Underwater Image Enhancement using Improved Bat Algorithm

Abstract

From the past decades, improving the superiority of an Underwater Image (UI) has received well recognition in terms of the deprived image visibility that is occurred due to the water medium physical property. The light absorption of wavelength-reliant, as well as scattering in an underwater view, degrades the image visibility which causes lesser contrast as well as distorted color casts. To overcome the issues, a highly developed technique is adopted for the advancement and it improves the UI classification. Specifically, by exploiting the Improved Bat Algorithm (IBA), the underwater input image RGB is enhanced. The next stage is feature extraction. To the enhanced Principle Component Analysis (PCA) technique, the extracted attributes are given as input; here the dimensions of the features are minimized. Subsequently, the classification operation is carried out by exploiting the ANFIS classifier. Finally, the classified improved deeper water images besides the improved shallow water images which are seen are available in the testing stage. Finally, the simulation outcomes for the proposed and conventional methods are analyzed. The developed UIE system shows superior accuracy while compared with the conventional techniques.