Achieving Low-Power Consumption by Using Fractal Coding in PVP

An approach based on fast local area search is proposed to reduce the computation time of fractal image coding which increases the power consumption of embedded system. The algorithm starts from a code computed by collage coding and keeps on improving this code with a heuristic until convergence to a locally optimal solution. Experimental result shows that compared with the conventional fractal coding method PIFS, the coding speed and compression ratio is increased significantly and power consumption of embedded system is decreased about 8%~12%, while the signal to noise ratio of it and the decoding image quality is acceptable.