CN114839789A - Diffraction focusing method and device based on binary space modulation - Google Patents
Diffraction focusing method and device based on binary space modulation Download PDFInfo
- Publication number
- CN114839789A CN114839789A CN202210553808.7A CN202210553808A CN114839789A CN 114839789 A CN114839789 A CN 114839789A CN 202210553808 A CN202210553808 A CN 202210553808A CN 114839789 A CN114839789 A CN 114839789A
- Authority
- CN
- China
- Prior art keywords
- binarization
- model
- array
- evaluation model
- training
- 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.)
- Granted
Links
Images
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 invention discloses a diffraction focusing method and a device based on binary space 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 incident waves, and acquiring a plurality of diffraction wave intensities corresponding to the binarization arrays in a diffraction wave intensity acquisition area; constructing an evaluation model, and training the evaluation model according to the plurality of diffraction wave intensities, the selected position to be focused and the plurality of binarization arrays; constructing a strategy model, and training the strategy model by adopting a completely trained evaluation model; and acquiring an optimal array by adopting a strategy model with complete training, binarizing the optimal array and setting the modulation state of each binary space modulator 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, small influence of noise and the like.
Description
Technical Field
The invention relates to the technical field of computational imaging, in particular to a diffraction focusing method and device based on binary space modulation.
Background
The wave surface propagated in the space is divided into a plurality of independent units by utilizing a space modulation mode, amplitude or phase modulation is applied to each unit, the diffraction propagation of the subsequent wave surface can be regulated and controlled, and further the focusing at a specified position is realized. Compared with continuous phase or continuous amplitude modulation, binary modulation is easier to realize and the modulation speed is faster. For example, continuous phase modulation is difficult for extreme ultraviolet light or X-rays, but binary modulation can be achieved by controlling "transmission" and "non-transmission" at different positions in space, and a typical example is a zone plate. In the visible light wave band, the binary space modulator based on the digital micro-mirror device can reach the modulation frequency of tens of thousands of hertz, which is far higher than the continuous phase or continuous amplitude space modulator based on the liquid crystal at present.
When the wave surface has unknown amplitude and phase spatial distribution or undergoes a non-free propagation process such as scattering during the propagation process, the wave surface needs to be focused by combining a wavefront correction technology. For example, in the optical field, a binarization wavefront correction technology based on point-by-point trial or a genetic algorithm can realize focusing of light transmitted through a scatterer by using a digital micromirror device, but cannot flexibly change a focusing position; the entire wavefront correction process needs to be repeated if the focal position needs to be changed. The transmission matrix measurement-based binarization wavefront correction technology can realize focusing at a plurality of positions after a scattering transmission characteristic matrix is obtained through multiple measurements, but has the defects of long calculation time, high possibility of being influenced by noise and the like. The method can effectively realize the focusing based on the binary space modulation, and has the advantages of simple realization mode, strong expandability of the model construction method, short calculation time and less influence of noise.
Disclosure of Invention
The invention aims to provide a diffraction focusing method and device based on binary space modulation, which have the advantages of simple implementation mode, strong expandability of a model construction method, short calculation time, small noise influence and the like.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a diffractive focusing method comprising the steps of:
randomly generating a plurality of binarization arrays, configuring the modulation state of a binarization spatial modulator, carrying out spatial modulation on the wave surface of incident waves and obtaining a plurality of diffracted wave intensities, wherein each diffracted wave intensity is obtained in a preset diffracted wave intensity acquisition range;
constructing an evaluation model, and training the evaluation model according to the selected position to be focused, the random binary array and the corresponding diffracted wave intensity; the evaluation model is used for reflecting the mapping relation between the binary array and the diffracted wave intensity of the position to be focused in the diffracted wave intensity;
constructing a strategy model, and training the strategy model by adopting a completely 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 carrying out binarization on the optimal array and configuring the modulation state of a binarization space modulator so as to realize focusing at a position to be focused.
In some embodiments, the randomly generating a plurality of binarization arrays and configuring a modulation state of a binarization spatial modulator, and performing spatial modulation on an incident wave front and obtaining a plurality of diffracted wave intensities includes:
step one, randomly generating a binary array;
changing the modulation state of the binarization space modulator according to the binarization array;
acquiring the diffracted wave intensity of an incident wave surface corresponding to the modulation state in an effective diffraction area behind the spatial modulator and acquired by a sensor;
and step four, repeating the step one to the step three to obtain a plurality of diffraction wave intensities and a binarization array corresponding to the diffraction wave intensities.
In some embodiments, the constructing an evaluation model, and training the evaluation model according to the selected position to be focused, the random binarization array, and the corresponding diffracted wave intensity includes:
selecting a position to be focused, and respectively obtaining the diffracted wave intensity of the position to be focused in each diffracted wave intensity to obtain a plurality of training pairs, wherein the training pairs are a binary array and the diffracted 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 diffracted wave intensity of a position to be focused in the diffracted wave intensity.
In some embodiments, the constructing a policy model, and the training the policy model using a fully-trained 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, taking the maximization of the output result of the evaluation model as a training target, and till the strategy model outputs an optimal array, wherein the optimal array can maximize the output of the evaluation model when being used as the input of the evaluation model.
In some embodiments, the binarizing the optimal array and configuring a modulation state of a binary spatial modulator to realize focusing at a position to be focused includes:
and acquiring an optimal array, carrying out binarization processing on the optimal array, and configuring the modulation state of the binarization space modulator according to the optimal array after the binarization processing so as to realize focusing of a 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, the training of the evaluation model, the training of the strategy model, the binarization of the optimal array output by the model, and the configuration of the binarization spatial modulator may be performed again.
In a second aspect, the present invention further provides a diffractive focusing apparatus 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 required for executing the diffraction focusing method based on the binary spatial modulation, wherein the calculation and storage device executes the generation of an array and the construction and training of a model, reads the intensity of the intensity detection device and controls the modulation state of the binary spatial modulation device, and the wave generation source is used for generating incident waves.
Compared with the prior art, the diffraction focusing method and the diffraction focusing device provided by the invention have the advantages that the evaluation model and the strategy model are built, the modulation state of the binary space modulator can be optimized by utilizing the evaluation model and the strategy model, waves which are difficult to carry out continuous phase or amplitude modulation can be controlled, and effective focusing at a specified position is further completed, in addition, a specific focusing position is not required to be specified when random diffraction intensity signals are collected, so that the random diffraction intensity signals are not required to be collected again when different focusing positions are changed, the process is saved, the implementation mode is simple, the model building method is strong in expandability, and higher efficiency is still realized when the number of space modulation units is more.
Drawings
FIG. 1 is a flow chart of one embodiment of a diffractive focusing method provided by the present invention;
FIG. 2 is a schematic view of the apparatus in the example;
FIG. 3 is a graph showing the focusing effect of the scattered light at a selected focusing position in the example.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The diffraction focusing method and device based on the binary 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 scattering body. The emergent light waves are diffracted and then changed into speckle forms, and effective focusing cannot be formed. Therefore, it is necessary to spatially divide the incident light into independent cells, to reserve cells that interfere constructively at a selected focal position, and to remove cells that interfere destructively, and this cell division and the selection of whether to reserve can be performed by a spatial light modulator, and the reservation state of each cell can be optimized in conjunction with the method of the present invention to achieve focusing at the selected focal position.
According to the present invention, a method for scattering and focusing light can be provided, referring to fig. 1, comprising the following steps:
s100, randomly generating a plurality of binarization arrays, configuring the modulation state of a binarization spatial modulator, spatially modulating the wave surface of incident waves and acquiring a plurality of diffracted wave intensities, wherein each diffracted wave intensity is acquired within a preset diffracted wave intensity acquisition range.
In specific implementation, the step S100 specifically includes:
step one, randomly generating a binarization array, wherein in this embodiment, the binarization array is a binarization array randomly composed of-1, it should be understood that the binarization array is not limited to be composed of-1, and in other embodiments, a mode of, for example, being composed of-0.1, 0.1 may also be used, which is not limited in this embodiment of the present invention;
changing the modulation state of the binarization space modulator according to the binarization array;
acquiring the diffracted wave intensity of an incident wave surface which is acquired by a sensor and is positioned in an effective area behind the binarization spatial modulator and corresponds to the modulation state;
and step four, repeating the step one to the step three to obtain a plurality of diffraction wave intensities and a binarization array corresponding to the diffraction wave intensities.
Specifically, referring to fig. 2, the 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 incident thereon out of the optical path. Then, after being focused by a focusing lens 2, the light enters the surface 3 of the common A4 printing paper and is scattered, and the diameter of a focusing area is about 1.5 mm. The center of the image sensor 4 is about 6cm from the focal area, and the size of the imaging area is 5.7mm × 4.8 mm. The computer 5 generates 2200 binary arrays S consisting of-1, 1 randomly, the size of the array is 100 multiplied by 100, and the modulation states of each modulation unit of the DMD are respectively controlled; the scattered light intensity I is collected 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 binary array and the corresponding diffracted wave intensity; the evaluation model is used for reflecting the mapping relation between the binarization array and the diffracted wave intensity of the position to be focused in the diffracted wave intensity.
In some embodiments, step S200 specifically includes:
selecting a position to be focused, and respectively obtaining the diffracted wave intensity of the position to be focused in each diffracted wave intensity to obtain a plurality of training pairs, wherein the training pairs are a binary array and the diffracted 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 diffracted wave intensity of a position to be focused in the diffracted wave intensity.
Wherein the evaluation model is a machine learning model including, but not limited to, a neural network model.
Specifically, positions to be focused are selected in an imaging area of the image sensor, the sum Ic of the diffraction signal intensities of the positions to be focused in each I is calculated respectively, and a training data pair is formed by the sum Ic and S corresponding to the sum Ic; the position to be focused can be selected from any position of an imaging plane of the image sensor, such as the position shown in fig. 3, and comprises 5 × 5 adjacent pixels. The evaluation model adopts a fully-connected neural network as an evaluation model and comprises an input layer, 2 hidden layers and an output layer, the number of neurons in the output layer is 1, and the number of neurons in each of the other layers is 64. The activation function of the input layer and the hidden layer is ReLU, and the output layer does not use the activation function. Initializing the evaluation neural network, taking S as input, calculating the output of the evaluation neural network and IcAnd training by using a gradient descent method by using the square sum error as an error function. The evaluation of neural network parameters is optimized by adopting a root mean square propagation method, and the learning rate is set to be 2 multiplied by 10 -3 。
S300, constructing a strategy model, and training the strategy model by adopting a completely 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, taking the output maximization of the evaluation model as a training target, and enabling the output of the evaluation model to be maximized when the strategy model outputs an optimal array which is taken as the input of the completely trained evaluation model.
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 may be updated by using a gradient ascending method, and of course, in other embodiments, other methods that can update the policy model may also be used, which is not limited in the embodiments of the present invention.
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 ascending method to take the output of the maximum 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 . The output array of the strategy neural network after the training is finished is the optimal arrayThe optimal array may maximize the output of the evaluation model.
S400, carrying out binarization on the optimal array and configuring the modulation state of the binarization spatial modulator so as to realize focusing at a position to be focused.
Specifically, step S400 specifically includes:
and acquiring an optimal array, carrying out binarization processing on the optimal array, and configuring the modulation state of the binarization space modulator according to the optimal array after the binarization processing so as to realize focusing of a 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 diffraction focusing method based on binary space modulation, the present invention further provides a diffraction focusing apparatus based on binary space modulation, which includes a wave generation source, a binary space modulator, a wave intensity detection device, and a calculation and storage device required for executing the diffraction focusing method based on binary space modulation as described in the above embodiments, wherein the calculation and storage device executes generation of an array and construction and training of a model, and reads the intensity of the intensity detection device and controls the modulation state of the binary space modulation device, and the wave generation source is used for generating an incident wave.
Since the light scattering focusing method and device based on the binary spatial modulation have been described in detail above, they are not described in detail here.
The present invention has been described in detail, and it should be understood that the detailed description and specific examples, while indicating the embodiments of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
Claims (8)
1. A diffraction focusing method and device based on binary space modulation are characterized by comprising the following steps:
randomly generating a plurality of binarization arrays, configuring the modulation state of a binarization spatial modulator, carrying out spatial modulation on the wave surface of incident waves and obtaining a plurality of diffracted wave intensities, wherein each diffracted wave intensity is obtained in a preset diffracted wave intensity acquisition range;
constructing an evaluation model, and training the evaluation model according to the selected position to be focused, the random binary array and the corresponding diffracted wave intensity; the evaluation model is used for reflecting the mapping relation between the binaryzation 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 completely-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 carrying out binarization on the optimal array and configuring the modulation state of a binarization space modulator so as to realize focusing at a position to be focused.
2. The binary spatial modulation based diffraction focusing method according to claim 1, wherein the randomly generating a plurality of binary arrays and configuring a modulation state of the binary spatial modulator, spatially modulating an incident wave surface and obtaining a plurality of diffracted wave intensities comprises:
step one, randomly generating a binary array;
changing the modulation state of the binarization space modulator according to the binarization array;
acquiring the diffracted wave intensity of an incident wave surface which is acquired by a sensor and is positioned in an effective area behind the binarization spatial modulator and corresponds to the modulation state;
and step four, repeating the step one to the step three to obtain a plurality of diffraction wave intensities and a binarization array corresponding to the diffraction wave intensities.
3. The diffraction focusing method based on binarization spatial modulation as recited in claim 2, wherein the constructing an evaluation model, and the training the evaluation model according to the selected position to be focused, the random binarization array and the corresponding diffracted wave intensity comprises:
selecting a position to be focused, and respectively obtaining the diffracted wave intensity of the position to be focused in each diffracted wave intensity to obtain a plurality of training pairs, wherein the training pairs are a binary array and the diffracted 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 diffracted wave intensity of a position to be focused in the diffracted wave intensity.
4. The diffraction focusing method based on binarization spatial modulation as recited in claim 3, wherein the constructing the strategy model, and the training the strategy model by adopting a fully-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, taking the output maximization of the evaluation model as a training target, and enabling the output of the evaluation model to be maximized when the strategy model outputs an optimal array which is taken as the input of the completely trained evaluation model.
5. The diffraction focusing method based on the binarization spatial modulation as recited in claim 4, wherein the binarizing the optimal array and configuring the modulation state of the binarization spatial modulator to realize focusing at the position to be focused comprises:
and acquiring an optimal array, carrying out binarization processing on the optimal array, and configuring the modulation state of the binarization space modulator according to the optimal array after the binarization processing so as to realize focusing of a position to be focused.
6. A binary spatial modulation based diffractive focusing method according to any one of claims 1 to 5 characterized in that said evaluation model and said strategy model are machine learning models including but not limited to neural network models.
7. A binary spatial modulation based diffractive focusing method according to any one of claims 1 to 5 characterized in that when said selected focusing position changes, the training of evaluation model, the training of strategy model, the binarization of model output optimal array and the configuration of binary spatial modulator are re-performed.
8. A diffractive focusing device based on binary spatial modulation, comprising:
a wave generation source for generating incident waves, a binary spatial modulator, a wave intensity detection device, and a calculation and storage device required for executing the binary spatial modulation-based diffraction focusing method according to any one of claims 1 to 7, wherein the calculation and storage device executes generation of an array and construction and training of a model, and reads the intensity measured by the intensity detection device and controls the modulation state of the binary spatial modulation 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 true CN114839789A (en) | 2022-08-02 |
| CN114839789B 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 (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020060831A1 (en) * | 1999-11-08 | 2002-05-23 | Gerchberg Ralph W. | System and method for recovering phase information of a wave front |
| US20120029829A1 (en) * | 2010-07-28 | 2012-02-02 | Nellcor Puritan Bennett Llc | Light Focusing Continuous Wave Photoacoustic Spectroscopy And Its Applications To Patient Monitoring |
| 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 |
| US20210073959A1 (en) * | 2018-05-22 | 2021-03-11 | Ramot At Tel-Aviv University Ltd. | Method and system for imaging and image processing |
| 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***工程研究所 | Situation assessment method based on deep learning parameter anchoring |
| US20220082529A1 (en) * | 2020-09-15 | 2022-03-17 | Supersonic Imagine | Method and system for ultrasonic characterization of a medium |
-
2022
- 2022-05-20 CN CN202210553808.7A patent/CN114839789B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020060831A1 (en) * | 1999-11-08 | 2002-05-23 | Gerchberg Ralph W. | System and method for recovering phase information of a wave front |
| US20120029829A1 (en) * | 2010-07-28 | 2012-02-02 | Nellcor Puritan Bennett Llc | Light Focusing Continuous Wave Photoacoustic Spectroscopy And Its Applications To Patient Monitoring |
| 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 |
| US20210073959A1 (en) * | 2018-05-22 | 2021-03-11 | Ramot At Tel-Aviv University Ltd. | Method and system for imaging and image processing |
| 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 |
| US20220082529A1 (en) * | 2020-09-15 | 2022-03-17 | Supersonic Imagine | Method and system for ultrasonic characterization of a medium |
| 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***工程研究所 | Situation assessment method based on deep learning parameter anchoring |
Non-Patent Citations (3)
| Title |
|---|
| DUYGU AKBULUT ET,AL: "Focusing light through turbid media by binary amplitude modulation", pages 1 * |
| YUNQI LUO ET,AL: "Towards smart optical focusing:deep learning-empowered dynamic wavefront shaping through nonstationary scattering media", vol. 9, no. 8, pages 262 - 278 * |
| 方兆翔: "光场波前调控及其在散射介质中聚焦特性的研究", no. 5, pages 1 - 91 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114839789B (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7512573B2 (en) | Optical processor for an artificial neural network | |
| CN109459852B (en) | Scattering medium optical imaging method based on neural network | |
| CN106950195A (en) | Programmable optical elements and light field regulator control system and method based on scattering medium | |
| CN111582435B (en) | Diffraction depth neural network system based on residual error network | |
| CN108332866B (en) | Wavefront on-line rapid reconstruction device and method based on amplitude modulation | |
| US5056039A (en) | Holographic interconnect system | |
| WO2019060645A1 (en) | Photonic neural network system | |
| Mikhaylov et al. | High accuracy beam splitting using spatial light modulator combined with machine learning algorithms | |
| KR20180064884A (en) | Optical convolutional neural network system based on holographic technology | |
| CN106094487A (en) | Terahertz in-line holographic imaging systems based on multiple recording distances and formation method | |
| US20230298145A1 (en) | Massively parallel amplitude-only optical processing system and methods for machine learning | |
| CN113985566B (en) | Scattered light focusing method based on spatial light modulation and neural network | |
| EP0411108A1 (en) | Optical neural network and training method. | |
| CN114839789A (en) | Diffraction focusing method and device based on binary space modulation | |
| US5068801A (en) | Optical interconnector and highly interconnected, learning neural network incorporating optical interconnector therein | |
| JPH03504053A (en) | How to make multi-holographic lenses | |
| CN111652372A (en) | Wavefront restoration method and system based on diffractive optical neural network | |
| CN114518659A (en) | Scattering medium light field focusing method and device based on complex amplitude light field regulation | |
| CN114815961A (en) | On-chip optical diffraction calculation processor and all-optical image classification equipment | |
| EP4150430A1 (en) | Super ising emulator with multi-body interactions and all-to-all connections | |
| EP0999481A1 (en) | Phase type computer hologram and optical instrument | |
| Wang et al. | Design and implementation of a linear array laser emitting optical system based on diffractive principles | |
| CN114924410B (en) | Focusing method and device based on small phase modulation and phase compensation | |
| Krotov et al. | Multiple beam diffractive setup for intraocular accommodation evaluation | |
| EP0499469A2 (en) | Artificial neural network pattern recognition system |
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 |