الخلاصة

De-hazing image is big challenge for the researchers, although there are many good algorithms but all of them not regards as a perfect algorithm. In this paper we try to introduce new de-hazing method based on many steps. We first preprocess the image to remove some of noise using average filter before we estimate the dark channel prior which is estimated based on average. The main contribution in this paper is the estimation of Air light value. We suggest new method based on comparing the standard deviation for RGB image and the HSV color space image. For that, we suggested many rules to control the Air light value according to experiments. Enhance local contrast implement based on V channel of color space HSV to construct visually pleasing images. The quality of de-hazed images measured visually and by using many quality measuring metrics (blind quality and reference quality) which gives promised results. Although the proposed method is not perfect method but it was more efficient than other algorithms when compared with them.