A new image enhancement method considering both dynamic range and color constancy

This paper proposes an approach to improving color images suffering from low dynamic range by employing both histogram matching and histogram stretching techniques. In the first stage, the color image was transformed from RGB into HSV color space, in which the color information was separated from intensity. Then, an appropriate reference image was selected by comparing component V of the enhanced image with component V of the database images using a similarity measure. The selected image was used as the target image in histogram matching algorithm for enhancement. In the second stage, components V and S were linearly stretched in order to recover the image color information. Finally, using the treated V and S components and untreated component of H, the enhanced image was obtained in RGB color space by inverse transform. The qualitative and quantitative results showed that the contrast and color of the resultant image were greatly improved using the proposed method, which outperformed the current state-of-the-art methods.