A Novel Approach for Underwater Image Enhancement

A well-known problem concerning the underwater images is related to the density of the water in the sea which is considered 800 times denser than air. So reflection of the light varies greatly depending on the structure of the sea. Another main concern is related to the water that bends the light either to make crinkle patterns or to diffuse it. For example, the movement of autonomous underwater vehicles generates shadows in the scene while the optical camera provides limited visibility when it is used to capture underwater images. Due to these problems clarity of underwater images is degraded by light absorption and catering. This causes one color to dominate the image. In order to improve the perception of underwater mages, we propose an approach based on stretching and filtering. The objective of this approach is twofold. Firstly, contrast equalization by contrast limited adaptive histogram equalization. Secondly apply following four filters sequentially, filters as Homomorphic filtering, wavelet de-noising, bilateral filter and we apply contrast and intensity stretching for normalizing the color values. These filters are applied sequentially on degraded underwater images for smoothing the image. After that we will conduct the experiments using estimated optimal parameters for evaluating the proposed technique. We will also evaluate the technique such as Peak Signal to Noise Ratio (PSNR), Mean Square Error (MSE), and Signal to Noise Ratio (SNR) of the images.