CN114839789B - Diffraction focusing method and device based on binarization spatial modulation - Google Patents
Diffraction focusing method and device based on binarization spatial modulation Download PDFInfo
- Publication number
- CN114839789B CN114839789B CN202210553808.7A CN202210553808A CN114839789B CN 114839789 B CN114839789 B CN 114839789B CN 202210553808 A CN202210553808 A CN 202210553808A CN 114839789 B CN114839789 B CN 114839789B
- Authority
- CN
- China
- Prior art keywords
- diffraction
- binarization
- model
- array
- evaluation model
- 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
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/42—Diffraction optics, i.e. systems including a diffractive element being designed for providing a diffractive effect
- G02B27/4266—Diffraction theory; Mathematical models
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/0012—Optical design, e.g. procedures, algorithms, optimisation routines
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Optical Modulation, Optical Deflection, Nonlinear Optics, Optical Demodulation, Optical Logic Elements (AREA)
Abstract
The application discloses a diffraction focusing method and a device based on binarization spatial modulation, wherein the method comprises the following steps: randomly generating a plurality of binarization arrays, respectively controlling a binarization spatial modulator to spatially modulate the wave surface of the incident wave, and acquiring a plurality of diffraction wave intensities corresponding to the plurality of binarization arrays in a diffraction wave intensity acquisition area; constructing an evaluation model, and training the evaluation model according to the diffraction wave intensities, the selected positions to be focused and the binary arrays; constructing a strategy model, and training the strategy model by adopting a well-trained evaluation model; and acquiring an optimal array by adopting a complete strategy model, binarizing the optimal array and setting the modulation state of each binarization spatial modulator so as to realize focusing at a position to be focused. The method has the advantages of simple implementation mode, strong expandability of the model construction method, short calculation time, less influence of noise and the like.
Description
Technical Field
The application relates to the technical field of computational imaging, in particular to a diffraction focusing method and device based on binarization spatial modulation.
Background
The wave surface propagated in space is divided into a plurality of independent units by utilizing a space modulation mode, amplitude or phase modulation is applied to each unit, diffraction propagation of the subsequent wave surface can be regulated and controlled, and further focusing at a specified position is realized. Binary modulation is easier to implement and modulation speed is faster than continuous phase or continuous amplitude modulation. For example, continuous phase modulation is difficult for extreme ultraviolet light or X-rays, but binary modulation can be achieved by controlling the "transmission" and "non-transmission" at different positions in space, a typical example being a zone plate. In the visible light wave band, the binary spatial modulator based on the digital micromirror device can reach a modulation frequency of tens of thousands of hertz, which is far higher than the current continuous phase or continuous amplitude spatial modulator based on liquid crystal.
Focusing is achieved by combining wavefront correction techniques when the wavefront has an unknown spatial distribution of amplitude and phase, or undergoes non-free propagation such as scattering during propagation. For example, in the optical field, binary wavefront correction techniques based on point-by-point attempts or genetic algorithms can utilize digital micromirror devices to achieve focusing of light through a diffuser, but cannot flexibly change the focal position; the entire wavefront correction process needs to be re-performed if the focus position needs to be changed. The binary wavefront correction technology based on transmission matrix measurement can realize focusing at a plurality of positions after obtaining a scattering transmission characteristic matrix through multiple measurements, but has the defects of long calculation time, easiness in being influenced by noise and the like. The application can effectively realize focusing based on binarization spatial modulation, and has simple implementation mode, strong expandability of the model construction method, short calculation time and less influence of noise.
Disclosure of Invention
The application aims to provide a diffraction focusing method and device based on binarization spatial modulation, which have the advantages of simple implementation mode, strong expandability of a model construction method, short calculation time, less influence of noise and the like.
In order to achieve the technical purpose, the application adopts the following technical scheme:
in a first aspect, the present application provides a diffraction focusing method comprising the steps of:
randomly generating a plurality of binarization arrays, configuring a modulation state of a binarization spatial modulator, spatially modulating an incident wave surface, and acquiring a plurality of diffraction wave intensities, wherein each diffraction wave intensity is acquired in a preset diffraction wave intensity acquisition range;
constructing an evaluation model, and training the evaluation model according to the selected position to be focused, the random binarization array and the corresponding diffraction wave intensity; the evaluation model is used for reflecting the mapping relation between the binarization array and the diffraction wave intensity of the position to be focused in the diffraction wave intensity;
constructing a strategy model, and training the strategy model by adopting a well-trained evaluation model, wherein the strategy model is used for generating an optimal array, and the optimal array can maximize the output of the evaluation model when being used as the input of the evaluation model;
and binarizing the optimal array and configuring the modulation state of a binarization spatial modulator to realize focusing at a position to be focused.
In some embodiments, the randomly generating a plurality of binary arrays and configuring a modulation state of a binary spatial modulator spatially modulates an incident wave surface and obtains a plurality of diffracted wave intensities includes:
step one, randomly generating a binarization array;
changing the modulation state of the binary space modulator according to the binary array;
step three, obtaining diffraction wave intensity of an incident wave surface corresponding to the modulation state in an effective diffraction area behind the spatial modulator acquired by the sensor;
and fourth, repeating the first step to the third step to obtain a plurality of diffraction wave intensities and a binary array corresponding to the diffraction wave intensities.
In some embodiments, the constructing an evaluation model, training the evaluation model according to the selected position to be focused, the random binary array, and the corresponding diffraction wave intensity, includes:
selecting a position to be focused, and respectively acquiring diffraction wave intensity of the position to be focused in each diffraction wave intensity to obtain a plurality of training pairs, wherein the training pairs are a binarization array and diffraction wave intensity of the position to be focused;
and training the constructed evaluation model by adopting a plurality of training pairs, wherein the input of the evaluation model is a binarization array, and the output of the evaluation model is the diffraction wave intensity of the position to be focused in the diffraction wave intensity.
In some embodiments, the constructing the policy model, training the policy model with a training complete evaluation model, includes:
constructing a strategy model and randomly generating an input array;
and updating the strategy model according to the output of the evaluation model by taking the input array as the input of the strategy model, taking the output of the strategy model as the input of the evaluation model and taking the maximization of the output result of the evaluation model as a training target until the strategy model outputs an optimal array, wherein the output of the evaluation model can be maximized when the optimal array is taken as the input of the evaluation model.
In some embodiments, the binarizing the optimal array and configuring a modulation state of a binarized spatial modulator to achieve focusing at a position to be focused includes:
and obtaining an optimal array, carrying out binarization processing on the optimal array, and configuring the modulation state of the binarization spatial modulator according to the binarized optimal array so as to realize focusing of the position to be focused.
In some of these embodiments, the evaluation model and the policy model are machine learning models, including but not limited to neural network models.
In some embodiments, when the selected position to be focused changes, training of the evaluation model, training of the strategy model, binarization of the model output optimal array and configuration of the binarized spatial modulator are performed again.
In a second aspect, the present application also provides a diffraction focusing device based on binary spatial modulation, including:
the system comprises a wave generation source, a binary spatial modulator, a wave intensity detection device and a calculation and storage device, wherein the calculation and storage device is used for generating an array, constructing and training a model, reading the intensity of the intensity detection device and controlling the modulation state of the binary spatial modulator, and the calculation and storage device is required for executing the diffraction focusing method based on the binary spatial modulation.
Compared with the prior art, the diffraction focusing method and device provided by the application have the advantages that the evaluation model and the strategy model are constructed, the modulation state of the binary space modulator can be optimized by utilizing the evaluation model and the strategy model, the waves which are difficult to carry out continuous phase or amplitude modulation can be controlled, further, the effective focusing at the designated position is completed, in addition, the specific focusing position is not required to be designated when the random diffraction intensity signal is acquired, so that the random diffraction intensity signal is not required to be acquired again when different focusing positions are changed, the flow is saved, the implementation mode is simple, the model construction method has strong expandability, and higher efficiency is still realized when the number of the spatial modulation units is more.
Drawings
FIG. 1 is a flow chart of an embodiment of a diffraction focusing method provided by the present application;
FIG. 2 is a schematic diagram of an apparatus in an embodiment;
fig. 3 is a graph of the focusing effect of scattered light at a selected focus position in an embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. 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 application.
The diffraction focusing method and device based on binarization spatial modulation can be used in an optical scattering focusing system. In an optical scattering focusing system, the incident light is subjected to complex and unknown amplitude and phase modulation due to the scatterers. The outgoing light wave becomes a speckle form after diffraction, and effective focusing cannot be formed. Therefore, it is necessary to spatially divide the incident light into individual cells, preserve cells that can constructively interfere at the selected focal position, and remove cells that can destructively interfere, such cell division and selection of whether or not to preserve can be accomplished by a spatial light modulator, and the preserving state of each cell can be optimized in conjunction with the method of the present application to achieve focusing at the selected focal position.
According to the present disclosure, a method for scattering and focusing light may be provided, referring to fig. 1, including the following steps:
s100, randomly generating a plurality of binarization arrays, configuring a modulation state of a binarization spatial modulator, spatially modulating an incident wave surface, and acquiring a plurality of diffraction wave intensities, wherein each diffraction wave intensity is acquired in a preset diffraction wave intensity acquisition range.
In specific implementation, the step S100 specifically includes:
step one, randomly generating a binary array, wherein in the embodiment, the binary array is a binary array formed by random-1, it is to be understood that the binary array is not limited to the binary array formed by random-1, and in other embodiments, the binary array can also be formed by, for example, -0.1,0.1, and the embodiment of the application is not limited thereto;
changing the modulation state of the binary space modulator according to the binary array;
step three, obtaining diffraction wave intensity of an incident wave surface corresponding to the modulation state in an effective area behind the binarization spatial modulator, wherein the diffraction wave intensity is acquired by a sensor;
and fourth, repeating the first step to the third step to obtain a plurality of diffraction wave intensities and a binary array corresponding to the diffraction wave intensities.
Specifically, referring to fig. 2, a semiconductor laser generates laser light with a center wavelength of 635nm, and the laser light is incident on the surface of the DMD spatial light modulator 1. The illumination area of the spatial light modulator 1 is divided into 100×100 individual modulation units, each of which can advance or deflect light impinging thereon in the light path. Then, after being focused by the focusing lens 2, the light is incident on the surface 3 of the common A4 printing paper and scattered, and the diameter of a focusing area is about 1.5mm. The center of the image sensor 4 is about 6cm from the focal region, and the imaging region size is 5.7mm×4.8mm. The computer 5 generates 2200 binary arrays S consisting of-1, 1 randomly, the array size is 100 multiplied by 100, and the modulation states of all the modulation units of the DMD are respectively controlled; the scattered light intensity I is acquired using the image sensor 4 and normalized.
S200, constructing an evaluation model, and training the evaluation model according to the selected position to be focused, the random binarization array and the corresponding diffraction wave intensity; the evaluation model is used for reflecting the mapping relation between the binarization array and the diffraction wave intensity of the diffraction wave intensity at the position to be focused.
In some embodiments, step S200 specifically includes:
selecting a position to be focused, and respectively acquiring the diffraction wave intensity of the position to be focused in each diffraction wave intensity to obtain a plurality of training pairs, wherein the training pairs are a binarization array and the diffraction wave intensity of the position to be focused;
and training the constructed evaluation model by adopting a plurality of training pairs, wherein the input of the evaluation model is a binarization array, and the output of the evaluation model is the diffraction wave intensity of the position to be focused in the diffraction wave intensity.
Wherein the evaluation model is a machine learning model including, but not limited to, a neural network model.
Specifically, selecting a position to be focused in an imaging area of an image sensor, respectively calculating the sum Ic of diffraction signal intensities of the position to be focused in each I, and forming a training data pair with corresponding S; the position to be focused can be chosen to be any position of the imaging plane of the image sensor, e.g. the position shown in fig. 3, comprising 5 x 5 adjacent pixels. The evaluation model adopts a fully-connected neural network as the evaluation model and comprises an input layer, a 2-layer hidden layer and an output layer, wherein the number of neurons of the output layer is 1, and the number of neurons of each other layer is 64. The activation functions of the input layer and the hidden layer are ReLU, and the output layer does not use the activation functions. Initializing an evaluation neural network, taking S as an input, calculating an error between the output of the evaluation neural network and Ic, using a square sum error as an error function, and training by adopting a gradient descent method. The evaluation neural network parameters are optimized by adopting a root mean square propagation method, and the learning rate is set to be 2 multiplied by 10 -3 。
And S300, constructing a strategy model, and training the strategy model by adopting a well-trained evaluation model, wherein the strategy model is used for generating an optimal array, and the optimal array can maximize the output of the evaluation model when being used as the input of the evaluation model.
In some embodiments, step S300 specifically includes:
constructing a strategy model and randomly generating an input array;
and updating the strategy model according to the output of the evaluation model by taking the input array as the input of the strategy model, taking the output of the strategy model as the input of the evaluation model and maximizing the output result of the evaluation model as a training target until the strategy model outputs an optimal array, wherein the optimal array can maximize the output of the evaluation model when being taken as the input of the evaluation model with complete training.
Wherein the policy model is a machine learning model including, but not limited to, a neural network model. When the policy model is a neural network model, the model can be updated by adopting a gradient rising method, however, in other embodiments, other methods for updating the policy model can also be adopted, and the embodiment of the application is not limited to this.
Specifically, a fully connected neural network is used as a strategy model and initialized, the strategy model comprises an input layer, a 2-layer hidden layer and an output layer, the activation functions of the input layer and the hidden layer are ReLU, and the output layer does not use the activation functions; randomly generating an array as input, taking the output of the strategy neural network as the input of an evaluation model, and adopting a gradient rising method to maximize the output of the evaluation model as a training target; the strategy neural network is trained by adopting a root mean square propagation method, and the learning rate is set to be 2 multiplied by 10 -5 . After training, the output array of the strategy neural network is an optimal array, and the optimal array can maximize the output of the evaluation model.
S400, binarizing the optimal array and configuring the modulation state of a binarization spatial modulator to realize focusing at a position to be focused.
Specifically, step S400 specifically includes:
and obtaining an optimal array, carrying out binarization processing on the optimal array, and configuring the modulation state of the binarization spatial modulator according to the binarized optimal array so as to realize focusing of the position to be focused.
The binarization method is that a positive value in the optimal array is changed into 1, and a negative value is changed into-1.
Based on the above-mentioned diffraction focusing method based on the binary spatial modulation, the present application further provides a diffraction focusing device based on the binary spatial modulation, which includes a wave generating source, a binary spatial modulator, a wave intensity detecting device, and a computing and storing device required for executing the diffraction focusing method based on the binary spatial modulation according to the above embodiments, wherein the computing and storing device performs generation of an array and construction and training of a model, reads the intensity of the intensity detecting device, and controls the modulation state of the binary spatial modulating device, and the wave generating source is used for generating an incident wave.
Since the light scattering focusing method and apparatus based on the binarized spatial modulation have been described in detail above, the detailed description thereof is omitted.
The foregoing detailed description of the application has been presented for purposes of illustration and description, but is not intended to limit the scope of the application, i.e., the application is not limited to the details shown and described.
Claims (8)
1. The diffraction focusing method based on binarization spatial modulation is characterized by comprising the following steps:
randomly generating a plurality of binarization arrays, configuring a modulation state of a binarization spatial modulator, spatially modulating an incident wave surface, and acquiring a plurality of diffraction wave intensities, wherein each diffraction wave intensity is acquired in a preset diffraction wave intensity acquisition range;
constructing an evaluation model, and training the evaluation model according to the selected position to be focused, the binary array and the corresponding diffraction wave intensity; the evaluation model is used for reflecting the mapping relation between the binarization array and the diffraction wave intensity of the position to be focused in the diffraction wave intensity;
constructing a strategy model, and training the strategy model by adopting a well-trained evaluation model, wherein the strategy model is used for generating an optimal array, and the optimal array can maximize the output of the evaluation model when being used as the input of the evaluation model;
and binarizing the optimal array and configuring the modulation state of a binarization spatial modulator to realize focusing at a position to be focused.
2. The diffraction focusing method based on binarization spatial modulation according to claim 1, wherein the randomly generating a plurality of binarization arrays and configuring a modulation state of a binarization spatial modulator, spatially modulating an incident wave surface and obtaining a plurality of diffraction wave intensities, comprises:
step one, randomly generating a binarization array;
changing the modulation state of the binary space modulator according to the binary array;
step three, obtaining diffraction wave intensity of an incident wave surface corresponding to the modulation state in an effective area behind the binarization spatial modulator, wherein the diffraction wave intensity is acquired by a sensor;
and fourth, repeating the first step to the third step to obtain a plurality of diffraction wave intensities and a binary array corresponding to the diffraction wave intensities.
3. The diffraction focusing method based on binary spatial modulation according to claim 2, wherein the constructing an evaluation model, training the evaluation model according to the selected position to be focused, the binary array, and the corresponding diffraction wave intensity, comprises:
selecting a position to be focused, and respectively acquiring the diffraction wave intensity of the position to be focused in each diffraction wave intensity to obtain a plurality of training pairs, wherein the training pairs are a binarization array and the diffraction wave intensity of the position to be focused;
and training the constructed evaluation model by adopting a plurality of training pairs, wherein the input of the evaluation model is a binarization array, and the output of the evaluation model is the diffraction wave intensity of the position to be focused in the diffraction wave intensity.
4. The diffraction focusing method based on binarized spatial modulation according to claim 3, wherein the constructing a strategy model, training the strategy model with a well-trained evaluation model, comprises:
constructing a strategy model and randomly generating an input array;
and updating the strategy model according to the output of the evaluation model by taking the input array as the input of the strategy model, taking the output of the strategy model as the input of the evaluation model and maximizing the output result of the evaluation model as a training target until the strategy model outputs an optimal array, wherein the optimal array can maximize the output of the evaluation model when being taken as the input of the evaluation model with complete training.
5. The diffraction focusing method based on binarized spatial modulation according to claim 4, wherein binarizing the optimal array and configuring a modulation state of a binarized spatial modulator to achieve focusing at a position to be focused comprises:
and obtaining an optimal array, carrying out binarization processing on the optimal array, and configuring the modulation state of the binarization spatial modulator according to the binarized optimal array so as to realize focusing of the position to be focused.
6. The diffraction focusing method based on binarized spatial modulation according to any one of claims 1 to 5, wherein the evaluation model and the strategy model are machine learning models including neural network models.
7. The diffraction focusing method based on binarized spatial modulation according to any one of claims 1 to 5, wherein training of the evaluation model, training of the strategy model, binarization of the model output optimal array, and configuration of the binarized spatial modulator are performed again when the selected position to be focused is changed.
8. A diffraction focusing device based on binary spatial modulation, comprising:
a wave generation source for generating an incident wave, a binarized spatial modulator, an intensity detecting means for the wave, and a calculation and storage device required for performing the binarized spatial modulation-based diffraction focusing method according to any one of claims 1 to 7, wherein the calculation and storage device performs generation of an array and construction and training of a model, and reads the intensity measured by the intensity detecting means and controls the modulation state of the binarized spatial modulating device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210553808.7A CN114839789B (en) | 2022-05-20 | 2022-05-20 | Diffraction focusing method and device based on binarization spatial modulation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210553808.7A CN114839789B (en) | 2022-05-20 | 2022-05-20 | Diffraction focusing method and device based on binarization spatial modulation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114839789A CN114839789A (en) | 2022-08-02 |
| CN114839789B true CN114839789B (en) | 2023-09-12 |
Family
ID=82572664
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210553808.7A Active CN114839789B (en) | 2022-05-20 | 2022-05-20 | Diffraction focusing method and device based on binarization spatial modulation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114839789B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103299166A (en) * | 2010-10-27 | 2013-09-11 | 康奈尔大学 | Light field image sensor, method and applications |
| CN109459852A (en) * | 2019-01-07 | 2019-03-12 | 史丽 | A kind of scattering medium optical imaging method neural network based |
| CN109528161A (en) * | 2018-11-06 | 2019-03-29 | 浙江大学 | A kind of high speed and high resoltuion scanning microscopy imaging System and method for based on machine learning |
| DE102018108628A1 (en) * | 2018-04-11 | 2019-10-17 | Stiftung Caesar Center Of Advanced European Studies And Research | Method and system for generating a desired light distribution when passing through a diffuser |
| CN111354055A (en) * | 2020-03-13 | 2020-06-30 | 西南科技大学 | Optical coherence tomography depth reconstruction method based on depth learning |
| CN111552069A (en) * | 2020-04-21 | 2020-08-18 | 中国人民解放军国防科技大学 | Microscopic image automatic focusing method and system based on deep reinforcement learning |
| WO2020244952A1 (en) * | 2019-06-07 | 2020-12-10 | Ecole Polytechnique Federale De Lausanne (Epfl) | System and method for projecting images through scattering media |
| CN113296258A (en) * | 2021-04-29 | 2021-08-24 | 中国科学院西安光学精密机械研究所 | Focusing light spot scanning endoscopic imaging system and method based on multimode fiber coupler |
| CN113574438A (en) * | 2019-02-03 | 2021-10-29 | 巴伊兰大学 | System and method for imaging through scattering media |
| CN113985566A (en) * | 2021-09-10 | 2022-01-28 | 西南科技大学 | Scattered light focusing method based on spatial light modulation and neural network |
| CN114118361A (en) * | 2021-10-29 | 2022-03-01 | 北京宇航系统工程研究所 | Situation assessment method based on deep learning parameter anchoring |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6545790B2 (en) * | 1999-11-08 | 2003-04-08 | Ralph W. Gerchberg | System and method for recovering phase information of a wave front |
| US8930145B2 (en) * | 2010-07-28 | 2015-01-06 | Covidien Lp | Light focusing continuous wave photoacoustic spectroscopy and its applications to patient monitoring |
| WO2019224823A1 (en) * | 2018-05-22 | 2019-11-28 | Ramot At Tel-Aviv University Ltd. | Method and system for imaging and image processing |
| FR3114155B1 (en) * | 2020-09-15 | 2022-07-29 | Supersonic Imagine | METHOD AND SYSTEM FOR ULTRASOUND CHARACTERIZATION OF A MEDIUM |
-
2022
- 2022-05-20 CN CN202210553808.7A patent/CN114839789B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103299166A (en) * | 2010-10-27 | 2013-09-11 | 康奈尔大学 | Light field image sensor, method and applications |
| DE102018108628A1 (en) * | 2018-04-11 | 2019-10-17 | Stiftung Caesar Center Of Advanced European Studies And Research | Method and system for generating a desired light distribution when passing through a diffuser |
| CN109528161A (en) * | 2018-11-06 | 2019-03-29 | 浙江大学 | A kind of high speed and high resoltuion scanning microscopy imaging System and method for based on machine learning |
| CN109459852A (en) * | 2019-01-07 | 2019-03-12 | 史丽 | A kind of scattering medium optical imaging method neural network based |
| CN113574438A (en) * | 2019-02-03 | 2021-10-29 | 巴伊兰大学 | System and method for imaging through scattering media |
| WO2020244952A1 (en) * | 2019-06-07 | 2020-12-10 | Ecole Polytechnique Federale De Lausanne (Epfl) | System and method for projecting images through scattering media |
| CN111354055A (en) * | 2020-03-13 | 2020-06-30 | 西南科技大学 | Optical coherence tomography depth reconstruction method based on depth learning |
| CN111552069A (en) * | 2020-04-21 | 2020-08-18 | 中国人民解放军国防科技大学 | Microscopic image automatic focusing method and system based on deep reinforcement learning |
| CN113296258A (en) * | 2021-04-29 | 2021-08-24 | 中国科学院西安光学精密机械研究所 | Focusing light spot scanning endoscopic imaging system and method based on multimode fiber coupler |
| CN113985566A (en) * | 2021-09-10 | 2022-01-28 | 西南科技大学 | Scattered light focusing method based on spatial light modulation and neural network |
| CN114118361A (en) * | 2021-10-29 | 2022-03-01 | 北京宇航系统工程研究所 | Situation assessment method based on deep learning parameter anchoring |
Non-Patent Citations (1)
| Title |
|---|
| 方兆翔.光场波前调控及其在散射介质中聚焦特性的研究.《中国博士学位论文全文数据库 基础科学辑》.2019,(第5期),第1-91页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114839789A (en) | 2022-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111386538B (en) | Photonic Neural Network System | |
| Luo et al. | Focusing light through scattering media by reinforced hybrid algorithms | |
| JP4997334B2 (en) | Optical microscope with a novel digital method for achieving super-resolution | |
| CN111582435B (en) | Diffraction depth neural network system based on residual error network | |
| CN108332866A (en) | Wavefront based on amplitude modulation quick reconstructing device and method for reconstructing online | |
| Mikhaylov et al. | High accuracy beam splitting using spatial light modulator combined with machine learning algorithms | |
| US5056039A (en) | Holographic interconnect system | |
| JPH09500995A (en) | Multilayer photoelectric neural network | |
| CN114839789B (en) | Diffraction focusing method and device based on binarization spatial modulation | |
| Ye et al. | Robust phase retrieval with green noise binary masks | |
| WO2023175295A1 (en) | Method and apparatus for training a neural network | |
| US20200355983A1 (en) | Chip-Scale Optical Phased Array For Projecting Visible Light | |
| CN113985566B (en) | Scattered light focusing method based on spatial light modulation and neural network | |
| Owechko | Cascaded-grating holography for artificial neural networks | |
| US20230298145A1 (en) | Massively parallel amplitude-only optical processing system and methods for machine learning | |
| JP2010061718A (en) | Hologram reproducing device | |
| CN117114066A (en) | Optical computing topological structure, optical computing topological system and regulating and controlling method of optical computing topological system | |
| JP2023527135A (en) | Super Ising emulator with many-body interactions and all-to-all connectivity | |
| CN114924410B (en) | Focusing method and device based on small phase modulation and phase compensation | |
| Gene et al. | Hybrid optical convolutional neural network with convolution kernels trained in the spatial domain | |
| JP4974962B2 (en) | Light control device | |
| Frauel et al. | Topological map from a photorefractive self-organizing neural network | |
| WO2023184776A1 (en) | Optical computing device and computing method | |
| Yang et al. | Binary Optical Machine Learning: Million-Scale Physical Neural Networks with Nano Neurons | |
| Ye | Robust phase retrieval using optimization and deep learning techniques |
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 |