DCT-domain watermarking techniques for still images: detector performance analysis and a new structure

820 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Protecting Intellectual Property of Deep Neural Networks with Watermarking (2018, methodology): “most commonly used transforms are the Discrete Cosine Transform (DCT) [25, 44], Discrete Fourier Transform (DFT) [42, 55], Discrete Wavelet Transform (DWT) [9, 11, 31, 58] and the combination of”
Anti-collusion fingerprinting for multimedia (2003, methodology): “fied model used here with more sophisticated single-watermark detectors considering more realistic noise such as those in [25] and [26] to improve the performance in the watermark detection layer and, in turn, enhance the overall performance.”
MBRS: Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression (2021, methodology): “Digital watermarking was first introduced and defined by Ron van Schyndel in 1994 [23], and then was widely used for the protection of intellectual property of images [5, 13], videos [7, 16] and audios [4, 26].”
Robust Invisible Video Watermarking with Attention (2019, methodology): “In the frequency domain, the watermark can be embedded by modifying the coefﬁcients produced with any of the following transformations of the video sequence: the Discrete Cosine Transform (DCT) [11], the Discrete Fourier Transform [24], and the Discrete Wavelet Transform [33, 17, 14].”