基于分数阶微分和多尺度Retinex联合的雾霭图像增强算法

Foggy Image Enhancement by Combined Fractional Differential and Multi-Scale Retinex

针对传统的雾霭图像增强算法效果差,存在晕圈伪影的现象,提出一种基于分数阶微分和多尺度Retinex联合的雾霭图像增强算法。首先将原始图像用分数阶微分算法进行处理,以保留图像低频信息,将处理后的图像由RGB颜色空间转换到HSI颜色空间;然后,用引导滤波器代替多尺度Retinex算法中的高斯滤波器,以提取亮度分量和反射分量,同时以这2个分量之和作为新的亮度层,对饱和层使用伽马校正功能进行增强;最后,将HSI图像再转换为RGB图像。采用客观评价方法对算法的有效性进行评估,结果表明,所提算法去除图像雾霭的效率高,且去雾后的图像没有晕圈伪影。

Aiming at the halo artifacts caused by traditional hogging image enhancement algorithm, a fractional image enhancement algorithm combining fractional differential and multi-scale Retinex is proposed. The proposed algorithm first processes the original image with a fractional order differential algorithm to preserve its low frequency information, and converts the processed image from the RGB color space to the HSI color space. Then, the Gaussian filter in the multi-scale Retinex algorithm is replaced with a leading filter to extract the luminance component and the reflected component, and the sum of the two components is used as the new luminance layer, and the Gamma correction function is used for the saturation layer. Finally, the HSI image is converted back to RGB image. An objective evaluation method is used to evaluate the effectiveness of the algorithm. The experimental results show that the proposed algorithm has high efficiency and no halo artifacts present in the processed image.