Abstract: The multi-scale Retinex algorithm has some problems such as insufficient detail enhancement and long time-consumption in processing low-illumination image of underground coal mine. Aiming at the problem, a fast multi-scale Retinex algorithm based on illumination correction was proposed to enhance low-illumination image of underground coal mine. By calculating brightness value of each pixel of image after gaussian blur, the image is divided into dark and highlight areas, and illumination correction is carried out on dark and highlight areas, so as to reduce brightness of highlight area to avoid overexposure, and improve brightness of dark area to highlight more details. Three-times fast mean filtering is used instead of Gaussian filtering to estimate illumination intensity, so as to reduce time-consumption of the algorithm. The experimental results show that the algorithm can effectively improve brightness and contrast of image, enhance details of dark and highlight areas in image, and has fast processing speed.