Method and device for identifying ambrosia seed species based on ultrasonic scanning microscope technology, terminal equipment and storage medium

Abstract

The invention discloses an ambrosia seed variety identification method and device based on an ultrasonic scanning microscope technology, terminal equipment and a storage medium. The method comprises the following steps: acquiring ultrasonic two-dimensional data of ambrosia seeds to be detected; generating to-be-detected internal three-dimensional contour feature data and to-be-detected external three-dimensional contour feature data of the to-be-detected ambrosia seeds based on the ultrasonic two-dimensional data; performing data matching on the to-be-detected internal three-dimensional contour feature data and the to-be-detected external three-dimensional contour feature data and each known ragweed seed sample in a preset ragweed seed contour database to obtain an internal and external three-dimensional contour feature matching degree set of the to-be-detected ragweed seeds; and based on the internal and external three-dimensional contour feature matching degree set, selecting a category label corresponding to the known ragweed seed sample meeting a preset condition as an identification result of the to-be-detected ragweed seed. According to the method, the body of the to-be-detected ragweed seed is scanned through the ultrasonic technology, and the type of the to-be-detected ragweed seed can be identified under the condition that an original specimen is not damaged.

Description

Technical Field

[0001] This invention relates to the field of ultrasound, and in particular to a method, apparatus, terminal equipment, and storage medium for identifying ragweed seed species based on ultrasonic scanning microscopy. Background Technology

[0002] Existing technologies for identifying ragweed seeds include optical techniques. These techniques use optical principles to obtain the external contour features of ragweed seeds and then compare these features to identify different species. However, these methods have two problems: 1. Ragweed seeds are generally fragile, and their external contour features may be worn away or lost, resulting in incomplete specimens. 2. Some ragweed species cannot be identified solely by external features. For example, perennial ragweed and common ragweed have identical external features. DNA testing is necessary for differentiation. In summary, existing optical identification technologies suffer from low accuracy when identifying ragweed seeds.

[0003] Therefore, there is an urgent need for a ragweed seed identification strategy using ultrasonic scanning technology to solve the problem of low accuracy when using optical identification technology to identify ragweed seeds. Summary of the Invention

[0004] This invention provides a method, apparatus, terminal device, and storage medium for identifying Ragnarok seeds based on ultrasonic scanning microscopy, in order to solve the problem of low accuracy in optical identification technology for Ragnarok seed identification.

[0005] To address the aforementioned problems, one embodiment of the present invention provides a method for identifying Ragdoll seeds based on ultrasonic scanning microscopy, comprising:

[0006] Acquire two-dimensional ultrasonic data of the seeds of the genus *Ragnarökyi* to be tested;

[0007] Based on the ultrasonic two-dimensional data, the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the ragweed seed to be tested are generated.

[0008] The internal and external three-dimensional contour feature data to be tested are matched with each known ragweed seed sample in a pre-defined ragweed seed contour database to obtain the matching degree set of the internal and external three-dimensional contour features of the ragweed seed to be tested; wherein, the ragweed seed contour database includes: species labels corresponding to several known ragweed seed samples, internal three-dimensional contour feature sample data, and external three-dimensional contour feature sample data; the matching degree set of internal and external three-dimensional contour features includes: the matching degree of the internal and external three-dimensional contour features between the ragweed seed to be tested and each known ragweed seed sample.

[0009] Based on the matching degree set of the inner and outer three-dimensional contour features, the species label corresponding to the known ragweed seed sample that meets the preset conditions is selected as the identification result of the ragweed seed to be tested; wherein, the preset conditions are specifically: the matching degree of the inner and outer three-dimensional contour features is greater than or equal to the preset matching degree threshold.

[0010] As an improvement to the above scheme, the acquisition of ultrasonic two-dimensional data of the ragweed seeds to be tested includes:

[0011] The detection and control operations for the ultrasonic transducer are repeated until no reflected wave is received. Then, the ultrasonic two-dimensional images generated by each detection and control operation are summarized to generate ultrasonic two-dimensional data. The actual specimen of the ragweed seed to be tested is located directly below the ultrasonic transducer.

[0012] As an improvement to the above solution, the detection and control operation includes:

[0013] Using a slide table and an encoder, the ultrasonic transducer is controlled to move upwards according to a preset movement threshold. After the movement is completed, the ultrasonic transducer is controlled to emit ultrasonic waves. The encoder is used for distance measurement, and the slide table is used for vertical movement along the support. The slide table, the encoder, and the ultrasonic transducer are fixed together. The ultrasonic transducer stops emitting ultrasonic waves during movement.

[0014] Determine whether the reflected wave of the ultrasonic wave after it has been reflected from the physical specimen is received;

[0015] If so, a two-dimensional ultrasound image is generated based on the reflected wave, and the next detection control operation is executed;

[0016] If not, then stop the detection and control operation.

[0017] As an improvement to the above solution, controlling the ultrasonic transducer to move upward according to a preset movement threshold via a slide table and encoder includes:

[0018] The movement threshold is calculated based on the height of the ragweed seeds to be tested.

[0019] A slide table movement start command is generated based on the movement threshold, and the slide table movement start command is transmitted to the slide table so that the slide table moves upward based on the slide table movement start command; wherein, when the slide table moves, the encoder and the ultrasonic transducer move together with the slide table;

[0020] Receive the movement distance generated by the encoder;

[0021] Determine whether the movement distance is equal to the movement threshold;

[0022] If so, a slide stop command is generated and transmitted to the slide so that the slide can complete the movement based on the slide stop command;

[0023] Otherwise, do nothing.

[0024] As an improvement to the above scheme, the step of generating the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the tested *Ragnarökerii* seed based on the ultrasonic two-dimensional data includes:

[0025] For each two-dimensional ultrasound image in the ultrasound two-dimensional data, the white image region is extracted based on the edge segmentation algorithm;

[0026] Each white image region is combined according to the acquisition order of the two-dimensional ultrasound images to obtain a three-dimensional ultrasound model;

[0027] The internal contour of the ultrasound three-dimensional image is extracted to obtain the internal three-dimensional contour feature data of the object to be measured;

[0028] The external contour of the ultrasound three-dimensional image is extracted to obtain the external three-dimensional contour feature data of the object to be measured.

[0029] As an improvement to the above scheme, the internal and external three-dimensional contour feature matching degree includes: internal three-dimensional contour feature matching degree and external three-dimensional contour feature matching degree; the step of matching the internal three-dimensional contour feature data to be tested and the external three-dimensional contour feature data to be tested with each known ragweed seed sample in a preset ragweed seed contour database to obtain the internal and external three-dimensional contour feature matching degree set of the ragweed seed to be tested includes:

[0030] In the preset ragweed seed contour database, for each known ragweed seed sample: the internal three-dimensional contour feature data to be tested is matched with the internal three-dimensional contour feature sample data of the known ragweed seed samples to calculate the internal three-dimensional contour feature matching degree; and the external three-dimensional contour feature data to be tested is matched with the external three-dimensional contour feature sample data of the known ragweed seed samples to calculate the external three-dimensional contour feature matching degree.

[0031] The matching degree of the inner three-dimensional contour features and the matching degree of the outer three-dimensional contour features between the ragweed seeds to be tested and each known ragweed seed sample are summarized to obtain the set of inner and outer three-dimensional contour feature matching degrees.

[0032] As an improvement to the above scheme, the step of selecting the species label corresponding to a known *Ragnarökeri* seed sample that meets preset conditions based on the matching degree set of the inner and outer three-dimensional contour features, as the identification result of the *Ragnarökeri* seed to be tested, includes:

[0033] In the set of matching degrees of the inner and outer three-dimensional contour features, each matching degree of the inner and outer three-dimensional contour features is judged;

[0034] If the matching degree of the inner three-dimensional contour feature is greater than the matching degree threshold and the matching degree of the outer three-dimensional contour feature is greater than the matching degree threshold, then the identification result of the ragweed seed to be tested is the species label corresponding to the known ragweed seed sample corresponding to the current matching degree of the inner and outer three-dimensional contour features.

[0035] Otherwise, the identification result of the tested ragweed seed is output as unknown.

[0036] Accordingly, one embodiment of the present invention also provides a seed species identification device for the genus Ragweed based on ultrasonic scanning microscopy technology, including: a data acquisition module, a data analysis module, a data matching module, and a result generation module;

[0037] The data acquisition module is used to acquire ultrasonic two-dimensional data of the ragweed seeds to be tested;

[0038] The data analysis module is used to generate the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the ragweed seed to be tested based on the ultrasonic two-dimensional data.

[0039] The data matching module is used to match the internal three-dimensional contour feature data and the external three-dimensional contour feature data to be tested with each known ragweed seed sample in a preset ragweed seed contour database to obtain the internal and external three-dimensional contour feature matching degree set of the ragweed seed to be tested; wherein, the ragweed seed contour database includes: species labels corresponding to several known ragweed seed samples, internal three-dimensional contour feature sample data, and external three-dimensional contour feature sample data; the internal and external three-dimensional contour feature matching degree set includes: the internal and external three-dimensional contour feature matching degree between the ragweed seed to be tested and each known ragweed seed sample.

[0040] The result generation module is used to select the species label corresponding to the known ragweed seed sample that meets the preset conditions based on the inner and outer three-dimensional contour feature matching degree set, and use it as the identification result of the ragweed seed to be tested; wherein, the preset conditions are specifically: the inner and outer three-dimensional contour feature matching degree is greater than or equal to the preset matching degree threshold.

[0041] Accordingly, one embodiment of the present invention also provides a computer terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a method for identifying Ragnarok seed species based on ultrasonic scanning microscopy technology as described in the present invention.

[0042] Accordingly, one embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform a method for identifying Ragweed seed species based on ultrasonic scanning microscopy technology as described in the present invention.

[0043] As can be seen from the above, the present invention has the following beneficial effects:

[0044] This invention provides a method for identifying *Ragnarökerii* seeds based on ultrasonic scanning microscopy. The method involves acquiring two-dimensional ultrasonic data of the *Ragnarökerii* seed to be tested; generating internal and external three-dimensional contour feature data of the seed based on the ultrasonic two-dimensional data; matching the internal and external three-dimensional contour feature data with each known *Ragnarökerii* seed sample in a pre-defined *Ragnarökerii* seed contour database to obtain a matching degree set of the internal and external three-dimensional contour features of the seed to be tested; and selecting the species label corresponding to the known *Ragnarökerii* seed sample that meets preset conditions based on the matching degree set, using this as the identification result of the seed to be tested. This invention uses ultrasonic technology to scan the body of the *Ragnarökerii* seed to be tested, constructs a three-dimensional model based on the obtained ultrasonic two-dimensional data, and matches the three-dimensional model with known *Ragnarökerii* seed samples, thereby enabling the identification of the species of the seed to be tested without damaging the original specimen. Furthermore, this invention uses the internal and external contours of the three-dimensional model as reference factors for matching known ragweed seed samples. Compared with existing technologies that only consider the external features of ragweed seeds, this invention greatly improves the accuracy of optical recognition technology for identifying ragweed seeds. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating a method for identifying Ragnarok seed species based on ultrasonic scanning microscopy technology according to an embodiment of the present invention.

[0046] Figure 2 This is a schematic diagram of a ragweed seed species identification device based on ultrasonic scanning microscopy technology provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of a two-dimensional ultrasound image provided in an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of a two-dimensional ultrasound image provided in another embodiment of the present invention;

[0049] Figure 5 This is a schematic diagram of a terminal device structure provided in an embodiment of the present invention. Detailed Implementation

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0051] Example 1

[0052] See Figure 1 , Figure 1 This is a flowchart illustrating a method for identifying Ragdoll seeds based on ultrasonic scanning microscopy, as provided in an embodiment of the present invention. Figure 1 As shown, this embodiment includes steps 101 to 104, and the specific steps are as follows:

[0053] In this embodiment, ultrasonic scanning microscopy is employed, utilizing the propagation and reflection principles of ultrasound to acquire microscopic images of materials. It emits short-pulse ultrasonic beams and receives the ultrasonic signals reflected back from the material. Based on the propagation speed of ultrasound within the material and the characteristics of the reflected signals, information about the material's internal structure, interfaces, defects, density, etc., can be obtained. This invention uses an ultrasonic transducer to emit ultrasound waves and a detector string to receive them.

[0054] Step 101: Obtain two-dimensional ultrasonic data of the ragweed seeds to be tested.

[0055] In this embodiment, acquiring the ultrasonic two-dimensional data of the ragweed seed to be tested includes:

[0056] The detection and control operations for the ultrasonic transducer are repeated until no reflected wave is received. Then, the ultrasonic two-dimensional images generated by each detection and control operation are summarized to generate ultrasonic two-dimensional data. The actual specimen of the ragweed seed to be tested is located directly below the ultrasonic transducer.

[0057] In this embodiment, the detection and control operation includes:

[0058] Using a slide table and an encoder, the ultrasonic transducer is controlled to move upwards according to a preset movement threshold. After the movement is completed, the ultrasonic transducer is controlled to emit ultrasonic waves. The encoder is used for distance measurement, and the slide table is used for vertical movement along the support. The slide table, the encoder, and the ultrasonic transducer are fixed together. The ultrasonic transducer stops emitting ultrasonic waves during movement.

[0059] Determine whether the reflected wave of the ultrasonic wave after it has been reflected from the physical specimen is received;

[0060] If so, a two-dimensional ultrasound image is generated based on the reflected wave, and the next detection control operation is executed;

[0061] If not, then stop the detection and control operation.

[0062] In one specific embodiment, a specimen of *Ragnarok* seeds to be tested is placed on a tray, directly below an ultrasonic transducer. The ultrasonic transducer emits a 20Hz excitation, forming a first black-and-white two-dimensional image (i.e., the ultrasonic two-dimensional image described in this invention) at a height of 0.01 mm above the tray. Figure 3 As shown; after the ultrasonic transducer raises the movement threshold, a second black-and-white two-dimensional image is formed at the next position, as shown. Figure 4 As shown; each image only shows defect waves and normal waves. Since defect waves are voids, there is no feedback information after the ultrasound is emitted. Since normal waves are solid, feedback information can be received after the ultrasound is emitted. Defect waves are shown in black, and normal waves are shown in white.

[0063] In this embodiment, controlling the ultrasonic transducer to move upward according to a preset movement threshold via a slide table and encoder includes:

[0064] The movement threshold is calculated based on the height of the ragweed seeds to be tested.

[0065] A slide table movement start command is generated based on the movement threshold, and the slide table movement start command is transmitted to the slide table so that the slide table moves upward based on the slide table movement start command; wherein, when the slide table moves, the encoder and the ultrasonic transducer move together with the slide table;

[0066] Receive the movement distance generated by the encoder;

[0067] Determine whether the movement distance is equal to the movement threshold;

[0068] If so, a slide stop command is generated and transmitted to the slide so that the slide can complete the movement based on the slide stop command;

[0069] Otherwise, do nothing.

[0070] In one specific embodiment, the slide can only move up and down reciprocally. When the slide travels an actual distance S, the encoder pulley rotates a certain angle, and this rotation angle is converted into an electrical signal Z. Since the frequency of ultrasound is constant, the height Z of the detection surface changes with the movement of the slide, and can therefore be used as the height parameter Z of the point cloud data. When there is a physical object at a certain point (X,Y) on the detection surface, the detector string can receive the reflected wave, and the three-dimensional coordinates corresponding to (X,Y,Z) contain point cloud data. Conversely, when there is no physical object at a certain point on the detection surface, the detector string does not receive reflected wave information, and there is no point cloud data at that point. By moving the slide up and down, point cloud data on different detection surfaces Z can be obtained. The generated point cloud data can be used to generate two-dimensional ultrasound images or create three-dimensional models.

[0071] In one specific embodiment, the height of the *Ragnanthera* seeds placed on the tray is first measured, and a movement threshold is calculated based on the preset number of ultrasound 2D images required. If 5000 ultrasound 2D images are required, the movement threshold is the height of the *Ragnanthera* seeds divided by 5000.

[0072] Step 102: Generate the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the ragweed seed to be tested based on the ultrasonic two-dimensional data.

[0073] In this embodiment, generating the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the tested *Ragnarökerii* seed based on the ultrasonic two-dimensional data includes:

[0074] For each two-dimensional ultrasound image in the ultrasound two-dimensional data, the white image region is extracted based on the edge segmentation algorithm;

[0075] Each white image region is combined according to the acquisition order of the two-dimensional ultrasound images to obtain a three-dimensional ultrasound model;

[0076] The internal contour of the ultrasound three-dimensional image is extracted to obtain the internal three-dimensional contour feature data of the object to be measured;

[0077] The external contour of the ultrasound three-dimensional image is extracted to obtain the external three-dimensional contour feature data of the object to be measured.

[0078] In this embodiment, for edge-based segmentation methods of black and white images, commonly used algorithms include Canny edge detection, Sobel operator, and Laplacian operator.

[0079] Step 103: Match the internal three-dimensional contour feature data and the external three-dimensional contour feature data to be tested with each known ragweed seed sample in the preset ragweed seed contour database to obtain the internal and external three-dimensional contour feature matching degree set of the ragweed seed to be tested; wherein, the ragweed seed contour database includes: species labels corresponding to several known ragweed seed samples, internal three-dimensional contour feature sample data, and external three-dimensional contour feature sample data; the internal and external three-dimensional contour feature matching degree set includes: the internal and external three-dimensional contour feature matching degree between the ragweed seed to be tested and each known ragweed seed sample.

[0080] In one specific embodiment, this embodiment uses shape matching algorithms to compare the overall shape of the contours, thereby performing data matching. These algorithms can perform matching based on the curvature, curve features, or other shape features of the contours.

[0081] In this embodiment, the internal and external three-dimensional contour feature matching degree includes: internal three-dimensional contour feature matching degree and external three-dimensional contour feature matching degree; the step of matching the internal three-dimensional contour feature data to be tested and the external three-dimensional contour feature data to be tested with each known ragweed seed sample in a preset ragweed seed contour database to obtain the internal and external three-dimensional contour feature matching degree set of the ragweed seed to be tested includes:

[0082] In the preset ragweed seed contour database, for each known ragweed seed sample: the internal three-dimensional contour feature data to be tested is matched with the internal three-dimensional contour feature sample data of the known ragweed seed samples to calculate the internal three-dimensional contour feature matching degree; and the external three-dimensional contour feature data to be tested is matched with the external three-dimensional contour feature sample data of the known ragweed seed samples to calculate the external three-dimensional contour feature matching degree.

[0083] The matching degree of the inner three-dimensional contour features and the matching degree of the outer three-dimensional contour features between the ragweed seeds to be tested and each known ragweed seed sample are summarized to obtain the set of inner and outer three-dimensional contour feature matching degrees.

[0084] In a specific embodiment, the method for identifying ragweed seed species based on ultrasonic scanning microscopy technology described in this application is used to collect internal and external three-dimensional contour feature data of known ragweed seed samples. The collected internal and external three-dimensional contour feature data are then labeled with the species label of the known ragweed seed samples. Finally, the labeled internal and external three-dimensional contour feature data are used to establish a database of internal and external morphological features of ragweed seeds (i.e., the ragweed seed contour database described in this invention) based on the micro-Doppler algorithm.

[0085] It is understandable that all ragweed seeds are obovoid, beaked, without pappus, and have a smooth surface. The seeds are surrounded by involucral bracts, with 6-9 sharp teeth or spiny projections on the upper part. There are approximately 30 known species, including *Ragweed trilobata*, *Ragweed ragweed*, and perennial ragweed. This invention, in addition to external morphological characteristics, primarily distinguishes the internal structural features of the endosperm, embryo, and aleurone layer of each species. For example, the difference between *Ragweed trilobata* and *Ragweed ragweed* lies in the completely different shapes of the endosperm and embryo; *Ragweed trilobata* is larger and has a longer beak. To ensure the accuracy of the ragweed seed profile database, this invention randomly selects more than 50 known ragweed seeds from different storage periods during database training.

[0086] Step 104: Based on the matching degree set of the inner and outer three-dimensional contour features, select the species label corresponding to the known ragweed seed sample that meets the preset conditions as the identification result of the ragweed seed to be tested; wherein, the preset conditions are specifically: the matching degree of the inner and outer three-dimensional contour features is greater than or equal to the preset matching degree threshold.

[0087] In this embodiment, the step of selecting the species label corresponding to a known ragweed seed sample that meets preset conditions based on the inner and outer three-dimensional contour feature matching degree set as the identification result of the ragweed seed to be tested includes:

[0088] In the set of matching degrees of the inner and outer three-dimensional contour features, each matching degree of the inner and outer three-dimensional contour features is judged;

[0089] If the matching degree of the inner three-dimensional contour feature is greater than the matching degree threshold and the matching degree of the outer three-dimensional contour feature is greater than the matching degree threshold, then the identification result of the ragweed seed to be tested is the species label corresponding to the known ragweed seed sample corresponding to the current matching degree of the inner and outer three-dimensional contour features.

[0090] Otherwise, the identification result of the tested ragweed seed is output as unknown.

[0091] In one specific embodiment, the matching threshold can be set by the user according to their needs.

[0092] This embodiment utilizes ultrasonic scanning imaging technology, achieving a target acquisition accuracy of 0.01 mm. More importantly, it simultaneously obtains the internal and external features of the tested object, which is beneficial to improving the accuracy and efficiency of Ragnaröklü seeds identification. During the identification process, data inclusion determination is adopted, successfully solving the problem of incomplete specimens being unidentifiable. By using ultrasonic scanning technology, complete internal features of Ragnaröklü seeds can be obtained without damaging the original specimen, overturning traditional external morphological feature identification and anatomical identification methods.

[0093] See Figure 2 , Figure 2This is a schematic diagram of a ragweed seed species identification device based on ultrasonic scanning microscopy technology according to an embodiment of the present invention, including: a data acquisition module 201, a data analysis module 202, a data matching module 203, and a result generation module 204;

[0094] The data acquisition module is used to acquire ultrasonic two-dimensional data of the ragweed seeds to be tested;

[0095] The data analysis module is used to generate the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the ragweed seed to be tested based on the ultrasonic two-dimensional data.

[0096] The data matching module is used to match the internal three-dimensional contour feature data and the external three-dimensional contour feature data to be tested with each known ragweed seed sample in a preset ragweed seed contour database to obtain the internal and external three-dimensional contour feature matching degree set of the ragweed seed to be tested; wherein, the ragweed seed contour database includes: species labels corresponding to several known ragweed seed samples, internal three-dimensional contour feature sample data, and external three-dimensional contour feature sample data; the internal and external three-dimensional contour feature matching degree set includes: the internal and external three-dimensional contour feature matching degree between the ragweed seed to be tested and each known ragweed seed sample.

[0097] The result generation module is used to select the species label corresponding to the known ragweed seed sample that meets the preset conditions based on the inner and outer three-dimensional contour feature matching degree set, and use it as the identification result of the ragweed seed to be tested; wherein, the preset conditions are specifically: the inner and outer three-dimensional contour feature matching degree is greater than or equal to the preset matching degree threshold.

[0098] It is understood that the above system embodiments correspond to the method embodiments of the present invention, and can realize the method for identifying Ragnarok seed species based on ultrasonic scanning microscopy technology provided by any of the above method embodiments of the present invention.

[0099] This embodiment acquires ultrasonic two-dimensional data of a ragweed seed to be tested; based on the ultrasonic two-dimensional data, it generates internal and external three-dimensional contour feature data of the ragweed seed to be tested; it matches the internal and external three-dimensional contour feature data with each known ragweed seed sample in a preset ragweed seed contour database to obtain a matching degree set of internal and external three-dimensional contour features of the ragweed seed to be tested; based on the matching degree set of internal and external three-dimensional contour features, it selects the species label corresponding to the known ragweed seed sample that meets preset conditions as the identification result of the ragweed seed to be tested. This invention uses ultrasonic technology to scan the body of the ragweed seed to be tested, constructs a three-dimensional model based on the obtained ultrasonic two-dimensional data, and matches the three-dimensional model with known ragweed seed samples, thereby enabling the identification of the species of the ragweed seed to be tested without damaging the original specimen. Furthermore, this invention uses the internal and external contours of the three-dimensional model as reference factors for matching known ragweed seed samples. Compared with existing technologies that only consider the external features of ragweed seeds, this invention greatly improves the accuracy of optical recognition technology for identifying ragweed seeds.

[0100] Example 2

[0101] See Figure 5 , Figure 5 This is a schematic diagram of the terminal device structure provided in an embodiment of the present invention.

[0102] One terminal device in this embodiment includes: a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program, it implements the steps of the various methods for identifying Ragnaröker seed species based on ultrasonic scanning microscopy technology described in the embodiments, for example... Figure 1 The method for identifying Ragdoll seeds based on ultrasonic scanning microscopy is illustrated, including all steps. Alternatively, the processor, when executing the computer program, implements the functions of each module in the above-described device embodiments, for example: Figure 2 The diagram shows all modules of a ragweed seed species identification device based on ultrasonic scanning microscopy.

[0103] In addition, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method for identifying Ragweed seed species based on ultrasonic scanning microscopy as described in any of the above embodiments.

[0104] Those skilled in the art will understand that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the diagram, or combine certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0105] The processor 501 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor 501 is the control center of the terminal device, connecting various parts of the terminal device through various interfaces and lines.

[0106] The memory 502 can be used to store the computer programs and / or modules. The processor 501 implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0107] Wherein, if the modules / units integrated in the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of the various method embodiments described above. Wherein, the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0108] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0109] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for identifying genus *Ragnarökeri* seeds based on ultrasonic scanning microscopy, characterized in that, include: Acquire two-dimensional ultrasonic data of the seeds of the genus *Ragnarökyi* to be tested; Based on the ultrasonic two-dimensional data, the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the ragweed seed to be tested are generated. The internal and external three-dimensional contour feature data to be tested are matched with each known ragweed seed sample in a pre-defined ragweed seed contour database to obtain the matching degree set of the internal and external three-dimensional contour features of the ragweed seed to be tested; wherein, the ragweed seed contour database includes: species labels corresponding to several known ragweed seed samples, internal three-dimensional contour feature sample data, and external three-dimensional contour feature sample data; the matching degree set of internal and external three-dimensional contour features includes: the matching degree of the internal and external three-dimensional contour features between the ragweed seed to be tested and each known ragweed seed sample. Based on the matching degree set of the inner and outer three-dimensional contour features, the species label corresponding to the known ragweed seed sample that meets the preset conditions is selected as the identification result of the ragweed seed to be tested; wherein, the preset conditions are specifically: the matching degree of the inner and outer three-dimensional contour features is greater than or equal to the preset matching degree threshold.

2. The method for identifying Ragdoll seeds based on ultrasonic scanning microscopy as described in claim 1, characterized in that, The acquisition of ultrasonic two-dimensional data of the ragweed seeds to be tested includes: The detection and control operations for the ultrasonic transducer are repeated until no reflected wave is received. Then, the ultrasonic two-dimensional images generated by each detection and control operation are summarized to generate ultrasonic two-dimensional data. The actual specimen of the ragweed seed to be tested is located directly below the ultrasonic transducer.

3. The method for identifying Ragnarok seed species based on ultrasonic scanning microscopy as described in claim 2, characterized in that, The detection and control operations include: Using a slide table and an encoder, the ultrasonic transducer is controlled to move upwards according to a preset movement threshold. After the movement is completed, the ultrasonic transducer is controlled to emit ultrasonic waves. The encoder is used for distance measurement, and the slide table is used for vertical movement along the support. The slide table, the encoder, and the ultrasonic transducer are fixed together. The ultrasonic transducer stops emitting ultrasonic waves during movement. Determine whether the reflected wave of the ultrasonic wave after it has been reflected from the physical specimen is received; If so, a two-dimensional ultrasound image is generated based on the reflected wave, and the next detection control operation is executed; If not, then stop the detection and control operation.

4. The method for identifying Ragdoll seeds based on ultrasonic scanning microscopy as described in claim 3, characterized in that, The step of controlling the ultrasonic transducer to move upward according to a preset movement threshold via a slide table and encoder includes: The movement threshold is calculated based on the height of the ragweed seeds to be tested. A slide table movement start command is generated based on the movement threshold, and the slide table movement start command is transmitted to the slide table so that the slide table moves upward based on the slide table movement start command; wherein, when the slide table moves, the encoder and the ultrasonic transducer move together with the slide table; Receive the movement distance generated by the encoder; Determine whether the movement distance is equal to the movement threshold; If so, a slide stop command is generated and transmitted to the slide so that the slide can complete the movement based on the slide stop command; Otherwise, do nothing.

5. The method for identifying Ragdoll seeds based on ultrasonic scanning microscopy as described in claim 2, characterized in that, The process of generating the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the tested *Ragnarökerii* seed based on the ultrasonic two-dimensional data includes: For each two-dimensional ultrasound image in the ultrasound two-dimensional data, the white image region is extracted based on the edge segmentation algorithm; Each white image region is combined according to the acquisition order of the two-dimensional ultrasound images to obtain a three-dimensional ultrasound model. The internal contour of the ultrasound three-dimensional image is extracted to obtain the internal three-dimensional contour feature data of the object to be measured; The external contour of the ultrasound three-dimensional image is extracted to obtain the external three-dimensional contour feature data of the object to be measured.

6. The method for identifying Ragdoll seeds based on ultrasonic scanning microscopy as described in claim 1, characterized in that, The internal and external three-dimensional contour feature matching degree includes: internal three-dimensional contour feature matching degree and external three-dimensional contour feature matching degree; the step of matching the internal three-dimensional contour feature data to be tested and the external three-dimensional contour feature data to be tested with each known ragweed seed sample in the preset ragweed seed contour database to obtain the internal and external three-dimensional contour feature matching degree set of the ragweed seed to be tested includes: In the preset ragweed seed contour database, for each known ragweed seed sample: the internal three-dimensional contour feature data to be tested is matched with the internal three-dimensional contour feature sample data of the known ragweed seed samples to calculate the internal three-dimensional contour feature matching degree; and the external three-dimensional contour feature data to be tested is matched with the external three-dimensional contour feature sample data of the known ragweed seed samples to calculate the external three-dimensional contour feature matching degree. The matching degree of the inner three-dimensional contour features and the matching degree of the outer three-dimensional contour features between the ragweed seeds to be tested and each known ragweed seed sample are summarized to obtain the set of inner and outer three-dimensional contour feature matching degrees.

7. The method for identifying Ragdoll seeds based on ultrasonic scanning microscopy as described in claim 6, characterized in that, The step of selecting the species label corresponding to a known ragweed seed sample that meets preset conditions based on the matching degree set of the inner and outer three-dimensional contour features, as the identification result of the ragweed seed to be tested, includes: In the set of matching degrees of the inner and outer three-dimensional contour features, each matching degree of the inner and outer three-dimensional contour features is judged; If the matching degree of the inner three-dimensional contour feature is greater than the matching degree threshold and the matching degree of the outer three-dimensional contour feature is greater than the matching degree threshold, then the identification result of the ragweed seed to be tested is the species label corresponding to the known ragweed seed sample corresponding to the current matching degree of the inner and outer three-dimensional contour features. Otherwise, the identification result of the tested ragweed seed will be output as unknown.

8. A device for identifying ragweed seed species based on ultrasonic scanning microscopy, characterized in that, include: Data acquisition module, data analysis module, data matching module, and result generation module; The data acquisition module is used to acquire ultrasonic two-dimensional data of the ragweed seeds to be tested; The data analysis module is used to generate the internal three-dimensional contour feature data and the external three-dimensional contour feature data of the ragweed seed to be tested based on the ultrasonic two-dimensional data. The data matching module is used to match the internal three-dimensional contour feature data and the external three-dimensional contour feature data to be tested with each known ragweed seed sample in a preset ragweed seed contour database to obtain the internal and external three-dimensional contour feature matching degree set of the ragweed seed to be tested; wherein, the ragweed seed contour database includes: species labels corresponding to several known ragweed seed samples, internal three-dimensional contour feature sample data, and external three-dimensional contour feature sample data; the internal and external three-dimensional contour feature matching degree set includes: the internal and external three-dimensional contour feature matching degree between the ragweed seed to be tested and each known ragweed seed sample. The result generation module is used to select the species label corresponding to the known ragweed seed sample that meets the preset conditions based on the inner and outer three-dimensional contour feature matching degree set, and use it as the identification result of the ragweed seed to be tested; wherein, the preset conditions are specifically: the inner and outer three-dimensional contour feature matching degree is greater than or equal to the preset matching degree threshold.

9. A computer terminal device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements a method for identifying Ragnarok seed species based on ultrasonic scanning microscopy as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform a method for identifying Ragweed seed species based on ultrasonic scanning microscopy as described in any one of claims 1 to 7.

Images