High-Capacity Image Steganography Based on Improved Xception

Duan, Xintao; Gou, Mengxiao; Liu, Nao; Wang, Wenxin; Qin, Chuan

doi:10.3390/s20247253

Cited by 22 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The peak signal-to-noise ratio (PSNR) could evaluate the quality of the processed images, which is commonly used in the fields of super-resolution, compression, and restoration of images. PSNR was expressed as the logarithm of the ratio of the mean square error (MSE) between the reconstructed image and the true image to the maximum possible pixel value of the image [ 17 ].…”

Section: Methodsmentioning

confidence: 99%

Diagnosis of Early Cervical Cancer with a Multimodal Magnetic Resonance Image under the Artificial Intelligence Algorithm

Zhang

et al. 2022

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

This research was conducted to explore the value of multimodal magnetic resonance imaging (MRI) based on the alternating direction algorithm in the diagnosis of early cervical cancer. 64 patients diagnosed with early cervical cancer clinicopathologically were included, and according to the examination methods, they were divided into A group with conventional multimodal MRI examination and B group with the multimodal MRI examination under the alternating direction algorithm. The diagnostic results of two types of multimodal MRI for early cervical cancer staging were compared with the results of clinicopathological examination to judge the application value in the early diagnosis of cervical cancer. The results showed that in the 6 randomly selected samples of early cervical cancer patients, the peak signal-to-noise ratio (PSNR) and structural similarity image measurement (SSIM) of multimodal MRI images under the alternating direction algorithm were significantly higher than those of conventional multimodal MRI images and the image reconstruction was clearer under this algorithm. By comparing MRI multimodal staging, statistical analysis showed that the staging accuracy of B group was 75%, while that of A group was only 59.38%. For the results of postoperative medical examinations, the examination consistency of B group was better than that of A group, with a statistically significant difference ( P < 0.05). The area under the receiver operating characteristic (ROC) curve (AUC) of B group was larger than that of A group; thus, sensitivity was improved and misdiagnosis was reduced significantly. Multimodal MRI under the alternating direction algorithm was superior to conventional multimodal MRI examination in the diagnosis of early cervical cancer, as the lesions were displayed more clearly, which was conducive to the detection rate of small lesions and the staging accuracy. Therefore, it could be used as an ideal MRI method for the assistant diagnosis of cervical cancer staging.

show abstract

Section: Methodsmentioning

confidence: 99%

Diagnosis of Early Cervical Cancer with a Multimodal Magnetic Resonance Image under the Artificial Intelligence Algorithm

Zhang

et al. 2022

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

show abstract

“…Duan et al [9] modified the network structure of the encoder network, with the help of the advantages of the U-Net [6] network itself, the network structure of upsampling and downsampling has a connection operation, and the features of the shallow and deep layers of the image are preserved, so the reconstructed decrypted image has a high similarity with the original secret image, which effectively improves the quality of the image. Subsequently, Duan et al tried to modify different networks and introduced network structures such as FC-DenseNet [10], Xception [11], VQ-VAE [12], and continuously improved the similarity between the secret image and the secret image and the image of the decrypted image. quality.…”

Section: Information Hiding Model Based On Encoder-decoder Networkmentioning

confidence: 99%

Hiding Image within Image Based on Deep Learning

Yang¹,

Zhang²,

Wu³

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Information hiding technology is a technology that transmits secret information through a carrier, and is a research hotspot in the field of information security. The traditional information hiding algorithm relies on the meticulous design of human beings, and obtains the dense image through modification. With the development of deep learning, the integration of information hiding technology and deep learning has resulted in many information hiding technologies based on deep learning. Among them, image hiding has become a research hotspot due to its large steganographic capacity. Therefore, this paper reviews the information hiding technology based on deep learning. According to the difference of hidden models, it is analysed from four aspects: (1) information hiding model based on encoder-decoder; (2) information hiding model based on generative adversarial network; (3) information hiding model based on invertible network; (4) information hiding model based on neural network information hiding models for style transfer. Finally, these models are analysed and compared, and the future development direction is discussed and prospected.

show abstract

“…The network model in this paper consists of Xception [30], LSTM and CNN-Fusion. The innovation is the introduction of a recurrent network, which can extract the features of EEG signals, and build a feature Fusion network (CNN-Fusion).…”

Section: Rcnn-based Feature Extractionmentioning

confidence: 99%

Multi-feature data fusion based on common space model and recurrent convolutional neural networks for EEG tristimania recognition used in upper limb rehabilitation exercises

Sun¹

2018

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

Traditional tristimania recognition methods cannot accurately recognize the mood of patients, which cannot provide effective adjuvant therapy for rehabilitation. Therefore, this paper proposes a new multi-feature data fusion method for Electroencephalography (EEG) tristimania recognition. It combines common space model and recurrent convolutional neural networks to classify the tristimania group and control group. According to the phase lock value, the phase synchronization functional network between electrode channels is constructed, and the functional connection modes of two kinds under different frequency bands are analyzed. The Xception network and LSTM are used as two non-interfering parts to extract two feature matrices from EEG tristimania signals. They are fused into a single feature matrix by merge algorithm. The single feature matrix is input into the recurrent convolutional neural networks (RCNN) for feature extraction and pooling. L2 regularized Softmax function is used as the classifier to complete the training and testing of RCNN. Finally, combining the Fisher score feature selection method and the classifier dependency structure, a low dimensional and efficient feature subset is obtained. Experimental results on public tristimania data sets validate that the proposed method has better effect in terms of accuracy and PLV compared with other strategies.

show abstract

High-Capacity Image Steganography Based on Improved Xception

Cited by 22 publications

References 19 publications

Diagnosis of Early Cervical Cancer with a Multimodal Magnetic Resonance Image under the Artificial Intelligence Algorithm

Diagnosis of Early Cervical Cancer with a Multimodal Magnetic Resonance Image under the Artificial Intelligence Algorithm

Hiding Image within Image Based on Deep Learning

Multi-feature data fusion based on common space model and recurrent convolutional neural networks for EEG tristimania recognition used in upper limb rehabilitation exercises

Contact Info

Product

Resources

About