CN116743934B - Equal resolution image hiding and encrypting method based on deep learning and ghost imaging - Google Patents
Equal resolution image hiding and encrypting method based on deep learning and ghost imaging Download PDFInfo
- Publication number
- CN116743934B CN116743934B CN202310612463.2A CN202310612463A CN116743934B CN 116743934 B CN116743934 B CN 116743934B CN 202310612463 A CN202310612463 A CN 202310612463A CN 116743934 B CN116743934 B CN 116743934B
- Authority
- CN
- China
- Prior art keywords
- image
- net
- information
- secret
- hiding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003384 imaging method Methods 0.000 title claims abstract description 29
- 238000013135 deep learning Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000005286 illumination Methods 0.000 claims abstract description 7
- 230000003287 optical effect Effects 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 claims 1
- 230000017105 transposition Effects 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002474 experimental method Methods 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
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a depth learning and ghost imaging-based multi-resolution image hiding and encrypting method, which comprises the following steps: s1, training a plurality of image samples by using a deep learning method to obtain an equal resolution image steganography model ERIH-Net based on an encoder-decoder structure; s2, taking two test images (a plaintext image and a carrier image) as input ends of a ERIH-Net model Hide-Net image hiding network, and generating a secret image (a primary ciphertext image) containing plaintext image characteristic information; s3, loading a series of Hadamard phase modulation matrix modulation light fields through a Digital Micromirror Device (DMD) to generate a series of illumination speckles; illuminating the dense-containing image by illuminating the speckle, calculating light intensity information in the spatial range of the image by using a barrel detector device BD without spatial resolution, and generating a series of light intensity values (secondary ciphertext); s4, reconstructing a dense image by using the modulated light field information and the acquired barrel detector value through a compressed sensing image reconstruction algorithm; s5, taking the reconstructed dense image as an input end of a ERIH-Net model image extraction network Extract-Net, and successfully extracting plaintext image information. According to the invention, the security and the information hiding capacity of the optical image encryption system can be improved, and the hiding information quantity of unit pixel points can reach 8 bits.
Description
Technical Field
The invention relates to the technical field of optical image encryption, in particular to a method for hiding and encrypting an equal resolution image based on deep learning and ghost imaging.
Background
The ghost imaging has the advantages of delocalized imaging, strong anti-interference performance, high sensitivity and the like, and plays an important role in optical image encryption. The information hiding technology is also an important research direction of information security, and is widely applied to the copyright protection fields of digital watermarking, optical authentication and the like nowadays. However, the currently mainstream information hiding technology has the disadvantage of small encryption capacity, for example, digital watermarking technology based on Discrete Wavelet Transform (DWT) can only hide 1/4, even 1/8 and less of the image or text information of the carrier image.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide the equal resolution image hiding encryption method based on the deep learning and the ghost imaging, which is different from the previous research of applying the deep learning to the reconstruction direction of the ghost imaging image, and the deep learning is applied to the hiding encryption process of the image, so that the hiding and the extraction of the equal resolution image can be realized, and the information of the plaintext image can be extracted from the confidential image after the hidden image is encrypted and compressed, perceived and decrypted by the computing ghost imaging technology, thereby indicating that the encryption scheme has better robustness, the hiding encryption of the equal resolution image is realized, and the information hiding capacity of a hiding encryption system is greatly improved. To achieve the above objects and other advantages and in accordance with the purpose of the present invention, there is provided a multi-resolution image hiding encryption method based on deep learning and ghost imaging, comprising:
S1, designing and training a deep learning image steganography model ERIH-Net for hiding an image with equal resolution, wherein the deep learning image steganography model comprises two sub-networks, namely an image hiding network Hide-Net and an image extracting network Extract-Net;
S2, hiding a plaintext image into a non-secret image through an image hiding network Hide-Net in a pre-trained ERIH-Net to generate a secret image containing plaintext image characteristic information;
S3, loading 4096 Hadamard matrixes through the DMD for modulating a light field and generating illumination speckles, and utilizing the modulated illumination speckles to illuminate a dense image; collecting total light intensity values of the image containing the secret by a barrel detector to obtain 4096 light intensity value sequences, namely ciphertext information;
S4, reconstructing the image information containing the secret by using a compressed sensing image reconstruction algorithm through a ciphertext sequence and a Hadamard modulation mode (key);
s5, taking the compressed sensing reconstructed secret-containing image as an input end of an extraction network Extract-Net, and extracting initial secret image information.
Preferably, in step S1, the medium resolution image steganography model ERIH-Net performs feature extraction and downsampling through a plurality of convolution layers to obtain a high-dimensional feature map; and (3) up-sampling and feature reconstruction are carried out through a deconvolution layer on the basis of the high-dimensional feature map, so that an imaging result with the same size as the original image is obtained.
Preferably, the resolution of the plaintext image and the non-secret image input in step S2 is the same, and the size is 64×64×1 in the experiment.
Preferably, the optical ghost imaging system in step S3 includes a 532.8nm wavelength he—ne laser, a beam expander disposed at one side of the laser, a beam collimating lens, a DMD, a focusing lens disposed at one side of the DMD, a barrel detector BD without spatial resolution, and a computer PC.
Preferably, in step S4, the ciphertext is received through a public channel, the key is received through a secure channel, and the compressed sensing image reconstruction algorithm is an Orthogonal Matching Pursuit (OMP) algorithm.
Preferably, in step S5, the Extract-Net is composed of 6 different convolution layers, the first 5 convolution layers are connected with Relu activation functions, and the last convolution layer is added with a tanh activation function.
Compared with the prior art, the invention has the beneficial effects that:
(1) The image steganography model based on the deep learning is applied to a camouflage encryption process in the computing ghost imaging encryption, and compared with other traditional steganography methods, the image steganography process based on the deep learning is simple to operate and has strong generalization capability.
(2) The hiding and extraction between images with the same resolution can be realized through the equal resolution image steganography model, and after the reconstruction of the computed ghost images, the extraction network of the steganography model can also well extract the information of the plaintext image, so that the model has better robustness.
(3) The combination of the encoder-decoder based deep learning image steganography network and the calculated ghost image encryption and the use of the compressed sensing algorithm can improve the information hiding capacity, the safety and the imaging quality of the camouflage image encryption.
Drawings
FIG. 1 is a system flow diagram of a depth learning and ghost imaging based multi-resolution image hidden encryption method in accordance with the present invention;
FIG. 2 is a ERIH-Net block diagram of a multiple resolution image hiding encryption method based on deep learning and ghost imaging in accordance with the present invention;
FIG. 3 is a block diagram of a ghost imaging light path of a multi-resolution image hidden encryption method based on deep learning and ghost imaging according to the present invention;
FIG. 4 is a system encryption block diagram of a multiple resolution image hiding encryption method based on deep learning and ghost imaging according to the present invention;
FIG. 5 is a system decryption block diagram of a multiple resolution image hidden encryption method based on deep learning and ghosting in accordance with 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.
Referring to fig. 1-5, a depth learning and ghost imaging based multi-resolution image hiding encryption method includes the steps of:
s1, designing and training a deep learning image steganography model ERIH-Net for hiding an image with equal resolution;
S2, hiding a plaintext image into a non-secret image through an image hiding network Hide-Net in a pre-trained ERIH-Net to generate a secret image containing plaintext image characteristic information;
S3, loading 4096 Hadamard matrixes through the DMD for modulating a light field and generating illumination speckles, and utilizing the modulated illumination speckles to illuminate a dense image; collecting total light intensity values of the image containing the secret by a barrel detector to obtain 4096 light intensity value sequences, namely ciphertext information;
S4, reconstructing the image information containing the secret by using a compressed sensing image reconstruction algorithm through a ciphertext sequence and a Hadamard modulation mode (key);
s5, taking the compressed sensing reconstructed secret-containing image as an input end of an extraction network Extract-Net, and extracting initial secret image information.
Example 1
Step S1, firstly, designing an equal resolution image steganography model ERIH-Net based on a coder and decoder structure on a pytorch deep learning framework through python language. The ERIH-Net structure diagram is shown in FIG. 2, and comprises two sub-networks of an image hiding network Hide-Net and an image extracting network Extract-Net, wherein the Hide-Net comprises a preprocessing convolution layer, a downsampling convolution layer and a transposed convolution upsampling layer; the Extract-Net consists of 6 convolutional layers. The preprocessing block can adjust the size of the secret image to be the same resolution as the carrier image, and extract the high-dimensional characteristics of the original image; the convolution up-sampling block and the transpose convolution down-sampling block can perform feature fusion on the high-dimensional feature images formed by splicing the two images, and finally generate a secret image containing secret image information through a Tanh activation function. Setting the MSE loss function as the loss function of the network, and performing training iteration (beta is the weight of reconstruction errors) by taking the sum of the mean square error loss between the carrier image c and the carrier image c 'and the beta times of the mean square error loss between the secret image s and the extracted secret image s' as the total loss function of the equal resolution image steganographic network. The network uses an Adam optimizer to accelerate training, the initial learning rate lr is set to 0.001, the training period is 200 rounds, and after 80 th training and 150 th training, the learning rate is 1/10 times of the original learning rate. The batch processing size is Set to 8, the image size is 64 multiplied by 1, the data Set is 7300 Matlab2018b Oxford-IIIT _ Pets images processed by the gray scale of software, and the test Set is a plurality of sets 12 and Fashion Mnist and binary images, and the data Set is scaled to 64 multiplied by 64.
And S2, taking the secret image with the size of 64 multiplied by 64 pixels and the carrier image as input ends of Hide-Net, calling the pre-trained model parameters to hide the secret image, and generating a carrier image with the secret image characteristics.
The calculated ghost image light path structure diagram in step S3 is shown in fig. 3, wherein the beam emitted by the laser irradiates the transmitted object image after being expanded and collimated, the beam carrying the object amplitude information is irradiated onto DMD (Digital Micromirror Device) loaded with a series of random phase modulation matrixes after passing through the object, the phase information of the light field is modulated by the DMD, and the reflected light intensity information is collected by a Bucket Detector (Bucket Detector) and is recorded as D i. The DMD is sequentially loaded with N times of random phase modulation matrixes, N barrel detector values are obtained, the N barrel detector values are transmitted to a receiver through a public channel as ciphertext, the N phase modulation matrixes are flattened into N one-dimensional vectors, and the N one-dimensional vectors are transmitted to the receiver through a secure channel as secret keys.
And S4, after receiving the ciphertext and the secret key from the public channel and the secure channel, the receiver can calculate corresponding light field distribution information I i (x, y) according to the Fresnel diffraction theorem and a random phase modulation matrix in the secret key. And the receiver performs second-order correlation operation on the obtained light field information and the ciphertext information, so that decrypted image information can be obtained. In order to improve the imaging quality, a compressed sensing optimization decryption algorithm is adopted to realize high-quality reconstruction of secret information. The compressed sensing algorithm can break through the Nyquist sampling law, the image signal is compressed and sampled by utilizing the sparsity of the natural image, the important information of the signal can be reserved, and the original signal is recovered from the compressed data by solving a minimum L1 norm optimization problem.
And S5, the receiver takes the secret image reconstructed by the compressed sensing algorithm as the input of the extraction network to extract secret image information reconstructed by the associated imaging.
In summary, the existing mainstream encryption research of the calculated ghost imaging camouflage image has the defects of small image hiding capacity, complex image hiding process and the like. Aiming at the phenomenon, the invention analyzes various image hiding methods, such as digital watermarking, image steganography and the like, discovers the advantages of realizing image hiding and extraction based on a deep learning image steganography model, and has the advantages of high information hiding capacity, strong Fan Huaneng force, simple operation and the like. And then, a compressed sensing image reconstruction method is analyzed, and compared with other image reconstruction algorithms such as second-order correlation calculation, the method is found to be better in imaging quality effect, excellent in performance, good in robustness and strong in anti-interference capability, and the image reconstruction effect of ghost imaging calculation can be improved.
The number of devices and the scale of processing described herein are intended to simplify the description of the invention, and applications, modifications and variations of the invention will be apparent to those skilled in the art.
Although embodiments of the present invention have been disclosed above, it is not limited to the details and embodiments shown and described, it is well suited to various fields of use for which the invention would be readily apparent to those skilled in the art, and accordingly, the invention is not limited to the specific details and illustrations shown and described herein, without departing from the general concepts defined in the claims and their equivalents.
Claims (1)
1. An equal resolution image encryption method based on deep learning and computational correlation imaging is characterized by comprising the following steps:
S1, designing a deep learning image steganography model ERIH-Net for hiding an equal resolution image, and carrying out feature extraction and downsampling on the equal resolution image steganography model ERIH-Net through a plurality of convolution layers to obtain a high-dimensional feature map; up-sampling and feature reconstruction are carried out through a deconvolution layer on the basis of the high-dimensional feature map, and an imaging result with the same size as the original image is obtained; specifically, an equal resolution image steganography model ERIH-Net based on an encoder and decoder structure is designed on a pytorch deep learning framework through python language, wherein the ERIH-Net structure comprises an image hiding network Hide-Net and an image extraction network Extract-Net, and the Hide-Net comprises a preprocessing convolution layer, a downsampling convolution layer and a transposed convolution upsampling layer; the Extract-Net consists of 6 convolution layers; the size of the secret image can be adjusted to be the same resolution as the carrier image through the preprocessing block, and the high-dimensional characteristics of the original image are extracted; the convolution up-sampling block and the transposition convolution down-sampling block can perform feature fusion on the high-dimensional feature images formed by splicing the two images, and finally generate a secret image containing secret image information through a Tanh activation function; setting MSE loss function as network loss function, training and iterating by using sum of beta times of mean square error loss between carrier image c and carrier image c 'and mean square error loss between secret image s and extracted secret image s' as total loss function of the equal resolution image steganographic network,
S2, training a model, namely hiding a plaintext image into a non-secret image through an image hiding network Hide-Net in a pre-training ERIH-Net to generate a secret image containing plaintext image characteristic information;
S3, loading 4096 Hadamard matrixes through the DMD for modulating a light field and generating illumination speckles, and utilizing the modulated illumination speckles to illuminate a dense image; acquiring total light intensity values of a dense image through a barrel detector to obtain 4096 light intensity value sequences, namely ciphertext information, wherein the optical ghost imaging system comprises a He-Ne laser with 532.8nm wavelength, a beam Expander arranged at one side of the laser, a beam collimating lens L, a digital micromirror device DMD, a focusing lens L arranged at one side of the DMD, a barrel detector BD without space resolution capability and a computer PC; specifically, a light beam emitted by a laser emits a transmission object image after being expanded and collimated, the light beam carrying the object amplitude information is transmitted through the object and irradiates the DMD carrying a series of random phase modulation matrixes, the phase information of a light field is modulated by the DMD, the reflected light intensity information is collected by a barrel detector and recorded as Di, the DMD sequentially loads N random phase modulation matrixes, N barrel detector values are obtained, the N barrel detector values are transmitted to a receiver through a public channel by a sender as ciphertext, and the N phase modulation matrixes are flattened into N one-dimensional vectors to be transmitted to the receiver through a safety channel as keys;
S4, reconstructing the image information containing the secret by using a compressed sensing image reconstruction algorithm through a ciphertext sequence and a Hadamard modulation mode (key), wherein the ciphertext is received through a public channel, the key is received through a secure channel, the compressed sensing image reconstruction algorithm adopts an Orthogonal Matching Pursuit (OMP) algorithm, wherein an image sparse coefficient is set to be 1.5, and if a set value is greater than 1.5, the quality of an image reconstruction result is reduced, and the image extraction network Extract can not completely recover the plaintext image information; if the setting value is smaller than 1.5, the calculated amount is greatly increased, and the imaging time is slow; after receiving ciphertext and a secret key from a public channel and a secure channel, a specific receiver can calculate corresponding light field distribution information according to the Fresnel diffraction theorem and a random phase modulation matrix in the secret key The receiver carries out second-order correlation operation on the obtained light field information and ciphertext information, and decrypted image information can be obtained;
S5, taking the compressed sensing reconstructed dense-containing image as an input end of an extraction network Extract-Net, extracting initial secret image information, wherein the Extract-Net consists of 6 different convolution layers, the first 5 convolution layers are connected with Relu activation functions, and the last convolution layer is added with a tanh activation function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310612463.2A CN116743934B (en) | 2023-05-29 | 2023-05-29 | Equal resolution image hiding and encrypting method based on deep learning and ghost imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310612463.2A CN116743934B (en) | 2023-05-29 | 2023-05-29 | Equal resolution image hiding and encrypting method based on deep learning and ghost imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116743934A CN116743934A (en) | 2023-09-12 |
| CN116743934B true CN116743934B (en) | 2024-05-14 |
Family
ID=87905484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310612463.2A Active CN116743934B (en) | 2023-05-29 | 2023-05-29 | Equal resolution image hiding and encrypting method based on deep learning and ghost imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116743934B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117201691B (en) * | 2023-11-02 | 2024-01-09 | 湘江实验室 | Panoramic scanning associated imaging method based on deep learning |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6557103B1 (en) * | 1998-04-13 | 2003-04-29 | The United States Of America As Represented By The Secretary Of The Army | Spread spectrum image steganography |
| CN108989603A (en) * | 2018-07-18 | 2018-12-11 | 上海理工大学 | Image encryption method based on self-encoding encoder combination relevance imaging |
| CN112989371A (en) * | 2021-03-02 | 2021-06-18 | 浙江科技学院 | Multi-image encryption and decryption method based on Walsh transform and computational ghost imaging |
| CN114119786A (en) * | 2021-11-30 | 2022-03-01 | 浙江科技学院 | Dense Net-based pseudo ghost imaging encryption and decryption method |
| CN114119785A (en) * | 2021-11-30 | 2022-03-01 | 浙江科技学院 | Color ghost steganography method based on multi-discriminator confrontation generation network |
| CN114979407A (en) * | 2022-05-24 | 2022-08-30 | 浙江科技学院 | Multi-image encryption and decryption method based on code division multiple access and deep learning ghost imaging |
| CN115314602A (en) * | 2022-08-02 | 2022-11-08 | 上海理工大学 | Multi-image encryption system based on image scaling and associated imaging |
| CN115603830A (en) * | 2022-09-26 | 2023-01-13 | 浙江科技学院（Cn） | Optical image encryption and decryption method based on deep learning and random mask coding |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9639912B2 (en) * | 2014-12-30 | 2017-05-02 | University Of Macau | Method for reversible image data hiding |
| US11054310B2 (en) * | 2019-09-05 | 2021-07-06 | Coherent AI LLC | Spectral sensor system employing a deep learning model for sensing light from arbitrary angles of incidence, and related hyperspectral imaging sensor |
-
2023
- 2023-05-29 CN CN202310612463.2A patent/CN116743934B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6557103B1 (en) * | 1998-04-13 | 2003-04-29 | The United States Of America As Represented By The Secretary Of The Army | Spread spectrum image steganography |
| CN108989603A (en) * | 2018-07-18 | 2018-12-11 | 上海理工大学 | Image encryption method based on self-encoding encoder combination relevance imaging |
| CN112989371A (en) * | 2021-03-02 | 2021-06-18 | 浙江科技学院 | Multi-image encryption and decryption method based on Walsh transform and computational ghost imaging |
| CN114119786A (en) * | 2021-11-30 | 2022-03-01 | 浙江科技学院 | Dense Net-based pseudo ghost imaging encryption and decryption method |
| CN114119785A (en) * | 2021-11-30 | 2022-03-01 | 浙江科技学院 | Color ghost steganography method based on multi-discriminator confrontation generation network |
| CN114979407A (en) * | 2022-05-24 | 2022-08-30 | 浙江科技学院 | Multi-image encryption and decryption method based on code division multiple access and deep learning ghost imaging |
| CN115314602A (en) * | 2022-08-02 | 2022-11-08 | 上海理工大学 | Multi-image encryption system based on image scaling and associated imaging |
| CN115603830A (en) * | 2022-09-26 | 2023-01-13 | 浙江科技学院（Cn） | Optical image encryption and decryption method based on deep learning and random mask coding |
Non-Patent Citations (3)
| Title |
|---|
| Multiple-Image Encryption Mechanism Based on Ghost Imaging and Public Key Cryptography;Leihong Zhang ET AL;《 IEEE Photonics Journal 》;20190619;全文 * |
| Study on the Key Technology of Image Transmission Mechanism Based on Channel Coding Ghost Imaging;Leihong Zhang ET AL;《IEEE Photonics Journal》;20180726;全文 * |
| 康祎 ; 任治舟 ; 张雷洪 ; 张大伟 ; 庄松林. 关联成像技术在光学信息加密方面的研究现状及展望.《关联成像技术在光学信息加密方面的研究现状及展望》.2022,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116743934A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084734B (en) | Big data ownership protection method based on object local generation countermeasure network | |
| Liansheng et al. | Single-pixel correlated imaging with high-quality reconstruction using iterative phase retrieval algorithm | |
| CN105451024B (en) | Digital hologram coding transmission method adopting compressed sensing | |
| CN107306333B (en) | High-speed single-pixel imaging method | |
| Chen et al. | Deep learning for improving the robustness of image encryption | |
| CN110071798B (en) | Equivalent key obtaining method and device and computer readable storage medium | |
| Shamshad et al. | Compressed sensing-based robust phase retrieval via deep generative priors | |
| Zhou et al. | Optical image encryption based on two-channel detection and deep learning | |
| CN116743934B (en) | Equal resolution image hiding and encrypting method based on deep learning and ghost imaging | |
| Liansheng et al. | An optical color image watermarking scheme by using compressive sensing with human visual characteristics in gyrator domain | |
| Liansheng et al. | Optical image encryption via high-quality computational ghost imaging using iterative phase retrieval | |
| CN111709867B (en) | Novel full convolution network-based equal-modulus vector decomposition image encryption analysis method | |
| CN114894740A (en) | Terahertz single-pixel imaging method and system | |
| Chen et al. | Optical information authentication using optical encryption and sparsity constraint | |
| Zhou et al. | An optical image watermarking method based on computational ghost imaging and multiple logistic maps | |
| CN112217825A (en) | Asymmetric encryption system attack method based on resolution self-adaptive network | |
| Li et al. | Robust image steganography framework based on generative adversarial network | |
| Leihong et al. | Research on double-layers optical information encryption based on ghost imaging | |
| CN110599392A (en) | Optical image hiding method based on calculation ghost imaging | |
| Zhu et al. | Optical color ghost cryptography and steganography based on multi-discriminator generative adversarial network | |
| Zhou et al. | Learning-based optical authentication in complex scattering media | |
| Xue et al. | Deep-learning-assisted optical steganographic encryption via ghost encoding and binary hologram | |
| Kich et al. | Image steganography by deep CNN auto-encoder networks | |
| CN115272131B (en) | Image mole pattern removing system and method based on self-adaptive multispectral coding | |
| Xie et al. | Evading generated-image detectors: A deep dithering approach |
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 |