A high-capacity QRD-based blind color image watermarking algorithm incorporated with AI technologies

作者：

Highlights：

• A high-capacity QRD-based blind watermarking for color images is proposed.

• The proposed algorithm is incorporated with PSO and SRCNN of AI technology.

• PSO seeks the optimal parameters for enhancing performance.

• SRCNN facilitates visual recognition of extracted watermarks.

• It reaches better robustness and imperceptibility at a rate of 1/8 bit per pixel.

摘要

•A high-capacity QRD-based blind watermarking for color images is proposed.•The proposed algorithm is incorporated with PSO and SRCNN of AI technology.•PSO seeks the optimal parameters for enhancing performance.•SRCNN facilitates visual recognition of extracted watermarks.•It reaches better robustness and imperceptibility at a rate of 1/8 bit per pixel.

论文关键词：Blind image watermarking,QR decomposition,Particle swarm optimization,Super-resolution convolutional neural network,Watermark retrieval assurance

论文评审过程：Received 31 May 2021, Revised 8 September 2021, Accepted 29 March 2022, Available online 4 April 2022, Version of Record 11 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117134