COMPARISON OF WAVELET, CONTOURLET AND CURVELET TRANSFORM WITH MODIFIED PARTICLE SWARM OPTIMIZATION FOR DESPECKLING AND FEATURE ENHANCEMENT OF SAR IMAGE

This paper gives a comparative study of despeckling of SAR image with feature enhancement based on curvelet transform and modified particle swarm optimization with contourlet and wavelet transforms. Initially SAR despeckling and edge preservation are integrated with improved gain function which shrink and stretch the curvelet coefficient optimal parameter in the gain function are obtained in order to improve the quality of the despeckled and enhanced image. Finally modified PSO algorithm is applied as a global search strategy for the best result. The modified particle swarm optimization is proposed to increase the convergence speed and to avoid premature convergence which introduced new learning scheme and a mutation operator. This algorithm is compared with contourlet and wavelet transforms in which curvelet transform with modified PSO gives better results. Experimental results show that the curvelet with MPSO method can efficiently reduce the speckle noise and enhance edge features of SAR images compared to wavelet and contourlet transform. The quality of image outperforms other despeckling method that do not use edges preservation technique.