A blind robust image watermarking approach exploiting the DFT magnitude

Hamidi, Mohamed; Haziti, Mohamed El; Cherifi, Hocine; Aboutajdine, Driss

doi:10.1109/aiccsa.2015.7507124

Cited by 13 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Watermarking digital media [15,23,6,21,35,39,41,19] is an important and active area of research. Traditional video watermarking can be roughly classified into three groups: spatial domain, compressed domain, and transform domain methods, based on the domain it acts on [5].…”

Section: Related Workmentioning

confidence: 99%

DVMark: A Deep Multiscale Framework for Video Watermarking

Luo¹,

Li²,

Chang³

et al. 2021

Preprint

View full text Add to dashboard Cite

EncoderWatermarked Modified Video Decoder Message "001010..."Figure 1: DVMark hides a message into a video which can be robustly recovered. The encoder network takes a cover video and a binary message, and generates a watermarked video that appears identical to the human eye as the input. The watermarked message can still be reliably extracted by our decoder even if the video undergoes a series of common video editing operations, such as compression, crop, color shift, and padding the watermarked video with other video content.

show abstract

Section: Related Workmentioning

confidence: 99%

DVMark: A Deep Multiscale Framework for Video Watermarking

Luo¹,

Li²,

Chang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Digital watermarking [8,15,5,14,24,31,34,12] have been an active research area with many important applications such as content copyright protection. More re-cently, deep learning based approaches have been applied to train an end-to-end watermarking system [45,23,1,21,43] with impressive results.…”

Section: Watermarkingmentioning

confidence: 99%

Distortion Agnostic Deep Watermarking

Luo

Zhan

Chang

et al. 2020

Preprint

View full text Add to dashboard Cite

Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learningbased methods achieved impressive results in both visual quality and message payload under a wide variety of image distortions. However, these methods all require differentiable models for the image distortions at training time, and may generalize poorly to unknown distortions. This is undesirable since the types of distortions applied to watermarked images are usually unknown and non-differentiable. In this paper, we propose a new framework for distortionagnostic watermarking, where the image distortion is not explicitly modeled during training. Instead, the robustness of our system comes from two sources: adversarial training and channel coding. Compared to training on a fixed set of distortions and noise levels, our method achieves comparable or better results on distortions available during training, and better performance on unknown distortions.

show abstract

“…The embedding domain can be spatial or a transform domain. Spatial methods [ 4 ] embed the watermark by directly altering the pixels, while the transform domain methods embed the watermark after performing a transformation, such as DFT [ 5 , 6 ], DCT [ 7 ], DWT [ 8 ]. The extraction method can be a non-blind, or semi-blind, or a blind technique.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Robust Image Watermarking Method Based on DWT-DCT and SIFT for Copyright Protection

Hamidi¹,

Haziti

Cherifi³

2021

J. Imaging

Self Cite

View full text Add to dashboard Cite

In this paper, a robust hybrid watermarking method based on discrete wavelet transform (DWT), discrete cosine transform (DCT), and scale-invariant feature transformation (SIFT) is proposed. Indeed, it is of prime interest to develop robust feature-based image watermarking schemes to withstand both image processing attacks and geometric distortions while preserving good imperceptibility. To this end, a robust watermark is embedded in the DWT-DCT domain to withstand image processing manipulations, while SIFT is used to protect the watermark from geometric attacks. First, the watermark is embedded in the middle band of the discrete cosine transform (DCT) coefficients of the HL1 band of the discrete wavelet transform (DWT). Then, the SIFT feature points are registered to be used in the extraction process to correct the geometric transformations. Extensive experiments have been conducted to assess the effectiveness of the proposed scheme. The results demonstrate its high robustness against standard image processing attacks and geometric manipulations while preserving a high imperceptibility. Furthermore, it compares favorably with alternative methods.

show abstract

A blind robust image watermarking approach exploiting the DFT magnitude

Cited by 13 publications

References 16 publications

DVMark: A Deep Multiscale Framework for Video Watermarking

DVMark: A Deep Multiscale Framework for Video Watermarking

Distortion Agnostic Deep Watermarking

A Hybrid Robust Image Watermarking Method Based on DWT-DCT and SIFT for Copyright Protection

Contact Info

Product

Resources

About