Comparative analysis of underwater image enhancement methods in different color spaces

A difficult challenge in obtaining clear images in underwater environment is because of poor visibility of objects due to light attenuation and color distortion. A solution to this is to do some form of enhancement of the image that eventually leads to better visualization. This paper presents a comparative analysis of three different enhancements techniques: contrast stretching (CS), histogram equalization (HE) and contrast limited adaptive histogram equalization (CLAHE) in the RGB and HSV color spaces for underwater images. Besides visual inspection, two different quantitative performance evaluation metrics, namely the Edge Contrast (EC) and BRISQUE, are used to assess the quality of the enhanced underwater images. Experimental results show that the CLAHE method performs better than CS and HE methods in both color spaces from the quality scores obtained in the EC as well as with the subjective evaluations.