An intelligent reversible watermarking system for authenticating medical images using Wavelet and PSO

This paper presents a novel medical image authentication system through wavelet decomposition and particle swarm optimization (PSO). First medical image is treated with wavelet transformation and another image is treated with tent map and a hash function to further protect the secret watermark. Tent map ensures the sensitivity towards changes in the initial value which, can better protect and encrypt the original watermark. The operations performed on the binary coded image are based on the encryption sequences generated from chaotic map. Particle swarm optimization (PSO) results in producing optimal balance between embedding capacity and imperceptibility by exploiting the image pixel correlation of neighboring pixels. The novelty of the proposed technique lies in its ability to create a model that can find optimal wavelet coefficients for embedding using PSO and also acts as an absolute feature for embedding the watermark. The proposed method is thus able to embed watermark with low distortion, take out the secret information and also recovers the original image. The proposed technique is valuable with respect to robustness, capacity and imperceptibility.