CN116228520A - Image compressed sensing reconstruction method and system based on transform generation countermeasure network - Google Patents
Image compressed sensing reconstruction method and system based on transform generation countermeasure network Download PDFInfo
- Publication number
- CN116228520A CN116228520A CN202211502231.3A CN202211502231A CN116228520A CN 116228520 A CN116228520 A CN 116228520A CN 202211502231 A CN202211502231 A CN 202211502231A CN 116228520 A CN116228520 A CN 116228520A
- Authority
- CN
- China
- Prior art keywords
- image
- network
- network model
- layer
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005070 sampling Methods 0.000 claims abstract description 43
- 238000012549 training Methods 0.000 claims abstract description 37
- 230000006870 function Effects 0.000 claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 230000003042 antagnostic effect Effects 0.000 claims abstract description 9
- 230000007246 mechanism Effects 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 9
- 238000010276 construction Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000010606 normalization Methods 0.000 claims description 12
- 235000004257 Cordia myxa Nutrition 0.000 claims description 6
- 244000157795 Cordia myxa Species 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000008485 antagonism Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- 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
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/008—Specific post-processing after tomographic reconstruction, e.g. voxelisation, metal artifact correction
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Compression Of Band Width Or Redundancy In Fax (AREA)
Abstract
The invention belongs to the technical field of image processing, and particularly relates to an image compressed sensing reconstruction method and system based on a transform generation countermeasure network, wherein the method comprises the steps of acquiring an image sample set, dividing the image sample set into a training set and a testing set according to a proportion, and preprocessing an image; constructing a transducer to generate an countermeasure network model according to the sampling rate; setting a transducer to generate super parameters of an antagonistic network model, and selecting a loss function and an optimization method; training the network model by using the image data set under different sampling rates, and training the optimal parameters of the learning network model by using a loss function and an optimization method to obtain a trained Transformer under different sampling rates to generate an antagonistic network model; image compressed sensing reconstruction is performed on the countermeasure network model by using the trained transducer generation, and the performance of the network is verified by using the evaluation index. The present invention significantly improves reconstructed image quality using an attention-based mechanism Transformer Block construction depth generation countermeasure network.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to an image compressed sensing reconstruction method and system based on a transform generation countermeasure network.
Background
With the advent of the large data information age, the shortcomings of data sampling by means of the traditional sampling theorem became more apparent. Compressed sensing is an advanced data sampling theory, and based on the compressibility of signals, the sensing of a reconstructed signal is realized on a low-dimensional measured value. However, the conventional iterative optimization compressed sensing reconstruction algorithm has high time complexity and a less ideal reconstruction effect at a low sampling rate. With the development of deep learning, the time complexity of a reconstruction algorithm is greatly reduced and the reconstruction effect is improved by the presentation of a compressed sensing model based on the deep learning.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an image compressed sensing reconstruction method and system based on a transform generation countermeasure network, and the reconstructed image quality is remarkably improved by using a Transformer Block construction depth generation countermeasure network based on an attention mechanism.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the invention provides an image compressed sensing reconstruction method based on a transform generation countermeasure network, which comprises the following steps:
acquiring an image sample set, dividing the image sample set into a training set and a testing set according to a proportion, and preprocessing an image;
constructing a transducer to generate an countermeasure network model according to the sampling rate;
setting a transducer to generate super parameters of an antagonistic network model, and selecting a loss function and an optimization method;
training the network model by using the image data set under different sampling rates, and training the optimal parameters of the learning network model by using a loss function and an optimization method to obtain a trained Transformer under different sampling rates to generate an antagonistic network model;
image compressed sensing reconstruction is performed on the countermeasure network model by using the trained transducer generation, and the performance of the network is verified by using the evaluation index.
Further, each batch size resizes the image to 64×64 pixels prior to training.
Further, the transducer generating an countermeasure network model includes a sampling network, a generating network, and an authenticating network.
Further, the sampling network uses a convolution layer with a convolution kernel size of 32×32 and a step size of 32 to generate a measured value, and the number of output channels is set according to the sampling rate.
Further, the generating network comprises a flat layer, a full-connection layer, a first hidden layer and a second hidden layer, the measured value generated by the sampling network is flattened into one dimension through the flat layer, then nodes are expanded to 24567 through the full-connection layer, and then the output of the full-connection layer is adjusted to the specified image size through reshape operation; the first hidden layer is Transformer Block, wherein Transformer Block comprises the original image and its corresponding position encoding, a PixelNorm normalization layer, a multi-head self-attention mechanism, a PixelNorm normalization layer, and an MLP layer; the second layer of hidden layer is a sub-pixel convolution block, and the sub-pixel convolution block comprises a convolution layer with the size of 3 multiplied by 3, a batch normalization layer, a SELU activation function layer, a sub-pixel convolution layer and a SELU activation function layer.
Further, the authentication network determines whether the generated image of the generating network is true, including a plurality of convolution layers, a batch normalization layer, a flame layer, and a full connection layer.
Further, setting the Transformer to generate the hyper-parameters of the antagonistic network model includes: the initial learning rate is set to 0.001, and the number of network iterations is set to 20.
Further, parameters of the generated network are trained and updated by using an Adam optimization algorithm, and parameters of the identified network are trained and updated by using an RMSProp optimization algorithm.
Further, the performance of the network is verified using the evaluation index peak signal-to-noise ratio PSNR, structural similarity SSIM.
The invention also provides an image compressed sensing reconstruction system based on a transform generation countermeasure network, which comprises the following steps:
the image sample set acquisition module is used for acquiring an image sample set, dividing the image sample set into a training set and a testing set according to a proportion, and preprocessing an image;
the network model construction module is used for constructing a transducer to generate an countermeasure network model according to the sampling rate;
the super-parameter setting module is used for setting a trans-former to generate super-parameters of the countermeasure network model and selecting a loss function and an optimization method;
the training module is used for training the network model under different sampling rates by using the image data set, training the optimal parameters of the learning network model through a loss function and an optimization method, and obtaining the trained Transformer under different sampling rates to generate an countermeasure network model;
and the image reconstruction module is used for performing image compressed sensing reconstruction on the countermeasure network model by using the trained transducer generation and verifying the performance of the network by using the evaluation index.
Compared with the prior art, the invention has the following advantages:
1. the convolution layer is used as a sampling network to simulate the traditional compressed sensing measurement process to measure the image to obtain the measured value, so that the correlation between the measured value and the image is improved. And the measured value is subjected to full-connection layer and reshape operation of the convolutional neural network, and the preliminary reconstruction from the measured vector to the original image is completed. The depth generation countermeasure network is constructed by using the Transformer Block based on the attention mechanism, the primary reconstructed image is fed into the depth generation countermeasure network, the attention mechanism in Transformer Block can acquire global information of the initial reconstructed image, ensure content dependence between the initial reconstructed image and attention weight, increase the receptive field of the network to capture more context information, and iteratively improve the quality of the reconstructed image by generating the countermeasure.
2. The image compressed sensing reconstruction method can be applied to the field of medical MRI, and compared with the traditional scanning method, the image compression sensing reconstruction method has the advantages that the imaging speed is greatly increased, the imaging quality is improved, and the scanning time is shortened. The accurate and efficient image is obtained at the same time of low time cost, and the detail information of the image is reserved; the scanning time of the patient is reduced, and the rapid diagnosis of doctors is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for compressed sensing reconstruction of an image based on a transform generated countermeasure network according to an embodiment of the present invention;
FIG. 2 is a block diagram of a transform generation countermeasure network model in accordance with an embodiment of the present invention;
FIG. 3 is a block diagram of a sampling network and a generation network of an embodiment of the present invention;
fig. 4 is a block diagram of an authentication network according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the present embodiment provides an image compressed sensing reconstruction method based on a transform generating an countermeasure network, which includes the following steps:
step S1, an image sample set is obtained and is divided into a training set and a testing set according to proportion, and the image is preprocessed.
And S2, constructing a transducer to generate an countermeasure network model according to the sampling rate.
And S3, setting a transducer to generate super parameters of the countermeasure network model, and selecting a loss function and an optimization method.
And S4, training the network model by using the image data set under different sampling rates, and training and learning optimal parameters of the network model by using a loss function and an optimization method to obtain a trained transducer under different sampling rates to generate an countermeasure network model.
And S5, performing image compressed sensing reconstruction on the countermeasure network model by using the trained transducer generation, and verifying the performance of the network by using the evaluation index.
In step S1, 202599 images 178×218 of CelebA in the public training dataset were divided into 162770 as training sets, 19867 as verification sets, and 19962 as test sets. Before training, each batch size resizes the image to 64×64 pixels.
Further, the generation of the countermeasure network model by the transducer in step S2 includes three parts, namely, a sampling network, a generating network and an authentication network, as shown in fig. 2.
As shown in fig. 3, the sampling network uses a convolution layer with a convolution kernel size of 32×32 and a step size of 32 to generate a measured value, and the number of output channels is set according to the sampling rate. For an image of size mxn, a convolution layer analog sampling operation with a convolution kernel of size bxbχl and a step size bxb is used, with the final measurement value obtained having a size of
As shown in fig. 3, the generation network includes a flat layer, a fully connected layer, a first layer hidden layer, and a second layer hidden layer. The measured value generated by the sampling network is flattened into one dimension through the flat layer, then nodes are expanded to 24567 through the full-connection layer, and then output 24567 of the full-connection layer is remolded into a characteristic diagram with the image size of 8 x 8 and the channel number of 384 through reshape operation.
The first hidden layer is Transformer Block, and the image is reconstructed with high quality by Transformer Block, wherein Transformer Block comprises the original image and its corresponding position code, pixelNorm normalization layer, multi-head self-attention mechanism, pixelNorm normalization layer, and MLP layer. The structure can be expressed as: [ Embedded Patches-Pixel Norm-Multi headself Attention-Pixel Norm-MLP ], number of output channels is 384. A Multi-head self-Attention mechanism (Multi-head self-Attention) in Transformer Block can block the image and extract global information of the image in the block, and the Attention mechanism can capture more context information and calculate weights of the complexity degree of textures of various parts in the image and allocate computing resources according to the sizes of the weights. The image size is enlarged stage by collocating with sub-pixel convolution, and the reconstruction quality is continuously improved by generating countermeasure.
The second hidden layer is a sub-pixel convolution block, the multiple of the image size is increased through the sub-pixel convolution block, the sub-pixel convolution block comprises a convolution layer with the size of 3 multiplied by 3, a batch normalization layer, a SELU activation function layer, a sub-pixel convolution layer and a SELU activation function layer, and the structure of the sub-pixel convolution block can be expressed as [ Conv ] 3×3 -BN-SeLU-subpixelConv 3×3 ]Transformer Block the output image size is 8 x 8, the output channel number is 384, the image size is 16 x 16 after the sub-pixel convolution, the channel number is 96, the image size is 64 x 64 after the combination of the sub-pixel convolution and Transformer Block for a plurality of times, the channel number is 6, and the reconstructed image with the channel number of 3 and the image size of 64 x 64 is finally obtained after a convolution layer.
As shown in FIG. 4, the authentication network determines whether the image generated by the generation network is true, and the authentication network includes a plurality of convolution layers, a batch normalization layer, a Flatten layer, and a full connection layer, and its structure may be expressed as [ Conv ] 3×3 -LreLU-BN-…-Conv 3×3 -BN-Flatten-DenseLayer]The number of channels of the input image is 3, then the dimension is continuously increased to 512 through a plurality of convolution layers, and then the number of channels is continuously expanded through a full connection layerTo 1024, a true/false result is finally output. By the mutual antagonism of the generation network and the identification network, iterative training, the identification network can help to generate better optimization parameters of the network, so that the quality of the reconstructed image is improved.
In step S3, the images in the training set are input into the network model built in step S2 according to the batch size, the appropriate batch size is set according to the condition of hardware, the batch size is set to 16 in this example, and the transform is set to generate the super parameters of the antagonistic network model: the initial learning rate is set to 0.001, and the number of network iterations is set to 20.
(1) Setting a target loss function of the generating network as follows:
wherein n is the number of training images in the training set, and x i As the original image is to be taken,
a reconstructed image of the network output is generated. And training and updating parameters of the generated network by using an Adam optimization algorithm.
(2) Setting a target loss function of the authentication network as follows:
wherein n is the number of training images in the training set, and x i As the original image is to be taken,
a reconstructed image of the network output is generated. Parameters of the authentication network are trained and updated by using an RMSProp optimization algorithm.
Specifically, the step S4 specifically includes the following steps:
step S401, the channel number of the sampling convolution layer is set according to the sampling rate.
And step S402, the trained model is stored in a npz format.
Specifically, in step S5, the performance of the network is verified by using the evaluation index peak signal-to-noise ratio PSNR and the structural similarity SSIM, which specifically includes the following steps:
step S501, selecting an image in a test set, inputting the image into a trained transducer generation countermeasure network model, obtaining a measured value through a sampling network, entering the measured value into a generation network, and finally outputting a reconstructed image.
In step S502, the reconstruction effect of the network model is measured using PSNR, where a larger PSNR indicates a better reconstruction effect, and the calculation formula is as follows:
mean Square Error (MSE):
MSE represents the current image
And mean square error of the reference image f (i, j); m and N are the height and width of the image, respectively.
Peak signal to noise ratio (PSNR):
n is the number of bits per pixel, typically taken as 8, i.e., the pixel gray scale number is 256 in dB.
In step S503, the reconstruction effect of the network model is measured using SSIM, where a larger SSIM indicates a better reconstruction effect, and the calculation formulas of SSIM for the given images x and y are as follows:
wherein mu x Is the average value of x, mu y Is the average value of y and is,
variance of x>
Variance of t, sigma xy Covariance of x, y, c 1 ＝(k 1 L) 2 ,c 2 ＝(k 2 L) 2 Is a constant for maintaining stability, L is the dynamic range of pixel values, k 1 ＝0.01，k 2 ＝0.03。
Compared with a sub-pixel convolution antagonistic neural network SCGAN, the network model used by the invention has the advantages that PSNR is averagely improved by 2.0018dB and SSIM is averagely improved by 0.0609 on the MNIST data set. PSNR increased by 1.0031dB on the Fashion-MNIST dataset on average and SSIM increased by 0.0513 on average. PSNR increased by 1.2301db on average and ssim increased by 0.1123 on average on the CelebA dataset. Experimental results show that the method has a reconstruction effect superior to that of the current advanced depth compressed sensing algorithm.
Correspondingly to the image compressed sensing reconstruction method based on the transformation generating the countermeasure network, the embodiment also provides an image compressed sensing reconstruction system based on the transformation generating the countermeasure network, which comprises an image sample set acquisition module, a network model construction module, a super-parameter setting module, a training module and an image reconstruction module.
The image sample set acquisition module is used for acquiring an image sample set, dividing the image sample set into a training set and a testing set according to a proportion, and preprocessing an image;
the network model construction module is used for constructing a transducer to generate an countermeasure network model according to the sampling rate;
the super-parameter setting module is used for setting a trans-former to generate super-parameters of the countermeasure network model and selecting a loss function and an optimization method;
the training module is used for training the network model under different sampling rates by using the image data set, training the optimal parameters of the learning network model through a loss function and an optimization method, and obtaining the trained Transformer under different sampling rates to generate an countermeasure network model;
and the image reconstruction module is used for performing image compressed sensing reconstruction on the countermeasure network model by using the trained transducer generation and verifying the performance of the network by using the evaluation index.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only illustrative of the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (10)
1. The image compressed sensing reconstruction method based on the Transformer generating countermeasure network is characterized by comprising the following steps of:
acquiring an image sample set, dividing the image sample set into a training set and a testing set according to a proportion, and preprocessing an image;
constructing a transducer to generate an countermeasure network model according to the sampling rate;
setting a transducer to generate super parameters of an antagonistic network model, and selecting a loss function and an optimization method;
training the network model by using the image data set under different sampling rates, and training the optimal parameters of the learning network model by using a loss function and an optimization method to obtain a trained Transformer under different sampling rates to generate an antagonistic network model;
image compressed sensing reconstruction is performed on the countermeasure network model by using the trained transducer generation, and the performance of the network is verified by using the evaluation index.
2. The transform-based generation of image compressed sensing reconstruction method of claim 1, wherein each batch size resizes the image to 64 x 64 pixels prior to training.
3. The method of claim 1, wherein the transform generation countermeasure network model comprises a sampling network, a generation network, and an authentication network.
4. A method of reconstructing compressed sensing of an image based on a transform generation countermeasure network according to claim 3, wherein the sampling network uses a convolution layer with a convolution kernel size of 32 x 32 and a step size of 32 to generate the measured value, and the number of output channels is set according to the sampling rate.
5. The method for reconstructing image compressed sensing based on a Transformer generating countermeasure network according to claim 4, wherein the generating network comprises a flat layer, a full-connection layer, a first hidden layer and a second hidden layer, the measured value generated by the sampling network is flattened into one dimension through the flat layer, then nodes are expanded to 24567 through the full-connection layer, and then the output of the full-connection layer is adjusted to a specified image size through a reshape operation; the first hidden layer is Transformer Block, wherein Transformer Block comprises the original image and its corresponding position encoding, a PixelNorm normalization layer, a multi-head self-attention mechanism, a PixelNorm normalization layer, and an MLP layer; the second layer of hidden layer is a sub-pixel convolution block, and the sub-pixel convolution block comprises a convolution layer with the size of 3 multiplied by 3, a batch normalization layer, a SELU activation function layer, a sub-pixel convolution layer and a SELU activation function layer.
6. The method of claim 3, wherein the authentication network determines whether the image generated by the generating network is true, and comprises a plurality of convolution layers, a batch normalization layer, a layer and a full connection layer.
7. The method of claim 1, wherein setting hyper-parameters of a transducer generated countermeasure network model comprises: the initial learning rate is set to 0.001, and the number of network iterations is set to 20.
8. A method for reconstructing compressed sensing of an image based on a transform generated against a network according to claim 3, wherein parameters of the generated network are trained and updated by Adam optimization algorithm, and parameters of the identified network are trained and updated by RMSProp optimization algorithm.
9. The method for reconstructing image compressed sensing based on a transform generated countermeasure network according to claim 1, wherein the performance of the network is verified by using an evaluation index peak signal to noise ratio PSNR, structural similarity SSIM.
10. An image compressed sensing reconstruction system based on a Transformer generated countermeasure network, comprising:
the image sample set acquisition module is used for acquiring an image sample set, dividing the image sample set into a training set and a testing set according to a proportion, and preprocessing an image;
the network model construction module is used for constructing a transducer to generate an countermeasure network model according to the sampling rate;
the super-parameter setting module is used for setting a trans-former to generate super-parameters of the countermeasure network model and selecting a loss function and an optimization method;
the training module is used for training the network model under different sampling rates by using the image data set, training the optimal parameters of the learning network model through a loss function and an optimization method, and obtaining the trained Transformer under different sampling rates to generate an countermeasure network model;
and the image reconstruction module is used for performing image compressed sensing reconstruction on the countermeasure network model by using the trained transducer generation and verifying the performance of the network by using the evaluation index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502231.3A CN116228520A (en) | 2022-11-28 | 2022-11-28 | Image compressed sensing reconstruction method and system based on transform generation countermeasure network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211502231.3A CN116228520A (en) | 2022-11-28 | 2022-11-28 | Image compressed sensing reconstruction method and system based on transform generation countermeasure network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116228520A true CN116228520A (en) | 2023-06-06 |
Family
ID=86589863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211502231.3A Pending CN116228520A (en) | 2022-11-28 | 2022-11-28 | Image compressed sensing reconstruction method and system based on transform generation countermeasure network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116228520A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117319656A (en) * | 2023-11-30 | 2023-12-29 | 广东工业大学 | Quantized signal reconstruction method based on depth expansion |
-
2022
- 2022-11-28 CN CN202211502231.3A patent/CN116228520A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117319656A (en) * | 2023-11-30 | 2023-12-29 | 广东工业大学 | Quantized signal reconstruction method based on depth expansion |
| CN117319656B (en) * | 2023-11-30 | 2024-03-26 | 广东工业大学 | Quantized signal reconstruction method based on depth expansion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522857B (en) | People number estimation method based on generation type confrontation network model | |
| CN103475898B (en) | Non-reference image quality assessment method based on information entropy characters | |
| CN110473196B (en) | Abdomen CT image target organ registration method based on deep learning | |
| CN112116601B (en) | Compressed sensing sampling reconstruction method and system based on generation of countermeasure residual error network | |
| CN107274462B (en) | Classified multi-dictionary learning magnetic resonance image reconstruction method based on entropy and geometric direction | |
| CN110021037A (en) | A kind of image non-rigid registration method and system based on generation confrontation network | |
| CN109872305B (en) | No-reference stereo image quality evaluation method based on quality map generation network | |
| CN111127316B (en) | Single face image super-resolution method and system based on SNGAN network | |
| CN111915490A (en) | License plate image super-resolution reconstruction model and method based on multi-scale features | |
| CN107341776A (en) | Single frames super resolution ratio reconstruction method based on sparse coding and combinatorial mapping | |
| CN112991483B (en) | Non-local low-rank constraint self-calibration parallel magnetic resonance imaging reconstruction method | |
| CN113538616A (en) | Magnetic resonance image reconstruction method combining PUGAN and improved U-net | |
| CN112950480A (en) | Super-resolution reconstruction method integrating multiple receptive fields and dense residual attention | |
| CN117333750A (en) | Spatial registration and local global multi-scale multi-modal medical image fusion method | |
| CN107944497A (en) | Image block method for measuring similarity based on principal component analysis | |
| CN114359629A (en) | Pneumonia X chest radiography classification and identification method based on deep migration learning | |
| CN116228520A (en) | Image compressed sensing reconstruction method and system based on transform generation countermeasure network | |
| CN115984110A (en) | Swin-transform-based second-order spectral attention hyperspectral image super-resolution method | |
| CN113569632A (en) | Small sample local surface slow-speed moving object classification method based on WGAN | |
| CN117974693B (en) | Image segmentation method, device, computer equipment and storage medium | |
| CN112184552B (en) | Sub-pixel convolution image super-resolution method based on high-frequency feature learning | |
| CN116843679B (en) | PET image partial volume correction method based on depth image prior frame | |
| CN114529519B (en) | Image compressed sensing reconstruction method and system based on multi-scale depth cavity residual error network | |
| CN109766810B (en) | Face recognition classification method based on collaborative representation, pooling and fusion | |
| CN116071270A (en) | Electronic data generation method and system for generating countermeasure network based on deformable convolution |
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 |