基于暗原色先验模型的混合滤波图像去雾算法

基于暗原色先验模型去雾方法,提出混合滤波快速图像去雾算法.该算法在暗原色先验模型的基础上,对雾图的暗原色图像进行最大值滤波,继而求出透射率矩阵;利用最小值滤波估算透射率矩阵的下限值作为透射率的补偿值,再使用指导滤波修复透射率矩阵;利用小波变换方法对去雾后的图像进行滤波和平滑处理,有效改善了去雾图像的视觉效果.本算法有效解决了由于图像边缘估值失真导致的重建后去雾图像存在景深边缘处白色晕块和斑状奇异点的问题,以及带雾图像不同景深、景深边缘透射率的误差修复问题.

Mixed Filter Image Haze-Removal Algorithm Based on Dark Channel Prior

According to the theory of dark channel prior, a mixed filter image haze-removal algorithm is proposed. The algorithm obtains the transmission matrix of the dark channel prior model by using maximum value filter,and then obtains the value of transmission lower limit by using minimum filter. Finally,wavelet is adopted to smooth the de-hazed image,it improves the visual effect of the image dramatically. The white halos and patchy singularities which exist at the edge of the depth field in the reconstructed image are eliminated,and the deviation of the transmission is refined.