Abstract: Under water environments are dynamic and complex, and obtaining a clear picture of the obstacles and movements of objects in this environment is difficult. The disturbances caused by various factors affect the image quality which leads to incorrect analysis. Sonar image quality can be assessed in terms of quality parameters like contrast, illumination variation and Noise. A non-parametric statistical wavelet denoising method is proposed in this paper. The proposed method incorporates the edge coefficients and non-edge coefficients as it picks up the homogeneous neighbor of non-edge coefficients and estimate the noise-free coefficients and outperforms the traditional approach.