Image imaging parameter indexing method, system, device and computer program product
By generating a simulated data set to compare with the target image, iteratively optimizes the negative spherical electron microscope image imaging parameters, solving the problem of time-consuming and labor-intensive and error-free imaging parameter control in the prior art, and achieving efficient and accurate indexing of image imaging parameters. Reduces image distortion.
Patent Information
- Application Number
- CN202411080336.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-07
AI Technical Summary
In the prior art, the control of negative spherical electron microscope image imaging parameters is time-consuming and labor-intensive, and it is prone to manual alignment errors, resulting in image distortion, and lacks an efficient quality evaluation method.
By generating a simulated data set to compare with the target image, setting image imaging parameters iteratively, optimizing imaging parameters using SSIM structure similarity indicators, realizing automated image imaging parameter indexing, reducing artificial errors and reducing image distortion.
Fast and accurate image imaging parameters are realized, the degree of image distortion during negative spherical electron microscopy is reduced, and the error caused by manual comparison is avoided.
Smart Images

Figure CN119090812A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of image processing technology, and in particular to an image imaging parameter indexing method, system, device and computer program product. Background Art
[0002] In the related technology, by using a spherical aberration corrector to adjust the spherical aberration coefficient to a negative value, and combining it with the optimization of overfocus imaging conditions, it is possible to obtain a negative spherical aberration transmission electron microscope image with high imaging quality without losing atomic-level resolution, which greatly improves the contrast of ultra-light elements (such as oxygen) in high-resolution images and provides a way to obtain the microscopic structure information of ultra-light elements.
[0003] However, a certain degree of image distortion will occur in the process of acquiring negative spherical aberration electron microscope images. The degree of image distortion is directly affected by the imaging parameters. Therefore, the control of imaging parameters of negative spherical aberration images is of great significance for the acquisition of high-quality negative spherical aberration images. The simulated image of negative spherical aberration electron microscope images is usually jointly regulated and affected by multiple parameters including sample structure parameters, electron microscope instrument parameters, electron microscope aberration correction degree, and detector parameters.
[0004] At present, the indexation of imaging parameters of negative spherical aberration images is usually based on the repeated comparison of simulated images with a series of control of imaging parameters and experimental images, which is time-consuming and labor-intensive, and there is a certain degree of manual comparison error. Therefore, there is an urgent need for a quality evaluation method specifically for negative spherical aberration electron microscope images for the indexation of imaging parameters of negative spherical aberration electron microscope images. Summary of the invention
[0005] The embodiments of the present invention provide an image imaging parameter indexing method, system, device and computer program product to solve the above technical problems.
[0006] In order to achieve the above objectives, in a first aspect, the present application provides an image imaging parameter indexing method, comprising the following steps:
[0007] Generate a simulated data set according to a preset first image and a preset first label; wherein the simulated data set includes N first images and N first labels in one-to-one correspondence, the first label is crystallographic information, and is used to characterize the parameter value of the manually set image imaging parameter, and N is an integer greater than 1;
[0008] Comparing the simulated data set with a first target image to obtain a second label corresponding to the first image, wherein the second label is used to represent an image structure similarity index between the first target image and the first image;
[0009] Iteratively set the first label according to the first label and the second label to obtain a label database consisting of N second labels;
[0010] The label database is analyzed to obtain at least one second label as a first optimal label and obtain a label value of the first optimal label.
[0011] Furthermore, the first tag includes:
[0012] At least two of the crystallographic information including atomic coordinates, unit cell parameters, orientation of crystal zone axes, Debye-Waller factor, sample thickness, electron gun accelerating voltage, aperture angle, wave function sampling rate, camera modulation contrast function, convergence half angle, degree of mechanical vibration of sample stage, tilt angle, defocus spread, defocus amount, second-order astigmatism coefficient, third-order astigmatism coefficient, coma coefficient and spherical aberration coefficient.
[0013] Furthermore, the step of iteratively setting the first tag according to the first tag and the second tag to obtain a tag database consisting of N second tags includes:
[0014] Obtaining an element sequence of the first tag according to the element composition sorting in the first tag;
[0015] According to a preset iterative setting method and the element sequence, the value range of each element in the element sequence of the first label is set in turn, the Cartesian product between all elements is obtained and the Cartesian product is used as the element sequence set of the first label;
[0016] A second label set corresponding to the feature sequence set is generated according to the second label and the feature sequence set.
[0017] Furthermore, the step of comparing the simulated data set with the first target image to obtain a second label corresponding to the first image one by one includes:
[0018] sorting the first images in the simulation data set to obtain an image sequence;
[0019] According to the image sequence, based on a preset iterative setting method, the first image is sequentially compared with the first target image to obtain a SSIM structural similarity index of each of the first images, wherein the order of the SSIM structural similarity indexes constitutes an index sequence, and the index sequence corresponds to the image sequence one by one;
[0020] The SSIM structural similarity index is used as the second label to form a similarity result data set.
[0021] Furthermore, the iterative setting method comprises the following steps:
[0022] Set N of the first tags, where N is an integer greater than 1;
[0023] Obtaining the corresponding N second tags;
[0024] Obtaining a first label corresponding to a second optimal label among the N second labels, wherein the second optimal label is configured as the second label with the highest value;
[0025] Based on the first label corresponding to the second optimal label, refiningly set X first labels and obtain corresponding X second label values, where X is an integer greater than 1;
[0026] Obtain a first label corresponding to the second best label among the N+X second labels.
[0027] Furthermore, before the step of generating a simulation data set including N first images according to the preset first images and the preset first labels, the method further includes:
[0028] Acquire an original image and preprocess the original image to obtain the first target image;
[0029] Acquire N first labels, wherein the first labels are obtained based on manually performing initial calibration setting on the first target image, and N is an integer greater than 1;
[0030] According to the N first tags, N first images are obtained.
[0031] Furthermore, the step of iteratively setting the first tag according to the first tag and the second tag to obtain a tag database consisting of N second tags includes:
[0032] Analyze the similarity result data set to obtain an analysis result data set, wherein the analysis result data set includes the second label with the best SSIM structural similarity index and corresponding parameter values;
[0033] The parameter value interval is optimized to improve the SSIM structural similarity index;
[0034] When the SSIM structural similarity index iterates to a target value, a crystallographic feature adjustment is performed to obtain the iterated first label and the corresponding second label.
[0035] In a second aspect, the present application provides an image imaging parameter indexing system, comprising:
[0036] A simulation image data set generation module, wherein the simulation image data set generation module is used to generate a simulation data set according to a preset first image and a preset first label, wherein the simulation data set includes N first images and N first labels, each of the first images corresponds to one first label, the first label is crystallographic information, and is used to characterize a parameter value of an artificially set image imaging parameter, and N is an integer greater than 1;
[0037] An image structure similarity comparison module, wherein the image structure similarity comparison module is used to compare the simulated data set with a first target image to obtain a second label corresponding to the first image one by one, wherein the second label is used to characterize an image structure similarity index between the first target image and the first image;
[0038] A loop iteration module, wherein the loop iteration module is used to iteratively set the first label according to the first label and the second label to obtain a label database consisting of N second labels;
[0039] A data result analysis and output module is used to analyze the label database, obtain at least one second label as a first optimal label and obtain a label value of the first optimal label.
[0040] In a third aspect, the present application provides an image imaging parameter indexing device, comprising a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to implement any method described in the first aspect.
[0041] In a fourth aspect, the present application provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any method described in the first aspect are implemented.
[0042] The above technical solution has the following technical effects:
[0043] The present application sets multiple parameter ranges for a preset first image and a first label, quickly generates a simulated data set of changes in a multi-parameter series (i.e., the first label), compares and judges the simulated data set with the experimental image with high precision, obtains a quantitative value of the degree of fit of the simulated image relative to the experimental image (i.e., the second label), and then iterates the imaging parameters to achieve accurate search and screening of the imaging parameters. Finally, the obtained data values are integrated and analyzed to obtain a visualized result, thereby automatically comparing the imaging parameters of the simulated image and the experimental image and completing the indexing of the image imaging parameters, avoiding the errors caused by manual comparison, and reducing the degree of image distortion generated in the process of acquiring negative spherical aberration electron microscope images. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A schematic diagram of a flow chart of an image imaging parameter indexing method according to an embodiment of the present invention;
[0045] Figure 2 A schematic diagram of a flow chart of an image imaging parameter indexing method according to another embodiment of the present invention;
[0046] Figure 3 A schematic diagram of an image imaging parameter indexing method according to another embodiment of the present invention;
[0047] Figure 4 The figure is a schematic diagram of the structure of an image imaging parameter indexing system according to an embodiment of the present invention. DETAILED DESCRIPTION
[0048] To further illustrate the various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, a person of ordinary skill in the art should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.
[0049] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.
[0050] It should be noted that one of the links in the indexing of diffraction data processing is usually the first step, which is to determine the unit cell parameters of the crystal and the position orientation of the crystal during data collection by analyzing the positions of the diffraction points, and use this information to correspond each diffraction point to the grid point in the reciprocal space, so as to prepare for the subsequent collection of the intensity of each reciprocal grid point.
[0051] Embodiment 1:
[0052] An embodiment of a method for indexing image imaging parameters comprises the following steps:
[0053] S1. Generate a simulated data set according to a preset first image and a preset first label; wherein the simulated data set includes N first images and N first labels in one-to-one correspondence, the first label is crystallographic information, and is used to characterize the parameter value of the manually set image imaging parameter, and N is an integer greater than 1;
[0054] Optionally, the first tag includes:
[0055] At least two of the crystallographic information including atomic coordinates, unit cell parameters, orientation of crystal zone axes, Debye-Waller factor, sample thickness, electron gun accelerating voltage, aperture angle, wave function sampling rate, camera modulation contrast function, convergence half angle, degree of mechanical vibration of sample stage, tilt angle, defocus spread, defocus amount, second-order astigmatism coefficient, third-order astigmatism coefficient, coma coefficient and spherical aberration coefficient.
[0056] Optionally, before the step of generating a simulation data set including N first images according to the preset first images and the preset first labels, the method further includes:
[0057] Acquire an original image and preprocess the original image to obtain the first target image;
[0058] Acquire N first labels, wherein the first labels are obtained based on manually performing initial calibration setting on the first target image, and N is an integer greater than 1;
[0059] Obtaining N first images according to the N first labels;
[0060] Specifically, the original image may be a negative spherical aberration transmission electron microscope experimental image image1, and a region of interest ROI1 of a specific size is selected according to the experimental image image1, and in the experimental image, according to the periodicity of the unit cell, as many regions as possible, such as ROI2, ROI3, ROI4, ROI5, etc., which are consistent in size with ROI1 and have the same structure as ROI1, are selected, and after image superposition and noise reduction, a first target image image2 is obtained, and then crystallographic information such as the interplanar spacing in the first target image image2 is measured, and the band axis is indexed according to the obtained crystallographic information, and a cif crystallographic information file with indexed structural parameters (unit cell parameters, crystal band axis, Debye-Waller factor) is output, that is, a first label, and the first label is matched one by one with the first target image image2 to obtain the first image;
[0061] When generating a simulated data set, according to the known electron microscope instrument parameter values (voltage, aperture size, wave function sampling rate, detector modulation transfer function, convergence half angle, etc.) during the experiment, set the initial interval range1 of the image simulation parameter value, use the Cartesian product for multiple parameters, obtain the parameter array and select the cif crystallographic information file for image simulation to obtain the simulated data set data1 of the first image.
[0062] S2. Compare the simulated data set with the first target image to obtain a second label corresponding to the first image, wherein the second label is used to represent an image structure similarity index between the first target image and the first image;
[0063] Optionally, the step of comparing the simulated data set with the first target image to obtain a second label corresponding one-to-one to the first image includes:
[0064] sorting the first images in the simulation data set to obtain an image sequence;
[0065] According to the image sequence, based on a preset iterative setting method, the first image is sequentially compared with the first target image to obtain a SSIM structural similarity index of each of the first images, wherein the order of the SSIM structural similarity indexes constitutes an index sequence, and the index sequence corresponds to the image sequence one by one;
[0066] Using the SSIM structural similarity index as the second label;
[0067] Further optionally, the iterative setting method comprises the following steps:
[0068] Set N of the first tags, where N is an integer greater than 1;
[0069] Obtaining the corresponding N second tags;
[0070] Obtaining a first label corresponding to a second optimal label among the N second labels, wherein the second optimal label is configured as the second label with the highest value;
[0071] Based on the first label corresponding to the second optimal label, refiningly set X first labels and obtain corresponding X second label values, where X is an integer greater than 1;
[0072] Obtain a first label corresponding to the second best label among the N+X second labels.
[0073] Specifically, the simulated data set data1 of the first image is compared with the first target image image2 using the SSIM structural similarity index to obtain a similarity result data set data2 corresponding to the images in the simulated data set data1.
[0074] S3. Iteratively set the first label according to the first label and the second label to obtain a label database consisting of N second labels;
[0075] Optionally, the step of iteratively setting the first tag according to the first tag and the second tag to obtain a tag database consisting of N second tags includes:
[0076] Analyze the similarity result data set data 2 to obtain an analysis result data set, wherein the analysis result data set includes the second label with the best SSIM structural similarity index and corresponding parameter values;
[0077] The parameter value interval is optimized to improve the SSIM structural similarity index;
[0078] When the SSIM structural similarity index iterates to a target value, a crystallographic feature adjustment is performed to obtain the iterated first label and the corresponding second label.
[0079] S4. Analyze the label database, obtain at least one second label as a first optimal label, and obtain a label value of the first optimal label;
[0080] Specifically, outputting at least one SSIM structural similarity index with the highest parameter value and the corresponding parameter value, i.e., the first optimal label, to complete the image imaging parameter indexing of the first target image;
[0081] Optionally, the completed simulation data set can be written into the database. As users continue to enrich the database content by generating simulation data sets under different parameters, when other users use the same parameters, they can directly read the simulation data set in the database for index comparison and analysis, thereby reducing the duplication and redundancy time of the simulation data set and speeding up the data processing progress.
[0082] Embodiment 2:
[0083] Reference Figure 2 , an embodiment of an image imaging parameter indexing method, applied to the quantitative analysis of imaging parameters of DyScO3 atomic-level negative spherical aberration images, comprises the following steps:
[0084] S21, acquiring an original image and preprocessing the original image to obtain the first target image;
[0085] Specifically, refer to Figure 3 , the DyScO3 atomic-level negative spherical aberration image is input as the original image, a region of interest ROI1 of a specific size is selected, and in the experimental image, according to the periodicity of the DyScO3 unit cell, as many regions as possible such as ROI2, ROI3, ROI4, ROI5, etc. with the same size and structure as ROI1 are selected, and the first target image is obtained after image superposition and noise reduction.
[0086] S22, obtaining N first labels, wherein the first labels are obtained based on manually performing initial calibration setting on the first target image, and N is an integer greater than 1;
[0087] Specifically, the crystallographic information such as the interplanar spacing, atomic coordinates, unit cell parameters, and crystal zone axis orientation is measured for the first target image, the zone axis is indexed based on the obtained crystallographic information, and a cif crystallographic information file with indexed structural parameters (unit cell parameters, crystal zone axis, Debye-Waller factor) is output to complete the acquisition of the first label. The number N of the first labels is the same as the number of crystallographic information.
[0088] S23, obtaining N first images according to the N first tags;
[0089] Specifically, by making a one-to-one correspondence between the first labels and the first target images, N first images can be obtained.
[0090] S24, generating a simulated data set according to a preset first image and a preset first label; wherein the simulated data set includes N first images and N first labels in one-to-one correspondence, the first label is crystallographic information, and is used to characterize a parameter value of an artificially set image imaging parameter, and N is an integer greater than 1;
[0091] Specifically, when generating a simulated data set, according to the known electron microscope instrument parameter values (voltage, aperture size, wave function sampling rate, detector modulation transfer function, convergence half angle, etc.) during the experiment, the initial interval range1 of the image simulation parameter value is set, and the Cartesian product is used for multiple parameters to obtain the parameter array and select the cif crystallographic information file for image simulation to obtain the simulated data set data1 of the first image.
[0092] S25, comparing the simulated data set with the first target image to obtain a second label corresponding to the first image one by one, wherein the second label is used to represent an image structure similarity index between the first target image and the first image;
[0093] Specifically, the method for obtaining the preset iteration setting includes:
[0094] Set N of the first tags, where N is an integer greater than 1;
[0095] Obtaining the corresponding N second tags;
[0096] Obtaining a first label corresponding to a second optimal label among the N second labels, wherein the second optimal label is configured as the second label with the highest value;
[0097] Based on the first label corresponding to the second optimal label, refiningly set X first labels and obtain corresponding X second label values, where X is an integer greater than 1;
[0098] Obtain the first label corresponding to the second best label among the N+X second labels;
[0099] Based on the above-mentioned iterative setting method, the first image is compared with the first target image in sequence to obtain the SSIM structural similarity index of each of the first images, wherein the order of the SSIM structural similarity indexes constitutes an index sequence, and the index sequence corresponds to the image sequence one by one;
[0100] The SSIM structural similarity index is used as the second label.
[0101] S26. Analyze the similarity result data set to obtain an analysis result data set, wherein the analysis result data set includes the second label with the best SSIM structural similarity index and corresponding parameter values.
[0102] S27, optimizing the parameter value interval to improve the SSIM structural similarity index;
[0103] Specifically, steps S24 to S26 are repeated to optimize the parameter value interval and improve the SSIM structural similarity index.
[0104] S28, when the SSIM structural similarity index iterates to a target value, performing crystallographic feature adjustment to obtain the iterated first label and the corresponding second label;
[0105] Specifically, in this embodiment, when continuous iterations reach a specific index requirement (0.9), adjustments are made to crystallographic characteristics such as atomic polarization, doping, vacancies and their Debye-Waller factors, a cif file is output, and steps S24 to S27 are repeated.
[0106] S29, analyzing the label database, obtaining at least one second label as a first optimal label and obtaining a label value of the first optimal label;
[0107] Specifically, at least one optimal parameter value corresponding to the SSIM structural similarity index is output to complete the indexation of the image imaging parameters of the first target image.
[0108] Embodiment three:
[0109] The present invention also provides an image imaging parameter indexing system, referring to Figure 4 ,include:
[0110] A simulation image data set generation module, wherein the simulation image data set generation module is used to generate a simulation data set according to a preset first image and a preset first label; wherein the simulation data set includes N first images and N first labels in one-to-one correspondence, wherein the first label is crystallographic information, and is used to characterize a parameter value of an artificially set image imaging parameter, and N is an integer greater than 1;
[0111] An image structure similarity comparison module, wherein the image structure similarity comparison module is used to compare the simulated data set with a first target image to obtain a second label corresponding to the first image one by one, wherein the second label is used to characterize an image structure similarity index between the first target image and the first image;
[0112] A loop iteration module, wherein the loop iteration module is used to iteratively set the first label according to the first label and the second label to obtain a label database consisting of N second labels;
[0113] A data result analysis and output module is used to analyze the label database, obtain at least one second label as a first optimal label and obtain a label value of the first optimal label.
[0114] Embodiment 4:
[0115] The present invention also provides an image imaging parameter indexing device, comprising a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to implement the method described above.
[0116] Further, as an executable solution, the image imaging parameter indexing device can be a computer unit, and the computer unit can be a computing device such as a desktop computer, a notebook, a handheld computer, and a cloud server. The computer unit may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that the composition structure of the above-mentioned computer unit is only an example of a computer unit and does not constitute a limitation on the computer unit. It may include more or less components than the above, or a combination of certain components, or different components. For example, the computer unit may also include input and output devices, network access devices, buses, etc., which are not limited in the embodiments of the present invention.
[0117] Further, as an executable solution, the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer unit, and various interfaces and lines are used to connect the various parts of the entire computer unit.
[0118] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the computer unit by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0119] Embodiment five:
[0120] The present invention also provides a computer program product, including a computer program, which implements the steps of the above method in the embodiment of the present invention when executed by a processor.
[0121] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.
Claims
1. A method for indexing image imaging parameters, characterized in that: The following steps are involved: Generate a simulated data set according to a preset first image and a preset first label; wherein the simulated data set includes N first images and N first labels in one-to-one correspondence, the first label is crystallographic information, and is used to characterize the parameter value of the manually set image imaging parameter, and N is an integer greater than 1; Comparing the simulated data set with a first target image to obtain a second label corresponding to the first image, wherein the second label is used to represent an image structure similarity index between the first target image and the first image; According to the first label and the second label, the first label is iteratively set to obtain a label database consisting of N second labels; The label database is analyzed to obtain at least one second label as a first optimal label and obtain a label value of the first optimal label.
2. The method for indexing image parameters according to claim 1, characterized in that: The first tag includes: At least two of the crystallographic information including atomic coordinates, unit cell parameters, orientation of crystal zone axes, Debye-Waller factor, sample thickness, electron gun accelerating voltage, aperture angle, wave function sampling rate, camera modulation contrast function, convergence half angle, degree of mechanical vibration of sample stage, tilt angle, defocus spread, defocus amount, second-order astigmatism coefficient, third-order astigmatism coefficient, coma coefficient and spherical aberration coefficient.
3. The method for indexing image parameters according to claim 2, characterized in that: The step of iteratively setting the first tag according to the first tag and the second tag to obtain a tag database consisting of N second tags includes: Obtaining an element sequence of the first tag according to the element composition sorting in the first tag; According to a preset iterative setting method and the element sequence, the value range of each element in the element sequence of the first label is set in turn, the Cartesian product between all elements is obtained and the Cartesian product is used as the element sequence set of the first label; A second label set corresponding to the feature sequence set is generated according to the second label and the feature sequence set.
4. The method for indexing image parameters according to claim 1, characterized in that: The step of comparing the simulated data set with the first target image to obtain a second label corresponding to the first image one by one includes: sorting the first images in the simulation data set to obtain an image sequence; According to the image sequence, based on a preset iterative setting method, the first image is sequentially compared with the first target image to obtain a SSIM structural similarity index of each of the first images, wherein the order of the SSIM structural similarity indexes constitutes an index sequence, and the index sequence corresponds to the image sequence one by one; The SSIM structural similarity index is used as the second label to form a similarity result data set.
5. The method for indexing image parameters according to claim 4, characterized in that: The iterative setting method comprises the following steps: Set N of the first tags, where N is an integer greater than 1; Obtaining the corresponding N second tags; Obtaining a first label corresponding to a second optimal label among the N second labels, wherein the second optimal label is configured as the second label with the highest value; Based on the first label corresponding to the second optimal label, refiningly set X first labels and obtain corresponding X second label values, where X is an integer greater than 1; Obtain a first label corresponding to the second best label among the N+X second labels.
6. The method for indexing image parameters according to claim 1, characterized in that: Before the step of generating a simulation data set including N first images according to the preset first images and the preset first labels, the method further includes: Acquire an original image and preprocess the original image to obtain the first target image; Acquire N first labels, wherein the first labels are obtained based on manually performing initial calibration setting on the first target image, and N is an integer greater than 1; According to the N first tags, N first images are obtained.
7. The method for indexing image parameters according to claim 4, characterized in that: The step of iteratively setting the first tag according to the first tag and the second tag to obtain a tag database consisting of N second tags includes: Analyze the similarity result data set to obtain an analysis result data set, wherein the analysis result data set includes the second label with the best SSIM structural similarity index and corresponding parameter values; The parameter value interval is optimized to improve the SSIM structural similarity index; When the SSIM structural similarity index iterates to a target value, a crystallographic feature adjustment is performed to obtain the iterated first label and the corresponding second label.
8. An image imaging parameter indexing system, characterized in that: include: A simulation image data set generation module, wherein the simulation image data set generation module is used to generate a simulation data set according to a preset first image and a preset first label; wherein the simulation data set includes N first images and N first labels in one-to-one correspondence, wherein the first label is crystallographic information, and is used to characterize a parameter value of an artificially set image imaging parameter, and N is an integer greater than 1; An image structure similarity comparison module, the image structure similarity comparison module is used to compare the simulated data set with a first target image to obtain a second label corresponding to the first image one by one, wherein the second label is used to characterize an image structure similarity index between the first target image and the first image; A loop iteration module, the loop iteration module is used to iteratively set the first label according to the first label and the second label to obtain a label database consisting of N second labels; A data result analysis and output module is used to analyze the label database, obtain at least one second label as a first optimal label and obtain a label value of the first optimal label.
9. An image imaging parameter indexing device, characterized in that: The method comprises a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to implement the method according to any one of claims 1 to 7.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Crystal form prediction method and device and electronic equipment
CN113850801A
Enterprise production safety assessment method, system and device and storage medium
CN114444863A
Label classification method and device, electronic equipment and storage medium
CN116433974A
Metric learning prediction of simulation parameters
US20200393840A1
