Digital Image Authentication Model Based on Edge Adaptive Steganography

摘要

With the rapid growth of internet in the present world, social networking websites like Twitter, Facebook and Instagram are being increasingly used by people to share their life moments and events via images. But this vastly popular phenomenon of image sharing on internet is exposed to many risks. At present, these social networking websites are not bound by stringent privacy and copyright laws. Thus original image, once shared, can be easily downloaded and edited by the miscreants. Modified images can be then uploaded, morphed or shared further without the consent of the original owner of the image. Validation of the ownership of these images is practically impossible due to high degree of replication. This calls for an urgent requirement of an image authentication system. A digital image authentication system using adaptive steganography (Edge detection with variable LSB as the embedding technique) has been proposed in this paper. In the proposed technique the secret data related to person's login detail and current timestamp will be hidden in the original image using steganography without affecting the visual quality of the image. The information behind that image can be decoded only by the authorized party containing the original data of the person. This will validate the source and ownership of the shared image. It has been shown by the experimental results that the quality of image is not degraded even after the addition of secret data.