Driver Face Image Enhancement Based on Guided Filter

The paper proposes a method based on guided filter to enhance the driver face image under weak light environment. First, image is converted from RGB color space to HSV color space. Then based on the theory of Retinex algorithm, guided filter is applied to estimate the illumination, obtaining the reflection image which only contains the characteristics of the object. In order to restore the color of image, the coefficient of correlation is used to adaptively adjust the saturation component. Finally, by transforming HSV model to RGB model, the enhanced image with color restoration is obtained. Experimental results show that this algorithm has good enhancement result and high efficiency.