2019
DOI: 10.1007/s11554-019-00917-3
|View full text |Cite
|
Sign up to set email alerts
|

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

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
64
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
6
4

Relationship

0
10

Authors

Journals

citations
Cited by 132 publications
(65 citation statements)
references
References 25 publications
1
64
0
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%
“…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%
“…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%
“…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%