A variational-based fusion model for non-uniform illumination image enhancement via contrast optimization and color correction

Non-uniform illumination images are of limited visibility due to under-exposure, over-exposure, or a combination of these two factors. Enhancing these images is a very challenging task in image processing. Although there are numerous enhancement methods to improve the visual quality of images, many of these methods produce undesirable results with regard to contrast and saturation improvements. In order to improve the visibility of images without over-enhancement or under-enhancement, a variational-based fusion method is proposed for adaptively enhancing non-uniform illumination images. First, a hue-preserving global contrast adaptive enhancement algorithm obtains a globally enhanced image. Second, a hue-preserving local contrast adaptive enhancement method produces a locally enhanced image. Finally, an enhanced result is obtained by a variational-based fusion model with contrast optimization and color correction. The final result represents a trade-off between global contrast and local contrast, and also maintains the color balance between the globally enhanced image and the locally enhanced image. This method produces visually desirable images in terms of contrast and saturation improvements. Experiments were conducted on a dataset that included different kinds of non-uniform illumination images. The results demonstrate that the proposed method outperforms the compared enhancement algorithms both qualitatively and quantitatively.