摘要：In this paper, we model HVS characteristics using hybrid Fuzzy-BPN to implement a novel image watermarking scheme to embed a permuted binary watermark in gray-scale images. The signed images yield high values of full reference metrics - PSNR and SSIM which suggest their good visual quality. Extracted watermarks yield high normalized correlation values which indicate successful watermark recovery. Eight different image processing attacks are carried out to examine the robustness of embedding scheme. High computed values of normalized correlation from the attacked images clearly indicate that the proposed algorithm is robust against the selected attacks. Time complexity analysis indicates fast execution of watermarking processes. It is found that the proposed watermarking scheme is fast enough to carry out these operations on a real timescale. Overall, it is concluded that the Fuzzy-BPN is successful candidate for implementing novel gray-scale image watermarking scheme meeting real timelines.
关键词：Image watermarking
; Human visual system
; Fuzzy-BP network
; Hybrid intelligent system
; Normalized cross-correlation
Loading...
