HSV空间的明度对数斜率变换的低照图像增强

Low Light Image Enhancement Based on Logarithmic Slope Transformation of Lightness in HSV Space

为了在保持图像颜色自然的同时,适宜地提升图像的亮度和对比度,丰富图像的细节信息,提出了HSV空间的明度对数斜率变换的低照图像增强方法。将低照图像转到HSV颜色空间,将明度分量V进行多尺度Retinex分解,得到多尺度的细节层图像和光照图像;对多尺度的细节层图像进行自适应分数拉普拉斯增强,而用自适应的对数斜率变换对光照图像进行增强;将增强后的明度分量V与色调H和饱和度S分量组合,得到亮度适宜、高对比度和高清晰度的图像。与部分现有方法进行比较,实验数据显示所提方法的增强图像的视觉效果更佳、信息熵和平均梯度更高,因此具有更优的图像增强性能。

In order to maintain the color naturalness,properly improve the brightness and contrast,and enrich the details for the image,a low light image enhancement method based on logarithmic slope transformation of lightness in HSV space is proposed,which transforms the low light image into HSV color space,and performs multi-scale Retinex decomposition on the lightness component V,so as to achieve multi-scale detail layer images and illumination image.The multi-scale detail layer images are subjected to adaptive fractional Laplace enhancement,and the illumination image is enhanced by adaptive logarithmic slope transformation.The combination of the enhanced lightness component V,the hue H and saturation S obtains an image with appropriate brightness,high contrast and high definition.Compared with some existing methods,the data show that the enhanced image of the proposed method has better visual effect,higher information entropy and higher average gradient.Thus,the proposed method has superior image enhancement performance.