Hybrid filter with wavelet denoising and anisotropic diffusion filter for image despeckling

SAR imaging is an efficient tool for retrieval of useful information about the surfaces of earth and various other planets as well. The synthetic aperture radar (SAR) generates severely degraded images due to a form of multiplicative noise called speckle. It is produced by the random interference of the electromagnetic waves which are backscattered because of the roughness of imaged surface. Numerous filters were developed which helped in enhancing the image quality to some extent. However, recent filtering techniques which were based on non local image modelling technique, proved to build way better filters which resulted in despeckling the images without tampering with its edges or oversmoothing the images. This paper introduces one such filtering technique which is based on the wavelet transformation followed by anisotropic filtering. The results are found and compared for Peak Signal to Noise Ratio, Coefficient of Correlation and Equivalent No of looks.