning YOLO classification models are trained respectively based on a large number of sample translucent images, standard white light images, and classification information, with an accuracy rate higher than 90%, and the model accuracy can be continuously improved as the training photo set increases. For the crabs to be determined, the ovarian development degree, gender and maturity type, oiliness type, and fullness type are determined respectively according to the abdominal photo, translucent photo, and fatness using the three YOLO classification models and the fullness threshold, and the grade of the butter crab is comprehensively determined.

[0036] 2. The specific steps are as follows: Step 1: Tie the large claws of the mud crab and place it in the first light-shielding box with its abdomen facing upward. Place a D65 standard white light above the first light-shielding box. The color temperature of the light is 6500K and the color rendering index CRI≥98. Under the standard white light, use a standard gray card to calibrate the white balance of the camera and take a picture of the mud crab's abdomen to obtain the shape and color characteristics of the abdominal carapace and the color characteristics of the articular membrane.

[0037] Step 2: In a dark environment, illuminate the left side of the crab's carapace from below with a strong light, and take a photo of the left side from above. Repeat the same method to take a photo of the right side, thus obtaining the shape and width characteristics of the shadows. The strong light should be a downlight with a power of 2000 lm or higher.

[0038] Step 3: Measure the weight and carapace length of the mud crab, and calculate the condition factor (CF). The carapace length is the horizontal distance from the tip of the foremost serration to the rearmost end of the carapace. Condition factor = weight / (carapace length) 3 .

[0039] Step 4: Determine sex and maturity type based on plastron characteristics, including male crabs, immature crabs, and mature female crabs. Male crabs have a long, pointed triangular plastron; immature crabs have a wide, light-colored, triangular plastron; and mature female crabs have a wide, round, dark-colored plastron. Determine oiliness based on the yellow-blue value (b) of the swimming leg joint membrane: b ≥ 10 indicates an oily type, and b < 10 indicates a non-oily type. Dissect the crab to determine if it is a water crab; crabs with more water and less meat are water crabs, and vice versa. Determine ovarian development stage and ovarian index. Ovarian development stages I–II indicate immature ovaries. For individuals with ovarian development stage III and above, weigh the ovaries and calculate the gonadosomatic index (GSI) based on body weight. An ovarian index ≤ 5% indicates ovarian prematurity, and an ovarian index > 5% indicates ovarian maturity. Ovarian index = ovarian weight / body weight.

[0040] Step 5: Perform steps 1-4 on 200 mud crab samples of different sex-maturity, oily type, and ovarian development levels, including photography, measurement, dissection, and determination.

[0041] Step 6: Select the latest YOLO11n-cls classification model and train the first YOLO model using abdominal photos of blue crab samples with different sexes and maturity types. Referring to Figure 5, the model achieved a maximum accuracy of 1.0 during training and a 100% accuracy rate during model validation. See Figures 5 and 6 for details.

[0042] The plumpness threshold of 0.50 was obtained by using plumpness samples of different plumpness types.

[0043] A second YOLO model was trained using abdominal photographs of blue crabs with different oil content. The highest accuracy (accuracy_top1) during model training reached 0.9, and the model validation accuracy was 90%. Only a small number of oily and non-oily crabs were misclassified from each other, as shown in Figures 7 and 8.

[0044] A third YOLO model was trained using translucent photographs of mud crabs at different stages of ovarian development. The highest accuracy (accuracy_top1) during training reached 0.946, and the model validation accuracy was 94.6%. The accuracy rate for identifying ovarian maturity type was 100%, with only a small number of misclassifications between immature and nascent ovarian types, as shown in Figures 9 and 10.

[0045] Step 7: Referring again to Figure 1, perform steps S100-S120 on the crab to be judged. The fatness of the example crab to be judged is 0.55. Using a pre-trained first YOLO model, determine the sex-maturity type based on the abdominal photograph of the crab to be judged, including male crab, immature crab, and mature female crab. Using a fatness threshold, determine the plumpness type based on the fatness of the crab to be judged, including water crab and non-water crab. Using a pre-trained second YOLO model, determine the oiliness type based on the abdominal photograph, including oily and non-oily. Using a pre-trained third YOLO model, determine the ovarian development level based on two translucent photographs, including immature ovary, early-maturing ovary, and mature ovary. Referring to Figure 11, the three pre-trained YOLO models respectively classify the example crab to be judged as a mature female crab, oily, and early-maturing ovary, and the fatness threshold classifies it as a non-water crab.

[0046] Step 8: Referring again to Figure 3, comprehensively determine the grade of the yellow oil crab by considering its sex-maturity type, plumpness type, oiliness type, and ovarian development level. The comprehensive determination method is as follows: The crab to be judged is determined using the first YOLO model to determine its sex-maturity type, including male crabs, immature crabs, and mature female crabs; among mature female crabs, the plumpness threshold is used to determine the plumpness type. If it is a water crab, the crab to be judged is classified as a water crab; if it is not a water crab, it is initially classified as a normal mature female crab; among normal mature female crabs, the second YOLO model is used to determine the oiliness type. If it is not oily, the crab to be judged is classified as a normal crab; if it is oily, the crab to be judged is initially classified as a yellow oil crab; among yellow oil crabs, the third YOLO model is used to determine the ovarian development level. If the ovary is immature, the crab to be judged is classified as a full-oil yellow oil crab; if the ovary is just beginning to mature, the crab to be judged is classified as a head-and-hand yellow oil crab; if the ovary is mature, the crab to be judged is classified as a roe-oil yellow oil crab. Example: The crab to be judged was comprehensively determined to be a head-and-hand full-oil crab.

[0047] Step 9: Determine the correct photos and accumulate them in the photo set for model training. Regularly retrain the model to continuously improve its accuracy.

[0048] Referring to Figure 12, this application embodiment also provides an intelligent determination device for the grade of yellow crab, which can realize the above-mentioned intelligent determination method for the grade of yellow crab. The device includes: a first shooting unit, used to place the crab to be determined in a standard white light shooting device, and use a camera to take a picture of the abdomen of the crab to be determined through the first through hole under standard white light to obtain a corresponding picture of the abdomen to be tested; a second shooting unit, used to place the crab to be determined in a strong light shooting device, and use a camera to take pictures of both sides of the crab to be determined through the second through hole under strong light to obtain corresponding pictures of the light transmission to be tested; a plumpness calculation unit, used to calculate the plumpness of the crab to be determined; and a sex and maturity type identification unit, used to use... A pre-trained first YOLO model determines the sex and maturity type of the crab based on the abdominal photograph of the crab to be judged; a plumpness recognition unit determines the plumpness type of the crab to be judged based on the plumpness; an oiliness recognition unit uses a pre-trained second YOLO model to determine the oiliness type of the crab to be judged based on the abdominal photograph of the crab to be judged; an ovary recognition unit uses a pre-trained third YOLO model to determine the ovarian development degree of the crab to be judged based on the shape and width of the shadow in the translucent photograph of the crab to be judged; and a grading unit is used to determine the grade of the crab to be judged by combining the sex and maturity type, the plumpness type, the oiliness type, and the ovarian development degree.

[0049] Figure 13 is an example diagram of an intelligent determination device for the grade of yellow crabs. Specifically, it includes the following: a first shooting unit, including a first light-shielding box 1, a first light-shielding cover 2, a standard white light lamp 3, and a camera 4.

[0050] The first light-shielding box 1 is uncovered and black, and can be a cuboid, cube, or cylinder. A first light-shielding cover 2 is placed on top of the first light-shielding box 1, ensuring that the cover completely covers it, making it airtight and preventing external light from interfering with the standard white light and affecting the colors captured in the image. The first light-shielding cover 2 has a central opening 5, the size of which is adapted to the size of the camera lens 4. The camera 4 photographs the interior of the box through the central opening 5 of the first light-shielding cover 2.

[0051] The standard white light fixture 3 has a color temperature of 6500K and a color rendering index (CRI) ≥ 98. It is ring-shaped and adhered to the underside of the first light-shielding cover 2. The inner diameter of the standard white light fixture 3 is larger than the central hole 5 of the first light-shielding cover 2 to ensure it does not block the central hole 5; its outer diameter is smaller than the first light-shielding housing 1. The standard white light fixture 3 is powered by a power cord 6. A small groove 7 is provided on the lower side of the first light-shielding cover 2 to allow the power cord 6 to pass through, preventing light leakage from the device due to exposed power cord.

[0052] The second shooting unit includes a second light-shielding box 8, a third light-shielding box 9, a second light-shielding cover 10, a high-intensity light 11, and a camera 19.

[0053] The second light-shielding box 8 is bottomless and lidless, cylindrical in shape, and made of acrylic sheet or other rigid material. Its thickness must be sufficient to prevent a live crab from moving the rigid tube inside. Its diameter should be 2-4 cm larger than the top opening of the third light-shielding box 9 to ensure that it can cover the circular hole 16 at the top of the third light-shielding box 9.

[0054] The third light-shielding enclosure 9 is made of opaque black acrylic sheet, thick enough to withstand a certain weight. The third light-shielding enclosure 9 has a side door 12, which is connected to the third light-shielding enclosure 9 via hinges 13, and is equipped with a door handle 14 and a magnetic closure 15. The top center of the third light-shielding enclosure 9 has a circular hole 16 with a diameter of 18cm, through which a transparent panel 17 is inlaid using glue or other processes. The transparent panel 17 can be made of a high-transmittance material such as transparent acrylic sheet or quartz glass.

[0055] The second light-shielding cover 10 covers the second light-shielding box 8, and the diameter of the second light-shielding cover 10 is larger than the diameter of the second light-shielding box 8. The second light-shielding cover 10 has a central opening 18, the size of which is adapted to the size of the lens of the camera 19. The camera 19 takes pictures of the interior of the second light-shielding box 8 through the central opening 18 of the second light-shielding cover 10.

[0056] A high-intensity light 11 is placed inside the third light-shielding box 9, with the light 11 facing upwards and the light opening close to the top of the third light-shielding box 9. If necessary, the high-intensity light can be raised from the bottom.

[0057] The fullness calculation unit includes an electronic balance and a vernier caliper. It should be noted that the fullness calculation unit is not shown in Figure 13.

[0058] The intelligent recognition unit is primarily a computer with built-in software containing three pre-trained YOLO models. The camera can connect to the computer via wired or wireless means. The software includes units for gender and maturity type recognition, crab-like (water crab) recognition, oily (oily) recognition, and grading.

[0059] The specific operating method of the shooting device is as follows: First shooting unit: Before shooting, turn on the power of the standard white light fixture 3, place the standard gray card under the light, and calibrate the white balance of the camera 4 by aligning it with the standard gray card through the central hole 5 of the first light-shielding cover 2. During shooting, tie the large claws of the blue crab with cable ties or rope to prevent it from turning over. Place the blue crab belly-up in the box, turn on the light of the standard white light fixture 3, and use the camera 4 to take a picture of the blue crab's belly.

[0060] Second shooting unit: During shooting, place the blue crab with its back facing up above the transparent plate 17, inside the second light-shielding box 8. Cover with the second light-shielding cover 10 and position the camera. Open the side door 12, reach your arm into the third light-shielding box 9, adjust the position of the strong light 11 so that it is aimed at the left side of the blue crab's carapace, close the side door 12 and take a photo of the blue crab with light shining through its left side; adjust the position of the strong light again and take a photo of the blue crab with light shining through its right side.

[0061] After shooting, the first light-shielding box 1, the first light-shielding cover 2, the standard white light fixture 3 and the camera 4, the second light-shielding box 8, the second light-shielding cover 10, the high-intensity light 11 and the camera 19 can be stored inside the third light-shielding box 9 to reduce storage space.

[0062] Body fatness calculation unit: The weight of the mud crab is measured using an electronic balance, and the length of the carapace is measured using vernier calipers to calculate the body fatness. The carapace length is the horizontal distance from the tip of the foremost serrated tooth to the rearmost end of the carapace. Body fatness = weight / (carapace length) 3 .

[0063] Intelligent Recognition Unit: Camera 9 captures one abdominal photo and two translucent photos of the crab to be judged, which are transmitted to computer software via wired or wireless means. The crab's plumpness level is also input into the software. The software uses a first YOLO model to determine sex-maturity type, plumpness to determine fullness type, a second YOLO model to determine oiliness type, and a third YOLO model to determine ovarian development level, comprehensively determining the crab's grade. Photos with correct judgment results are accumulated in the model training photo set, allowing for periodic retraining and continuous improvement of the model's accuracy.

[0064] The advantages of this device are as follows: The first imaging unit blocks external light interference, using standard white light to accurately capture and record the color of the crab's plastron and articular membranes, which is crucial for distinguishing between immature female crabs and mature female crabs, and for determining their oily type. The second imaging unit blocks external light from entering, ensuring the penetration effect of the strong light 11; the second light-shielding box 8 limits the crab's activity range, and the small, dark, enclosed space allows the crab to lie down comfortably, preventing it from standing upright in defense and thus affecting the imaging. The entire device can be stored in the third light-shielding box 9 for easy portability. The intelligent recognition unit can be continuously optimized and its accuracy improved as the photo set increases.

[0065] This device provides high-quality and accurate image acquisition support for the intelligent identification method of butter crab grades. Conversely, this method also guides the structural design and functional optimization of this device. The two complement each other, rely on each other, and are inseparable in the research and application process, together forming the complete technical system of the intelligent butter crab grade determination method.

[0066] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0067] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method of this application. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0068] It is understood that the content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the methods of this application, and the beneficial effects achieved are the same as those achieved by the methods of this application.

[0069] Please refer to Figure 14, which illustrates the hardware structure of an electronic device according to another embodiment. The electronic device includes: a processor 1401, which can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, for executing related programs to implement the technical solutions provided in the embodiments of this application; and a memory 1402, which can be implemented using a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM), etc. The memory 1402 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1402 and is called and executed by the processor 1401. The input / output interface 1403 is used to implement information input and output. The communication interface 1404 is used to realize communication interaction between this device and other devices. Communication can be realized by wired means (e.g., USB, network cable, etc.) or by wireless means (e.g., mobile network, WIFI, Bluetooth, etc.). The bus 1405 transmits information between the various components of the device (e.g., processor 1401, memory 1402, input / output interface 1403 and communication interface 1404). The processor 1401, memory 1402, input / output interface 1403 and communication interface 1404 are connected to each other within the device through the bus 1405.

[0070] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of this application.

[0071] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0072] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0073] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0074] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0075] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0076] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0078] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0079] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0081] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0082] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0083] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0084] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for intelligently determining the grade of butter crab, characterized in that, The standard white light imaging device used in the method includes a first light-shielding box and a first light-shielding cover. The first light-shielding cover is placed on top of the first light-shielding box, and a standard white light lamp is connected below the first light-shielding cover. The first light-shielding cover has a first through hole. The high-intensity light imaging device used in the method includes a second light-shielding box, a second light-shielding cover, a third light-shielding box, and a high-intensity light lamp. The high-intensity light lamp is placed inside the third light-shielding box. The bottom of the second light-shielding box is connected to the top of the third light-shielding box. The bottom of the second light-shielding box is a transparent plate. The illumination of the high-intensity light lamp is set to shine on the transparent plate and the light direction is adjustable. The second light-shielding cover has a second through hole. The method includes the following steps: placing the crab to be judged in the standard white light imaging device, and using a camera to photograph the abdomen of the crab to be judged under standard white light through the first through hole to obtain the image. The process involves: taking a photograph of the crab's abdomen; placing the crab in a high-intensity light imaging device and using a camera to take photographs of both sides of the crab under the high-intensity light through the second through-hole to obtain corresponding translucent photographs; calculating the crab's plumpness; using a pre-trained first YOLO model to determine the crab's sex and maturity type based on the abdominal photographs; comparing the plumpness with a plumpness threshold to determine the crab's fullness type; using a pre-trained second YOLO model to determine the crab's oiliness type based on the abdominal photographs; using a pre-trained third YOLO model to determine the crab's ovarian development level based on the shape and width of the shadows in the translucent photographs; and finally, determining the crab's grade based on a combination of the sex and maturity type, the fullness type, the oiliness type, and the ovarian development level.

2. The intelligent method for determining the grade of butter crab according to claim 1, characterized in that, The process of using a pre-trained third YOLO model to determine the ovarian development level of the crab to be judged based on the shape and width of the shadow in the translucent photograph to be tested, classifying them into immature ovarian crabs, nascent ovarian crabs, and mature ovarian crabs, includes the following steps: If the pre-trained third YOLO model identifies that the shape of the shadow in the translucent photograph to be tested gradually narrows from the center to both sides, then the ovarian development level of the crab to be judged is determined to be immature ovarian crabs; if the pre-trained third YOLO model identifies that the width of the shadow in the translucent photograph to be tested is uniform and less than a set width threshold, then the ovarian development level of the crab to be judged is determined to be nascent ovarian crabs; if the pre-trained third YOLO model identifies that the width of the shadow in the translucent photograph to be tested is uniform and reaches the set width threshold, then the ovarian development level of the crab to be judged is determined to be mature ovarian crabs.

3. The intelligent method for determining the grade of butter crab according to claim 1, characterized in that, The method of determining the grade of the crab to be judged based on the sex and maturity type, the plumpness type, the oiliness type, and the degree of ovarian development includes the following steps: if the sex and maturity type is male, then the crab to be judged is determined to be male; if the sex and maturity type is immature crab, then the crab to be judged is determined to be immature crab; if the sex and maturity type is mature female, then the crab to be judged is initially determined to be mature female; if the plumpness type of the mature female crab is water crab, then the crab to be judged is determined to be water crab; if the plumpness type of the mature female crab is non-water crab, If the crab to be judged is initially determined to be a normal mature female crab; if the normal mature female crab has no oil, then the crab to be judged is determined to be a common crab; if the normal mature female crab has oil, then the crab to be judged is initially determined to be a yellow butter crab; if the yellow butter crab's ovary development is immature, then the crab to be judged is a full-oil yellow butter crab; if the yellow butter crab's ovary development is early-mature, then the crab to be judged is a head-and-hand yellow butter crab; if the yellow butter crab's ovary development is mature, then the crab to be judged is a roe-oil yellow butter crab.

4. The intelligent method for determining the grade of butter crab according to claim 1, characterized in that, The method further includes the following steps: placing multiple sample crabs in the standard white light imaging device, and using a camera to take pictures of the abdomen of each sample crab through the first through-hole under standard white light to obtain corresponding sample abdominal photos; placing each sample crab in the high-intensity light imaging device, and using a camera to take pictures of both sides of each sample crab through the second through-hole under high-intensity light to obtain corresponding sample translucent photos; calculating the plumpness of each sample crab; determining the sex, maturity type, plumpness type, oiliness type, and ovarian development degree of each sample crab by measurement and dissection; and using the ventral carapace shape in the sample abdominal photos of each sample crab. The first YOLO model is constructed based on the state and color features, as well as the corresponding sex and maturity type of each sample crab. The fullness thresholds for water crabs and non-water crabs are determined using the fullness and corresponding plumpness type of each sample crab. The second YOLO model is constructed using the color of the articular membrane in the abdominal photographs of each sample crab, as well as the corresponding oiliness type. The third YOLO model is constructed using the shape and width of the shadows in the translucent photographs of each sample crab, as well as the corresponding ovarian development level. The first YOLO model, the second YOLO model, and the third YOLO model are then trained.

5. The intelligent method for determining the grade of butter crab according to claim 4, characterized in that, Determining the gender, maturity type, fullness type, oiliness type, and ovarian development degree of each of the sample crabs through measurement and dissection includes the following steps: determining the gender and maturity type according to the shape of the ventral carapace; among them, a long and pointed triangular ventral carapace indicates a male crab, a wide triangular ventral carapace with a lighter color indicates a young crab, and a broad and round ventral carapace with a darker color indicates a mature female crab; determining the oiliness type according to the yellow-blue value b of the swimming leg joint membrane, where a determination of b≥X indicates oiliness, and a determination of b<X indicates no oiliness; where X is a preset oiliness threshold; determining the fullness type according to the condition of the crab body after dissection, where a crab with more water and less meat is a watery crab, and vice versa is a non-watery crab; determining the ovarian development degree according to the ovarian development stage and ovarian index; among them, a determination of ovarian development stage I–II indicates immature ovaries, for individuals with ovarian development reaching stage III and above, the ovarian weight is measured, and the ovarian index is calculated in combination with the body weight, a determination of ovarian index≤Y indicates initial ovarian maturity, and a determination of ovarian index>Y indicates ovarian maturity; where ovarian index = ovarian weight / body weight, and Y is a preset ovarian index threshold.

6. A method for intelligently determining the grade of butter crab according to any one of claims 1 to 5, characterized in that, The method further includes the following steps: regularly retraining the first YOLO model using the test abdominal photos for which the gender and maturity type have been determined to be correctly classified; regularly retraining the second YOLO model using the test abdominal photos for which the oiliness type has been determined to be correctly classified; regularly retraining the third YOLO model using the test translucent photos for which the ovarian development degree has been determined to be correctly classified.

7. A smart device for determining the grade of butter crabs, characterized in that, The device includes: a first photographing unit for placing the crab to be determined in a standard white light photographing device and obtaining a corresponding test abdominal photo by photographing the abdomen of the crab to be determined through the first through hole under standard white light using a camera; a second photographing unit for placing the crab to be determined in a strong light photographing device and obtaining a corresponding test translucent photo by photographing both sides of the crab to be determined through the second through hole under strong light using a camera; a fatness calculation unit for calculating the fatness of the crab to be determined; a gender and maturity type recognition unit for determining the gender and maturity type of the crab to be determined according to the test abdominal photo using a pre-trained first YOLO model; a fullness recognition unit for determining the fullness type of the crab to be determined according to the fatness; an oiliness recognition unit for determining the oiliness type of the crab to be determined according to the test abdominal photo using a pre-trained second YOLO model; an ovarian recognition unit for determining the ovarian development degree of the crab to be determined according to the shape and width of the shadow in the test translucent photo using a pre-trained third YOLO model; a grade classification unit for comprehensively determining the grade of the crab to be determined based on the gender and maturity type, the fullness type, the oiliness type, and the ovarian development degree.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1 to 6 is implemented.

Images