Imperceptible Digital Image Watermarking Based on Discrete Wavelet Transform and Schur Decomposition

Blind Color Image Watermarking using Deep Artificial Neural Network using statistical features

“…Figure 5 shows the NC comparison with Verma V. S. et al [23] for common image attacks and it shows that proposed method performs better against SLP (0.01) and MF(3x3) attacks. Figure 6 and Figure 7 shows the BER comparison with Kang, X. et al [19] and Mellimi, S. et al [13] for Peppers and Lena standard image respectively and it shows that proposed method performs good against some image attacks. Figure 8 shows the PSNR comparison with [15,28,29] in terms of dB for Lena, Pepper and Mandril color image.…”

“…One of the important steps is to select the region for watermarking it may be done using segmentation [4] or other method. Discrete wavelet transforms (DWT) [5][6], discrete cosine transforms (DCT) [7][8], discrete fourier transform (DFT) [9][10], redundant discrete wavelet transforms (RDWT) [11][12], and integer/Lifting wavelet transform (IWT/LWT) [13][14][15][16][17][18] have previously been used for image watermarking. LWT is second generation wavelet and it has various advantages over the conventional methods and it is most significantly known for absorbing more image distortion due to having more energy compaction properties.…”