A Hybrid Approach for Dehazing Images

Abstract

Bad weather conditions including haze, fog, rain etc. degrade the picture quality which causes poor visualizations. Various methods have been proposed to eradicate the effects of above conditions. Initially, polarization filters were used to restore the foggy image. Though this method estimates airlight to quite good an extent but at the same time uses multiple images therefore, cannot be applied on dynamic scenes. In addition, it has very high time complexity. To overcome the use of multiple images Dark channel prior technique was used that effectively calculates the transmission map to restore the foggy image. For this purpose it requires usage of soft matting technique that causes halo effect and has high time complexity. We are of the opinion that if transmission map is calculated using dark channel prior and airlight is estimated using polarisation filters, the resultant process will not only have lower time complexity but at the same time overcomes the drawback of multiple images. The above mentioned technique is implemented in MATLAB-9 and analysed in this paper. The results shows that usage of this hybrid approach gives quite better results.