A Modified Haze Removal Algorithm Using Dark Channel Prior

摘要

In this paper, we propose a new algorithm to remove haze from a single input image. Based on the Dark Channel Prior proposed by He [1], we exploit the Gauss Bilateral Filter and the min operation to obtain an edgepreserving dark channel image ， which is non-iterative, requires less time. We further utilize this dark channel image to extract the estimation of medium transmission, and finally recover a haze-free image from that. Furthermore, we use a self-adaptive algorithm to set the haze parameters to solve the color shift problem for large sky region. Experiments demonstrate our algorithm can effectively remove haze from a foggy image while keep edges sharp.