End-to-End Image Steganography Using Deep Convolutional Autoencoders

Subramanian, N.; Cheheb, Ismahane; Elharrouss, Omar; Al-Maadeed, Somaya; Bouridane, Ahmed

doi:10.1109/access.2021.3113953

Cited by 35 publications

(13 citation statements)

References 39 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, gradient sections of the CXI are calculated by employing the one-dimension balanced method in two different directions, namely, vertical and horizontal. Gradient sections are calculated by using the following Equations ( 25) and (26).…”

Section: Histogram Of Oriented Gradientsmentioning

confidence: 99%

“…Deep learning (DL) and artificial intelligence methods are utilized by scientists for the detection of COVID-19 using CT and chest x-rays images (CXI). DL techniques (20)(21)(22)(23)(24)(25)(26) have shown extraordinary results in research applications and are commonly employed due to the enhanced performance comparative to the conventional techniques. Compared to machine learning and conventional techniques, features are not selected manually.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Framework for Epidemic Analysis, Prediction and Detection of COVID-19

Hassan

Albahli

Javed

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

Covid-19 has become a pandemic that affects lots of individuals daily, worldwide, and, particularly, the widespread disruption in numerous countries, namely, the US, Italy, India, Saudi Arabia. The timely detection of this infectious disease is mandatory to prevent the quick spread globally and locally. Moreover, the timely detection of COVID-19 in the coming time is significant to well cope with the disease control by Governments. The common symptoms of COVID are fever as well as dry cough, which is similar to the normal flu. The disease is devastating and spreads quickly, which affects individuals of all ages, particularly, aged people and those with feeble immune systems. There is a standard method employed to detect the COVID, namely, the real-time polymerase chain reaction (RT-PCR) test. But this method has shortcomings, i.e., it takes a long time and generates maximum false-positive cases. Consequently, we necessitate to propose a robust framework for the detection as well as for the estimation of COVID cases globally. To achieve the above goals, we proposed a novel technique to analyze, predict, and detect the COVID-19 infection. We made dependable estimates on significant pandemic parameters and made predictions of infection as well as potential washout time frames for numerous countries globally. We used a publicly available dataset composed by Johns Hopkins Center for estimation, analysis, and predictions of COVID cases during the time period of 21 April 2020 to 27 June 2020. We employed a simple circulation for fast as well as simple estimates of the COVID model and estimated the parameters of the Gaussian curve, utilizing a parameter, namely, the least-square parameter curve fitting for numerous countries in distinct areas. Forecasts of COVID depend upon the potential results of Gaussian time evolution with a central limit theorem of data the Covid prediction to be justified. For gaussian distribution, the parameters, namely, extreme time and thickness are regulated using a statistical Y2 fit for the aim of doubling times after 21 April 2020. Moreover, for the detection of COVID-19, we also proposed a novel technique, employing the two features, namely, Histogram of Oriented Gradients and Scale Invariant Feature Transform. We also designed a CNN-based architecture named COVIDDetectorNet for classification purposes. We fed the extracted features into the proposed COVIDDetectorNet to detect COVID-19, viral pneumonia, and other lung infections. Our method obtained an accuracy of 96.51, 92.62, and 86.53% for two, three, and four classes, respectively. Experimental outcomes illustrate that our method is reliable to be employed for the forecast and detection of COVID-19 disease.

show abstract

Section: Histogram Of Oriented Gradientsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Robust Framework for Epidemic Analysis, Prediction and Detection of COVID-19

Hassan

Albahli

Javed

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence and deep learning methods are the most commonly used methods by researchers for the detection of coronavirus infection from CT and CXR images. Deep learning methods have shown significant performance in many research applications, such as computer vision [ 7 ], object tracking [ 8 ], gesture recognition [ 9 ], face recognition [ 10 ], and steganography [ [11] , [12] , [13] ]. Deep learning methods are widely used because of their improved performance compared to traditional methods.…”

Section: Introductionmentioning

confidence: 99%

A review of deep learning-based detection methods for COVID-19

Subramanian

Elharrouss

Al‐Maadeed

et al. 2022

Computers in Biology and Medicine

Self Cite

View full text Add to dashboard Cite

COVID-19 is a fast-spreading pandemic, and early detection is crucial for stopping the spread of infection. Lung images are used in the detection of coronavirus infection. Chest X-ray (CXR) and computed tomography (CT) images are available for the detection of COVID-19. Deep learning methods have been proven efficient and better performing in many computer vision and medical imaging applications. In the rise of the COVID pandemic, researchers are using deep learning methods to detect coronavirus infection in lung images. In this paper, the currently available deep learning methods that are used to detect coronavirus infection in lung images are surveyed. The available methodologies, public datasets, datasets that are used by each method and evaluation metrics are summarized in this paper to help future researchers. The evaluation metrics that are used by the methods are comprehensively compared.

show abstract

“…In regardless of the techniques used, image steganography has always been faced with challenges relating to payload capacity, security and robustness. Some approaches like the steganoGAN [18], encoder-decoder: DCGAN [19], HidingGAN [20] and many more have been adopted to solve these inadequacies, but ended in trade-off between the payload capacity and the security of image steganography systems. Zhang et al [21] suggested that these in adequacies could be solved when an appropriate cover is selected and used for a targeted secret image.…”

Section: Introductionmentioning

confidence: 99%

GAN-Based Encoding Model for Reversible Image Steganography

Kuyoro¹,

Nzenwata²,

Awodele³

et al. 2022

RIA

View full text Add to dashboard Cite

In carrying out reversible image steganography, the Generative Adversarial Networks (GANs-based) models have proven to be the most suitable deep learning models for image steganography. Image steganography is a steganography system that hides secret data in an image cover medium without arousing suspicion, and it is defined by the ability to reconstruct the cover medium with no visible distortion after the steganography system has been decoded by extracting the hidden data. In this study, we try achieve the encoding phase in image steganography, where two GAN-base models (CycleGAN and DCGAN) were proposed. Empirical analysis was done to determine a better model for the encoding of image steganography. The Peak Signal-to-Noise Ratio (PSNR), the Structural Similarity Index Metric (SSIM), and bit per pixel (bpp) were used as the metrics for the analysis. The outcome of DCGAN yielded (SSIM=0.48; PSNR=19.86; bpp=24.79) and the outcome of using CycleGAN yielded (SSIM=0.97; PSNR=41.45; bpp=24.97). These values concluded that the CycleGAN was preferable over the DCGAN. Hence, the CycleGAN was adopted as the encoding model.

show abstract

End-to-End Image Steganography Using Deep Convolutional Autoencoders

Cited by 35 publications

References 39 publications

A Robust Framework for Epidemic Analysis, Prediction and Detection of COVID-19

A Robust Framework for Epidemic Analysis, Prediction and Detection of COVID-19

A review of deep learning-based detection methods for COVID-19

GAN-Based Encoding Model for Reversible Image Steganography

Contact Info

Product

Resources

About