An efficient and Highly Scalable Listless SPIHT Image Compression Framework

Abstract

The set partitioning in hierarchical trees is a powerful image compression algorithm. It has reasonable complexity and produces a rate scalable bit-stream. Unfortunately, SPIHT fails to explore the multi-resolution nature of the wavelet transform as the output bit-stream doesn't support resolution scalability. Moreover it requires huge memory and has complex memory management as it depends on utilizing lists with memory of about 2.5 the image size. This paper proposes three related algorithms. The first one modifies SPIHT to reduce its complexity and improve its efficiency especially at low rates. The second is the main contribution of the paper. It provides a simultaneous solution to the memory and scalability problems of SPIHT. Memory is reduced by utilizing status bits of average 2.5 bits per pixel instead of the lists. Resolution scalability is maintained by encoding the resolution levels in increasing order within each coding pass. Another important attribute of our algorithm is that it has very little increment in complexity in comparison with the original SPIHT algorithm. In contrast, the existing solutions have much more complexity, and/or more memory resources. The third has slightly lower complexity and memory than the second but at the same time, it has slightly lower performance.