Abstract
In this paper we proposed a fuzzy method based on dark channel prior to enhance the visibility of images
that are degraded by fog or haze. In order to improve the perceptual visibility of RGB images, we modified the dark
channel prior through fuzzy logic. The dark channel prior significantly measures the statistical estimation of haze-free
outdoor images. It is based on fact that in haze free images most patches include pixels which have very low intensity
in channel that is effective in estimation of thickness of haze and is capable to recover high quality haze-free images.
We applied fuzzy logic with dark channel prior for computing probabilistic values other than lowest pixel intensity
values among channels of images. Our experimental finding reveals that proposed method for restoration of foggy
images using fuzzy logic along with atmospheric light, transmission map, and scene radiance effectively recovers
the original fog free image. To further enhance the image perceptual quality, the guided filter was applied on the
resultant fog free images for edge smoothing and noise removal. For performance evaluation of proposed method, we
used Realistic Single Image De-hazing (RESIDE) dataset consisting of foggy images of different haze density. We
introduce proposed scheme by combining the fuzzy logic with dark channel prior and demonstrate that the proposed
method is capable to estimate the corresponding fog function which is significant for fog removal, improve image
visibility, and increase user safety.
