New low-pass split wavelet pyramids and their application to efficient zerotree coding of medical images

We have developed and tested alternative transforms which create different zerotree structures. These new transforms can significantly improve the performance of image compression algorithms that use zerotrees without a significant modification of the latter. A new wavelet pyramid that results in an effective non-integer up- and down-sampling of the high-frequency sub-bands is presented in this paper. Non-integer sub-sampled pyramids can also be used to reduce the data dependency in the compression algorithm, and therefore reduce the execution time in a processor with multiple parallel processing units