A high speed array architecture for 2-D wavelet transform

In this paper, an efficient, simple and fast systolic-like architecture for a 2-D Discrete Wavelet Transform (DWT) is proposed. The “approximation” and “detailed” components of a signal are computed simultaneously in the first octave and alternately in other octaves. Each processing element has its own local memory for storing the intermediate data. The proposed architecture uses the same clock frequency for every octave level. It has a 100% utilization for a 2-octave level architecture, and N²+N period cycle. The architecture is scalable for different filter length (divisible by 2) and different octave levels