Optimization of stego image retaining secret information using genetic algorithm with 8-connected PSNR

Abstract

Due to the fast advancement of internet and digital technology, secured transmission of data over networks offers a great challenge. This problem of secrecy of information has long been received the attention of researchers due to its immense demand in real life applications such as information security systems. The problem is to optimize the stego image close to the cover image without affecting the secret embedded image, resulting in high visual stego image quality. In this paper, we have presented an improved genetic algorithm as the optimization algorithm to solve this problem. We have proposed a heuristic initialization technique to generate initial population and a new fitness function based on the Peak Signal to Noise Ratio (PSNR) obtained from 8-connected neighbors of each pixel. The proposed genetic algorithm is applied for the entire stego image and executed for a certain number of generations. The experimental results demonstrate that the proposed scheme is found to be relatively better than some existing steganography techniques in terms of enhanced PSNR of the stego image.