Abstract:

Underwater imaging is an emerging area of research. Underwater image processing has played an important role in various fields such as submarine terrain scanning, submarine communication cable laying, underwater vehicles, underwater search and rescue. However, there are many difficulties in the process of acquiring underwater images. Underwater Image suffers from serious color distortion and low contrast problems because of complex light propagation in the ocean. Underwater image capturing is a challenging task due to attenuation of light in water. Scattering and absorption are results of light attenuation which leads to faded colors and reduced contrast of images, respectively. To deal with these issues, to provide better visual quality image and in view of computing constraints of underwater vehicles, Hue preservation based high-efficiency under water image correlation and enhancement using deep-learning Technique is presented. The framework contains three convolutional neural networks for underwater image color restoration. At first, CNN is used to convert the input underwater image into the gray scale image. Next, grayscale underwater image is enhanced by the second CNN and then, the color correction is formed to the input underwater image by the third CNN. At last, color-corrected image is obtained by integrating the outputs of three CNNs based on the hue preservation.

Description:

Underwater image, Hue preservation, Convolutional Neural Network