High-Quality Video Watermarking Based on Deep Neural Networks and Adjustable Subsquares Properties Algorithm

Abstract

This paper presents a method of high-capacity and transparent watermarking based on the usage of deep neural networks with the adjustable subsquares properties algorithm to encode the data of a watermark in high-quality video using the H.265/HEVC (High-Efficiency Video Coding) codec. The aim of the article is to present a method of embedding a watermark in a video with HEVC codec compression by making changes in a video in a way that is not noticeable to the naked eye. The method presented here is characterised by focusing on ensuring the accuracy of the original image in relation to the watermarked image, providing the transparency of the embedded watermark, while ensuring its survival after compression by the HEVC codec. The article includes a presentation of the practical results of watermark embedding with a built-in variation mechanism of its capacity and resistance, thanks to the adjustable subsquares properties algorithm. The obtained PSNR (peak signal-to-noise ratio) results are at the level of 40 dB or better. There is the possibility of the complete recovery of a watermark from a single frame compressed in the CRF (constant rate factor) range of up to 16, resulting in a BER (bit error rate) equal to 0 for the received watermark.

High-Quality Video Watermarking Based on Deep Neural Networks for Video with HEVC Compression

“…The previous publication [ 22 ] presented only the most efficient way of extracting values from the subsquares in the form of the median used in the ASPA operation. Watermark extraction results using the mean and the most frequent element (value) are also included in the results discussed.…”

“…The encoder and decoder subsystems use ASPA for efficient encoding of information in the image, which was discussed in detail in a previous publication [ 22 ], however the main idea of the algorithm will be briefly explained here as well.…”

“…The aim of this article is to present an improved method compared to the previously published method for embedding a watermark in a high-quality video based on DNN under High-Efficiency Video Coding (HEVC) [ 18 , 19 , 20 , 21 ] codec compression conditions [ 22 ]. The main research problem was to ensure the resistance of the watermark under higher HEVC compression levels than in a previous paper [ 22 ] and in comparison to other methods. Additionally higher capacity size for the watermark was achieved while providing higher values of carrier PSNR.…”

“…The presented method of embedding the watermark takes into account the subsampling of the YUV420p chrominance in a way that ensures its recovery while providing high accuracy of the video with the embedded watermark in relation to the original video. The method is based on the use of a DNN autoencoder (using a real HEVC compression channel and mimicked by a trained coder in the training process) and on the use of an adjustable subsquares properties algorithm (ASPA) [ 22 ] method for watermark generation in chrominance channels.…”

Deep Learning-Based Watermarking Techniques Challenges: A Review of Current and Future Trends

“…Despite the good number of existing techniques of deep learning-based watermarking proposed for images, video watermarking based on deep learning has only recently begun to be explored and is still an open problem. In fact, as far as we know, there are only a very few number of video watermarking techniques based on deep learning in the literature [16,26,35,40,43,56,59,65,91,97] that appeared since 2019.…”