测试技术学报2025，Vol.39Issue(3)：322-329,8.DOI:10.62756/csjs.1671-7449.2025040
基于多尺度融合的低光照图像增强
Low Light Image Enhancement Based on Multi-Scale Fusion
摘要
Abstract
To address the issues of low brightness,low contrast,color distortion,and noise in low-light images,a multi-scale fusion-based low-light image enhancement method is proposed.Firstly,a fast and efficient algorithm is employed to enhance the image brightness.Subsequently,the enhanced RGB image is transformed into the image in HSV color space,the luminance components are processed by the improved contrast limited adaptive histogram equalization(CLAHE),guided filtering,and sharp-smoothing filtering,respectively,and three luminance components are obtained.Finally,the three pro-cessed luminance components and corresponding weights are fused by multi-scale fusion,and the obtained HSV image is transformed into the image in RGB color space,and the ultimate enhanced image is attained.The experimental results show that the proposed algorithm is superior in the evaluation index and has better information entropy,natural image quality,and average gradient values.The algorithm improves image brightness,enhances details,eliminates noise significantly,processes images more com-prehensively,and improves the visual quality and clarity of images significantly.关键词
图像增强/多尺度融合/锐化平滑滤波/对比度限制自适应直方图均衡化Key words
image enhancement/multi-scale fusion/sharpening and smoothing filtering/contrast limited adaptive histogram equalization(CLAHE)分类
电子信息工程引用本文复制引用
郭依婷,胡红萍,杨正民..基于多尺度融合的低光照图像增强[J].测试技术学报,2025,39(3):322-329,8.基金项目
山西省基础研究计划资助项目(20210302123019,20210302124195,20210302124212,20210302123189) （20210302123019,20210302124195,20210302124212,20210302123189）
山西省回国留学人员科研项目(2021-108) （2021-108）
