CN109615676B - Optical image reconstruction method, device, computer equipment and storage medium - Google Patents
Optical image reconstruction method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109615676B CN109615676B CN201811527175.2A CN201811527175A CN109615676B CN 109615676 B CN109615676 B CN 109615676B CN 201811527175 A CN201811527175 A CN 201811527175A CN 109615676 B CN109615676 B CN 109615676B
- Authority
- CN
- China
- Prior art keywords
- optical image
- recovery function
- function
- image
- super
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 185
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011084 recovery Methods 0.000 claims abstract description 85
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 122
- 239000011159 matrix material Substances 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 10
- 239000004973 liquid crystal related substance Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012014 optical coherence tomography Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000003325 tomography Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 210000004087 cornea Anatomy 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an optical image reconstruction method, an optical image reconstruction device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring an original optical image acquired by an optical camera, and performing function modeling on the original image; obtaining a recovery function for reconstructing an image according to the established function model, and performing function optimization; and carrying out iterative solution on the recovery function, and carrying out optical image reconstruction to obtain a super-resolution optical image. According to the invention, the original optical image is modeled and the recovery function is obtained, so that the recovery function is obtained, and the original optical image is reconstructed according to the recovery function, so that the optical image with low resolution is constructed into the optical image with super resolution, and the definition of fine features in the image is improved.
Description
Technical Field
The present invention relates to the field of optical image processing technologies, and in particular, to an optical image reconstruction method, an optical image reconstruction device, a computer device, and a storage medium.
Background
The imaging quality of optical images plays an important role in medical analysis, and existing optical image imaging techniques mainly include the following two types. The optical coherence tomography (Optical Coherence Tomography, OCT for short) is a new tomography with the most development prospect in recent years, has the characteristics of no contact, no damage and real-time measurement, and can perform non-contact and non-invasive tomography of the microscopic structure of the eye tissue. Corneal Visualization Scheimpflug Technology instrument (Corvis ST Tonometry) is a non-invasive technical instrument for measuring the entire process of deformation of the cornea in the body after blowing the balloon.
However, both of the above techniques have certain drawbacks in obtaining optical images. The resolution of OCT images is limited by the bandwidth of the light source, while the resolution of Corvis ST images is physically limited by the diffraction limit of light; in addition, due to limitations in instrument hardware, optical images acquired by both techniques are subject to blurring, downsampling distortion, noise interference, and the like. These effects reduce the resolution of the optical image, causing fine features in the image to become blurred, thereby making an accurate determination of the optical image impossible.
Accordingly, the prior art is still in need of improvement and development.
Disclosure of Invention
The invention aims to solve the technical problems that the resolution of an optical image is reduced and fine features in the image become blurred due to the influence of blurring, downsampling distortion, noise interference and the like in the prior art.
The technical scheme adopted for solving the technical problems is as follows:
a method of optical image reconstruction, wherein the method comprises:
acquiring an original optical image acquired by an optical camera, and performing function modeling on the original image;
obtaining a recovery function for reconstructing an image according to the established function model, and performing function optimization;
and carrying out iterative solution on the recovery function, and carrying out optical image reconstruction to obtain a super-resolution optical image.
Preferably, the optical image reconstruction method, wherein the step of acquiring an original optical image acquired by an optical camera and performing functional modeling on the original image specifically includes:
acquiring an original optical image acquired by an optical camera, and drawing a fractional number-fractional number graph according to pixel value distribution of the original optical image;
carrying out pixel intensity matching analysis on the drawn quantile-quantile graph and a quantile-quantile graph in a preset probability distribution form, and determining the probability distribution form of damaged pixel areas and noise in the original optical image;
and modeling the original optical image according to the determined probability distribution form.
Preferably, the optical image reconstruction method, wherein the step of obtaining a recovery function for reconstructing an image according to the established function model and performing function optimization specifically includes:
establishing a recovery function based on maximum posterior estimation according to the established function model, wherein the recovery function comprises a pixel matrix for reconstructing the super-resolution optical image;
and carrying out noise reduction processing on the original optical image, and optimizing the recovery function by using an alternate direction multiplier method so as to eliminate constraint conditions in the recovery function.
Preferably, the optical image reconstruction method, wherein the step of iteratively resolving the recovery function and performing optical image reconstruction to obtain a super-resolution optical image specifically includes:
calculating the optimized recovery function by using an iterative algorithm to obtain a pixel matrix and auxiliary parameters of the reconstructed super-resolution optical image;
and performing optical image reconstruction according to the pixel matrix and auxiliary parameters of the super-resolution optical image to obtain the super-resolution optical image.
An optical image reconstruction apparatus, wherein the apparatus comprises:
the image modeling module is used for acquiring an original optical image acquired by the optical camera and performing function modeling on the original image;
the recovery function acquisition module is used for acquiring a recovery function for reconstructing an image according to the established function model and performing function optimization;
and the image reconstruction module is used for carrying out iterative calculation on the recovery function and carrying out optical image reconstruction to obtain a super-resolution optical image.
Preferably, the optical image reconstruction device, wherein the image modeling module specifically includes:
the system comprises a fractional number graph drawing unit, a fractional number graph drawing unit and a pixel value analysis unit, wherein the fractional number graph drawing unit is used for acquiring an original optical image acquired by an optical camera and drawing a fractional number-fractional number graph according to the pixel value distribution of the original optical image;
the probability distribution matching unit is used for carrying out pixel intensity matching analysis on the drawn quantile-quantile graph and a quantile-quantile graph in a preset probability distribution form, and determining the probability distribution form of damaged pixel areas and noise in the original optical image;
and the image modeling unit is used for modeling the original optical image according to the determined probability distribution form.
Preferably, the optical image reconstruction device, wherein the recovery function acquisition module specifically includes:
a recovery function establishing unit, configured to establish a recovery function based on the maximum posterior estimation according to the established function model, where the recovery function includes a pixel matrix for reconstructing the super-resolution optical image;
and the recovery function optimization unit is used for carrying out noise reduction processing on the original optical image and optimizing the recovery function by using an alternate direction multiplier method so as to eliminate constraint conditions in the recovery function.
Preferably, the optical image reconstruction device, wherein the image reconstruction module specifically includes:
the function resolving unit is used for resolving the optimized recovery function by using an iterative algorithm to obtain a pixel matrix and auxiliary parameters of the reconstructed super-resolution optical image;
and the image reconstruction unit is used for carrying out optical image reconstruction according to the pixel matrix and the auxiliary parameters of the super-resolution optical image to obtain the super-resolution optical image.
A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of any of the methods described above when the computer program is executed.
A storage medium having stored thereon a computer program, wherein the computer program when executed by a processor performs the steps of the method of any of the preceding claims.
The invention has the beneficial effects that: according to the invention, the original optical image is modeled and the recovery function is obtained, so that the recovery function is obtained, and the original optical image is reconstructed according to the recovery function, so that the optical image with low resolution is constructed into the optical image with super resolution, and the definition of fine features in the image is improved.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the optical image reconstruction method of the present invention.
Fig. 2 is an effect diagram of reconstructing a Corvis ST image by applying the optical image reconstruction method of the present invention.
Fig. 3 is a block diagram of an optical image reconstruction apparatus according to a preferred embodiment of the present invention.
FIG. 4 is a functional block diagram of a preferred embodiment of the computer device of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear and clear, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The optical image reconstruction method provided by the invention can be applied to a terminal. The terminal may be, but is not limited to, various personal computers, notebook computers, cell phones, tablet computers, car computers, and portable wearable devices. The terminal of the invention adopts a multi-core processor. The processor of the terminal may be at least one of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), a video processing unit (Video Processing Unit, VPU), and the like.
As either the prior art or the acquisition of the optical image is affected by blurring, downsampling distortion, noise disturbance, etc. These effects reduce the resolution of the optical image, causing fine features in the image to become blurred, thereby making an accurate determination of the optical image impossible. In order to solve the above-mentioned problems, the present embodiment provides an optical image reconstruction method, in which an original low-resolution optical image is mainly constructed into a super-resolution optical image, so that fine features in the image can be clearly represented. As shown in fig. 1 in particular, the optical image reconstruction method comprises the following steps:
and step S100, acquiring an original optical image acquired by an optical camera, and performing functional modeling on the original image.
In particular, in this embodiment, an original optical image acquired by an optical camera is first acquired, where the original optical image is an image that is not subjected to any image processing, and the resolution of the image is low. After the original optical image is acquired, a quantile-quantile graph is further drawn from the pixel value distribution of the original optical image. The quantile-quantile plot plots one quantile of the univariate distribution against another corresponding quantile. It is a powerful visualization tool that allows a user to observe whether there is drift from one distribution to another. Thus, drawing a quantile-quantile graph can intuitively show the pixel distribution in the original optical image.
After drawing the quantile-quantile diagram, the embodiment performs pixel intensity matching analysis on the drawn quantile-quantile diagram and the quantile-quantile diagram in a preset probability distribution form, and determines the probability distribution form of damaged pixel areas and noise in the original optical image. For example, the preset probability distribution forms include normal distribution, gamma distribution, poisson distribution and rice distribution, and the pixel intensity contrast matching is performed on the drawn quantile-quantile map and the quantile-quantile map corresponding to the normal distribution, gamma distribution, poisson distribution and rice distribution, respectively, so as to determine the damaged pixel area of the original optical image and the probability distribution form of noise in the embodiment.
After the probability distribution form of noise of the original optical image is determined, modeling the original optical image according to the determined probability distribution form. Preferably, the model established in this embodiment is as follows:
wherein y is E R N For the pixel matrix of the original optical image (low resolution) acquired by the optical pick-up instrument, x is E R N The method is characterized in that the method comprises the steps of (1) obtaining a pixel matrix of a target image (namely, a pixel matrix of a super-resolution image which is required to be obtained through reconstruction), wherein N is the number of pixels; since the obtained image is affected by blurring and downsampling distortion due to limitations on hardware equipment of the optical camera, H and D represent blurring and downsampling matrices respectively,a model function is built for the probability distribution form matched according to the analysis.
Further, step S200, according to the established function model, obtains a recovery function for reconstructing the image, and performs function optimization.
In specific implementation, the function processing is performed on the model function established in the embodiment, and a recovery function is established based on the maximum a posteriori (Maximum a posteriori estimation, MAP) estimation, wherein the recovery function comprises a pixel matrix for reconstructing the super-resolution optical image. Specifically, the recovery function established in the present embodiment is as follows:
wherein lambda is a penalty parameter,is a regular term.
After the recovery function is established, the present embodiment performs noise reduction processing on the original optical image, and optimizes the recovery function using an alternate direction multiplier method (Alternating Direction Method of Multipliers) to optimize the recovery function with constraint conditions as a recovery function without constraint conditions, that is, to eliminate constraint conditions in the recovery function, and also solves for auxiliary parameters generated in the process. Because constraint conditions exist in the recovery function, if the recovery function is directly solved in the subsequent step, the solution is difficult, and the solution result is inaccurate. Thus, the alternate direction multiplier method is employed in embodiments to decompose the recovery function into a plurality of auxiliary parameters, thereby eliminating constraints. The auxiliary parameters are easy to solve, so that the elimination of the constraint function is really a simplification of the solution of the recovery function for the subsequent steps.
Preferably, the noise reduction processing manner in this embodiment may adopt a commonly used method such as gaussian filtering denoising, mean filtering denoising, wavelet denoising, and the like. The present embodiment is not limited thereto.
Specifically, in this embodiment, the optimized recovery function may be:
where μ is a regularization parameter that varies iteratively in non-decreasing order, and z is an auxiliary parameter generated during the optimization.
Further, step S300 is to perform iterative solution on the recovery function, and perform optical image reconstruction to obtain a super-resolution optical image.
In the embodiment, the iterative algorithm is used to solve the optimized recovery function to obtain the pixel matrix and the auxiliary parameters of the reconstructed super-resolution optical image, and preferably, the iterative algorithm is used to solve the optimized recovery function for 20 times. Of course, the specific iteration number may be set autonomously, and the number is not limited in this embodiment.
Specifically, in performing the calculation, the following algorithm may be employed:
wherein, the liquid crystal display device comprises a liquid crystal display device, in order to select the denoising method, T is the transposition operation of the matrix, I is the identity matrix, k is the current iteration number, and v is an auxiliary parameter generated in the solution process.
And when the pixel matrix and the auxiliary parameters are obtained, performing optical image reconstruction according to the pixel matrix and the auxiliary parameters of the super-resolution optical image to obtain the super-resolution optical image. According to the invention, the original optical image (low-resolution image) is subjected to function modeling and function processing, so that the pixel matrix and auxiliary parameters of the super-resolution image are obtained, and further the optical image is reconstructed, so that the low-resolution optical image is constructed into the super-resolution optical image, and the definition of fine features in the image is improved.
Further, as shown in fig. 2, fig. 2 is an effect diagram of reconstructing a Corvis ST image by applying the optical image reconstruction method of the present invention. Where a in fig. 2 is an original optical image (low resolution image), and b in fig. 2 is a super resolution image obtained by reconstruction via the optical image reconstruction method of the present invention. C in fig. 2 is a region detail view of an original optical image, and d in fig. 2 is a region detail view of a super-resolution image obtained by reconstruction via the optical image reconstruction method of the present invention. After c and d are compared and analyzed, the super-resolution image obtained by reconstruction through the optical image reconstruction method is clearer in detail characteristics, so that more accurate analysis of medical images is facilitated, and misjudgment are avoided.
It should be noted that, in this embodiment, the specific form of constructing the image according to the pixel matrix and the auxiliary parameters may be implemented according to the prior art, but the present invention focuses on how to process the image with low resolution, so as to obtain the pixel matrix and the auxiliary parameters that can construct the super-resolution image, and how to convert the pixel matrix and the auxiliary parameters into the image, which is completely implemented in the prior art.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or sub-steps of other steps.
Based on the above embodiment, the present invention further provides an optical image reconstruction device, as shown in fig. 3, including: an image modeling module 310, a recovery function acquisition module 320, and an image reconstruction module 330. Wherein, the liquid crystal display device comprises a liquid crystal display device,
the image modeling module 310 is configured to obtain an original optical image acquired by the optical camera, and perform functional modeling on the original image;
a recovery function obtaining module 320, configured to obtain a recovery function for reconstructing an image according to the established function model, and perform function optimization;
and the image reconstruction module 330 is configured to perform iterative solution on the recovery function, and perform optical image reconstruction to obtain a super-resolution optical image.
In one embodiment, the image modeling module 310 specifically includes:
the system comprises a fractional number graph drawing unit, a fractional number graph drawing unit and a pixel value analysis unit, wherein the fractional number graph drawing unit is used for acquiring an original optical image acquired by an optical camera and drawing a fractional number-fractional number graph according to the pixel value distribution of the original optical image;
the probability distribution matching unit is used for carrying out pixel intensity matching analysis on the drawn quantile-quantile graph and a quantile-quantile graph in a preset probability distribution form, and determining the probability distribution form of damaged pixel areas and noise in the original optical image;
and the image modeling unit is used for modeling the original optical image according to the determined probability distribution form.
In one embodiment, the recovery function acquisition module 320 specifically includes:
a recovery function establishing unit, configured to establish a recovery function based on the maximum posterior estimation according to the established function model, where the recovery function includes a pixel matrix for reconstructing the super-resolution optical image;
and the recovery function optimization unit is used for carrying out noise reduction processing on the original optical image and optimizing the recovery function by using an alternate direction multiplier method so as to eliminate constraint conditions in the recovery function.
In one embodiment, the image reconstruction module 330 specifically includes:
the function resolving unit is used for resolving the optimized recovery function by using an iterative algorithm to obtain a pixel matrix and auxiliary parameters of the reconstructed super-resolution optical image;
and the image reconstruction unit is used for carrying out optical image reconstruction according to the pixel matrix and the auxiliary parameters of the super-resolution optical image to obtain the super-resolution optical image.
For specific limitations of the optical image reconstruction device, reference may be made to the above limitations of the optical image reconstruction method, and no further description is given here. The above-described respective modules of the optical image reconstruction apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Based on the above embodiment, the present invention further provides a computer device, which may be a terminal, and its functional block diagram may be shown in fig. 4. The computer device includes a processor, a memory, a network interface, a display screen, and a temperature sensor connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of optical image reconstruction. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the temperature sensor of the computer device is preset in the computer device and is used for detecting the current running temperature of the internal device.
It will be appreciated by those skilled in the art that the functional block diagram shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be implemented, as a specific computer device may include more or fewer components than those shown, or may be combined with certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring an original optical image acquired by an optical camera, and performing function modeling on the original image;
obtaining a recovery function for reconstructing an image according to the established function model, and performing function optimization;
and carrying out iterative solution on the recovery function, and carrying out optical image reconstruction to obtain a super-resolution optical image.
Based on the above embodiments, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring an original optical image acquired by an optical camera, and performing function modeling on the original image;
obtaining a recovery function for reconstructing an image according to the established function model, and performing function optimization;
and carrying out iterative solution on the recovery function, and carrying out optical image reconstruction to obtain a super-resolution optical image.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.
Claims (6)
1. A method of reconstructing an optical image, the method comprising:
acquiring an original optical image acquired by an optical camera, and performing function modeling on the original optical image;
obtaining a recovery function for reconstructing an image according to the established function model, and performing function optimization;
performing iterative solution on the recovery function, and performing optical image reconstruction to obtain a super-resolution optical image;
the step of acquiring an original optical image acquired by an optical camera and performing functional modeling on the original optical image specifically comprises the following steps:
acquiring an original optical image acquired by an optical camera, and drawing a fractional number-fractional number graph according to pixel value distribution of the original optical image;
carrying out pixel intensity matching analysis on the drawn quantile-quantile graph and a quantile-quantile graph in a preset probability distribution form, and determining the probability distribution form of damaged pixel areas and noise in the original optical image;
modeling the original optical image according to the determined probability distribution pattern,
the built model is as follows:
，
wherein y is E R N For the pixel matrix of the original optical image acquired by the optical camera, x is E R N For a matrix of pixels of the target image, N is the number of pixels, H and D represent the blur and downsampling matrices respectively,a model function established according to the probability distribution form matched by analysis;
the step of obtaining a recovery function for reconstructing an image according to the established function model and performing function optimization specifically comprises the following steps:
establishing a recovery function based on the maximum a posteriori estimation according to the established function model, wherein the recovery function comprises a pixel matrix for reconstructing the super-resolution optical image,
the recovery function is:
wherein λ is a penalty parameter, ++>Is a regular term;
noise reduction processing is carried out on the original optical image, and the recovery function is optimized by using an alternate direction multiplier method so as to eliminate constraint conditions in the recovery function, wherein the optimized recovery function is as follows:
，
where μ is a regularization parameter that varies iteratively in non-decreasing order, and z is an auxiliary parameter generated during the optimization.
2. The method for reconstructing an optical image according to claim 1, wherein the step of iteratively solving the recovery function and reconstructing the optical image to obtain a super-resolution optical image specifically comprises:
calculating the optimized recovery function by using an iterative algorithm to obtain a pixel matrix and auxiliary parameters of the reconstructed super-resolution optical image;
and performing optical image reconstruction according to the pixel matrix and auxiliary parameters of the super-resolution optical image to obtain the super-resolution optical image.
3. An optical image reconstruction apparatus, the apparatus comprising:
the image modeling module is used for acquiring an original optical image acquired by the optical camera and performing function modeling on the original optical image;
the recovery function acquisition module is used for acquiring a recovery function for reconstructing an image according to the established function model and performing function optimization;
the image reconstruction module is used for carrying out iterative calculation on the recovery function and carrying out optical image reconstruction to obtain a super-resolution optical image;
the image modeling module specifically comprises:
the system comprises a fractional number graph drawing unit, a fractional number graph drawing unit and a pixel value analysis unit, wherein the fractional number graph drawing unit is used for acquiring an original optical image acquired by an optical camera and drawing a fractional number-fractional number graph according to the pixel value distribution of the original optical image;
the probability distribution matching unit is used for carrying out pixel intensity matching analysis on the drawn quantile-quantile graph and a quantile-quantile graph in a preset probability distribution form, and determining the probability distribution form of damaged pixel areas and noise in the original optical image;
an image modeling unit for modeling the original optical image according to the determined probability distribution form,
the built model is as follows:
，
wherein y is E R N For the pixel matrix of the original optical image acquired by the optical camera, x is E R N For a matrix of pixels of the target image, N is the number of pixels, H and D represent the blur and downsampling matrices respectively,a model function established according to the probability distribution form matched by analysis;
the recovery function acquisition module specifically includes:
a recovery function establishing unit, configured to establish a recovery function based on the maximum a posteriori estimation according to the established function model, where the recovery function includes a pixel matrix for reconstructing a super-resolution optical image, and the recovery function is:
wherein λ is a penalty parameter, ++>Is a regular term;
the recovery function optimizing unit is used for carrying out noise reduction processing on the original optical image, optimizing the recovery function by using an alternate direction multiplier method so as to eliminate constraint conditions in the recovery function, wherein the optimized recovery function is as follows:
，
where μ is a regularization parameter that varies iteratively in non-decreasing order, and z is an auxiliary parameter generated during the optimization.
4. An optical image reconstruction apparatus according to claim 3, wherein the image reconstruction module specifically comprises:
the function resolving unit is used for resolving the optimized recovery function by using an iterative algorithm to obtain a pixel matrix and auxiliary parameters of the reconstructed super-resolution optical image;
and the image reconstruction unit is used for carrying out optical image reconstruction according to the pixel matrix and the auxiliary parameters of the super-resolution optical image to obtain the super-resolution optical image.
5. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 2 when the computer program is executed.
6. A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of any of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811527175.2A CN109615676B (en) | 2018-12-13 | 2018-12-13 | Optical image reconstruction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811527175.2A CN109615676B (en) | 2018-12-13 | 2018-12-13 | Optical image reconstruction method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109615676A CN109615676A (en) | 2019-04-12 |
| CN109615676B true CN109615676B (en) | 2023-08-29 |
Family
ID=66009191
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811527175.2A Active CN109615676B (en) | 2018-12-13 | 2018-12-13 | Optical image reconstruction method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109615676B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279935A (en) * | 2013-06-09 | 2013-09-04 | 河海大学 | Method and system of thermal infrared remote sensing image super-resolution reconstruction based on MAP algorithm |
| WO2015180053A1 (en) * | 2014-05-28 | 2015-12-03 | 北京大学深圳研究生院 | Method and apparatus for rapidly reconstructing super-resolution image |
| CN107220936A (en) * | 2017-05-26 | 2017-09-29 | 首都师范大学 | A kind of image super-resolution reconstructing method and system |
| CN108230251A (en) * | 2016-12-22 | 2018-06-29 | 深圳清华大学研究院 | Combined type image recovery method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002300461A (en) * | 2001-03-30 | 2002-10-11 | Minolta Co Ltd | Image restoring device, image restoring method and program thereof and recording medium |
-
2018
- 2018-12-13 CN CN201811527175.2A patent/CN109615676B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103279935A (en) * | 2013-06-09 | 2013-09-04 | 河海大学 | Method and system of thermal infrared remote sensing image super-resolution reconstruction based on MAP algorithm |
| WO2015180053A1 (en) * | 2014-05-28 | 2015-12-03 | 北京大学深圳研究生院 | Method and apparatus for rapidly reconstructing super-resolution image |
| CN108230251A (en) * | 2016-12-22 | 2018-06-29 | 深圳清华大学研究院 | Combined type image recovery method and device |
| CN107220936A (en) * | 2017-05-26 | 2017-09-29 | 首都师范大学 | A kind of image super-resolution reconstructing method and system |
Non-Patent Citations (1)
| Title |
|---|
| Recovery of a quantile function from moments;Robert M. Mnatsakanov 等;《Journal of Computational and Applied Mathematics》;20171231;第315卷;第354-364页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109615676A (en) | 2019-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Deep unfolding network for image super-resolution | |
| CN109377457B (en) | Pill coating image processing method and device, computer equipment and storage medium | |
| CN110084868B (en) | Image correction method, apparatus, computer device, and readable storage medium | |
| Xu et al. | Nonlocal similarity based DEM super resolution | |
| Li et al. | Single image super-resolution using combined total variation regularization by split Bregman Iteration | |
| CN109461192B (en) | Image iterative reconstruction method, device and equipment and storage medium | |
| Zhao et al. | Gibbs-ringing artifact suppression with knowledge transfer from natural images to MR images | |
| CN113610752A (en) | Mammary gland image registration method, computer device and storage medium | |
| Huang et al. | Effective blind image deblurring using matrix-variable optimization | |
| Ge et al. | Blind image deblurring with gaussian curvature of the image surface | |
| JP6645442B2 (en) | Information processing apparatus, information processing method, and program | |
| CN109615676B (en) | Optical image reconstruction method, device, computer equipment and storage medium | |
| CN111681297B (en) | Image reconstruction method, computer device, and storage medium | |
| CN110189386B (en) | Medical image processing method, medical image processing device, storage medium and computer equipment | |
| CN111815692A (en) | Method, system and storage medium for generating artifact-free data and artifact-containing data | |
| Hou et al. | Image deconvolution with multi-stage convex relaxation and its perceptual evaluation | |
| Xie et al. | Bidirectionally aligned sparse representation for single image super-resolution | |
| Jiang et al. | Antialiased super-resolution with parallel high-frequency synthesis | |
| CN111105362B (en) | Brain image correction method, computer device, and readable storage medium | |
| CN113269812A (en) | Image prediction model training and application method, device, equipment and storage medium | |
| Chen et al. | Adaptive blind deconvolution using generalized cross-validation with generalized lp/lq norm regularization | |
| CN116309922B (en) | De-artifact method, device, equipment and storage medium for CT perfusion image | |
| CN111462059A (en) | Parallel processing method and device for intelligent target detection of fetal ultrasound image | |
| El Malki et al. | Enhancing deblurring through optimal controlled bilevel with nonlocal weighted model | |
| CN110910436A (en) | Distance measuring method, device, equipment and medium based on image information enhancement technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |