Method, device, terminal and storage medium for sorting based on the size of fruit cores
Through low-field MRI technology imaging and data analysis, the problem of fruit core size detection in fruit sorting is solved, and lossless and accurate fruit core size sorting is achieved, which improves commodity value and production efficiency.
Patent Information
- Application Number
- CN202210038450.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-13
- Publication Date
- 2025-07-25
- Estimated Expiration
- 2042-01-13
AI Technical Summary
The existing fruit sorting technology cannot accurately detect the internal core size of the fruit, resulting in a mixture of high-quality varieties and inferior varieties in commercial sales, affecting commodity prices.
The fruit is imaged through low-field magnetic resonance technology, the images of the flesh and core are obtained, the area or volume ratio is calculated, and the size ratio interval of the fruit category is combined to achieve the sorting of the core size.
It realizes lossless and accurate core size sorting, improves commodity value and production efficiency, reduces dependence on chemical reagents, and has strong safety.
Smart Images
Figure CN114387256B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of sorting, and particularly to a method, device, terminal and storage medium for sorting based on the size of fruit pits. Background Art
[0002] Litchi is a seasonal fruit in the south and one of the four major fruits in the south. There are many varieties; for different varieties of litchi, the fruit pits are of different sizes, and the price difference can be as high as 10 times. However, it is difficult for ordinary people to distinguish different varieties based on the appearance. In commercial sales, if cheap varieties with large fruit pits are mixed in high-quality varieties, it is unfavorable to consumers. In addition, for the same variety of litchi, there are also degenerated seedless fruits. For these small-pit fruits, if they can be effectively sorted, the commodity price can be appropriately increased. Therefore, rapid and efficient sorting of fruit pit sizes is also a key process in the fruit processing production line.
[0003] Current fruit sorting technologies mainly sort fruits based on fruit size, color, weight, and surface damage, respectively using industrial cameras, color recognition sensors, weight detection sensors, or cooperating with vision devices to collect the shape, size, color, and weight of fruits as the measurement basis for fruit sorting. However, these are only detections and sorting based on the external quality of fruits. Since the fruit pit is inside the fruit, these current methods cannot accurately detect the size of the fruit pit inside the fruit and sort based on the size of the fruit pit. Summary of the Invention
[0004] In view of this, the present invention proposes a method, device, terminal and storage medium for sorting based on the size of fruit pits to solve the problems in the prior art.
[0005] Specifically, the present invention proposes the following specific embodiments:
[0006] An embodiment of the present invention proposes a method for sorting based on the size of fruit pits, including:
[0007] Performing imaging on the fruit to be detected through low-field nuclear magnetic resonance to obtain an image of the pulp part and an image of the fruit pit part in the fruit to be detected;
[0008] Determining the ratio of the pulp part to the fruit pit part in the fruit to be detected based on the image; the ratio includes an area ratio or a volume ratio;
[0009] Determining the size of the fruit pit through the ratio and a size ratio interval corresponding to the category of the fruit to be detected;
[0010] Sorting the fruit to be detected based on the size of the fruit pit.
[0011] In a specific embodiment, different categories correspond to their respective size ratio intervals.
[0012] In a specific embodiment, the categories of the fruits to be detected include: litchi, longan, cherry, plum, mango, apricot, and peach.
[0013] In a specific embodiment, the fruits to be detected include the original fruit state and the peeled state;
[0014] The step of "imaging the fruits to be detected by low-field nuclear magnetic resonance to obtain the images of the pulp part and the pit part of the fruits to be detected" includes:
[0015] Injecting the fruits to be detected in the original fruit state or the peeled state;
[0016] Imaging a preset cross-section of the injected fruits to be detected by low-field nuclear magnetic resonance to obtain the images of the pulp part and the pit part of the fruits to be detected; the images include: planar images or three-dimensional images; the preset cross-section includes two mutually perpendicular planes or a plurality of uniformly distributed parallel planes.
[0017] In a specific embodiment, different categories correspond to their respective low-field nuclear magnetic resonance imaging parameters;
[0018] The step of "imaging the fruits to be detected by low-field nuclear magnetic resonance" includes:
[0019] Determining the category of the fruits to be detected;
[0020] Determining the low-field nuclear magnetic resonance imaging parameters corresponding to the category;
[0021] Performing low-field nuclear magnetic resonance on the fruits to be detected by the determined low-field nuclear magnetic resonance imaging parameters to image the fruits to be detected.
[0022] In a specific embodiment, the low-field nuclear magnetic resonance imaging parameters include: number of scan layers, slice thickness, number of repeated samplings, waiting time for repeated samplings, and echo time.
[0023] In a specific embodiment, there are multiple preset region sets, and different region sets correspond to different categories; each region set includes multiple regions, and different regions correspond to different pit sizes;
[0024] The step of "sorting the fruits to be detected based on the size of the pit" includes:
[0025] Sorting the fruits to be detected into the regions corresponding to the category and the pit size based on the size of the pit and the category of the fruits to be detected.
[0026] An embodiment of the present invention also provides a sorting device based on the size of the pit, including:
[0027] An imaging module, configured to image a fruit to be detected by low-field nuclear magnetic resonance to obtain an image of the pulp part and an image of the pit part in the fruit to be detected;
[0028] A ratio module, configured to determine the ratio of the pulp part to the pit part in the fruit to be detected based on the image; the ratio includes an area ratio or a volume ratio;
[0029] A determination module, configured to determine the size of the pit through the ratio and a size ratio interval corresponding to the category of the fruit to be detected;
[0030] A sorting module, configured to sort the fruit to be detected based on the size of the pit.
[0031] An embodiment of the present invention further provides a terminal, including a memory and a processor, where the memory stores a computer program, and the processor runs the computer program to cause the processor to execute the above method for sorting based on the size of the pit.
[0032] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above method for sorting based on the size of the pit is implemented.
[0033] Therefore, an embodiment of the present invention provides a method, device, terminal and storage medium for sorting based on the size of the pit. The method includes: imaging a fruit to be detected by low-field nuclear magnetic resonance to obtain an image of the pulp part and an image of the pit part in the fruit to be detected; determining the ratio of the pulp part to the pit part in the fruit to be detected based on the image; the ratio includes an area ratio or a volume ratio; determining the size of the pit through the ratio and a size ratio interval corresponding to the category of the fruit to be detected; sorting the fruit to be detected based on the size of the pit. This solution utilizes the characteristics that the pulp of the fruit to be detected contains a lot of water while the pit is waterless, and the signal of the pit cannot be detected or the signal is weak in a low-field nuclear magnetic resonance instrument. Through imaging technology and data analysis, the size of the pit and the ratio of the pit to the pulp are determined, so as to perform effective screening, realize non-destructive sorting of the pit size, without using chemical reagents, with a low nuclear magnetic field strength and no radiation, and strong safety. This solution can be applied to a fruit processing production line to accurately grade and sort fruits, which can improve the commercial value; at the same time, it can improve the rate of pit removal processing and production efficiency, and is beneficial to the reformation of fruit processing equipment and the accurate adjustment of the production line. Description of the Drawings
[0034] To more clearly illustrate the technical solution of the present invention, the accompanying drawings required in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the protection scope of the present invention. In each drawing, similar components are numbered similarly.
[0035] Figure 1 Fig. shows a schematic flow chart of a method for sorting based on the size of fruit kernels proposed in an embodiment of the present invention;
[0036] Figure 2 Fig. shows the low-field nuclear magnetic resonance imaging images of whole litchi fruits of various categories obtained by a method for sorting based on the size of fruit kernels proposed in an embodiment of the present invention and the comparison diagrams after their physical cutting;
[0037] Figure 3 Fig. shows the low-field nuclear magnetic resonance imaging images of whole longan fruits obtained by a method for sorting based on the size of fruit kernels proposed in an embodiment of the present invention;
[0038] Figure 4 Fig. shows the low-field nuclear magnetic resonance imaging images of whole cherry fruits obtained by a method for sorting based on the size of fruit kernels proposed in an embodiment of the present invention;
[0039] Figure 5 Fig. shows a schematic structural diagram of a device for sorting based on the size of fruit kernels proposed in an embodiment of the present invention.
[0040] Legend:
[0041] 201 - imaging module; 202 - ratio module; 203 - determination module; 204 - sorting module. Detailed implementation manners
[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of the embodiments.
[0043] The components of the embodiments of the present invention generally described and illustrated in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.
[0044] As used hereinafter, the terms "comprising", "having" and their cognates that may be used in various embodiments of the present invention are only intended to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as precluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or as precluding the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.
[0045] In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be construed as indicating or implying relative importance.
[0046] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which various embodiments of the present invention pertain. The terms (such as those defined in commonly used dictionaries) will be construed to have the same meaning as the contextual meaning in the relevant technical field and will not be construed to have an idealized meaning or an overly formal meaning unless clearly defined in various embodiments of the present invention.
[0047] Embodiment 1
[0048] Embodiment 1 of the present invention discloses a method for sorting based on the size of fruit cores, as Figure 1 shown, including the following steps:
[0049] Step S101: Image the fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the fruit core part in the fruit to be detected; specifically, the images of the pulp part and the fruit core part can be planar images or three-dimensional images (specific three-dimensional images can be composed of multiple planar images).
[0050] Specifically, the principle of low-field nuclear magnetic resonance technology is to apply a radio frequency pulse to a sample in a constant magnetic field (below 1T), causing hydrogen protons to resonate, resulting in some low-energy hydrogen protons absorbing energy and transitioning to high-energy states. When the radio frequency pulse is turned off, these protons release the absorbed radio frequency waves in a non-radiative form, and the energy returns to the ground state to reach Boltzmann equilibrium. This process is called the relaxation process, and the time constant for completing the relaxation process is called the relaxation time.
[0051] There are obvious differences in the water content and state between the pulp and the fruit core in fruits. The pulp has a higher water content, mainly consisting of immobilized water and free water, while only a small amount of water in the fruit core exists in the form of bound water. Therefore, the hydrogen protons of water molecules inside the fruit have different relaxation times under low-field nuclear magnetic resonance. The differences in these relaxation times are recorded, located, and digitized by electrical signals, and after computer processing, they become nuclear magnetic resonance images.
[0052] In addition, in a specific embodiment, depending on the type of fruit, the fruit to be detected includes the original fruit state and the peeled state. Thus, the step of "imaging the fruit to be detected by low-field nuclear magnetic resonance to obtain the images of the pulp part and the pit part of the fruit to be detected" in step S101 includes: injecting the fruit to be detected in the original fruit state or the peeled state; imaging a preset cross-section of the injected fruit to be detected by low-field nuclear magnetic resonance to obtain the images of the pulp part and the pit part of the fruit to be detected; the images include: planar images or three-dimensional images; the preset cross-section includes two mutually perpendicular planes or a plurality of uniformly distributed parallel planes.
[0053] Specifically, the injection can be carried out through a pipeline. Generally, if the injection is in the original fruit state, then all the fruits to be detected in a batch are injected in the original fruit state; if the injection is in the peeled state, then all the fruits to be detected in a batch are injected in the peeled state.
[0054] Specifically, for example, the entire fruit to be detected can be imaged, or certain cross-sections of the fruit to be detected can be imaged. The specific cross-sections can be two or more mutually perpendicular cross-sections, such as a vertical plane and a horizontal plane, or a plurality of parallel planes of the fruit to be detected can be imaged. The specific plurality of parallel planes can be a plurality of vertical planes or a plurality of horizontal planes. In this way, planar images can be obtained. When the parallel planes are dense enough, a three-dimensional image can be obtained by summarizing the plurality of parallel planes.
[0055] Furthermore, different categories correspond to their respective low-field nuclear magnetic resonance imaging parameters; the step of "imaging the fruit to be detected by low-field nuclear magnetic resonance" in step S101 includes: determining the category of the fruit to be detected; determining the low-field nuclear magnetic resonance imaging parameters corresponding to the category; performing low-field nuclear magnetic resonance on the fruit to be detected by the determined low-field nuclear magnetic resonance imaging parameters to image the fruit to be detected.
[0056] The low-field nuclear magnetic resonance imaging parameters include: the number of scanning layers, layer thickness, number of repeated samplings, waiting time for repeated samplings, and echo time.
[0057] In a specific embodiment, when collecting low-field nuclear magnetic resonance imaging data, the values and ranges of the parameters can be: the number of scanning layers is 1 - 30; the layer thickness is 0.05 - 50 mm; the number of repeated samplings is 2 - 100; the waiting time for repeated samplings is 100 - 10,000 ms; the echo time is 1 - 100 ms.
[0058] Step S102: Determine the ratio of the pulp part to the pit part in the fruit to be detected based on the image; the ratio includes the area ratio or the volume ratio;
[0059] Based on the processing of the image, the ratio between the image of the pulp part and the pit part in the fruit to be detected can be obtained. For example, when processing a planar image, the obtained ratio is the area ratio; if processing a three-dimensional image, the obtained ratio is the volume ratio.
[0060] Step S103: Determine the size of the pit based on the ratio and the size ratio interval corresponding to the category of the fruit to be detected;
[0061] Furthermore, the categories of the fruit to be detected include: litchi, longan, cherry, plum, mango, apricot, and peach.
[0062] In this case, each of the different categories corresponds to its own size ratio interval.
[0063] For example, for litchi, taking the area ratio as an example for illustration, the size ratio interval can be: if the area ratio of the pulp to the pit is greater than 9, it is determined as a small pit; if the area ratio of the pulp to the pit is 3 - 9, it is determined as a medium-sized pit; if the area ratio of the pulp to the pit is less than 3, it is determined as a large pit.
[0064] For other categories of fruits, their own size ratio intervals can be correspondingly set.
[0065] Step S104: Sort the fruit to be detected based on the size of the pit.
[0066] In addition, there are multiple preset area sets, and different area sets correspond to different categories; each area set includes multiple areas, and different areas correspond to different pit sizes; thus, the "sorting the fruit to be detected based on the size of the pit" includes: sorting the fruit to be detected into the area corresponding to the category and the pit size based on the size of the pit and the category of the fruit to be detected.
[0067] Specifically, generally, the sorting of one batch is for fruits of the same category. For example, for longan, sorting is carried out; however, this solution can also sort multiple different categories of fruits in one batch. Specifically, by setting different area sets, and each area set includes multiple areas to correspond to fruits with different pit sizes under different categories.
[0068] Embodiment 2
[0069] In a specific embodiment, taking litchi as an example to illustrate this solution, it specifically includes the following steps:
[0070] a. Raw material feeding: Feeding the original litchi fruits;
[0071] b. Low-field nuclear magnetic resonance imaging data acquisition: Number of layers = 1; Slice thickness = 2.5 mm; Field of view FOV = 100 mm × 100 mm; Number of repeated samplings Average = 2; Repetition time TR = 2000.00 ms; Echo time TE = 18.125 ms.
[0072] c. Data analysis: Calculate the area ratio of pulp and pit after imaging;
[0073] d. Sorting: Sort the fruits according to the designed area ratio of pulp and pit. Among them, if the area ratio of pulp and pit is greater than 9, it is determined as a small pit; if the area ratio of pulp and pit is 3 - 9, it is determined as a medium pit; if the area ratio of pulp and pit is less than 3, it is determined as a large pit.
[0074] Specifically, as Figure 2 shown, it is the low-field nuclear magnetic resonance imaging image of the whole litchi fruits of various types and the comparison diagram after the actual fruits are cut. It can be seen that the size of the pit can be accurately judged in this scheme.
[0075] Example 3
[0076] In a specific embodiment, taking longan as an example to illustrate this scheme, it specifically includes the following steps:
[0077] a. Raw material injection: Inject the original longan fruits;
[0078] b. Low-field nuclear magnetic resonance imaging data acquisition: Number of layers = 1; Slice thickness = 2.5 mm; Field of view FOV = 100 mm × 100 mm; Number of repeated samplings Average = 2; Repetition time TR = 2000.00 ms; Echo time TE = 18.125 ms. The obtained image is as Figure 3 shown.
[0079] c. Data analysis: Calculate the area ratio of pulp and pit after imaging;
[0080] d. Sorting: Sort the fruits according to the designed area ratio of pulp and pit.
[0081] Example 4
[0082] In a specific embodiment, taking cherry as an example to illustrate this scheme, it specifically includes the following steps:
[0083] Raw material injection: Inject the original cherry fruits;
[0084] b. Low-field nuclear magnetic resonance imaging data acquisition: Number of layers = 1; Slice thickness = 2.5 mm; Field of view FOV = 100 mm × 100 mm; Number of repeated samplings Average = 4; Repeated sampling waiting time TR = 1000.00 ms; Echo time TE = 18.125 ms. The obtained image is as Figure 4 shown.
[0085] c. Data analysis: Calculate the area ratio of the pulp and the pit in the imaging result;
[0086] d. Sorting: Sort the fruits according to the area ratio of the pulp and the pit designed by the program.
[0087] Example 5
[0088] For further illustration of the present invention, Example 5 of the present invention also discloses a device for sorting based on the size of the pit, as Figure 5 shown, including:
[0089] Imaging module 201, configured to image the fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the pit part of the fruit to be detected;
[0090] Ratio module 202, configured to determine the ratio of the pulp part to the pit part in the fruit to be detected based on the image; the ratio includes an area ratio or a volume ratio;
[0091] Determination module 203, configured to determine the size of the pit through the ratio and the size ratio range corresponding to the category of the fruit to be detected;
[0092] Sorting module 204, configured to sort the fruit to be detected based on the size of the pit.
[0093] In a specific embodiment, different categories correspond to respective size ratio ranges.
[0094] In a specific embodiment, the categories of the fruit to be detected include: litchi, longan, cherry, plum, mango, apricot, peach, etc.
[0095] In a specific embodiment, the fruit to be detected includes the original fruit state and the peeled state;
[0096] The imaging module 201 "images the fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the pit part of the fruit to be detected", including:
[0097] Inject the fruit to be detected in the original fruit state or the peeled state;
[0098] Performing imaging on a preset cross-section of the to-be-detected fruit in the sample injection through low-field nuclear magnetic resonance to obtain an image of the pulp part and an image of the pit part in the to-be-detected fruit; the image includes: a planar image or a three-dimensional image; the preset cross-section includes two mutually perpendicular planes or a plurality of uniformly distributed parallel planes.
[0099] In a specific embodiment, different categories correspond to respective low-field nuclear magnetic resonance imaging parameters;
[0100] The imaging module 201 "performs imaging on the to-be-detected fruit through low-field nuclear magnetic resonance", including:
[0101] Determining the category of the to-be-detected fruit;
[0102] Determining the low-field nuclear magnetic resonance imaging parameters corresponding to the category;
[0103] Performing low-field nuclear magnetic resonance on the to-be-detected fruit through the determined low-field nuclear magnetic resonance imaging parameters to perform imaging on the to-be-detected fruit.
[0104] In a specific embodiment, the low-field nuclear magnetic resonance imaging parameters include: the number of scan layers, slice thickness, number of repeated samplings, waiting time for repeated samplings, and echo time.
[0105] In a specific embodiment, there are multiple region sets preset, and different region sets correspond to different categories; each region set includes multiple regions, and different regions have different pit sizes;
[0106] The sorting module 204 is used for:
[0107] Sorting the to-be-detected fruit into a region corresponding to the category and the pit size based on the size of the pit and the category of the to-be-detected fruit.
[0108] Embodiment 6
[0109] Embodiment 6 of the present invention also discloses a terminal, including a memory and a processor, the memory stores a computer program, and the processor runs the computer program to enable the processor to execute the method for sorting based on the pit size described in Embodiment 1.
[0110] Embodiment 7
[0111] Embodiment 7 of the present invention also discloses a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method for sorting based on the pit size described in Embodiment 1.
[0112] Accordingly, the embodiments of the present invention provide a method, device, terminal and storage medium for sorting based on the size of fruit kernels. The method includes: imaging a fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the fruit kernel part in the fruit to be detected; determining the ratio of the pulp part to the fruit kernel part in the fruit to be detected based on the images; the ratio includes an area ratio or a volume ratio; determining the size of the fruit kernel through the ratio and a size ratio interval corresponding to the category of the fruit to be detected; sorting the fruit to be detected based on the size of the fruit kernel. This solution utilizes the characteristics that the pulp of the fruit to be detected contains a lot of water while the fruit kernel is waterless, and the signal of the fruit kernel cannot be detected or is weak in a low-field nuclear magnetic resonance instrument. Through imaging technology and data analysis, the size of the fruit kernel and the ratio of the fruit kernel to the pulp are determined, so as to perform effective screening, realize non-destructive sorting of the fruit kernel size, without using chemical reagents, with a low nuclear magnetic field strength and no radiation, and strong safety. This solution can be applied to a fruit processing production line to accurately grade and sort fruits, which can improve the commercial value; at the same time, it can improve the rate of core removal processing and production efficiency, which is beneficial to the reformation of fruit processing equipment and the accurate adjustment of the production line.
[0113] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and structure diagrams in the drawings show the possible architectures, functions and operations of devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment or a part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks may occur in a different order than marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structure diagram and / or flowchart, as well as the combination of blocks in the structure diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.
[0114] In addition, each functional module or unit in various embodiments of the present invention may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.
[0115] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.
[0116] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention.
Claims
1. A sorting method based on the size of fruit cores, characterized in that, Comprising: Imaging the fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the pit part in the fruit to be detected; Determining the ratio of the pulp part to the pit part in the fruit to be detected based on the images; the ratio includes an area ratio or a volume ratio; Determining the size of the pit through the ratio and the size ratio range corresponding to the category of the fruit to be detected; Sorting the fruit to be detected based on the size of the pit; Wherein, the fruit to be detected includes the original fruit state and the peeled state, and "imaging the fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the pit part in the fruit to be detected" includes: Injecting the fruit to be detected in the original fruit state or the peeled state; Imaging a preset cross-section of the injected fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the pit part in the fruit to be detected; the images include: planar images or three-dimensional images; the preset cross-section includes two mutually perpendicular planes or a plurality of uniformly distributed parallel planes; Different categories correspond to their respective low-field nuclear magnetic resonance imaging parameters, and "imaging the fruit to be detected by low-field nuclear magnetic resonance" includes: Determining the category of the fruit to be detected; Determining the low-field nuclear magnetic resonance imaging parameters corresponding to the category; Performing low-field nuclear magnetic resonance on the fruit to be detected by the determined low-field nuclear magnetic resonance imaging parameters to image the fruit to be detected; There are multiple preset region sets, and different region sets correspond to different categories; each region set includes multiple regions, and different regions correspond to different pit sizes; The "sorting the fruit to be detected based on the size of the pit" includes: Sorting the fruit to be detected into the regions corresponding to the category and the pit size based on the size of the pit and the category of the fruit to be detected.
2. The method according to claim 1, wherein Different categories correspond to their respective size ratio ranges.
3. The method according to claim 1 or 2, characterized in that The categories of the fruit to be detected include: litchi, longan, cherry, plum, mango, apricot and peach.
4. The method according to claim 1, characterized in that, The low-field nuclear magnetic resonance imaging parameters include: number of scan layers, slice thickness, number of repeated samplings, waiting time for repeated samplings, and echo time.
5. A device for sorting based on the size of fruit cores, characterized in that, Comprising: An imaging module for imaging the fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the pit part in the fruit to be detected; A ratio module for determining the ratio of the pulp part to the pit part in the fruit to be detected based on the images; the ratio includes an area ratio or a volume ratio; A determination module for determining the size of the pit through the ratio and the size ratio range corresponding to the category of the fruit to be detected; A sorting module for sorting the fruit to be detected based on the size of the pit; wherein, the fruit to be detected includes the original fruit state and the peeled state, and "imaging the fruit to be detected by low-field nuclear magnetic resonance to obtain images of the pulp part and the pit part in the fruit to be detected" includes: Injecting the fruit to be detected in the original fruit state or the peeled state; Imaging a preset cross-section of the fruit to be detected in the sample by low-field nuclear magnetic resonance to obtain an image of the pulp part and an image of the pit part in the fruit to be detected; the image includes: a planar image or a three-dimensional image; the preset cross-section includes two mutually perpendicular planes or a plurality of uniformly distributed parallel planes; Each of the different categories corresponds to its own low-field nuclear magnetic resonance imaging parameters. The "imaging the fruit to be detected by low-field nuclear magnetic resonance" includes: Determining the category of the fruit to be detected; Determining the low-field nuclear magnetic resonance imaging parameters corresponding to the category; Performing low-field nuclear magnetic resonance on the fruit to be detected by the determined low-field nuclear magnetic resonance imaging parameters to image the fruit to be detected; A plurality of region sets are preset, and different region sets correspond to different categories; each region set includes a plurality of regions, and different regions have different pit sizes; The "sorting the fruit to be detected based on the size of the pit" includes: Sorting the fruit to be detected into the region corresponding to the category and the pit size based on the size of the pit and the category of the fruit to be detected.
6. A terminal, characterized in that, It includes a memory and a processor. The memory stores a computer program, and the processor runs the computer program so that the processor executes the method for sorting based on the pit size as described in any one of claims 1-4.
7. A storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the method for sorting based on the pit size as described in any one of claims 1-4.