Underwater Image Enhancement using deep learning

Image capture systems fail to capture high-resolution images when used at great depth underwater, and the equipment is also expensive. With the use of image processing algorithms, it is possible to reconstruct and improve image quality without any costly and reliable image acquisition programs. Developing and rebuilding an underwater image is a daunting task and has gained momentum in recent years. The aim is to improve underwater images by removing graininess, fine-tuning, and sharpening the images using deep learning models.In this work, the authors train four Convolution Neural Network (CNN) based models (two 3-layered and two 5-layered) over GAN-augmented datasets viz. EUVP (Enhancing Underwater Visual Perception)and UIEB (Underwater Image Enhancement Benchmark). Comparisons of these four models are done with the state-of-the-art methods with the aim of identifying the best model. The results showed that the 5-layered model with SGD optimizer performs the best.