一种基于L通道照度估计和伽马函数的图像增强算法

A Retinex Image Enhancement Based on L Channel Illumination Estimation and Gamma Function

为了提高低光照图像对比度增强处理效果并消除伪影,提出了一种基于L通道照度估计和二维伽马函数的彩色Retinex图像增强算法。首先,该算法通过Lab色彩空间变换将L通道图像强度视为相关反射率和照度的产物,采用双边滤波估计全局照明的强度。然后,采用二维伽马函数完成像素映射,实现局部细节的自适应调节。实验结果表明,相比其他Retinex图像增强算法,提出算法增强后的效果更自然并且没有产生增强伪影,能够有效保留图像局部细节。

In order to improve the contrast of low illumination image, enhance the processing effect and eliminate artifacts, a color Retinex image enhancement algorithm based on L channel illumination estimation and two dimensional gamma function is proposed. Firstly, the L image intensity is regarded as the product of correlation reflectivity and illumination through lab color space transformation, and the intensity of global illumination is estimated by bilateral filtering. Then, two dimensional gamma function is used to complete the pixel mapping, and the local details can be adaptively adjusted. Experimental results show that compared with other Retinex image enhancement algorithms, the proposed algorithm enhances the effect more naturally and produces no enhancement artifacts, it can effectively preserve the local details of the image.