Global and Local Contrast Adaptive Enhancement for Non-Uniform Illumination Color Images

Qi-Chong Tian, Laurent D. Cohen; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 3023-3030

Color images captured by digital devices may contain some non-uniform illuminations. Many enhancement methods produce undesirable results in the aspect of contrast improvement or naturalness preservation. A global and local contrast enhancement method is proposed for adaptively enhancing the non-uniform illumination images. Firstly, a novel global contrast adaptive enhancement algorithm obtains the global enhancement image. Secondly, a hue-preserving local contrast adaptive enhancement algorithm produces the local enhancement image. Finally, a contrast-brightness-based fusion algorithm obtains the final result, which represents a trade-off between global contrast and local contrast. This method improves the visual quality and preserves the image naturalness. Experiments are conducted on a dataset including different kinds of non-uniform illumination images. Results demonstrate the proposed method outperforms the compared enhancement algorithms both qualitatively and quantitatively.