Generating balanced descriptions using classification-based approach

When transmitting multimedia information over non-prioritized networks subject to packet losses or multiple channels subject to independent channel drops, multiple description coding becomes an effective choice, in order to minimize the end-to-end distortion. The generated descriptions should have similar rate and distortion when the two physical or logical pathes, over which descriptions travel, have similar bandwidth and probability of failure. In this paper, we propose an efficient and low complexity method to generate balanced descriptions so as to overcome the week point of the previously proposed method for generatirng rate-distortion based descriptions for JPEG 2000 and motion JPEG 2000.