Dark Image Enhancement Using Perceptual Color Transfer

In this paper, we introduce an image enhancing approach for transforming dark images into lightened scenes, and we evaluate such method in different perceptual color spaces, in order to find the best-suited for this particular task. Specifically, we use a classical color transfer method where we obtain first-order statistics from a target image and transfer them to a dark input, modifying its hue and brightness. Two aspects are particular to this paper, the application of color transfer on dark imagery and in the search for the best color space for the application. In this regard, the tests performed show an accurate transference of colors when using perceptual color spaces, being RLAB the best color space for the procedure. Our results show that the methodology presented in this paper can be a good alternative to low-light or night vision processing techniques. Besides, the proposed method has a low computational complexity, property that is important for real time applications or for low-resource systems. This method can be used as a preprocessing step in order to improve the recognition and interpretation of dark imagery in a wide range of applications.