Underwater Image Enhancement Using Convolutional Neural Network
This work addresses image enhancement for underwater photography, but it is incremental as it builds on existing histogram equalization techniques.
The authors tackled the problem of degraded colorfulness and contrast in underwater images by proposing a method that combines histogram equalization with a convolutional neural network to retain colors, achieving better results on underwater image datasets.
This work proposes a method for underwater image enhancement using the principle of histogram equalization. Since underwater images have a global strong dominant colour, their colourfulness and contrast are often degraded. Before applying the histogram equalisation technique on the image, the image is converted from coloured image to a gray scale image for further operations. Histogram equalization is a technique for adjusting image intensities to enhance contrast. The colours of the image are retained using a convolutional neural network model which is trained by the datasets of underwater images to give better results.