On the transmission of a class of hidden Markov sources over Gaussian channels with applications to image communication

We address the problem of transmission of a useful class of hidden Markov sources with Gaussian observations over a discrete-time power-constrained AWGN channel. Our source model approximates the wavelet representation of natural images, and is motivated by the successful modeling approaches in the state-of-the-art image compression and restoration methods. We derive information-theoretic performance bounds, and propose a simple yet efficient joint source-channel coding solution which combines analog and digital modes of transmission. Our results indicate the promise of the proposed approach to the problem of robust image communication