The paper gives a new scheme for the restoration of images corrupted by Gaussian noise, impulse noise, speckle noise and mixed noise. The new algorithm works well on different noises and produce better image restoration than existing standard median filter (SMF), Centre weighted median filter (CWF) and threshold decomposition filter (TDF).The proposed algorithm (PA) is tested on different images corrupted by mixed noises and is found to produce better results in terms of the qualitative and quantitative measures of the image for noise densities up to 30% noise level for impulse noise, mean zero and 0.9% variance of Gaussian noise. The filter works well for speckle noise up to 0.8% variance. The proposed algorithm is targeted on Xc3e5000-5fg900 FPGA using Xilinx 7.1 compiler version which requires 3689 slices and a low power of 100mw and a optimum speed when compared to the other median finding architectures.

Keywords:Rank order filter, threshold decomposition, Modified decomposition filter, field programmable gate array.