An Effectual Underwater Image Enhancement using Deep Learning Algorithm

Abstract

Digital image processing domain is growing day-by-day by introducing novel technologies to provide assistance for several applications such as robotic activities, underwater network formation, and so on. In particular, underwater image processing is considered as the crucial task in image processing industry due to the flow of light waves that are not in the specific and expected range under the water level. While image restoration technology can adequately consider removing this same haze from source images, they need to obtain several images from a certain place that prevent it from being used in a real-time system. To overcome this issue, a deep study approach is developed by providing excellent outcomes of deep learning approaches in several other image analysis concerns such as colorizing images or object identification. A convolution neural network (CNN) model is trained to de-haze the individual images with image restoration in order to perform further with an image improvement. The proposed approach can produce images with image restoration quality by including a standard image input and here, the neural network is evaluated by using images and features, which are obtained from separate areas to prove its capacity to generalize. The efficiency of the proposed approach is high when compared to other existing methods.