PROJECT TITLE :
A Block-Based Pass-Parallel SPIHT Algorithm
Set-partitioning in hierarchical trees (SPIHT) may be a widely used compression algorithm for wavelet-remodeled images. One in all its main drawbacks could be a slow processing speed thanks to its dynamic processing order that depends on the image contents. To overcome this drawback, this paper presents a modified SPIHT algorithm called block-based mostly pass-parallel SPIHT (BPS). BPS decomposes a wavelet-reworked image into 4$,times,$four blocks and simultaneously encodes all the bits in a very bit-plane of a four$,times,$four block. To exploit parallelism, BPS reorganizes the three passes of the initial SPIHT algorithm and then BPS encodes/decodes the reorganized three passes in a parallel and pipelined manner. The precalculation of the stream length of each pass allows the parallel and pipelined execution of those 3 passes by not only an encoder however conjointly a decoder. The modification of the processing order slightly degrades the compression efficiency. Experimental results show that the height signal-to-noise ratio loss by BPS is between approximately zero.23 and 0.59 dB in comparison to the first SPIHT algorithm. Each an encoder and a decoder are implemented in the hardware which will method a hundred and twenty million samples per second at an operating clock frequency of one hundred MHz. This processing speed allows a video of size of 1920$,times,$1080 within the 4:2:2 format to be processed at the rate of thirty frames/s. The gate count of the hardware is regarding 43.9 K.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here