基于明亮区域和天空识别的图像去雾算法

针对去雾算法对存在大面积明亮区域的图像去雾效果不佳的问题,根据暗原色先验原理提出了一种基于明亮区域和天空区域识别的图像去雾算法。根据天空区域和明亮区域的特点,建立了明亮区域和天空区域的判别机制,对不同类型的图像采用不同方法求取大气光值;基于点暗原色原理,采用中值滤波和双边滤波对点透射率进行细化,与块透射率相比,采用点透射率可以保留更多的图像细节。结果显示,采用均方误差、峰值信噪比、可见边梯度和结构相似性4个参数作为图像去雾效果的客观评价指标,优化后算法的综合评价指标均优于其他算法。所提出的算法对不同类型图像均可取得较好的去雾效果,消除了去雾图像的光晕、块效应和天空区域过饱和现象。

Image dehazing algorithm based on high light region and sky region detection

The existing image dehazing algorithms cannot achieve satisfactory performance in the cases that the image has large high light regions. To solve this problem, an improved image haze removal method is proposed based on sky region and high light region detection. Discriminant mechanism for sky region and high light region is established, and different methods are used to calculate the atmospheric light value for different types of images. Based on the principle of point dark channel, the transmission is further detailed by median filtering and bilateral filtering in order to retain more image details. Finally, the mean square error (MSE), peak signal to noise ratio(PSNR), visible edge gradient method and structure similarit(SSIM) are used as the objective criterion to judge the dehazing effect. The calculation results show that the optimized algorithm is superior to other algorithms in the aspect of comprehensive evaluation index. The proposed method has better performance in haze removal for different types of images, effectively eliminating the image halo, block effect and over saturation of the sky.