A hybrid of fuzzy theory and quadratic function for estimating and refining transmission map

Abstract

In photographs captured in outdoor environments, particles in the air cause light attenuation and degradeimage quality. This effect is especially obvious in hazy environments. In this study, a fuzzy theory is proposed to estimatethe transmission map of a single image. To overcome the problem of oversaturation in dehazed images, a quadraticfunction-based method is proposed to refine the transmission map. In addition, the color vector of the atmosphericlight is estimated using the top 1% of the brightest light area. Finally, the dehazed image is reconstructed using thetransmission map and the estimated atmospheric light. Experimental results demonstrate that the proposed hybridmethod performs better than the other existing methods in terms of color oversaturation, visibility, and quantitativeevaluation.