Fast intelligent watermarking of heterogeneous image streams through mixture modeling of PSO populations

In intelligent watermarking (IW), evolutionary computing (EC) is employed in order to automatically set the embedding parameters of digital watermarking systems for each image. However, the computational complexity of EC techniques makes IW unfeasible for large scale applications involving heterogeneous images. In this paper, we propose a dynamic particle swarm optimization (DPSO) technique which relies on a memory of Gaussian mixture models (GMMs) of solutions in the optimization space. This technique is employed in the optimization of embedding parameters of a multi-level (robust/fragile) bi-tonal watermarking system in high data rate applications. A compact density representation of previously-found DPSO solutions is created through GMM in the optimization space, and stored in memory. Solutions are re-sampled from this memory, re-evaluated for new images and have their distribution of fitness values compared with that stored in the memory. When the distributions are similar, memory solutions are employed in a straightforward manner, avoiding costly re-optimization operations. A specialized memory management mechanism allows to maintain and adapt GMM distributions over time, as the image stream changes. This memory of GMMs allows an accurate representation of the topology of a stream of optimization problems. Consequently, new cases of optimization can be matched against previous cases more precisely (when compared with a memory of static solutions), leading to considerable decrease in computational burden. Simulation results on heterogeneous streams of images indicate that compared to full re-optimization for each document image, the proposed approach allows to decrease the computational requirement linked to EC by up to 97.7% with little impact on the accuracy for detecting watermarks. Comparable results were obtained for homogeneous streams of document images.