Coverless real-time image information hiding based on image block matching and dense convolutional network

Luo, Yuanjing; Qin, Jiaohua; Xiang, Xuyu; Tan, Yun; Liu, Qiang; Xiang, Lingyun

doi:10.1007/s11554-019-00917-3

Cited by 132 publications

(65 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We adopt the idea of FPN to obtain richer semantic information. Low-resolution but strong semantic feature maps are up sampled and fused with high-resolution but weak semantic feature maps [36] to construct a feature pyramid sharing rich semantics at all levels. Taking the 8 × 8 × 1024 feature map obtained by Darknet62 as an example, the 8 × 8 × 105 predicted result can be obtained through V1 (CBL × 3 + maxpool × 4 + CBL × 3) and V2 (CBL×2).…”

Section: Five-scale Recognition Network With a Prior Anchor Allocatiomentioning

confidence: 99%

A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss

Gao

Chen

Shi

et al. 2020

Sensors

View full text Add to dashboard Cite

Effective traffic sign recognition algorithms can assist drivers or automatic driving systems in detecting and recognizing traffic signs in real-time. This paper proposes a multiscale recognition method for traffic signs based on the Gaussian Mixture Model (GMM) and Category Quality Focal Loss (CQFL) to enhance recognition speed and recognition accuracy. Specifically, GMM is utilized to cluster the prior anchors, which are in favor of reducing the clustering error. Meanwhile, considering the most common issue in supervised learning (i.e., the imbalance of data set categories), the category proportion factor is introduced into Quality Focal Loss, which is referred to as CQFL. Furthermore, a five-scale recognition network with a prior anchor allocation strategy is designed for small target objects i.e., traffic sign recognition. Combining five existing tricks, the best speed and accuracy tradeoff on our data set (40.1% mAP and 15 FPS on a single 1080Ti GPU), can be achieved. The experimental results demonstrate that the proposed method is superior to the existing mainstream algorithms, in terms of recognition accuracy and recognition speed.

show abstract

Section: Five-scale Recognition Network With a Prior Anchor Allocatiomentioning

confidence: 99%

A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss

Gao

Chen

Shi

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Similarly, Hu et al [16] pointed out that the traditional embedding-based steganography will inevitably leave traces of modification after embedding secret information into a cover image, it is threatened by more and more advanced steganalysis algorithms based on deep learning, but the embedding-free steganography (SWE) without modifying the cover image data seems to be able to overcome such detection problems, therefore, a new image SWE method is proposed, this method is based on a deep convolution to generate an adversarial network, has the characteristics of high accuracy of information extraction and strong antidetection ability. In order to better resist third-party image decryption and steganalysis, Luo et al [17] proposed a carrier-free information hiding method. This method can select the appropriate carrier according to the needs, and at the same time, combined with DCT to generate a hash sequence to achieve a better robust image steganography method.…”

Section: Introductionmentioning

confidence: 99%

StegoPNet: Image Steganography With Generalization Ability Based on Pyramid Pooling Module

et al. 2020

View full text Add to dashboard Cite

In terms of payload capacity and visual effects, the existing image steganography technology based on deep neural networks still needs improvement, to solve this problem, this paper proposes a new deep convolutional steganography network based on the pyramid pooling module to achieve better image steganography. The deep convolutional neural network itself can extract features efficiently. Based on the combination of up-sampling structure, we added a pyramid pool module, under the premise of ensuring safety, fully integrated the previous important global features, achieved good hiding and extraction effects, fully integrated the previous important global features, and effective it reduces the loss of contextual information between different sub-regions in the feature extraction process and achieves better hiding and extraction effects under the premise of ensuring security. Experiments show that the average peak signalto-noise ratio (PSNR)/structure similarity (SSIM) and other indicators between the images obtained by this method have achieved good results in the experiment. Also, we have verified through ablation experiments that the pyramid pooling module can enhance the steganography effect of the network model and can further cut down the loss function of the model. INDEX TERMS Image steganography, deep neural network, pyramid pooling module.

show abstract

“…The research in the paper is mainly aimed at image learning algorithms based on deep learning. In recent years, convolutional neural networks (CNN) [17,18] have greatly improved the performance of semantic image classification [19][20][21][22], object detection [23][24][25][26][27], and image segmentation tasks [28,29]. Researchers have used CNN models for image inpainting tasks, but the image inpainting methods using only CNNs have low accuracy and great room for improvement in performance.…”

Section: Introductionmentioning

confidence: 99%

The image inpainting algorithm used on multi-scale generative adversarial networks and neighbourhood

Zhou

2020

Automatika

View full text Add to dashboard Cite

Various problems existed in the image inpainting algorithms, which can't meet people's requirements visually. Aiming at the defects of the existing image inpainting algorithms, such as low accuracy, poor visual consistency, and unstable training, an improved image inpainting algorithm used on a multi-scale generative adversarial network (GAN) and neighbourhood model have been proposed in the paper. The proposed algorithm mainly improves the network structure of the discriminator, and introduces a multi-scale discriminator based on the global discriminator and the local discriminator. The multi-scale discriminators were trained on images of different resolutions. Discriminators of different scales have different receptive fields, which can guide the generator to generate more global image views and finer details. Aiming at the problem of gradient disappearance or gradient explosion that often occurs in GAN training, the method of WGAN (Wasserstein GAN) has been used to simulate the sample data distribution using EM distance. The proposed model has been trained and tested on the CelebA, ImageNet, and Place2. The experimental results show that compared with the previous algorithm model, the proposed algorithm improves the accuracy of image inpainting and can generate more realistic repairing images, and it is suitable for many types of images.

show abstract

Coverless real-time image information hiding based on image block matching and dense convolutional network

Cited by 132 publications

References 25 publications

A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss

A Multiscale Recognition Method for the Optimization of Traffic Signs Using GMM and Category Quality Focal Loss

StegoPNet: Image Steganography With Generalization Ability Based on Pyramid Pooling Module

The image inpainting algorithm used on multi-scale generative adversarial networks and neighbourhood

Contact Info

Product

Resources

About