Sub-band discrete cosine transform-based greyscale image watermarking using general regression neural network

In this paper, a new grey scale image watermarking scheme based on sub-band discrete Cosine transform (SB-DCT) using general regression neural network (GRNN) is proposed. The image features are extracted by applying the SB-DCT to each non-overlapping block of the image. These features are used to form the dataset, which act as input to GRNN. The output obtained by GRNN is used to embed the binary watermark logo in the selected low variance blocks of the image. Owing to the good function approximation and high generalisation property of GRNN, we are able to recover the watermark after performing several image processing operations. Through the extensive experimental results, high peak signal-to-noise ratio (PSNR) value of watermarked image and high bit correct ratio (BCR), normalised correlation (NC) value of the extracted watermark proves the imperceptibility and robustness of the proposed scheme compared to the state-of-art techniques.