Method and device for obtaining corn ear phenotype

Abstract

The application provides a corn ear phenotype acquisition method and device, and belongs to the technical field of image processing, and comprises the following steps: acquiring all edge pixel points of a cross-sectional image of a target ear; determining an angle value of each edge pixel point based on a preset pixel number, wherein the preset pixel number is determined based on a pixel size of the cross-sectional image; generating an ear row connection point of the target ear based on all the angle values, so as to determine an ear row phenotype index of the target ear. The corn ear phenotype acquisition method and device can quickly and automatically extract the ear row number phenotype index of the ear by analyzing and processing a digital image of the cross-sectional surface of the ear, calculating the data of the concave points on the edge of the cross-sectional image of the ear, and greatly reducing the demand for computing resources, improving the real-time performance of the calculation, and realizing online real-time measurement, so that the accuracy of the data can be quickly checked during measurement.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a corn ear phenotype acquisition method and device. BACKGROUND

[0002] The corn ear phenotype index is an important parameter for new variety breeding, and in particular, the ear row number index can directly reflect the grain yield of the ear.

[0003] In recent years, the method of detecting corn ear phenotype index through digital image processing is widely used. In terms of ear row number, after the panoramic image is spliced by using the continuous image sequence of the ear surface, the grain arrangement characteristics are analyzed to calculate the ear row number index of the ear.

[0004] However, the above method needs to obtain a large number of ear surface images, and subsequent image splicing and grain arrangement analysis operations consume a large amount of computing resources, resulting in low calculation efficiency and inability to realize online real-time measurement. SUMMARY

[0005] The corn ear phenotype acquisition method and device provided by the present application solve the defects in the prior art that a large number of ear surface images need to be obtained, subsequent image splicing and grain arrangement analysis operations consume a large amount of computing resources, resulting in low calculation efficiency and inability to realize online real-time measurement, and realize fast and automatic extraction of ear row number phenotype index, greatly reducing the demand for computing resources, improving the real-time calculation, enabling online real-time measurement, and facilitating fast checking of data accuracy during measurement.

[0006] The present application provides a corn ear phenotype acquisition method, comprising:

[0007] obtaining all edge pixel points of a cross-sectional image of a target ear;

[0008] determining an angle value of each edge pixel point based on a preset number of pixels, wherein the preset number of pixels is determined based on the pixel size of the cross-sectional image;

[0009] generating an ear row connection point of the target ear based on all angle values to determine an ear row phenotype index of the target ear.

[0010] According to the corn ear phenotype acquisition method provided by the present application, the generation of the ear row connection point of the target ear based on all angle values comprises:

[0011] determining a position pixel point in all edge pixel points according to the numerical relationship between the angle threshold value and the angle value of each edge pixel point; the position pixel point includes a grain top approximate point and an ear row connection approximate point;

[0012] According to the opening direction of the pixel angle of each position pixel point, an ear row connection approximate point is determined in the position pixel point;

[0013] All the pixel points in the ear row connection pixel point set are clustered to obtain a plurality of clusters;

[0014] According to all the clusters, the ear row connection point is determined.

[0015] According to the corn ear phenotype acquisition method provided by the application, the ear row connection point includes a first type of ear row connection point and a second type of ear row connection point;

[0016] According to all the clusters, the ear row connection point is determined.

[0017] The point with the smallest angle value in each cluster is determined as the first type of ear row connection point;

[0018] The connection point spacing between each adjacent two first type of ear row connection points is determined;

[0019] In the case that there is an abnormal spacing in the connection point spacing, the normal spacing and the abnormal spacing are determined from all the connection point spacings; and the second type of ear row connection point is determined according to the normal spacing and the abnormal spacing.

[0020] According to the corn ear phenotype acquisition method provided by the application, the preset number of pixels includes a first preset number and a second preset number, and the angle value of each edge pixel point is determined based on the preset number of pixels, including:

[0021] Any edge pixel point is determined as a first pixel point;

[0022] Based on the first pixel point, a second pixel point and a third pixel point are determined in the edge pixel points; the first pixel point and the second pixel point are separated by the first preset number of edge pixel points, and the second pixel point and the third pixel point are separated by the second preset number of edge pixel points;

[0023] Based on the first pixel point, the second pixel point and the third pixel point, the angle value of the pixel angle of the second pixel point is determined;

[0024] The angle value of the pixel angle of each edge pixel point is obtained.

[0025] According to the corn ear phenotype acquisition method provided by the application, all the edge pixel points of the cross-sectional image of the target ear are obtained, including:

[0026] The target ear is cut off to obtain the cross-sectional image;

[0027] Determine the edge pixel points of the target ear based on the color difference between the target ear and the background in the cross-sectional image.

[0028] The method for obtaining the phenotype of the corn ear further comprises the following steps after determining the ear row connection points based on all the clusters:

[0029] Determine the number of the ear row connection points as the ear row number of the target ear.

[0030] Take the ear row number as the ear row phenotype index of the target ear.

[0031] The application further provides a device for obtaining the phenotype of the corn ear, which comprises:

[0032] An acquisition module is configured to acquire all the edge pixel points of the cross-sectional image of the target ear.

[0033] A determination module is configured to determine the angle value of each edge pixel point based on a preset pixel number, which is determined based on the pixel size of the cross-sectional image.

[0034] A generation module is configured to generate the ear row connection points of the target ear based on all the angle values, so as to determine the ear row phenotype index of the target ear.

[0035] The application further provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for obtaining the phenotype of the corn ear according to any one of the above embodiments when executing the program.

[0036] The application further provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executable on the processor to implement the method for obtaining the phenotype of the corn ear according to any one of the above embodiments.

[0037] The application further provides a computer program product, which comprises a computer program, and the computer program is executable on the processor to implement the method for obtaining the phenotype of the corn ear according to any one of the above embodiments.

[0038] The method and device for obtaining the phenotype of the corn ear provided by the application can quickly and automatically extract the ear row number phenotype index of the ear by analyzing and processing the digital image of the cross-sectional surface of the ear, calculating the data of the concave points on the edge of the cross-sectional image of the ear, and greatly reducing the demand for computing resources and improving the real-time performance of the calculation, so that online real-time measurement can be realized and the accuracy of the data can be quickly checked during measurement. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0040] Figure 1 is one of the flowcharts of the corn ear phenotype acquisition method provided by the present application;

[0041] Figure 2 is a schematic diagram of the cross-sectional area of the corn ear provided by the present application;

[0042] Figure 3 is another flowchart of the corn ear phenotype acquisition method provided by the present application;

[0043] Figure 4 is a structural schematic diagram of the corn ear phenotype acquisition device provided by the present application;

[0044] Figure 5 is a structural schematic diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0045] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0046] The traditional method counts the number of corn ear rows by artificial counting, which is low in efficiency, poor in precision and high in labor intensity.

[0047] In the acquisition of ear phenotype, the pixel number of the feature region of the image is counted to obtain the length and width indicators of the ear, and the RGB channel value is used to obtain the color indicator of the ear.

[0048] In the description of the present application, it should be understood that the terms "first", "second" and the like are only used for description purpose, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features with "first", "second" and the like can explicitly or implicitly include one or more features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0049] The embodiments of the present application will be described below in combination with Figures 1-5 the corn ear phenotype acquisition method and device provided by the embodiments of the present application.

[0050] The corn ear phenotype acquisition method provided in the embodiments of the present application can be implemented by an electronic device or a software or a functional module or a functional entity capable of implementing the corn ear phenotype acquisition method in the electronic device, and the electronic device in the embodiments of the present application includes but is not limited to a server. It should be noted that the above execution subject does not constitute a limitation on the present application.

[0051] Figure 1 is one of the flowcharts of the corn ear phenotype acquisition method provided in the present application, as shown in Figure 1 includes but is not limited to the following steps:

[0052] First, in step S1, all edge pixel points of the cross-sectional image of the target ear are acquired.

[0053] After the cross-sectional image of the target ear is collected, the cross-sectional image can be binarized to remove the background pixels and the internal pixels of the ear cross section, and only the edge pixel points of the cross-sectional contour are retained.

[0054] Optionally, the acquisition of all edge pixel points of the cross-sectional image of the target ear includes:

[0055] The target ear is cut off to acquire the cross-sectional image;

[0056] Based on the color difference degree between the target ear and the shooting background in the cross-sectional image, the all edge pixel points are determined.

[0057] The corn ear is cut off, the side of the ear exposed on the endosperm is shot by using an image acquisition device, and the lens of the image acquisition device is kept perpendicular to the cross section of the ear when the cross-sectional image is acquired.

[0058] Figure 2 is a schematic diagram of the cross-sectional region of the corn ear provided in the present application, as shown in Figure 2 According to the difference between the color of the ear cross section and the background color, the fixed threshold method is used to remove the background part in the image and retain the ear cross-sectional region, for example, the image background pixel value is 0 and the cross-sectional region pixel value is 255.

[0059] Then, the edge pixel points located on the contour are extracted from the retained ear cross-sectional region.

[0060] According to the corn ear phenotype acquisition method provided in the present application, the image is preliminarily processed to only retain the pixels of the edge part of the ear cross section, thereby greatly reducing the calculation amount of image processing and providing a basis for the acquisition of the ear phenotype.

[0061] Further, in step S2, an angle value of each edge pixel point is determined based on a preset pixel number, which is determined based on a pixel size of the cross-sectional image.

[0062] The preset pixel number is determined based on the pixel size of the cross-sectional image. The larger the pixel of the cross-sectional image, the larger the preset pixel number. The smaller the pixel of the cross-sectional image, the smaller the preset pixel number.

[0063] For example, for a cross-sectional image with a resolution of 5000x4000, the preset pixel number can be set to 100.

[0064] Taking any edge pixel point X as an example, two edge pixel points Y and Z which are spaced apart from the pixel by 100 pixels can be determined in all edge pixel points, and ∠YXZ is determined as the pixel angle of the edge pixel point X.

[0065] Optionally, the preset pixel number includes a first preset number and a second preset number, and the determining of the angle value of each edge pixel point based on the preset pixel number includes:

[0066] determining any edge pixel point as a first pixel point;

[0067] determining a second pixel point and a third pixel point in the edge pixel points based on the first pixel point; the first pixel point and the second pixel point are spaced apart by the first preset number of edge pixel points, and the second pixel point and the third pixel point are spaced apart by the second preset number of edge pixel points;

[0068] determining the angle value of the pixel angle of the second pixel point based on the first pixel point, the second pixel point and the third pixel point;

[0069] obtaining the angle value of the pixel angle of each edge pixel point.

[0070] The first preset number and the second preset number are both determined based on the pixel size of the cross-sectional image. The first preset number and the second preset number can be the same or different.

[0071] Starting from clockwise or counterclockwise, the edge point sequence is formed according to the front and rear adjacency relationship where i=1, 2, …, n, and n is the number of edge pixel points.

[0072] For example, the first preset number is 99, and the second preset number is 100. For the first edge pixel point in the sequence , the 100th edge pixel point is taken as the first pixel point, and the 200th edge pixel point is taken as the second pixel point. For the third pixel, at this point, As the second pixel pixel angle A 100 ,calculate The angle values ​​are calculated and stored in an angle value sequence. Then, all edge pixels are traversed in the same direction, and the angle value of each edge pixel is calculated to obtain the angle value sequence A for each edge pixel. j When calculating the n-100th edge pixel... At that time, extract from the beginning of the sequence. A total of 200 edge pixels are spliced ​​to the end of the sequence, that is... Then, continue until the angle values ​​of the pixel corners of all edge pixels are obtained.

[0073] According to the corn ear phenotype acquisition method provided by the present invention, the pixel angle of each pixel is calculated by determining a preset number of pixels related to pixel resolution, thereby providing a basis for acquiring the ear phenotype.

[0074] Further, in step S3, based on all angle values, the ear row connection points of the target ear are generated to determine the ear row phenotypic index of the target ear.

[0075] Based on the angle value of the pixel angle of each edge pixel, all pixels that may be the row connection points of the ear are selected. Thus, among the selected pixels, all the row connection points of the target ear are determined. The number of row connection points is the number of rows of the target ear, which can be used as the phenotypic index of the row of the target ear.

[0076] Optionally, generating the row connection points of the target ear based on all angle values ​​includes:

[0077] Based on the numerical relationship between the angle threshold and the angle value of each edge pixel, the position pixel is determined among all edge pixels; the position pixel includes the approximate point at the top of the grain and the approximate point connecting the ear rows.

[0078] Based on the opening orientation of the pixel corner of each location pixel, determine the approximate point of the grain connection in the location pixel;

[0079] Cluster all pixels in the set of connected pixels of the grain row to obtain multiple clusters;

[0080] Based on all the clusters, determine the connection points of the ear rows.

[0081] The angle threshold value can be an empirical value determined according to the ear row shape feature of the corn, can be related to the preset pixel number, for example, 120 degrees can effectively separate the points near the ear row connection point, and the numerical relationship between the angle threshold value and the angle value of the edge pixel point can be a size relationship.

[0082] Traverse the angle value sequence A1, A2,..., A j If the angle of the pixel angle of any edge pixel point is less than the angle threshold value 120 degrees, it is considered that the edge pixel point can be located near the ear row connection point or near the kernel top, and the two cases can be distinguished through the opening direction of the pixel angle of the edge pixel point.

[0083] For example, if the opening of the pixel angle of the edge pixel point faces the corn ear, the edge pixel point is a point near the kernel top, which is a kernel top approximate point; on the contrary, if the opening of the pixel angle of the edge pixel point faces away from the corn ear, the edge pixel point is a point near the ear row connection point, which is an ear row connection approximate point. The ear row connection approximate point is retained, and all the kernel top approximate points are removed.

[0084] In all the ear row connection approximate points, each ear row connection point near contains a plurality of points meeting the condition, the ear row connection approximate points near each ear row connection point can be clustered through a clustering algorithm, a plurality of clusters composed of points can be obtained, and in each cluster, the edge pixel point with the smallest angle value is selected as the ear row connection point, and other redundant points are removed, so that there is only one point at each ear row connection.

[0085] According to the corn ear phenotype acquisition method provided by the application, the edge pixel points are screened by using the angle value, and the opening direction of the angle is further screened, and finally the ear row connection point of the corn is obtained, which is simple in calculation and accurate in result.

[0086] Optionally, the ear row connection point includes a first type of ear row connection point and a second type of ear row connection point.

[0087] The ear row connection point is determined according to all the clusters, including:

[0088] The point with the smallest angle value in each cluster is determined as the first type of ear row connection point.

[0089] The connection point spacing between each adjacent two first type of ear row connection points is determined.

[0090] In the case that there is an abnormal spacing in the connection point spacing, the normal spacing and the abnormal spacing are determined from all the connection point spacings; and the second type of ear row connection point is determined according to the normal spacing and the abnormal spacing.

[0091] Wherein, the abnormal interval is obviously close to 2 times or more of other normal intervals.

[0092] Since the kernel distribution of the corn ear often appears irregular, the ear row connection point is not necessarily a concave point, and the ear row connection point may not be obtained through the angle screening method, in view of this situation, the distance of the connection point before all adjacent first type ear row connection points is calculated, and the interval of all connection points is analyzed, if there is an abnormal interval in the connection point interval, the average value of the normal interval is taken as the interval threshold, the multiple relationship of the abnormal interval and the interval threshold is calculated, and the second type ear row connection point in the abnormal interval is determined, and a point is added at the corresponding position. For example, an abnormal interval is 2 times of the interval threshold, and a second type ear row connection point is added at 1 / 2 of the abnormal interval.

[0093] According to the corn ear phenotype acquisition method provided by the application, the complexity of the cross-sectional image of the ear is considered, the data is corrected through the distance threshold, the ear row connection point in the abnormal state is determined, the calculation result is supplemented, the robustness of the calculation method is improved, and the obtained phenotype index is more accurate.

[0094] Optionally, after determining the ear row connection point according to all the clusters, the method further includes:

[0095] The number of the ear row connection points is determined as the number of ear rows of the target ear.

[0096] The number of the ear rows is taken as the ear row phenotype index of the target ear.

[0097] The number of the ear row connection points is equal to the number of ear rows of the corn ear, and the number of ear rows can be taken as the ear row phenotype index of the target ear.

[0098] In addition, the position of the kernel on the cross-sectional image is also located through the position of the ear row connection point, which is helpful for developing other organ phenotype extraction algorithms of kernels, ear shafts and the like.

[0099] The corn ear phenotype acquisition method provided by the application can quickly and automatically extract the ear row number phenotype index of the ear through the analysis and processing of the digital image of the cross section of the ear, greatly reduces the demand for calculation resources, improves the real-time performance of calculation, can realize online real-time measurement, and is convenient for quickly checking the accuracy of data during measurement.

[0100] Figure 3 is a flowchart of the corn ear phenotype acquisition method provided by the application, as shown in Figure 3 includes:

[0101] First, the cross-sectional image of the ear is obtained.

[0102] Secondly, the fruit cluster cross-section image is segmented;

[0103] Next, the angle of the pixel angle of each edge pixel point is calculated;

[0104] Then, the cluster row connection approximation points are positioned;

[0105] Finally, the redundant points are removed, the cluster row connection points are obtained, and the position and number of the cluster row connection points are taken as the cluster row phenotype index of the corn ear.

[0106] The corn ear phenotype acquisition device provided by the present application is described below, and the corn ear phenotype acquisition device described below can be correspondingly referred to the corn ear phenotype acquisition method described above.

[0107] Figure 4 is a structural schematic diagram of the corn ear phenotype acquisition device provided by the present application, as Figure 4 shown, comprising:

[0108] The acquisition module 401 is configured to acquire all edge pixel points of a cross-section image of a target ear;

[0109] The determination module 402 is configured to determine an angle value of each edge pixel point based on a preset pixel number, wherein the preset pixel number is determined based on a pixel size of the cross-section image;

[0110] The generation module 403 is configured to generate cluster row connection points of the target ear based on all angle values, so as to determine a cluster row phenotype index of the target ear.

[0111] During the operation of the device, the acquisition module 401 acquires all edge pixel points of a cross-section image of a target ear; the determination module 402 determines an angle value of each edge pixel point based on a preset pixel number, wherein the preset pixel number is determined based on a pixel size of the cross-section image; and the generation module 403 generates cluster row connection points of the target ear based on all angle values, so as to determine a cluster row phenotype index of the target ear.

[0112] The corn ear phenotype acquisition device provided by the present application can quickly and automatically extract the cluster row number phenotype index of the ear by analyzing and processing the digital image of the cross-section of the ear, calculating the data of the concave points on the edge of the cross-section image that meet the conditions, and calculating the cluster row number, greatly reducing the demand for computing resources, improving the real-time performance of the calculation, realizing online real-time measurement, and facilitating the rapid checking of the accuracy of the data during measurement.

[0113] Figure 5 is a structural schematic diagram of the electronic device provided by the present application, as Figure 5As shown, the electronic device can include a processor 510, a communications interface 520, a memory 530, and a communications bus 540, wherein the processor 510, the communications interface 520, and the memory 530 complete mutual communication through the communications bus 540. The processor 510 can invoke a logical instruction in the memory 530 to execute a corn ear phenotype acquisition method, which includes: acquiring all edge pixel points of a cross-sectional image of a target ear; determining an angle value of each edge pixel point based on a preset pixel number, the preset pixel number being determined based on a pixel size of the cross-sectional image; and generating an ear row connection point of the target ear based on all angle values to determine an ear row phenotype index of the target ear.

[0114] In addition, the logical instruction in the memory 530 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0115] On the other hand, the present application also provides a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the corn ear phenotype acquisition method provided by the above-mentioned methods, which includes: acquiring all edge pixel points of a cross-sectional image of a target ear; determining an angle value of each edge pixel point based on a preset pixel number, the preset pixel number being determined based on a pixel size of the cross-sectional image; and generating an ear row connection point of the target ear based on all angle values to determine an ear row phenotype index of the target ear.

[0116] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the method for obtaining the ear phenotype of a corn ear provided by any of the above methods, and the method comprises: obtaining all edge pixel points of a cross-sectional image of a target ear; determining an angle value of each edge pixel point based on a preset number of pixels, the preset number of pixels being determined based on a pixel size of the cross-sectional image; and generating a row connection point of the target ear based on all angle values to determine a row phenotype index of the target ear.

[0117] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0118] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in terms of contribution to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0119] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for obtaining a phenotype of a maize ear, characterized in that, The method comprises the following steps: obtaining all edge pixel points of a cross-sectional image of a target ear; determining an angle value of each edge pixel point based on a preset pixel number, wherein the preset pixel number is determined based on a pixel size of the cross-sectional image; generating an ear row connection point of the target ear based on all angle values to determine an ear row phenotype index of the target ear; the step of generating the ear row connection point of the target ear based on all angle values comprises: determining a position pixel point in all edge pixel points according to a numerical relationship between an angle threshold and the angle value of each edge pixel point; the position pixel point comprises a grain top approximate point and an ear row connection approximate point; determining the ear row connection approximate point in the position pixel point according to an opening direction of a pixel angle of each position pixel point; performing clustering processing on all pixel points in the ear row connection pixel point set to obtain a plurality of clusters; determining the ear row connection point based on all clusters; the ear row connection point comprises a first type ear row connection point and a second type ear row connection point; the step of determining the ear row connection point based on all clusters comprises: determining a point with the smallest angle value in each cluster as the first type ear row connection point; determining a connection point interval between each adjacent two first type ear row connection points; in the case that there is an abnormal interval in the connection point interval, determining a normal interval and an abnormal interval from all connection point intervals; determining a second type ear row connection point according to the normal interval and the abnormal interval.

2. The method of claim 1, wherein the method is performed on a corn ear phenotype. the preset pixel number comprises a first preset number and a second preset number; the step of determining an angle value of each edge pixel point based on a preset pixel number comprises: determining any edge pixel point as a first pixel point; determining a second pixel point and a third pixel point in the edge pixel point based on the first pixel point; the first pixel point and the second pixel point are separated by the first preset number of edge pixel points, and the second pixel point and the third pixel point are separated by the second preset number of edge pixel points; determining an angle value of a pixel angle of the second pixel point based on the first pixel point, the second pixel point and the third pixel point; obtaining an angle value of a pixel angle of each edge pixel point.

3. The method of claim 1, wherein the method is performed on a corn ear phenotype. the step of obtaining all edge pixel points of a cross-sectional image of a target ear comprises: cutting the target ear to obtain the cross-sectional image; determining all edge pixel points based on a color difference degree of the target ear and a shooting background in the cross-sectional image.

4. The method of claim 1, wherein the method is performed on a corn ear phenotype. after the step of determining the ear row connection point based on all clusters, the method further comprises: determining the number of ear row connection points as the ear row number of the target ear; taking the ear row number as the ear row phenotype index of the target ear.

5. A device for obtaining maize ear phenotypes, using the maize ear phenotype obtaining method as described in claim 1, characterized in that, The method comprises the following steps: an obtaining module, configured to obtain all edge pixel points of a cross-sectional image of a target ear; a determining module, configured to determine an angle value of each edge pixel point based on a preset pixel number, wherein the preset pixel number is determined based on a pixel size of the cross-sectional image; a generating module, configured to generate an ear row connection point of the target ear based on all angle values to determine an ear row phenotype index of the target ear.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method for obtaining the ear phenotype of corn according to any one of claims 1-4 when executing the program.

7. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the method for obtaining the ear phenotype of corn according to any one of claims 1-4 when executed by the processor.

8. A computer program product comprising a computer program, characterized in that, The computer program implements the method for obtaining the ear phenotype of corn according to any one of claims 1-4 when executed by the processor.

Images