Enhancing low-light color image visibility with hybrid contrast and saturation modification using a saturation-aware map

In this paper, we present a two-stage technique for color image enhancement. In the first stage, we apply the well-established Histogram Equalization method to enhance the overall contrast of the image. This is followed by a local enhancement method to address the differences in average local contrast between the original and enhanced images. In the second stage, we introduce a novel weighted map within a variational framework to adjust the saturation of the contrast-enhanced image. This weighted map identifies regions that require saturation modification and enables a controllable level of adjustment. The map is then multiplied by a maximally saturated color image derived from the original image, and the result is merged with the contrast-enhanced image. Compared to the original low-light image, our method significantly improves image quality, structure, color preservation, and saturation. Additionally, numerical experiments demonstrate that the proposed method outperforms other enhancement techniques in both qualitative and quantitative evaluations.