Enhancement of Underwater Images using White-Balanced EMD and Convolution
Sampada Deshpande, Maitreyi Ekbote, Reena Sonkusare · 2022
When light travels through water, it gets attenuated due to the scattering of photons. This results in the addition of noise, low contrast, and blurring of images when the image is captured by the camera. This paper focuses on the enhancement of such underwater images with the help of the Empirical Mode Decomposition (EMD) algorithm. To improve the performance of the EMD algorithm, the images are white balanced before applying the EMD algorithm. The Gray World Algorithm is used to white balance the images. After applying the algorithm, the images are convoluted so that the output obtained has sharp images. With this approach, there was an approximately 93% to 98% reduction in the Mean Squared Error and a 31% gain in the Peak Signal to Noise Ratio when compared to the existing studies.