Turbo coded trellis-based constructions for data hiding

It has recently been discovered that many current applications such as data hiding and watermarking can be posed as the problem of channel coding with side information. As a result there has been considerable interest in designing codes (see Chou et. al,(4) Kesal et. al(5) and Eggers et. al(6)) to try and attain the theoretical capacity of the problem. It was shown by Pradhan et. al that in order to achieve capacity, a powerful channel codebook that partitions into a powerful source codebook should be chosen. The data to be embedded will index the source codebook partition. The constructions that exist in the literature, however, are typically based on powerful channel codebooks and weak source codebook partitions and hence remain at a considerable gap to capacity. In this paper, we present several methods of construction that are based on a powerful channel codebook (i.e. turbo codes) and powerful source codebook partitions (i.e., trellis coded quantization) to try and bridge the gap to capacity. For the Gaussian channel coding with side information (CCSI) problem at a transmission rate of I bit/channel use, our proposed approach comes within 2.72 dB of the information-theoretic capacity established by Costa.(1).