基于全局亮度自适应均衡化的海上图像带色彩恢复的多尺度Retinex算法

针对海上图像利用多尺度图像增强算法（MSRCR）不能有效地去除雾以及存在颜色纠偏过度问题，提出了一种基于全局亮度自适应均衡化的海上图像改进MSRCR算法。该算法首先计算海上雾天图像的取反图；其次对原图像和取反后图像进行MSRCR运算；然后利用全局亮度自适应直方图均衡化处理，并将处理后的亮度与经MSRCR处理后的反射分量进行低频信号线性叠加；最后计算叠加后图像的均值和标准差，并采用自适应拉伸图像灰度值，实现图像色彩对比度的提升。实验证明该算法处理后的图像，前景突出，细节清晰，色彩丰富，对于海上图像除雾，具有一定的意义。

Improved MSRCR Algorithm for Marine Image Based on Global Brightness Adaptive Equalization

A modified image MSRCR algorithm based on global brightness adaptive equalization is proposed to solve the problem of excessive color correction and invalidly of sea-fog removal. Firstly, the algorithm inverts the original sea-foggy image. Secondly, the original image and inverse image are processed by MSRCR algorithm.Then the adaptive histogram equalization of global luminance is proposed and the processed luminance and the reflected component processed by MSRCR are linearly superimposed.Finally, the mean and variance were calculated to decide the contrast stretching degree adaptively. The results show that the image processed by this algorithm has prominent foreground, clear detail and bright color, which is of certain significance for the sea image defogging.