Fusion of Mathematical Morphology with Adaptive Gamma Correction for Dehazing and Visibility Enhancement of Images

Abstract

Images contaminated with haze generally have faded colors and low contrast, and thus affect object tracking, object recognition, intelligent surveillance, etc. Therefore, dehazing becomes necessary and is aimed to recover the image without color distortion. This paper presents a dehazing approach combining dark channel prior (DCP) with mathematical morphology and a visibility enhancement algorithm. Adaptive gamma correction based weighted distribution (AGCWD) is employed for visibility restoration with a fast processing time. The proposed method is able to eliminate halo artifacts in the restored images. Experimental results obtained are compared with the state- of- the- art dehazing algorithms using some standard metrics.