基于GIF滤波分解的低照度图像增强算法

针对常见的对比度增强方法在处理低照度图像时不能兼顾提升图像亮度、对比度,和增强细节的问题,提出基于引导滤波器(guided image filter,GIF)的低照度图像增强算法。首先将输入图像从RGB颜色空间转换到HSV颜色空间;再利用GIF滤波器对图像进行图像分解,得到一个基本层和一个细节层;然后对基本层进行自适应Gamma校正,提高图像的整体亮度和对比度;再对细节层进行S型曲线增强,突出图像的局部细节;最后合成并恢复颜色,得到增强图像。将本文算法、全局Gamma校正、MSRCR 3种算法分别对低照度Bridge和Street图像进行处理,实验结果表明:本文算法能够在有效提升对比度的同时增强图像细节,提升了低照度图像的视觉效果。

A Low Illumination Image Enhancement Algorithm Based on GIF Filtering Decomposition

The ordinary contrast enhancement methods in the low illumination images processing exist problems of not be able to improve the brightness, the contrast and details of images simultaneously, proposes a low illumination image enhancement algorithm based on guided image filter (GIF) . The algorithm converts the input image from RGB color space to HSV color space, then decomposes the image into a base layer and a detail layer by a guided image filter, after that, conducts an adaptive Gamma correction on the base layer to improve the overall brightness and contrast of the image; enhances S-shape curve on the detail layer to highlight the local details of the image; finally reconstructs and restores the colors and obtains the enhanced image. A control experiment is conducted on 2 low illumination images (Bridge and Street) by the proposed method, global Gamma correction and MSRCR, respectively. The results indicate that the proposed method is able to improve the image contrast and details simultaneously, and enhances the visual quality of low illumination images.