Perceptual multiple description coding with randomly offset quantizers

A novel perceptual multiple description coding with randomly offset quantizers (PMDROQ) is proposed. In the proposed PMDROQ method, the input image is partitioned into M subsets, and then obtaining M descriptions. In each description, one subset is directly encoded and decoded with different-small perceptual quantization stepsizes in DCT domain, while other subsets are predictively coded and decoded with a large quantization stepsize. The perceptual quantization stepsize of low frequency coefficient is smaller than that of the high frequency coefficient. The proposed PMDROQ is applied to two-description lapped transform-based image coding. The experimental results show that the developed scheme obtains better performance than other methods in this category.