Underwater Image Enhancement by Rayleigh Stretching with Adaptive Scale Parameter and Energy Correction

Attenuation of light in water causes degradation of underwater images. This attenuation is caused by water molecules, suspended particles, and dissolved chemical compounds in water. The attenuation includes scattering and absorption of light in water. Backward scattering and fading of color are two major sources of degradation of underwater images. This paper proposed a method of enhancement of underwater images by providing a solution for degradation because of backward scattering. The proposed method corrects the effect of backward scattering by enhancing contrast of the image by Rayleigh stretching of each color channel using maximum likelihood estimation of scale parameter. After contrast enhancement, loss of energy in the signal is corrected, that recovers information loss caused by contrast enhancement. The results of the proposed method are compared quantitatively with state-of-the-art methods by applying it to underwater dataset. Comparison is done with mean square error (MSE), Structural SIMilarity index (SSIM), and Average Information Entropy (AIE) quality metrics. It is seen that the proposed method in this paper produces best results when compared with state-of-the-art methods.