CN111462026A - Method and device for recovering phase of synthesized image based on coding exposure - Google Patents
Method and device for recovering phase of synthesized image based on coding exposure Download PDFInfo
- Publication number
- CN111462026A CN111462026A CN202010137673.7A CN202010137673A CN111462026A CN 111462026 A CN111462026 A CN 111462026A CN 202010137673 A CN202010137673 A CN 202010137673A CN 111462026 A CN111462026 A CN 111462026A
- Authority
- CN
- China
- Prior art keywords
- phase
- image
- exposure
- sample
- coded
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000011084 recovery Methods 0.000 claims abstract description 39
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 238000003384 imaging method Methods 0.000 claims abstract description 26
- 239000002131 composite material Substances 0.000 claims abstract description 25
- 230000005540 biological transmission Effects 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 108091026890 Coding region Proteins 0.000 claims abstract description 10
- 230000000737 periodic effect Effects 0.000 claims abstract description 9
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 3
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 8
- 238000010587 phase diagram Methods 0.000 abstract description 8
- 230000001427 coherent effect Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
- G06T2207/10061—Microscopic image from scanning electron microscope
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Microscoopes, Condenser (AREA)
Abstract
The invention discloses a method and a device for recovering a phase of a synthetic image based on coding exposure, wherein the method comprises the following steps: presetting a coding sequence in an EMCCD time sequence circuit to control an exposure mode, controlling a microscope objective table to do periodic sinusoidal motion along the z-axis direction, collecting images and synthesizing based on the coding; acquiring a defocusing image and an in-focus image of a training sample by using a microscopic imaging system, and obtaining a phase image of the training sample by using a phase reconstruction algorithm based on an intensity transmission equation; and training the neural network by using the synthetic image of the training sample and the corresponding phase diagram as a training set. After the network training, the phase diagram can be restored by collecting the coded and exposed synthetic image and inputting the synthetic image into the network. The method has the advantages that the information content of the coded synthetic image is large, and the accuracy of the reconstructed phase diagram is high; the calculation speed is high, and the method is not limited by boundary conditions; can be used for phase recovery of fast dynamic samples; the coded composite image can be obtained simultaneously with the micro imaging by directly combining with the existing micro imaging system.
Description
Technical Field
The invention relates to the technical field of computational imaging, in particular to a method and a device for recovering a phase of a synthetic image based on coding exposure.
Background
When light waves impinge on an object, the object will have an effect on three properties of the waves: amplitude, wavelength, and phase. Because the frequency of light is high, the existing image acquisition equipment can only record the intensity information of the light and can not directly obtain the phase information, so the phase information needs to be recovered by the intensity information. The traditional phase recovery technology depends on the superposition of coherent light to a great extent, the interference device is complex, strict requirements on environmental stability are met, and a series of problems of resolution, stability sensitivity and the like exist. The traditional method for recovering the phase of the intensity transmission equation needs strict boundary conditions, and is large in calculation amount and poor in real-time performance.
The focal map only contains sample information when the focal map is located on a focal plane, the contained information amount is small, the phase recovery effect of the phase map obtained through the intensity transmission equation and the phase recovery effect of the neural network trained by the focal map are general, and the method can only be applied to phase recovery of static samples.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, an object of the present invention is to provide a method for recovering a phase of a synthesized image based on coded exposure, in which the amount of information contained in the coded synthesized image is large, and the accuracy of a reconstructed phase map is high; the calculation speed is high, and the method is not limited by boundary conditions; can be used for phase recovery of fast dynamic samples; the coded composite image can be obtained simultaneously with the micro imaging by directly combining with the existing micro imaging system.
Another object of the present invention is to provide a device for recovering the phase of a synthesized image based on coded exposure.
In order to achieve the above object, an embodiment of an aspect of the present invention provides a method for phase recovery of a synthesized image based on coded exposure, including the following steps: presetting a coding sequence in an EMCCD time sequence circuit to control an exposure mode, controlling a microscope objective table to do periodic sinusoidal motion along the z-axis direction, and collecting a plurality of images under coded exposure; solving the moving speed of the objective table when each exposure shooting point is taken, and combining a plurality of acquired images into one image by taking the speed as a weight; acquiring an in-focus image and a defocusing image at a symmetrical position of a sample by using a microscopic imaging system, and calculating the phase of a training sample by using a phase reconstruction algorithm based on an intensity transmission equation; establishing a neural network model, taking a coded synthetic graph of a sample as the input of a network, taking a corresponding TIE (time independent estimate) computed phase graph as a network true value, and training the network to obtain a trained neural network; acquiring a coded composite image of a sample to be recovered; and inputting the coded synthetic image of the sample to be recovered into the trained neural network to obtain a recovered phase image.
According to the method for restoring the phase of the synthetic image based on the coded exposure, the synthetic image with large information content is obtained in a coded exposure mode, and a neural network with higher phase restoration accuracy is trained; a partially coherent light source can be used, a complex interference device is not needed, boundary conditions are not needed to be considered, and the calculation speed is high; after the network is trained, the method can be applied to dynamic samples, and phase recovery can be realized only by acquiring coded composite images.
In addition, the method for recovering the phase of the synthetic image based on the coded exposure according to the above embodiment of the present invention may further have the following additional technical features:
further, in an embodiment of the present invention, the coded exposure sequence preset in the EMCCD timing circuit is a continuous exposure sequence.
Further, in an embodiment of the present invention, the weight is a scalar value of speed, and the stage moves periodically until a complete code sequence is acquired.
Further, in one embodiment of the present invention, the training sample is any sample used for microscopic imaging, including static samples and dynamic samples.
Further, in an embodiment of the present invention, the phase reconstruction algorithm based on the intensity transfer equation is based on the intensity transfer equation:
wherein k is a wave number, I is a light intensity distribution,
is the phase distribution, z is the vertical coordinate and r is the horizontal coordinate.
In order to achieve the above object, another embodiment of the present invention provides a device for phase recovery of a synthesized image based on coded exposure, including: the control module is used for presetting a coding sequence in the EMCCD time sequence circuit to control an exposure mode, controlling the microscope objective table to do periodic sinusoidal motion along the z-axis direction and collecting a plurality of images under coded exposure; the solving module is used for solving the moving speed of the objective table when each exposure shooting point is taken, and synthesizing a plurality of acquired images into one image by taking the speed as a weight; the acquisition module is used for acquiring an in-focus image and a defocusing image at a symmetrical position of a sample by using a microscopic imaging system and calculating the phase of a training sample by using a phase reconstruction algorithm based on an intensity transmission equation; the training module is used for establishing a neural network model, taking the coded synthetic graph of the sample as the input of the network, taking the corresponding TIE (time independent estimate) calculation phase graph as a network true value, and training the network to obtain a trained neural network; the acquisition module is used for acquiring a coded composite image of a sample to be recovered; and the input module is used for inputting the coded synthetic image of the sample to be recovered into the trained neural network so as to obtain a recovered phase image.
According to the synthetic image phase recovery device based on coding exposure, the synthetic image with large information content is obtained in a coding exposure mode, and the neural network with higher phase recovery accuracy is trained; a partially coherent light source can be used, a complex interference device is not needed, boundary conditions are not needed to be considered, and the calculation speed is high; after the network is trained, the method can be applied to dynamic samples, and phase recovery can be realized only by acquiring coded composite images.
In addition, the coded exposure-based composite image phase recovery apparatus according to the above-described embodiment of the present invention may further have the following additional technical features:
further, in an embodiment of the present invention, the coded exposure sequence preset in the EMCCD timing circuit is a continuous exposure sequence.
Further, in an embodiment of the present invention, the weight is a scalar value of speed, and the stage moves periodically until a complete code sequence is acquired.
Further, in one embodiment of the present invention, the training sample is any sample used for microscopic imaging, including static samples and dynamic samples.
Further, in an embodiment of the present invention, the phase reconstruction algorithm based on the intensity transfer equation is based on the intensity transfer equation:
wherein k is a wave number, I is a light intensity distribution,
is the phase distribution, z is the vertical coordinate and r is the horizontal coordinate.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method for phase retrieval of a composite image based on coded exposure according to an embodiment of the present invention;
FIG. 2 is an optical diagram of a combination of an EMCCD and a microscopic imaging system according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for coded exposure based phase retrieval of a composite image according to one embodiment of the present invention;
FIG. 4 is a diagram of a predetermined code pattern in an EMCCD timing circuit according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a device for phase recovery of a composite image based on coded exposure according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The method and apparatus for phase recovery of a synthetic image based on coded exposure according to an embodiment of the present invention will be described below with reference to the accompanying drawings, and first, the method for phase recovery of a synthetic image based on coded exposure according to an embodiment of the present invention will be described with reference to the accompanying drawings.
FIG. 1 is a flowchart of a method for phase retrieval of a composite image based on coded exposure according to an embodiment of the present invention.
As shown in fig. 1, the method for phase recovery of a composite image based on coded exposure comprises the following steps:
in step S101, a coding sequence is preset in the EMCCD timing circuit to control the exposure mode, and the microscope stage is controlled to perform periodic sinusoidal motion along the z-axis direction, so as to collect a plurality of images under coded exposure.
In one embodiment of the present invention, the EMCCD camera has the features of high resolution and high frame rate, and can be directly connected to the microscopic imaging system. The coding exposure sequence preset in the EMCCD time sequence circuit is a continuous exposure sequence.
In step S102, the moving speed of the stage at each exposure shot is calculated, and the plurality of acquired images are combined into one image with the speed as a weight.
In one embodiment of the present invention, the weight is a scalar value of speed, and the stage moves periodically until a complete code sequence is acquired.
In step S103, an in-focus image and a symmetrically-located out-of-focus image of the sample are acquired by using a microscopic imaging system, and the phase of the training sample is calculated by using a phase reconstruction algorithm based on an intensity transfer equation.
In one embodiment of the present invention, the microscopic imaging system is an optical microscope, and the light source may be a coherent light source or a partially incoherent light source. The training samples may be any samples used for microscopic imaging, including static samples and dynamic samples, in principle increasing the variety and number of training samples as much as possible.
Further, in one embodiment of the present invention, the phase reconstruction algorithm based on the intensity transfer equation is mainly based on the following intensity transfer equation (TIE):
wherein k is a wave number, I is a light intensity distribution,
is the phase distribution, z is the vertical coordinate and r is the horizontal coordinate.
In step S104, a neural network model is established, the coded synthetic graph of the sample is used as the input of the network, the corresponding TIE computation phase graph is used as the network truth value, and the network is trained to obtain the trained neural network.
In an embodiment of the present invention, the neural network model may be any neural network model used for image conversion, and the network only needs to be trained once, and the trained network may be applied to infinite static or dynamic sample phase recovery.
In step S105, an encoded composite image of a sample to be restored is acquired.
In step S106, the encoded composite image of the sample to be restored is input into the trained neural network, so that a restored phase image can be obtained.
To sum up, the method of the embodiment of the invention firstly presets a coding sequence in an EMCCD sequential circuit to control an exposure mode, controls a microscope stage to do periodic sinusoidal motion along the z-axis direction, acquires images and synthesizes the images based on the coding; secondly, acquiring a defocusing image and an in-focus image of the training sample by using a microscopic imaging system, and obtaining a phase image of the training sample by using a phase reconstruction algorithm based on an intensity transmission equation; and then training the neural network by using the synthetic image of the training sample and the corresponding phase diagram as a training set. After the network training, the phase diagram can be restored by collecting the coded and exposed synthetic image and inputting the synthetic image into the network.
The method for phase retrieval of a composite image based on coded exposures will be further explained by a specific embodiment.
An optical path of a combination of an EMCCD and a microscopic imaging system for implementing the method of the embodiment of the present invention is shown in fig. 2, and includes: the device comprises a light source module 1, a condenser lens 2, an iris diaphragm 3, a sample 4, a displacement table 5, an objective lens 6, a reflector 7, a converging lens 8 and an EMCCD camera 9. The light source module can adopt coherent light or partially coherent light, and the degree of coherence of the light source can be adjusted by the diaphragm. The light beam containing object information is collimated by the converging lens after passing through the reflector, and the encoded exposure intensity image is recorded by the EMCCD. As shown in fig. 3, the working flow of the synthetic image phase recovery method based on coded exposure is as follows:
an image acquisition stage: setting a microscope objective table to do periodic sinusoidal motion along the z-axis direction, taking a displacement center as a focal plane, and collecting an out-of-focus image at a symmetrical position of the focal plane and the focal plane; the method is characterized in that a coding sequence control exposure mode shown in figure 4 is preset in an EMCCD sequential circuit, and an objective table periodically moves until a section of complete coding sequence is acquired, so that a plurality of images under coding exposure are obtained.
And (3) image synthesis stage: and calculating the moving speed of the objective table at each exposure shooting point, standardizing the speed scalar values, combining a plurality of acquired images into one image as a weight, wherein the combined image contains the defocusing information and in-focus information of the sample and can reflect the motion condition of the dynamic sample.
And (3) executing a training phase: collecting defocusing images, in-focus images and encoding synthetic images of a large number (3000) of cell samples (HeLa cells), obtaining phase images of corresponding cells by using an intensity transfer equation phase recovery method to serve as truth values of a neural network, and training the neural network by using the phase images and the encoding synthetic images as a training set, wherein parameters of the neural network are as follows: the learning rate is 0.01, the batch size is 32, the decay rate is 0.995, the max epoch is 10000, and the Shuffle frequency is 0.01. The GPU used for network training is GTX 1080TI, and the training time is 4 hours.
And a recovery stage, namely, after the neural network training is finished, the phase recovery can be carried out only by inputting the coded composite image, and the recovery of a 256 × 256-pixel phase image only needs about 0.012 seconds.
The phase recovery result obtained by the synthetic image phase recovery method based on the coding exposure is compared with the recovery result of the intensity transmission equation, so that the accuracy of phase recovery is improved, the calculation speed is accelerated, and the recovery result of the neural network is not limited by edges.
Further, the embodiment of the invention has the following beneficial effects: after the neural network training is finished, the EMCCD and the microscopic imaging system are only needed to be combined to obtain a coded exposure synthetic image, and the coded exposure synthetic image is input into the trained network, so that the phase diagram of the sample can be recovered. Compared with the traditional strength transmission equation phase recovery method, the method has high calculation speed, only needs one training, and is not limited by boundary conditions; compared with the method using the in-focus image as the neural network training sample, the method is high in accuracy and good in real-time performance, and can be used for phase recovery of the dynamic sample.
According to the method for restoring the phase of the synthetic image based on the coding exposure, which is provided by the embodiment of the invention, the synthetic image with large information content is obtained in a coding exposure mode, and a neural network with higher phase restoration accuracy is trained; a partially coherent light source can be used, a complex interference device is not needed, boundary conditions are not needed to be considered, and the calculation speed is high; after the network is trained, the method can be applied to dynamic samples, and phase recovery can be realized only by acquiring coded composite images.
Next, a synthetic image phase recovery apparatus based on coded exposure proposed according to an embodiment of the present invention is described with reference to the drawings.
Fig. 5 is a schematic structural diagram of a composite image phase recovery apparatus based on coded exposure according to an embodiment of the present invention.
As shown in fig. 5, the apparatus 100 for phase recovery of a synthesized image based on coded exposure includes: control module 110, solving module 120, acquisition module 130, training module 140, acquisition module 150, and input module 160.
The control module 110 is used for presetting a coding sequence in the EMCCD time sequence circuit to control an exposure mode, controlling the microscope objective table to do periodic sinusoidal motion along the z-axis direction, and acquiring a plurality of images under coded exposure; the solving module 120 is configured to solve a moving speed of the object stage at each exposure shot point, and combine the acquired multiple images into one image by using the speed as a weight; the acquisition module 130 is configured to acquire an in-focus image and a symmetric out-of-focus image of a sample by using a microscopic imaging system, and calculate a phase of a training sample by using a phase reconstruction algorithm based on an intensity transmission equation; the training module 140 is configured to establish a neural network model, use the encoded synthetic graph of the sample as an input of the network, use the corresponding TIE computation phase diagram as a network true value, and train the network to obtain a trained neural network; the obtaining module 150 is configured to obtain a coded composite image of a sample to be restored; the input module 160 is configured to input the encoded composite image of the sample to be restored into the trained neural network, so as to obtain a restored phase image. The device 100 of the embodiment of the invention has large information content in the coded synthetic image and high accuracy of the reconstructed phase diagram; the calculation speed is high, and the method is not limited by boundary conditions; can be used for phase recovery of fast dynamic samples; the coded composite image can be obtained simultaneously with the micro imaging by directly combining with the existing micro imaging system.
Further, in an embodiment of the present invention, the coded exposure sequence preset in the EMCCD timing circuit is a continuous exposure sequence.
Further, in one embodiment of the present invention, the weight is a scalar value of velocity, and the stage moves periodically until a complete code sequence is acquired.
Further, in one embodiment of the present invention, the training sample is any sample used for microscopic imaging, including static samples and dynamic samples.
Further, in an embodiment of the present invention, the phase reconstruction algorithm based on the intensity transfer equation is based on the intensity transfer equation:
wherein k is a wave number, I is a light intensity distribution,
is the phase distribution, z is the vertical coordinate and r is the horizontal coordinate.
It should be noted that the foregoing explanation on the embodiment of the method for recovering a phase of a synthesized image based on coded exposure is also applicable to the apparatus for recovering a phase of a synthesized image based on coded exposure of this embodiment, and is not repeated here.
According to the synthetic image phase recovery device based on coding exposure, which is provided by the embodiment of the invention, a synthetic image with large information content is obtained in a coding exposure mode, and a neural network with higher phase recovery accuracy is trained; a partially coherent light source can be used, a complex interference device is not needed, boundary conditions are not needed to be considered, and the calculation speed is high; after the network is trained, the method can be applied to dynamic samples, and phase recovery can be realized only by acquiring coded composite images.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method for restoring the phase of a synthesized image based on coded exposure is characterized by comprising the following steps:
presetting a coding sequence in an EMCCD time sequence circuit to control an exposure mode, controlling a microscope objective table to do periodic sinusoidal motion along the z-axis direction, and collecting a plurality of images under coded exposure;
solving the moving speed of the objective table when each exposure shooting point is taken, and combining a plurality of acquired images into one image by taking the speed as a weight;
acquiring an in-focus image and a defocusing image at a symmetrical position of a sample by using a microscopic imaging system, and calculating the phase of a training sample by using a phase reconstruction algorithm based on an intensity transmission equation;
establishing a neural network model, taking a coded synthetic graph of a sample as the input of a network, taking a corresponding TIE (time independent estimate) computed phase graph as a network true value, and training the network to obtain a trained neural network;
acquiring a coded composite image of a sample to be recovered; and
and inputting the coded synthetic image of the sample to be recovered into the trained neural network to obtain a recovered phase image.
2. The method of claim 1, wherein the encoded exposure sequence preset in the EMCCD timing circuit is a continuous exposure sequence.
3. The method of claim 1, wherein the weight is a scalar value of velocity, and the stage moves periodically until a complete code sequence is acquired.
4. The method of claim 1, wherein the training sample is any sample used for microscopic imaging, including static samples and dynamic samples.
5. The method of claim 1,
the phase reconstruction algorithm based on the intensity transmission equation is as follows:
wherein k is a wave number, I is a light intensity distribution,
is the phase distribution, z is the vertical coordinate and r is the horizontal coordinate.
6. A composite image phase recovery apparatus based on coded exposure, comprising:
the control module is used for presetting a coding sequence in the EMCCD time sequence circuit to control an exposure mode, controlling the microscope objective table to do periodic sinusoidal motion along the z-axis direction and collecting a plurality of images under coded exposure;
the solving module is used for solving the moving speed of the objective table when each exposure shooting point is taken, and synthesizing a plurality of acquired images into one image by taking the speed as a weight;
the acquisition module is used for acquiring an in-focus image and a defocusing image at a symmetrical position of a sample by using a microscopic imaging system and calculating the phase of a training sample by using a phase reconstruction algorithm based on an intensity transmission equation;
the training module is used for establishing a neural network model, taking the coded synthetic graph of the sample as the input of the network, taking the corresponding TIE (time independent estimate) calculation phase graph as a network true value, and training the network to obtain a trained neural network;
the acquisition module is used for acquiring a coded composite image of a sample to be recovered; and
and the input module is used for inputting the coded synthetic image of the sample to be recovered into the trained neural network so as to obtain a recovered phase image.
7. The device of claim 6, wherein the encoded exposure sequence preset in the EMCCD timing circuit is a continuous exposure sequence.
8. The apparatus of claim 6, wherein the weight is a scalar value of velocity, and the stage moves periodically until a complete code sequence is acquired.
9. The apparatus of claim 6, wherein the training sample is any sample used for microscopic imaging, including static samples and dynamic samples.
10. The apparatus of claim 6,
the phase reconstruction algorithm based on the intensity transmission equation is as follows:
wherein k is a wave number, I is a light intensity distribution,
is the phase distribution, z is the vertical coordinate and r is the horizontal coordinate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010137673.7A CN111462026B (en) | 2020-03-02 | 2020-03-02 | Method and device for recovering phase of synthesized image based on coding exposure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010137673.7A CN111462026B (en) | 2020-03-02 | 2020-03-02 | Method and device for recovering phase of synthesized image based on coding exposure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111462026A true CN111462026A (en) | 2020-07-28 |
| CN111462026B CN111462026B (en) | 2023-04-07 |
Family
ID=71678187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010137673.7A Active CN111462026B (en) | 2020-03-02 | 2020-03-02 | Method and device for recovering phase of synthesized image based on coding exposure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111462026B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022095598A1 (en) * | 2020-11-04 | 2022-05-12 | 清华大学深圳国际研究生院 | Coded light illumination-based real-time focusing and scanning imaging device and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5831676A (en) * | 1992-08-19 | 1998-11-03 | Canon Kabushiki Kaisha | Image pickup device using plural control parameters for exposure control |
| CN104796609A (en) * | 2015-04-17 | 2015-07-22 | 南京理工大学 | Large-visual-field high-resolution microscopic imaging method based on optimal Hadamard codes |
| CN109685745A (en) * | 2019-01-02 | 2019-04-26 | 西北工业大学 | A kind of phase micro imaging method based on deep learning |
| US20190348011A1 (en) * | 2017-01-20 | 2019-11-14 | Semiconductor Energy Laboratory Co., Ltd. | Display system and electronic device |
-
2020
- 2020-03-02 CN CN202010137673.7A patent/CN111462026B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5831676A (en) * | 1992-08-19 | 1998-11-03 | Canon Kabushiki Kaisha | Image pickup device using plural control parameters for exposure control |
| CN104796609A (en) * | 2015-04-17 | 2015-07-22 | 南京理工大学 | Large-visual-field high-resolution microscopic imaging method based on optimal Hadamard codes |
| US20190348011A1 (en) * | 2017-01-20 | 2019-11-14 | Semiconductor Energy Laboratory Co., Ltd. | Display system and electronic device |
| CN109685745A (en) * | 2019-01-02 | 2019-04-26 | 西北工业大学 | A kind of phase micro imaging method based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| MA CHENGUANG 等: "Transparent Object Reconstruction via Coded Transport of Intensity", 《 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 * |
| 邓超 等: "单像素成像中的光信息编码与解码", 《红外与激光工程》 * |
| 陈卓等: "微结构形貌的光场显微三维重构分辨率增强技术", 《光学技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022095598A1 (en) * | 2020-11-04 | 2022-05-12 | 清华大学深圳国际研究生院 | Coded light illumination-based real-time focusing and scanning imaging device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111462026B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111288925B (en) | Three-dimensional reconstruction method and device based on digital focusing structure illumination light field | |
| CN109459923B (en) | Holographic reconstruction algorithm based on deep learning | |
| CN106371201A (en) | Fourier overlapping correlation imaging system and method based on computational ghost imaging | |
| US20210144278A1 (en) | Compressed sensing based object imaging system and imaging method therefor | |
| CN109873948A (en) | A kind of optical microscopy intelligence auto focusing method, equipment and storage equipment | |
| CN109685745B (en) | Phase microscopic imaging method based on deep learning | |
| CN103472256A (en) | Flow two-dimensional velocity profile measuring method and device based on planar array CCD spatial filter | |
| CN107093194B (en) | A kind of sub-aperture image-pickup method and system | |
| CN107845145B (en) | Three-dimensional reconstruction system and method under electron microscopic scene | |
| CN111462026B (en) | Method and device for recovering phase of synthesized image based on coding exposure | |
| CN113340236B (en) | High dynamic surface topography measuring method | |
| Yun et al. | Accurate 3-D shape recovery using curved window focus measure | |
| CN108876839A (en) | A kind of field depth extending method of structured light three-dimensional imaging system, device and system | |
| CN116958419A (en) | Binocular stereoscopic vision three-dimensional reconstruction system and method based on wavefront coding | |
| US11967096B2 (en) | Methods and apparatuses of depth estimation from focus information | |
| CN106663312B (en) | System and method for improved computational imaging | |
| CN113298700A (en) | High-resolution image reconstruction method in scattering scene | |
| KR102129069B1 (en) | Method and apparatus of automatic optical inspection using scanning holography | |
| Saha et al. | Turbulence strength C n2 estimation from video using physics-based deep learning | |
| CN111080533A (en) | Digital zooming method based on self-supervision residual error perception network | |
| CN106842535B (en) | Phase micro imaging system and its method based on light stream | |
| CN106504195B (en) | Super-resolution imaging method and aplanatism and non-aplanatism super-resolution imaging system | |
| CN111601096B (en) | Image synthesis method with single photon avalanche diode | |
| CN109257524A (en) | A kind of total focus scan imaging method based on Wigner distribution function | |
| CN117970660B (en) | Time domain compression super-resolution high-speed imaging device |
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 |