分析了Boosting提升模型, 提出一种以去雾后图像均方误差与信息熵比值为选择标准, 对多类不同的去雾算法进行排序, 并根据设定的阈值, 从多类的去雾算法中, 选择合适的去雾算法作为“极优增强器”, 再通过对优化学习率的方法。更新“极优增强器”的权重, 采取线性组合, 构建了最优去雾算法。经实验表明, 该算法实现了去雾后图像对比度和图像的信息损失之间的平衡。提升了图像对比度, 凸显了图像细节, 最大程度的减小了图像信息的损失。

The Boosting lifting model was analyzed. A selection criterion for the ratio of the mean square error and the entropy of the image after the defogging, and the different kinds of different defogging algorithms were sort out. According to the set the threshold, the appropriate defogging algorithm was selected as the "extreme best intensifier" from the multiple defogging algorithm. By optimizing the learning rate, the weight of the "optimal enhancer"was updated.A linear combination to construct an optimal fog removal algorithm was exopted was adopted. Experiments show that the algorithm achieves the balance between image contrast and image loss after fog removal. The image contrast is enhanced, the image details are highlighted, and the loss of image information is reduced to the greatest extent.