Image reconstruction method and device based on correlation imaging

Abstract

The present application discloses an image reconstruction method and device based on correlation imaging, which belongs to the field of optical imaging technology. The method includes: obtaining light intensity measurement data corresponding to the target object; establishing the first generation population for image reconstruction of the target object; reconstructing multiple nth generation feasible solutions of the nth generation population according to the light intensity measurement data to obtain multiple nth generation reconstruction solutions; optimizing multiple nth generation reconstruction solutions to obtain the n+1th generation population for image reconstruction of the target object, the n+1th generation population including multiple n+1th generation feasible solutions; when multiple n+1th generation feasible solutions meet the preset end conditions, obtaining a reconstructed image corresponding to the target object according to multiple n+1th generation feasible solutions. This method can alleviate the local optimal problem, and can also improve the global search capability and convergence speed of phase recovery, thereby obtaining good image reconstruction results.

Description

Technical Field

[0001] The present application relates to the field of optical imaging technology, and in particular to an image reconstruction method and device based on correlation imaging. Background Art

[0002] Correlation imaging technology is a lensless imaging technology that obtains the Fourier spectrum of the imaged object by calculating the coherence of the light intensity, obtains the phase information corresponding to the Fourier spectrum, and reconstructs the image of the object by inverse Fourier transform. Correlation imaging technology has the advantages of simple device, high resolution, long imaging distance, and low cost. However, in the actual imaging process, it is difficult to detect the phase information of the Fourier spectrum, which makes it impossible to reconstruct the image of the object by inverse Fourier transform.

[0003] In the related art, a hybrid input output (HIO) method can be used to determine the phase information of the Fourier spectrum. However, the HIO method is prone to the problem of local optimality, so that a good image reconstruction result cannot be obtained. Summary of the invention

[0004] To this end, the present application provides an image reconstruction method and device based on correlation imaging to solve the problem that when the HIO method is used to determine the Fourier spectrum phase, local optimality is easily generated, resulting in the inability to obtain good image reconstruction results.

[0005] In order to achieve the above-mentioned object, the first aspect of the present application provides an image reconstruction method based on correlation imaging, the method comprising:

[0006] Obtaining light intensity measurement data corresponding to a target object, wherein the light intensity measurement data is obtained by measuring a light signal generated by associated imaging of the target object;

[0007] Establishing a first generation population for image reconstruction of the target object, wherein the first generation population includes a plurality of first generation feasible solutions for image reconstruction;

[0008] Reconstructing multiple n-th generation feasible solutions of the n-th generation population according to the light intensity measurement data to obtain multiple n-th generation reconstructed solutions, where n is an integer greater than or equal to 1;

[0009] Optimizing the plurality of n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object, wherein the n+1-th generation population includes a plurality of n+1-th generation feasible solutions;

[0010] In the case that the plurality of the n+1th generation feasible solutions satisfy a preset termination condition, a reconstructed image corresponding to the target object is obtained according to the plurality of the n+1th generation feasible solutions.

[0011] Further, the light intensity measurement data includes measurement spectrum information;

[0012] The step of reconstructing multiple feasible solutions of the nth generation according to the light intensity measurement data to obtain multiple reconstructed solutions of the nth generation includes:

[0013] For the m-th reconstruction of any n-th generation feasible solution, perform Fourier transform on the n-th generation feasible solution to obtain an m-th n-th generation frequency domain feasible solution, where m is an integer greater than or equal to 1, and the m-th n-th generation frequency domain feasible solution includes the m-th n-th generation phase information;

[0014] Obtaining an mth nth generation frequency domain intermediate solution according to the measured spectrum information and the mth nth generation phase information;

[0015] Performing an inverse Fourier transform on the mth nth generation frequency domain intermediate solution to obtain an mth nth generation time domain intermediate solution;

[0016] Applying constraints to a preset support domain of the mth nth generation time-domain intermediate solution to obtain an mth nth generation reconstruction solution;

[0017] When the mth nth generation reconstruction solution satisfies a preset iteration stop condition, the nth generation reconstruction solution is obtained.

[0018] Further, the light source of the associated imaging includes a signal light and a reference light, and the light intensity measurement data includes first light intensity measurement data corresponding to the reference light and second light intensity measurement data corresponding to the signal light;

[0019] The measured spectrum information is spectrum data in the light intensity frequency domain measurement data obtained by performing a correlation operation on the first light intensity measurement data and the second light intensity measurement data.

[0020] Furthermore, the step of optimizing the plurality of n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object includes:

[0021] Determining the individual fitness of each of the n-th generation reconstruction solutions;

[0022] According to the individual fitness, the nth generation reconstruction solution is subjected to selection, mutation and crossover operations to obtain the n+1th generation population for image reconstruction of the target object.

[0023] Furthermore, the determining of the individual fitness of each of the n-th generation reconstruction solutions includes:

[0024] Performing Fourier transform on each of the n-th generation reconstruction solutions respectively to obtain an n-th generation frequency domain reconstruction solution corresponding to the n-th generation reconstruction solution, wherein the n-th generation frequency domain reconstruction solution includes n-th generation frequency spectrum information;

[0025] The individual fitness of each of the n-generation reconstruction solutions is calculated according to the n-generation spectrum information and the measured spectrum information, wherein the measured spectrum information is information obtained according to the spectrum data corresponding to the light intensity measurement data.

[0026] Furthermore, the calculating the individual fitness of each of the n-generation reconstruction solutions according to the n-generation spectrum information and the measured spectrum information includes:

[0027] Spectrum error data is determined according to the n-th generation spectrum information and the measured spectrum information, and the spectrum error data is used as the individual fitness of each of the n-th generation reconstruction solutions.

[0028] Furthermore, the selecting, mutating, and crossover operations are performed on the nth generation reconstruction solutions according to the individual fitness to obtain the n+1th generation population for image reconstruction of the target object, including:

[0029] Selecting two of the n-th generation reconstruction solutions as n-th generation target solutions;

[0030] Performing a difference operation on the two n-th generation target solutions to obtain a difference vector;

[0031] Performing a mutation operation on the nth generation reconstruction solutions except the nth generation target solution in the nth generation population according to the differential vector to obtain a plurality of nth generation mutation solutions;

[0032] Performing a crossover operation on the n-th generation variation solution and the n-th generation target solution to obtain multiple n-th generation crossover solutions;

[0033] According to the individual fitness, the n+1th generation feasible solution constituting the n+1th generation population is selected from the plurality of the nth generation crossover solutions.

[0034] Furthermore, selecting the n+1th generation feasible solution constituting the n+1th generation population from the plurality of the nth generation crossover solutions according to the individual fitness comprises:

[0035] Based on the greedy strategy, according to the individual fitness, multiple nth generation target crossover solutions are selected from the nth generation crossover solutions as the n+1th generation feasible solutions to obtain the n+1th generation population.

[0036] Furthermore, the n-th generation feasible solution is a predicted image of the reconstructed image corresponding to the target object in the time domain, and the n-th generation population is:

[0037] G n = {g k (n,i,j)}

[0038] Among them, G nrepresents the nth generation population, n represents the population generation, n is an integer greater than or equal to 1, g k (n,i,j) represents the nth generation feasible solution, k is used to represent the serial number of the nth generation feasible solution, k is an integer greater than or equal to 1, i and j represent the number of rows and columns of the predicted image corresponding to the nth generation feasible solution, respectively, k The value of (n,i,j) represents the value of the jth node in the i-th row of the predicted image corresponding to the n-th generation feasible solution.

[0039] A second aspect of the present application provides an image reconstruction device based on correlation imaging, the device comprising:

[0040] A measurement data acquisition module is configured to obtain light intensity measurement data corresponding to a target object, wherein the light intensity measurement data is obtained by measuring a light signal generated by associated imaging of the target object;

[0041] A population establishment module is configured to establish a first generation population for image reconstruction of the target object, wherein the first generation population includes a plurality of first generation feasible solutions for image reconstruction;

[0042] A reconstruction module is configured to reconstruct multiple n-th generation feasible solutions of the n-th generation population according to the light intensity measurement data to obtain multiple n-th generation reconstructed solutions, where n is an integer greater than or equal to 1;

[0043] an optimization module configured to optimize the plurality of n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object, wherein the n+1-th generation population includes a plurality of n+1-th generation feasible solutions;

[0044] The image acquisition module obtains a reconstructed image corresponding to the target object according to the multiple n+1 generation feasible solutions when the multiple n+1 generation feasible solutions meet a preset termination condition.

[0045] In order to achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, and one or more of the computer programs are executed by the at least one processor so that the at least one processor can perform the above-mentioned image reconstruction method.

[0046] In order to achieve the above-mentioned purpose, the fourth aspect of the present application provides a computer-readable medium on which a computer program is stored, wherein the computer program implements the above-mentioned image reconstruction method when executed by a processor.

[0047] This application has the following advantages:

[0048] The image reconstruction method and device based on associated imaging provided by the present application first use light intensity measurement data to reconstruct the nth generation feasible solution of the image to be reconstructed, and after obtaining the nth generation reconstruction solution, perform optimization operations such as selection, mutation and crossover to obtain the n+1th generation feasible solution. The above process is iteratively performed until the preset end condition is met, and the iteration is stopped. The reconstructed image is determined based on the current feasible solution, which can not only alleviate the local optimal problem, but also improve the global search capability and convergence speed of phase recovery, thereby obtaining a good image reconstruction result. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide further understanding of the present application and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present application, but do not constitute a limitation to the present application.

[0050] Figure 1 A flowchart of an image reconstruction method based on correlation imaging provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of a correlation imaging system provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of an image reconstruction method based on correlation imaging provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of a processing process of an image reconstruction method based on correlation imaging provided in an embodiment of the present application;

[0054] Figure 5 A block diagram of an image reconstruction device based on correlation imaging provided in an embodiment of the present application;

[0055] Figure 6 A block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The specific implementation of the present application is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present application, and is not used to limit the present application.

[0057] Optical imaging can be applied to medical testing, equipment maintenance and other technical fields. Traditional optical imaging methods generally use the first-order correlation of light fields to obtain information about the target object, such as microscopes and telescopes. In recent years, the combination of quantum physics and imaging technology has spawned a new interdisciplinary subject - quantum imaging, also known as correlation imaging, which uses high-order correlation of light fields to obtain spatial or phase information of the target object to achieve image reconstruction.

[0058] Whether it is traditional optical imaging or emerging correlation imaging, accurate phase information needs to be obtained during image reconstruction. However, existing phase acquisition or phase reconstruction methods are prone to local optimality, thus affecting the image reconstruction results.

[0059] In view of this, the embodiments of the present application provide an image reconstruction method and device based on correlation imaging, which can not only alleviate the local optimal problem, but also improve the global search capability and convergence speed of phase recovery, thereby obtaining good image reconstruction results.

[0060] A first aspect of the present application provides an image reconstruction method based on correlation imaging. Figure 1 The following is a flow chart of an image reconstruction method based on correlation imaging provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0061] Step S101, obtaining light intensity measurement data corresponding to a target object.

[0062] The light intensity measurement data is obtained by measuring the light signal generated by the associated imaging of the target object.

[0063] Step S102: establishing a first generation population for image reconstruction of the target object.

[0064] The first generation population includes multiple first generation feasible solutions for image reconstruction.

[0065] Step S103, reconstructing multiple n-generation feasible solutions of the n-generation population according to the light intensity measurement data to obtain multiple n-generation reconstructed solutions.

[0066] Wherein, n represents the generation of the population, and n is an integer greater than or equal to 1.

[0067] Step S104 , optimizing multiple n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object.

[0068] Among them, the n+1 generation population includes multiple n+1 generation feasible solutions.

[0069] Step S105 : when multiple n+1 generation feasible solutions satisfy a preset termination condition, a reconstructed image corresponding to the target object is obtained according to the multiple n+1 generation feasible solutions.

[0070] In some possible implementations, the end condition is used to indicate stopping the optimization of the reconstructed solution.

[0071] In some embodiments, the termination conditions include the number of iterations reaching a preset iteration threshold, and / or the accuracy of the feasible solution reaching a preset accuracy requirement, and / or the accuracy of the feasible solution no longer improves, etc.

[0072] It should be noted that the above termination conditions are merely examples and are not limited to this in the embodiments of the present application.

[0073] According to an embodiment of the present application, for the nth generation feasible solution of the image to be reconstructed, light intensity measurement data is first used for reconstruction. After the nth generation reconstruction solution is obtained, optimization operations such as selection, mutation and crossover are performed to obtain the n+1th generation feasible solution. The above process is iteratively performed until a preset end condition is met, and the iteration is stopped. The reconstructed image is determined based on the current feasible solution. This can not only alleviate the local optimal problem, but also improve the global search capability and convergence speed of phase recovery, thereby obtaining a good image reconstruction result.

[0074] Figure 2 Schematic diagram of a correlation imaging system provided in an embodiment of the present application. Figure 2 As shown, the correlation imaging system can be divided into a transmitting device, a target object (ie, an imaged object), a receiving device, and a data processing device.

[0075] Among them, the emitting device is a pseudothermal light source, which can be composed of a laser (the wavelength can be 532nm) 201, an aperture 202, a beam expander 203 and a rotating frosted glass sheet 204. The target object 205 is the imaged object. In the present embodiment, the target object is an object with a "hexagonal" perspective structure. Correspondingly, the ideal reconstructed image should also have a "hexagonal" structure. The receiving device includes a filter 206 and a detector 207, wherein the detector 207 can use a charge coupled device (CCD) camera. The data processing device 208 is a device connected to the detector 207, and is used to implement the image reconstruction method of the embodiment of the present application. The data processing device 208 includes various terminals with data processing capabilities such as computers and servers, and the embodiment of the present application does not limit this.

[0076] It should be noted that in some possible implementations, the light intensity measurement data may be collected by different detectors, for example, by using a barrel detector and / or an array detector to perform measurement to obtain the light intensity measurement data.

[0077] In one example, the light source for the associated imaging includes a signal light and a reference light. The signal light is used to illuminate the target object, and the transmitted light or reflected light is collected by a barrel-shaped detector without spatial resolution and the total light intensity value is recorded to obtain the first light intensity measurement data. The reference light is used to provide a reference and is not used to illuminate the target object. After the reference light freely propagates over a certain distance, its intensity distribution information is detected by an array detector with spatial resolution to obtain the second light intensity measurement data.

[0078] In some possible implementations, the nth generation feasible solution is a predicted image of the reconstructed image corresponding to the target object in the time domain, and the nth generation population is:

[0079] G n = {g k (n,i,j)}

[0080] Among them, G n represents the nth generation population, n represents the population generation, n is an integer greater than or equal to 1, g k (n,i,j) represents the nth generation feasible solution, k is used to represent the serial number of the nth generation feasible solution, k is an integer greater than or equal to 1, i and j represent the number of rows and columns of the predicted image corresponding to the nth generation feasible solution, respectively, k The value of (n,i,j) represents the value of the jth node in the i-th row of the predicted image corresponding to the n-th generation feasible solution.

[0081] In some possible implementations, the light intensity measurement data includes measurement spectrum information, and step S103 reconstructs the feasible solution, which can be implemented in the following manner:

[0082] For the mth reconstruction of any nth generation feasible solution, Fourier transform the nth generation feasible solution to obtain an mth nth generation frequency domain feasible solution, where m is an integer greater than or equal to 1, and the mth nth generation frequency domain feasible solution includes the mth nth generation phase information;

[0083] Obtaining an mth nth generation frequency domain intermediate solution according to the measured spectrum information and the mth nth generation phase information;

[0084] Perform inverse Fourier transform on the mth nth generation frequency domain intermediate solution to obtain the mth nth generation time domain intermediate solution;

[0085] Apply constraints to the preset support domain of the mth nth generation time-domain intermediate solution to obtain the mth nth generation reconstruction solution;

[0086] When the mth nth generation reconstruction solution satisfies a preset iteration stop condition, an nth generation reconstruction solution is obtained.

[0087] In other words, for any reconstruction process, the measured spectrum information of the light intensity measurement data is combined with the phase information of the mth nth generation frequency domain feasible solution to obtain the mth nth generation frequency domain intermediate solution, and it is converted into the time domain through the inverse Fourier transform to obtain the mth nth generation time domain intermediate solution, and constraints are imposed on the preset support domain of the mth nth generation time domain intermediate solution to obtain the mth nth generation reconstruction solution. When the mth nth generation reconstruction solution meets the preset iteration stop condition, the iteration is stopped to obtain the nth generation reconstruction solution.

[0088] The iteration stop condition is used to indicate to stop rebuilding the feasible solution.

[0089] In some embodiments, the iteration stopping condition includes the number of iterations reaching a preset iteration number threshold, and / or the accuracy of the reconstructed solution reaching a preset accuracy requirement, and / or the accuracy of the reconstructed solution no longer improves, etc.

[0090] It should be noted that the above iteration stopping conditions are merely examples and are not limited to this in the embodiments of the present application.

[0091] In some possible implementations, step S104 optimizes the reconstruction solution, which can be implemented in the following manner: first, determine the individual fitness of each n-th generation reconstruction solution; second, based on the individual fitness, select, mutate, and crossover operations are performed on the n-th generation reconstruction solution to obtain the n+1-th generation population for image reconstruction of the target object.

[0092] In some possible implementations, individual fitness can be obtained by the following method: first, perform Fourier transform on each n-generation reconstruction solution respectively to obtain an n-generation frequency domain reconstruction solution corresponding to the n-generation reconstruction solution, wherein the n-generation frequency domain reconstruction solution includes n-generation spectrum information; second, calculate the individual fitness of each n-generation reconstruction solution based on the n-generation spectrum information and the measured spectrum information, wherein the measured spectrum information is information obtained based on the spectrum data corresponding to the light intensity measurement data.

[0093] In one example, spectrum error data may be determined according to the n-th generation spectrum information and the measured spectrum information, and the spectrum error data may be used as the individual fitness of each n-th generation reconstruction solution.

[0094] In some possible implementations, the nth generation reconstruction solutions are selected, mutated, and crossovered according to individual fitness to obtain the n+1th generation population for image reconstruction of the target object, which can be implemented in the following manner: two nth generation reconstruction solutions are selected as nth generation target solutions;

[0095] Perform a difference operation on two n-th generation target solutions to obtain a difference vector;

[0096] According to the difference vector, the n-th generation reconstruction solution except the n-th generation target solution in the n-th generation population is mutated to obtain multiple n-th generation mutation solutions;

[0097] Perform a crossover operation on the n-th generation variation solution and the n-th generation target solution to obtain multiple n-th generation crossover solutions;

[0098] According to individual fitness, the n+1th generation feasible solution that constitutes the n+1th generation population is selected from multiple nth generation crossover solutions.

[0099] In some possible implementations, based on individual fitness, the n+1th generation feasible solution constituting the n+1th generation population is selected from multiple nth generation crossover solutions, which can be implemented in the following ways:

[0100] Based on the greedy strategy, according to individual fitness, multiple n-generation target crossover solutions are selected from the n-generation crossover solutions as n+1-generation feasible solutions to obtain the n+1-generation population.

[0101] Figure 3 A schematic diagram of an image reconstruction method based on correlation imaging provided in an embodiment of the present application. Figure 3 , the method comprising:

[0102] Step S301, obtaining light intensity measurement data corresponding to the target object.

[0103] The light intensity measurement data is obtained by measuring the light signal generated by the associated imaging of the target object.

[0104] Step S302: establishing a first generation population for image reconstruction of the target object.

[0105] The first generation population includes multiple first generation feasible solutions for image reconstruction.

[0106] In some possible implementations, the first waiting population may be established randomly or according to preset specified conditions.

[0107] Step S303: Reconstruct the n-th generation feasible solution using the HIO algorithm to obtain the n-th generation reconstructed solution.

[0108] Wherein, n represents the generation of the population, and n is an integer greater than or equal to 1.

[0109] In some possible implementations, the n-th generation feasible solution is reconstructed m times based on the HIO algorithm to obtain the n-th generation reconstructed solution.

[0110] In one example, for the mth reconstruction of any nth-generation feasible solution, the nth-generation feasible solution is first Fourier transformed to obtain the mth-generation frequency domain feasible solution, where m is an integer greater than or equal to 1, and the mth-generation frequency domain feasible solution includes the mth-generation phase information; secondly, based on the measured spectrum information and the mth-generation phase information, the mth-generation frequency domain intermediate solution is obtained (i.e., the strategy spectrum information is combined with the mth-generation phase information to generate a new frequency domain information); then, the mth-generation frequency domain intermediate solution is inverse Fourier transformed to obtain the mth-generation time domain intermediate solution; and, constraints are imposed on the preset support domain of the mth-generation time domain intermediate solution to obtain the mth-generation reconstruction solution; finally, when the mth-generation reconstruction solution satisfies the preset iteration stop condition, the nth-generation reconstruction solution is obtained.

[0111] Step S304, calculating the individual fitness of the n-th generation reconstruction solution.

[0112] In some possible implementations, calculating the individual fitness includes: first, performing Fourier transform on each n-generation reconstruction solution to obtain an n-generation frequency domain reconstruction solution corresponding to the n-generation reconstruction solution, wherein the n-generation frequency domain reconstruction solution includes n-generation spectrum information; then, calculating the spectrum error based on the spectrum information of the n-generation frequency domain reconstruction solution (i.e., the n-generation spectrum information) and the measured spectrum information, and using the spectrum error as the individual fitness of each n-generation reconstruction solution. The measured spectrum information is the spectrum data corresponding to the light intensity measurement data.

[0113] Step S305: mutate the nth generation reconstruction solution based on the improved differential evolution method.

[0114] In some possible implementations, the n-th generation reconstruction solution is mutated using a differential vector. In one example, first, two n-th generation reconstruction solutions are arbitrarily selected as the n-th generation target solutions, and then the two n-th generation target solutions are differentially operated to obtain a differential vector, and finally, the n-th generation reconstruction solutions other than the n-th generation target solution in the n-th generation population are mutated according to the differential vector, thereby obtaining multiple n-th generation mutated solutions.

[0115] Step S306, obtaining the nth generation crossover solution through a crossover operation.

[0116] Among them, the crossover operation is used to generate new individuals that are different from the original individuals in the population to improve the diversity of individuals in the population.

[0117] In some possible implementations, single-point crossover, multi-point crossover, uniform crossover, and arithmetic crossover may be used, which is not limited in the embodiments of the present application.

[0118] Step S307, according to the greedy strategy, select individuals constituting the n+1 generation population from the n generation crossover solution and the n generation reconstruction solution.

[0119] In some possible implementations, based on a greedy strategy, according to individual fitness, the nth generation crossover solution and the nth generation reconstruction solution with better fitness are selected as individuals constituting the n+1th generation population.

[0120] Step S308, determining whether a preset end condition is met.

[0121] Step S309, when the end condition is met, the iterative process ends and the image is reconstructed according to the individuals in the current population.

[0122] After obtaining the n+1th generation population that meets the termination condition, the image can be reconstructed in any manner according to the n+1th generation feasible solution, which is not limited in this embodiment of the present application.

[0123] It should be noted that, when the termination condition is not met, the process returns to step S303 to perform a new round of iteration.

[0124] Figure 4 A schematic diagram of the processing process of an image reconstruction method based on correlation imaging provided in an embodiment of the present application. Figure 4 , the method comprising:

[0125] Step S401: Based on the correlation imaging device, light intensity measurement data of the target object is acquired, and correlation calculation is performed to obtain a light intensity measurement spectrum F(u,v).

[0126] Step S402: using a differential evolution algorithm, globally optimizing the solution space of Fourier spectrum phase recovery, and reconstructing the image based on the optimized solution.

[0127] The specific process includes:

[0128] (I) Establishing the initial population: Randomly generate the initial population G n .

[0129] Among them, G n = {g k (n,i,j)}.

[0130] g k (n,i,j) is the nth generation feasible solution for target image reconstruction, n is the population number (n≥1); k is used to represent the sequence number of the nth generation feasible solution, k=1,2,...,p, p represents the population size. i, j represent the number of rows and columns of the predicted image corresponding to the nth generation feasible solution, respectively, g kThe value of (n,i,j) represents the value of the jth node in the i-th row of the predicted image corresponding to the n-th generation feasible solution.

[0131] (II) Reconstruct the nth generation feasible solution based on the HIO algorithm to obtain the nth generation reconstructed solution.

[0132] The specific process includes:

[0133] (i) For each g k (n,i,j), respectively, in the time domain space and Fourier space (i.e., frequency domain space) to achieve reconstruction. For the mth iterative reconstruction, g k (n,i,j) is denoted as The number of iterative reconstructions is represented by m.

[0134] Will Perform Fourier transform to obtain the corresponding mth nth generation frequency domain feasible solution

[0135]

[0136] Where FFT stands for Fourier transform, It represents the frequency domain feasible solution obtained by reconstructing the kth feasible solution in the nth generation population in the mth iteration.

[0137] (ii) The light intensity measurement spectrum |F(u,v)| The phase information in the mth and nth generation can be combined to obtain the mth and nth generation frequency domain intermediate solution.

[0138]

[0139] (iii) Perform inverse Fourier transform to obtain the mth and nth generation time domain intermediate solution

[0140]

[0141] Among them, FFT -1 represents the inverse Fourier transform.

[0142] (iv) By using the mth nth generation time domain intermediate solution By applying constraints on the preset support domain, the mth and nth generation reconstruction solutions can be obtained.

[0143]

[0144] Wherein, S represents a preset support region, which can be a rectangular region with a size smaller than (i, j), and β is a feedback parameter. The value of β can be determined based on experience or statistical data (for example, β = 0.7).

[0145] After obtaining the mth nth generation reconstruction solution, determine whether the preset iteration stop condition is met according to the mth nth generation reconstruction solution. If it is met, obtain the nth generation reconstruction solution (i.e. ). If it is not satisfied, the mth n-th generation reconstruction solution is used as the initial solution of the next round of iteration process, and a new iteration process is entered until the preset iteration stop condition is met, and the n-th generation reconstruction solution obtained when the iteration is stopped is used as the final n-th generation reconstruction solution, on this basis, the n-th generation reconstruction solution is optimized.

[0146] (III) Calculate individual fitness values.

[0147] The specific process includes:

[0148] Through correlation calculation, the light intensity measurement spectrum F(u,v) and the nth generation frequency domain reconstruction solution are obtained. The absolute error value erf F between the Fourier spectrum (i.e. the nth generation spectrum information) of

[0149]

[0150] (IV) Differential mutation operation: Randomly select 2 solutions from the n-th generation reconstruction solution as the n-th generation target solution, perform differential operation on them, and then perform mutation operation on the n-th generation reconstruction solution in the n-th generation population except the n-th generation target solution based on the differential vector to obtain multiple n-th generation mutation solutions.

[0151] Assume that the two n-th generation objective solutions are and Then the nth generation mutation solution is:

[0152] k≠r1 and k≠r2, where represents the nth generation variation solution, F represents the scaling factor of the differential variation, which generally takes any value between 1 and 2, and k, r1, and r2 are all positive integers not exceeding p.

[0153] (V) Crossover operation: Perform a crossover operation between individuals on the reconstructed solution in the nth generation population.

[0154]

[0155] in, To obtain the nth generation crossover solution, rand(0,1) returns a uniformly distributed random real number greater than or equal to 0 and less than 1, and CR is the preset crossover probability.

[0156] (VI) Selection operation: adopt a greedy strategy to select individuals with smaller erfF to enter the next generation population.

[0157]

[0158] The above process is repeated until the preset end condition is met, and the currently obtained feasible solution is obtained to achieve image reconstruction of the target object.

[0159] The step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this application.

[0160] A second aspect of the present application provides an image reconstruction device based on correlation imaging. Figure 5 A block diagram of an image reconstruction device based on correlation imaging provided in an embodiment of the present application. Figure 5 As shown, the device comprises:

[0161] The measurement data acquisition module 501 is configured to obtain light intensity measurement data corresponding to the target object.

[0162] The light intensity measurement data is obtained by measuring the light signal generated by the associated imaging of the target object.

[0163] The population building module 502 is configured to build a first generation population for image reconstruction of the target object.

[0164] The first generation population includes multiple first generation feasible solutions for image reconstruction.

[0165] The reconstruction module 503 is configured to reconstruct multiple n-th generation feasible solutions of the n-th generation population according to the light intensity measurement data to obtain multiple n-th generation reconstructed solutions.

[0166] Wherein, n is an integer greater than or equal to 1.

[0167] The optimization module 504 is configured to optimize multiple n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object.

[0168] Among them, the n+1 generation population includes multiple n+1 generation feasible solutions.

[0169] The image acquisition module 505 obtains a reconstructed image corresponding to the target object according to the multiple n+1 generation feasible solutions when the multiple n+1 generation feasible solutions meet the preset termination condition.

[0170] The image imaging device provided in the embodiment of the present application first uses the light intensity measurement data to reconstruct the nth generation feasible solution of the image to be reconstructed, and after obtaining the nth generation reconstruction solution, performs optimization operations such as selection, mutation and crossover to obtain the n+1th generation feasible solution. The above process is iteratively performed until a preset end condition is met, and the iteration is stopped. The reconstructed image is determined based on the current feasible solution, which can not only alleviate the local optimal problem, but also improve the global search capability and convergence speed of phase recovery, thereby obtaining a good image reconstruction result.

[0171] In some possible implementations, the nth generation feasible solution is a predicted image of the reconstructed image corresponding to the target object in the time domain, and the nth generation population is:

[0172] G n = {g k (n,i,j)}

[0173] Among them, G n represents the nth generation population, n represents the population generation, n is an integer greater than or equal to 1, g k (n,i,j) represents the nth generation feasible solution, k is used to represent the serial number of the nth generation feasible solution, k is an integer greater than or equal to 1, i and j represent the number of rows and columns of the predicted image corresponding to the nth generation feasible solution, respectively, k The value of (n,i,j) represents the value of the jth node in the i-th row of the predicted image corresponding to the n-th generation feasible solution.

[0174] In some possible implementations, the light intensity measurement data includes measurement spectrum information; the reconstruction module 503 includes: a first transformation unit, an intermediate solution acquisition unit, a second transformation unit, a reconstruction unit, and a reconstruction solution acquisition unit. Among them, the first transformation unit is used to perform Fourier transform on the nth generation feasible solution for the mth reconstruction of any nth generation feasible solution to obtain the mth nth generation frequency domain feasible solution, m is an integer greater than or equal to 1, and the mth nth generation frequency domain feasible solution includes the mth nth generation phase information; the intermediate solution acquisition unit is used to obtain the mth nth generation frequency domain intermediate solution according to the measured spectrum information and the mth nth generation phase information; the second transformation unit is used to perform inverse Fourier transform on the mth nth generation frequency domain intermediate solution to obtain the mth nth generation time domain intermediate solution; the reconstruction unit is used to impose constraints on the preset support domain of the mth nth generation time domain intermediate solution to obtain the mth nth generation reconstruction solution; the reconstruction solution acquisition unit is used to obtain the nth generation reconstruction solution when the mth nth generation reconstruction solution satisfies the preset iteration stop condition.

[0175] In some possible implementations, the light source of the associated imaging includes signal light and reference light, and the light intensity measurement data includes first light intensity measurement data corresponding to the reference light and second light intensity measurement data corresponding to the signal light; the measured spectrum information is spectrum data in the light intensity frequency domain measurement data obtained by performing a correlation operation on the first light intensity measurement data and the second light intensity measurement data.

[0176] In some possible implementations, the optimization module 504 includes: a fitness determination unit and an optimization execution unit. The fitness determination unit is used to determine the individual fitness of each n-th generation reconstruction solution; the optimization execution unit is used to select, mutate, and crossover the n-th generation reconstruction solution according to the individual fitness to obtain the n+1 generation population for image reconstruction of the target object.

[0177] In some possible implementations, the fitness determination unit includes a third transformation subunit and a calculation subunit. The third transformation subunit is used to perform Fourier transformation on each n-generation reconstruction solution to obtain an n-generation frequency domain reconstruction solution corresponding to the n-generation reconstruction solution, wherein the n-generation frequency domain reconstruction solution includes n-generation spectrum information; the calculation subunit is used to calculate the individual fitness of each n-generation reconstruction solution according to the n-generation spectrum information and the measured spectrum information, and the measured spectrum information is information obtained according to the spectrum data corresponding to the light intensity measurement data.

[0178] In one example, the calculation subunit is used to determine spectrum error data according to the n-th generation spectrum information and the measured spectrum information, and use the spectrum error data as the individual fitness of each n-th generation reconstruction solution.

[0179] In some possible implementations, the optimization execution unit includes: a first selection subunit, a difference subunit, a mutation subunit, a crossover subunit, and a second selection subunit. The first selection subunit is used to select two n-th generation reconstruction solutions as n-th generation target solutions; the difference subunit is used to perform a difference operation on the two n-th generation target solutions to obtain a difference vector; the mutation subunit is used to perform a mutation operation on the n-th generation reconstruction solutions other than the n-th generation target solution in the n-th generation population according to the difference vector to obtain multiple n-th generation mutation solutions; the crossover subunit is used to perform a crossover operation on the n-th generation mutation solution and the n-th generation target solution to obtain multiple n-th generation crossover solutions; the second selection subunit is used to select the n+1 generation feasible solution constituting the n+1 generation population from multiple n-th generation crossover solutions according to individual fitness.

[0180] In some possible implementations, the second selection subunit is used to select multiple nth generation target crossover solutions from the nth generation crossover solutions as n+1th generation feasible solutions based on a greedy strategy and according to individual fitness, to obtain the n+1th generation population.

[0181] Figure 6A block diagram of the composition of an electronic device provided in an embodiment of the present application.

[0182] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0183] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0184] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0185] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as an image reconstruction method based on associated imaging. For example, in some embodiments, the image reconstruction method based on associated imaging may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via ROM 602 and / or a communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the image reconstruction method based on associated imaging described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform an image reconstruction method based on associated imaging in any other appropriate manner (e.g., by means of firmware).

[0186] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0187] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0188] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0189] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0190] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0191] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0192] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0193] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present application, but the present application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of the present application, and these modifications and improvements are also considered to be within the scope of protection of the present application.

Claims

1. An image reconstruction method based on correlation imaging, characterized in that: The method comprises: Obtaining light intensity measurement data corresponding to a target object, wherein the light intensity measurement data is obtained by measuring a light signal generated by associated imaging of the target object; Establishing a first generation population for image reconstruction of the target object, wherein the first generation population includes a plurality of first generation feasible solutions for image reconstruction; Reconstructing multiple n-th generation feasible solutions of the n-th generation population according to the light intensity measurement data to obtain multiple n-th generation reconstructed solutions, where n is an integer greater than or equal to 1; Optimizing the plurality of n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object, wherein the n+1-th generation population includes a plurality of n+1-th generation feasible solutions; When the plurality of the n+1th generation feasible solutions satisfy a preset termination condition, obtaining a reconstructed image corresponding to the target object according to the plurality of the n+1th generation feasible solutions; Wherein, the light intensity measurement data includes measurement spectrum information; The step of reconstructing multiple n-generation feasible solutions of the n-generation population according to the light intensity measurement data to obtain multiple n-generation reconstructed solutions includes: For the m-th reconstruction of any n-th generation feasible solution, perform Fourier transform on the n-th generation feasible solution to obtain an m-th n-th generation frequency domain feasible solution, where m is an integer greater than or equal to 1, and the m-th n-th generation frequency domain feasible solution includes the m-th n-th generation phase information; Obtaining an mth nth generation frequency domain intermediate solution according to the measured spectrum information and the mth nth generation phase information; Performing an inverse Fourier transform on the mth nth generation frequency domain intermediate solution to obtain an mth nth generation time domain intermediate solution; Applying constraints to a preset support domain of the mth nth generation time-domain intermediate solution to obtain an mth nth generation reconstruction solution; When the mth nth generation reconstruction solution satisfies a preset iteration stop condition, obtaining the nth generation reconstruction solution; The step of optimizing the plurality of n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object includes: Determining the individual fitness of each of the n-th generation reconstruction solutions; According to the individual fitness, performing selection, mutation, and crossover operations on the nth generation reconstruction solution to obtain an n+1th generation population for image reconstruction of the target object; Wherein, determining the individual fitness of each of the n-th generation reconstruction solutions includes: Performing Fourier transform on each of the n-th generation reconstruction solutions respectively to obtain an n-th generation frequency domain reconstruction solution corresponding to the n-th generation reconstruction solution, wherein the n-th generation frequency domain reconstruction solution includes n-th generation frequency spectrum information; Calculating the individual fitness of each of the n-generation reconstruction solutions according to the n-generation spectrum information and the measured spectrum information, including: determining spectrum error data according to the n-generation spectrum information and the measured spectrum information, and using the spectrum error data as the individual fitness of each of the n-generation reconstruction solutions; the measured spectrum information is information obtained according to the spectrum data corresponding to the light intensity measurement data; Among them, the n-th generation reconstruction solution is selected, mutated, and crossovered according to the individual fitness to obtain the n+1-th generation population for image reconstruction of the target object, including: selecting two of the n-th generation reconstruction solutions as the n-th generation target solutions; performing a difference operation on the two n-th generation target solutions to obtain a difference vector; performing a mutation operation on the n-th generation reconstruction solutions other than the n-th generation target solution in the n-th generation population according to the difference vector to obtain a plurality of n-th generation mutated solutions; performing a crossover operation on the n-th generation mutated solutions and the n-th generation target solutions to obtain a plurality of n-th generation crossover solutions; and selecting the n+1-th generation feasible solution constituting the n+1-th generation population from the plurality of n-generation crossover solutions according to the individual fitness.

2. The image reconstruction method according to claim 1, characterized in that: The light source for the associated imaging includes a signal light and a reference light, and the light intensity measurement data includes first light intensity measurement data corresponding to the reference light and second light intensity measurement data corresponding to the signal light; The measured spectrum information is spectrum data in the light intensity frequency domain measurement data obtained by performing a correlation operation on the first light intensity measurement data and the second light intensity measurement data.

3. The image reconstruction method according to claim 1, characterized in that: The step of selecting the n+1th generation feasible solution constituting the n+1th generation population from the plurality of the nth generation crossover solutions according to the individual fitness comprises: Based on the greedy strategy, according to the individual fitness, multiple nth generation target crossover solutions are selected from the nth generation crossover solutions as the n+1th generation feasible solutions to obtain the n+1th generation population.

4. The image reconstruction method according to claim 1, characterized in that: The n-th generation feasible solution is the predicted image of the reconstructed image corresponding to the target object in the time domain, and the n-th generation population is: G n ={g k (n,i,j)} Among them, G n represents the nth generation population, n represents the population generation, n is an integer greater than or equal to 1, g k (n, i, j) represents the nth generation feasible solution, k is used to represent the serial number of the nth generation feasible solution, k is an integer greater than or equal to 1, i and j represent the number of rows and columns of the predicted image corresponding to the nth generation feasible solution, respectively, k The value of (n, i, j) represents the value of the jth node in the i-th row of the predicted image corresponding to the n-th generation feasible solution.

5. An image reconstruction device based on correlation imaging, characterized in that: The device comprises: A measurement data acquisition module is configured to obtain light intensity measurement data corresponding to a target object, wherein the light intensity measurement data is obtained by measuring a light signal generated by associated imaging of the target object; A population establishment module is configured to establish a first generation population for image reconstruction of the target object, wherein the first generation population includes a plurality of first generation feasible solutions for image reconstruction; A reconstruction module is configured to reconstruct multiple n-th generation feasible solutions of the n-th generation population according to the light intensity measurement data to obtain multiple n-th generation reconstructed solutions, where n is an integer greater than or equal to 1; an optimization module configured to optimize the plurality of n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object, wherein the n+1-th generation population includes a plurality of n+1-th generation feasible solutions; an image acquisition module, which, when the plurality of the n+1th generation feasible solutions satisfy a preset termination condition, obtains a reconstructed image corresponding to the target object according to the plurality of the n+1th generation feasible solutions; Wherein, the light intensity measurement data includes measurement spectrum information; The step of reconstructing multiple n-generation feasible solutions of the n-generation population according to the light intensity measurement data to obtain multiple n-generation reconstructed solutions includes: For the m-th reconstruction of any n-th generation feasible solution, perform Fourier transform on the n-th generation feasible solution to obtain an m-th n-th generation frequency domain feasible solution, where m is an integer greater than or equal to 1, and the m-th n-th generation frequency domain feasible solution includes the m-th n-th generation phase information; Obtaining an mth nth generation frequency domain intermediate solution according to the measured spectrum information and the mth nth generation phase information; Performing an inverse Fourier transform on the mth nth generation frequency domain intermediate solution to obtain an mth nth generation time domain intermediate solution; Applying constraints to a preset support domain of the mth nth generation time-domain intermediate solution to obtain an mth nth generation reconstruction solution; When the mth nth generation reconstruction solution satisfies a preset iteration stop condition, obtaining the nth generation reconstruction solution; The step of optimizing the plurality of n-th generation reconstruction solutions to obtain an n+1-th generation population for image reconstruction of the target object includes: Determining the individual fitness of each of the n-th generation reconstruction solutions; According to the individual fitness, performing selection, mutation, and crossover operations on the nth generation reconstruction solution to obtain an n+1th generation population for image reconstruction of the target object; Wherein, determining the individual fitness of each of the n-th generation reconstruction solutions includes: Performing Fourier transform on each of the n-th generation reconstruction solutions respectively to obtain an n-th generation frequency domain reconstruction solution corresponding to the n-th generation reconstruction solution, wherein the n-th generation frequency domain reconstruction solution includes n-th generation frequency spectrum information; Calculating the individual fitness of each of the n-generation reconstruction solutions according to the n-generation spectrum information and the measured spectrum information, including: determining spectrum error data according to the n-generation spectrum information and the measured spectrum information, and using the spectrum error data as the individual fitness of each of the n-generation reconstruction solutions; the measured spectrum information is information obtained according to the spectrum data corresponding to the light intensity measurement data; Among them, the n-th generation reconstruction solution is selected, mutated, and crossovered according to the individual fitness to obtain the n+1-th generation population for image reconstruction of the target object, including: selecting two of the n-th generation reconstruction solutions as the n-th generation target solutions; performing a difference operation on the two n-th generation target solutions to obtain a difference vector; performing a mutation operation on the n-th generation reconstruction solutions other than the n-th generation target solution in the n-th generation population according to the difference vector to obtain a plurality of n-th generation mutated solutions; performing a crossover operation on the n-th generation mutated solutions and the n-th generation target solutions to obtain a plurality of n-th generation crossover solutions; and selecting the n+1-th generation feasible solution constituting the n+1-th generation population from the plurality of n-generation crossover solutions according to the individual fitness.

6. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs executable by the at least one processor, and the one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the image reconstruction method according to any one of claims 1 to 4.

7. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the computer program implements the image reconstruction method according to any one of claims 1 to 4.

Images