Acgc: Adaptive Chrominance Gamma Correction for Low-Light Image Enhancement

Abstract

Capturing high-quality images becomes challenging in low-light conditions, often resulting in underexposed and blurry images. Only a few works can address these problems simultaneously. This paper presents a low- light image enhancement scheme based on the Y-I-Q transform and bilateral filter in least squares, named ACGC. The method involves applying a pre-correction to the input image, followed by the Y-I-Q transform. The obtained Y component is separated into its low and high-frequency layers. Local gamma correction is applied to the low-frequency layers, followed by contrast limited adaptive histogram equalization (CLAHE), and these layers are added up to produce an enhanced Y component. The remaining I and Q components are also enhanced with local gamma correction to provide images with amore natural color. Finally, the inverse Y-I-Q transform is employed to create the enhanced image. The experimental results demonstrate that the proposed approach yields superior visual quality and more natural colors compared to the state-of-the-art methods.