PROJECT TITLE :

Color Balance and Fusion for Underwater Image Enhancement - 2018

ABSTRACT:

We tend to introduce an efficient technique to reinforce the photographs captured underwater and degraded because of the medium scattering and absorption. Our method may be a single image approach that does not need specialized hardware or data concerning the underwater conditions or scene structure. It builds on the blending of 2 pictures that are directly derived from a color-compensated and white-balanced version of the initial degraded image. The two images to fusion, as well as their associated weight maps, are outlined to market the transfer of edges and color contrast to the output image. To avoid that the sharp weight map transitions create artifacts in the low frequency parts of the reconstructed image, we tend to additionally adapt a multiscale fusion strategy. Our extensive qualitative and quantitative analysis reveals that our enhanced images and videos are characterized by better exposedness of the dark regions, improved world contrast, and edges sharpness. Our validation also proves that our algorithm is fairly independent of the camera settings, and improves the accuracy of several Image Processing applications, such as Image Segmentation and keypoint matching.