Authentication of images using Zernike moment watermarking

The rapid development of the Internet and digital image modification software has invited the illegal access to and use of digital images. In response, digital watermarking has emerged as a unique tool for protecting the authenticity of digital images. This technique involves the insertion of an imperceptible message within the media. This paper proposes a semi-fragile watermarking system using content-based techniques that address the challenge of image authentication. The proposed algorithm exploits the Zernike moments to authenticate an image and the Sobel edge map to perform tamper detection. The main contributions of this work are the establishment of an authentication algorithm that is robust against scaling, translation, noise pollution, rotation and JPEG compression, which are considered to be non-malicious modifications, while significantly decreasing the computational complexity using optimum orders of Zernike moments. In addition, this work addresses the challenge of capacity in terms of watermark insertion while preserving the visual quality of the image, where the capacity is increased almost three fold, as shown in the results. This process can successfully distinguish malicious attacks and reject modifications to watermarked images made through additions, replacements, and image cropping.