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

This paper proposes an approach to improve color images suffering from low dynamic range, by employing both histogram matching and histogram stretching techniques. Firstly, the color image is transformed from RGB into HSV color space, in which the color information is separated from intensity. Then, an appropriate reference image is selected by comparing component V of the enhancing image with component V of the data base images using a similarity measure. This selected image is used as the goal image in histogram matching algorithm in order to enhance image brightness (Automatic Histogram Matching). Secondly, components V and S are 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 is obtained in RGB color space by inverse transform. The qualitative and quantitative results show that the contrast and color of resultant images are greatly improved using the proposed method, which outperforms the current state-of-the-art methods.