A sparse representation based image steganography using Particle Swarm Optimization and wavelet transform

• Main Authors: S.I. Nipanikar, V. Hima Deepthi, Nikita Kulkarni
• Format: Article
• Language: English
• Published: Elsevier 2018-12-01
• Series: Alexandria Engineering Journal
• Online Access: http://www.sciencedirect.com/science/article/pii/S1110016817302806

With the growth of information technology, information security is a major concern in the interactive environment, where there is no security for the messages send to and from the receiver. A technology named image steganography has been employed that ensures security to the covert communication and safeguarding the information. Image steganography hides the secret message in any of the recipient images and sends the secret message such that the message is visible only to the sender and the receiver. This paper proposes a method for image steganography using sparse representation, and an algorithm named Particle Swarm Optimization (PSO) algorithm for effective selection of the pixels for the purpose of embedding the secret audio signal in the image. PSO-based pixel selection procedure uses a fitness function that depends on the cost function. Cost function calculates the edge, entropy, and intensity of the pixel for evaluating fitness. Simulation has been done and comparison of the PSO with the other existing methods in terms of Peak-Signal-to-Noise-Ratio (PSNR) and Mean Square Error (MSE) determines the proposed PSO, as an effective method. The proposed method achieved a better PSNR and MSE values of 47.6 dB and 0.75 respectively. Keywords: DWT, Image steganography, IDWT, PSNR, MSE