Robust watermarking algorithm for digital images using discrete wavelet and probabilistic neural network

Digital watermarking, which has been proven effective for protecting digital data, has recently gained considerable research interest. This study aims to develop an enhanced technique for producing watermarked images with high invisibility. During extraction, watermarks can be successfully extracted without the need for the original image. We have developed discrete wavelet transform with a Haar filter to embed a binary watermark image in selected coefficient blocks. A probabilistic neural network is used to extract the watermark image. To evaluate the efficiency of the algorithm and the quality of the extracted watermark images, we used widely known image quality function measurements, such as peak signal-to-noise ratio (PSNR) and normalized cross correlation (NCC). Results indicate the excellent invisibility of the extracted watermark image (PSNR = 68.27 dB), as well as exceptional watermark extraction (NCC = 0.9779). Experimental results reveal that the proposed watermarking algorithm yields watermarked images with superior imperceptibility and robustness to common attacks, such as JPEG compression, rotation, Gaussian noise, cropping, and median filter.