Image dehazing and defogging based on second-generation wavelets and estimation of transmission map

Image dehazing is one of the pivotal topics in computer vision arena due to its significant effects on improving the foggy images that taken under poor weather conditions. Problems such as halo outliers and over-saturation are presented in the ridges i.e. high-frequency components of the hazy images which lead to false guesstimate of atmospheric light and transmission depth that negatively results on the task of visibility restoration image. In this paper, the proposed method has the ability to deal with hazy images with several haze density while most of state-of-the-art dehazing techniques suffer from lack of contrast of the observed object in the dehazed images due to unequal distribution of transmission depth. In order to achieve high visual quality from the contaminated hazy images, the proposed method is designed according to semi soft thresholding and Gamma transformation where the second-generation wavelet transformation is used to improve the transmission map. Qualitative and quantitative results showed that, the proposed method outperforms sophisticated state-of-the-art image haze removal techniques both in visual image quality and time efficiency.