RIHOOP: Robust Invisible Hyperlinks in Offline and Online Photographs

Jia, Jun; Gao, Zhongpai; Chen, Kang; Hu, Menghan; Min, Xiongkuo; Zhai, Guangtao; Yang, Xiaokang

doi:10.1109/tcyb.2020.3037208

Cited by 34 publications

(21 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On this basis, Jia et al. [17] proposed a scheme using differentiable 3D rendering and just noticeable difference (JND) loss. This method introduces a distortion network (DN) using differentiable 3D rendering to augment the encoded images, in which almost all distortions in print‐camera process are simulated.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A screen‐shooting resilient document image watermarking scheme using deep neural network

Fei

Xia

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

With the advent of the screen‐reading era, the confidential documents displayed on the screen can be easily captured by a camera without leaving any traces. Thus, this paper proposes a novel screen‐shooting resilient watermarking scheme for document image using deep neural network. By applying this scheme, when the watermarked image is displayed on the screen and captured by a camera, the watermark can be still extracted from the captured photographs. Specifically, the scheme is an end‐to‐end neural network with an encoder to embed watermark and a decoder to extract watermark. During the training process, a distortion layer between encoder and decoder is added to simulate the distortions introduced by screen‐shooting process in real scenes, such as camera distortion, shooting distortion, and light source distortion. Furthermore, a background sensitive loss and a lpips loss are used to improve visual quality of the watermarked document images in the training process. Besides, a strength factor adjustment strategy is also designed to improve the visual quality with little loss of bit extraction accuracy. The experimental results show that the proposed scheme has higher visual quality and robustness than the other two recent state‐of‐the‐art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…One is template-additive based methods [10][11][12]. The other two are transformed invariant domain-based methods [13][14][15] which is developed from PSR watermarking scheme, the last one methods are based on the deep neural network (DNN-based) [16,17].…”

Section: Introductionmentioning

confidence: 99%

A screen‐shooting resilient document image watermarking scheme using deep neural network

Fei

Xia

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…As mentioned in the Introduction, DVMark [9] used a pre-trained 3D-CNN to mimic video compression. Jia [13] combined StegaStamp [4] and light model [19], and RIVA-GAN [11] used a differentiable noise layer of DCT to simulate video compression. Essentially, these methods let the model learn the feature of 3D-CNN or differential distortion layer but real video compression.…”

Section: Compressionmentioning

confidence: 99%

“…Most of the existing end-to-end steganography algorithms are based on images, for example, Baluja's model [2], Hayes' model [3], SteganoGan [4], compression. To resist distortion of camera photographing and video compression, Jia [13] built a distortion network combined StegaStamp [14] and a 3D light model [19] All in all, there are many challenges to design an end-to-end video steganography network. First, it requires the steganography algorithm to have a high extraction rate, a large embedding capacity and good visual quality, which strongly depends on an excellent encoding and decoding deep learning network design.…”

Section: Introductionmentioning

confidence: 99%

An End-to-End Robust Video Steganography Model Based on a Multi-Scale Neural Network

Zhang

et al. 2022

Electronics

View full text Add to dashboard Cite

The purpose of video steganography is to hide messages in the video file and prevent them from being detected, and finally the secret message can be extracted completely at the receiver. In this paper, an end-to-end video steganography based on GAN and multi-scale deep learning network is proposed, which consists of the encoder, decoder and discriminator. However, in the transmission process, videos will inevitably be encoded. Thus, a noise layer is introduced between the encoder and the decoder, which makes the model able to resist popular video compressions. Experimental results show that the proposed end-to-end steganography has achieved high visual quality, large embedding capacity, and strong robustness. Moreover, the proposed method performances better compared to the latest end-to-end video steganography.

show abstract

“…Zhong et al [22] proposed a watermarking system based on Deep Neural Networks(DNN) using an unsupervised structure and a new loss calculation method, which is capable of extracting watermarks in camera captured images as well, with good practicality and robustness. Jia et al [23] proposed a new method for embedding hyperlinks into ordinary images that can detect watermarks by cameraequipped mobile devices. Incorporation of a distortion network which employs distinguishable 3D rendering operations among encoder and decoder can emulate distortion caused by the introduction of camera imaging and is somewhat robust to camera photography.…”

Section: Introductionmentioning

confidence: 99%

Robust Watermarking of Screen-Photography Based on JND

Gu¹,

Han²,

Sun³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

With the popularity of smartphones, it is often easy to maliciously leak important information by taking pictures of the phone. Robust watermarking that can resist screen photography can achieve the protection of information. Since the screen photo process can cause some irreversible distortion, the currently available screen photo watermarks do not consider the image content well and the visual quality is not very high. Therefore, this paper proposes a new screen-photography robust watermark. In terms of embedding region selection, the intensity-based Scale-invariant feature transform (SIFT) algorithm used for the construction of feature regions based on the density of feature points, which can make it more focused on the key content of the image; in terms of embedding strength, the Just noticeable difference (JND) model is applied to limit the intensity of the watermark embedding according to the luminance and texture of the picture to balance robustness and invisibility; after embedding watermark, the coefficients in the neighborhood are again adjusted with optimal constraints to improve the accuracy of watermark extraction. After experiments, it is shown that the method we proposed can improve the correct rate of watermark extraction, the quality of the visual aspect of the watermarked picture is also improved.

show abstract

RIHOOP: Robust Invisible Hyperlinks in Offline and Online Photographs

Cited by 34 publications

References 57 publications

A screen‐shooting resilient document image watermarking scheme using deep neural network

A screen‐shooting resilient document image watermarking scheme using deep neural network

An End-to-End Robust Video Steganography Model Based on a Multi-Scale Neural Network

Robust Watermarking of Screen-Photography Based on JND

Contact Info

Product

Resources

About