论文标题
一种新颖的图像除雪人和评估方法
A Novel Image Dehazing and Assessment Method
论文作者
论文摘要
在朦胧的天气条件下捕获的图像通常会遭受颜色对比度和颜色保真度。这种降解由传输图表示，该传输图表示代表添加噪声的颜色的衰减和气灯的量。在本文中，我们提出了一种使用雾光颜色而不是气光颜色估算传输图的方法，因为估计空气灯有一些歧义。提议的方法的定性和定量结果显示了给定方法的竞争力。此外，我们提出了两个指标，这些指标基于自然室外图像的统计数据，以评估雾化去除算法。
Images captured in hazy weather conditions often suffer from color contrast and color fidelity. This degradation is represented by transmission map which represents the amount of attenuation and airlight which represents the color of additive noise. In this paper, we have proposed a method to estimate the transmission map using haze levels instead of airlight color since there are some ambiguities in estimation of airlight. Qualitative and quantitative results of proposed method show competitiveness of the method given. In addition we have proposed two metrics which are based on statistics of natural outdoor images for assessment of haze removal algorithms.
