Underwater Image Denoising Based on Non-Local Methods

摘要

Due to the medium scattering and light absorption, the acquired underwater optical images suffer from poor visibility. Absorption and scattering effects are caused not only by the water itself but also by other floating particles. Moreover, backscattering is strengthened during the light is reflected and deflected multiple times by the suspended particles before reaching the camera. The backscattering gives rise to specific strong correlated noise together with a constant level degrading the image contrast. Although there are many effective dehazing methods to remove the veil background, they have ignored the influence of backscattering noise, which still exists in the dehazed images. In addition, because of the special characteristics of backscattering noise, the traditional image denoising methods are difficult to make sense, even cause distortion. Accordingly, this paper employed the non-local denoising methods which are referred to Non-Local Means algorithm and Block-Matching 3D collaborative filtering to suppress the backscattering noise. The experimental results show that they can effectively remove the backscattering noise of underwater image and achieve better image quality.