De-Mark GAN: Removing Dense Watermark with Generative Adversarial Network

Wu, Jinlin; Shi, Hailin; Zhang, Shu; Lei, Zhen; Yang, Yang; Li, Stan Z.

doi:10.1109/icb2018.2018.00021

Cited by 10 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two watermarks were used in this study, the goal was testing the effectiveness of a single visible watermark to protect a large set of images. Wu et al [41] used the generative adversarial networks [11] to remove watermark from faces images used in a biometric system. Cheng et al [42] proposed a method based on convolutional neural networks (CNN).…”

Section: Watermark Removalmentioning

confidence: 99%

DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

Souibgui,

Kessentini

2020

Preprint

View full text Add to dashboard Cite

Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system. In this paper, we propose an effective end-to-end framework named Document Enhancement Generative Adversarial Networks (DE-GAN) that uses the conditional GANs (cGANs) to restore severely degraded document images. To the best of our knowledge, this practice has not been studied within the context of generative adversarial deep networks. We demonstrate that, in different tasks (document clean up, binarization, deblurring and watermark removal), DE-GAN can produce an enhanced version of the degraded document with a high quality. In addition, our approach provides consistent improvements compared to state-of-the-art methods over the widely used DIBCO 2013, DIBCO 2017 and H-DIBCO 2018 datasets, proving its ability to restore a degraded document image to its ideal condition. The obtained results on a wide variety of degradation reveal the flexibility of the proposed model to be exploited in other document enhancement problems.

show abstract

Section: Watermark Removalmentioning

confidence: 99%

DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

Souibgui,

Kessentini

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…erefore, we have two sets constructed by LL2 max . For convenience, we denote the sets as S max (1) and S max (2), respectively.…”

Section: Embed Watermark In the Dwt Domainmentioning

confidence: 99%

“…According to the embedding equation ( 27), respectively embed 1/4 watermark W 2 ′ and W 3 ′ into S max (1) and S max (2) to obtain LL2 max ′ : LL2 max ′ �…”

Section: Embed Watermark In the Dwt Domainmentioning

confidence: 99%

“…e watermarked image I w was divided into nonoverlap 8 × 8 blocks according to equation (2). A total of 512 blocks, of which the row index was even, were selected for the DCT transformation.…”

Section: Preprocess Watermarked Imagementioning

confidence: 99%

“…Normally, we can increase the watermark embedding intensity to improve robustness, but it will lose imperceptibility and vice versa. Moreover, the advancement of analysis techniques for digital watermarking, especially the extensive application of deep learning in watermark removal technology [1,2], has made watermarking techniques unsecure. Hence, how to maintain the balance between robustness and imperceptibility as well as the security of watermarking is a key problem for a complex watermarking system [3].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Robust Blind Watermarking Scheme Improved by Entropy‐Based SVM and Optimized Quantum Genetic Algorithm

Zhang

Zhou

Yang

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the intensive study of machine learning in digital watermarking, its ability to balance the robustness and transparency of watermarking technology has attracted researchers’ attention. Therefore, quantum genetic algorithm, which serves as an intelligent optimized scheme combined with biological genetic mechanism and quantum computing, is widely used in various fields. In this study, an adaptive robust blind watermarking algorithm by means of optimized quantum genetics (OQGA) and entropy classification-based SVM (support vector machine) is proposed. The host image was divided into two parts according to the odd and even rows of the host image. One part was transformed by DCT (discrete cosine transform), and then the embedding intensity and position were separately trained by entropy-based SVM and OQGA; the other part was by DWT (discrete wavelet transform), in which the key fusion was achieved by an ergodic matrix to embed the watermark. Simulation results indicate the proposed algorithm ensures the watermark scheme transparency as well as having better resistance to common attacks such as lossy JPEG compression, image darken, Gaussian low-pass filtering, contrast decreasing, salt-pepper noise, and geometric attacks such as rotation and cropping.

show abstract

HD-VAE-GAN: Hiding Data with Variational Autoencoder Generative Adversarial Networks

Gandikota

Mishra

2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

De-Mark GAN: Removing Dense Watermark with Generative Adversarial Network

Cited by 10 publications

References 7 publications

DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

Adaptive Robust Blind Watermarking Scheme Improved by Entropy‐Based SVM and Optimized Quantum Genetic Algorithm

HD-VAE-GAN: Hiding Data with Variational Autoencoder Generative Adversarial Networks

Contact Info

Product

Resources

About