基于迭代多尺度引导滤波Retinex 的低照度图像增强

为提高低照度图像的视觉感知，提出了基于迭代多尺度引导滤波Retinex 的低照度图像增强算法。首先，将图像转换到YCbCr 空间；然后对Y 分量用迭代多尺度引导滤波算法估计照度图像，以指数形式迭代增加尺度参数与平滑参数，在保持边缘的同时消除各种对比度细节；接着用照度图像求得反射图像，并进行对比度校正；最后将图像转换到RGB 空间，得到最终增强后的图像。实验表明，该方法能更好地估计照度图像，从而使增强后的图像视觉效果获得明显改善。

Low-Light Image Enhancement Based on Iterative Multi-Scale Guided Filter Retinex

In order to improve the visual perception of low-light image, a kind of low-light imageenhancement algorithm based on iterative multi-scale guided filter Retinex was proposed. Firstly, thelow-light image was converted into YCbCr color space. Secondly, the illumination image of the Ychannel was estimated with iterative multi-scale guided filter. By increasing the scale parameter andthe smoothing parameter iteratively in exponential form, the edge was preserved and details ofdifferent contrasts was eliminate. And then, the reflected image was obtained by the estimatedillumination image and the contrast correction procedure. Finally, the image was converted into RGBcolor space, and this is the final enhanced image. Experimental results show that our method can betterobtain the illumination image so that the visual effect of the enhanced image can be improved obviously.