کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
562937 | 1451964 | 2014 | 19 صفحه PDF | دانلود رایگان |
• We first introduce the concept of the negative correction of photographic developing into dehazing algorithm.
• Instead of estimating the transmission map, the correction factor of negative images is estimated and it is used to rectify the corresponding haze images.
• In order to suppress halos, a modified maximum-filter is proposed to limit the maximum value of modified correction factor of local region.
• The proposed algorithm can effectively remove hazes. It can not only maintain the naturalness of images, but also enhance the details of images. Moreover, it can significantly reduce the computational complexity.
Dehazing is an important but difficult issue for image processing. Recently, many dehazing algorithms have been proposed based on the dark channel prior. However, these algorithms fail to achieve a good tradeoff between the dehazing performance and the computational complexity. Moreover, the perceptual quality of these algorithms can be further improved, especially for sky areas. Therefore, this paper firstly introduces the concept of negative correction inspired by the practical application of photographic developing and a fast image dehazing algorithm is accordingly proposed. Based on the observation of the photographic developing, we find that the contrast of images can be enlarged and their saturation can also be increased when their negative images (or reverse image) are rectified. Thus, instead of estimating the transmission map, the correction factor of negative is estimated and it is used to rectify the corresponding haze images. In order to suppress halos, a modified maximum-filter is proposed to limit the larger value of correction factor of local region. The experimental results demonstrate that the proposed algorithm can effectively remove hazes and maintain the naturalness of images. Moreover, the proposed algorithm can significantly reduce the computational complexity by 56.14% on average when compared with the state-of-the-art.
Journal: Signal Processing - Volume 103, October 2014, Pages 380–398