Haze-Free Underwater Image Enhancement

Abstract

Image enhancement is a process of improving the quality of image by improving its feature. The underwater image suffers from low contrast and resolution, due to Light Scattering and color change. hence object identification become typical task. In this project a fish tank is designed the camera and light source is inserted in the tank for taking the still photograph of the object. This image is taken as the source image. That is equalized using Histogram equalization. To reduce the noise in the image noise reduction filter is used and a new up scaling method, Iterative Curvature Based Interpolation (ICBI) based on a two-step grid filling and an iterative correction of the interpolated pixels obtained by minimizing an objective function depending on the second order directional derivatives of the image intensity. The constraints used to derive the function are related with a well-known New edge-directed interpolation (i.e., NEDI) method that providing good results but computationally heavy. The high quality of the images enlarged with the new method is demonstrated with objective and subjective tests, while the computation time is reduced of 1-2 orders of magnitude with respect to NEDI.