湖北汽车工业学院学报2025，Vol.39Issue(3)：7-13,7.DOI:10.3969/j.issn.1008-5483.2025.03.002
基于改进加权引导滤波Retinex的反光图像增强方法
Image Enhancement Method Based on Improved Weighted Guided Filtering Retinex for Reflection
摘要
Abstract
In view of uneven brightness and low contrast in images caused by workpiece reflection,an image enhancement algorithm based on improved weighted guided filtering Retinex for reflection(OC-ISF-WGIFR)was proposed.By taking the detection of the driving disk of the silicone oil fan clutch as an example,Otsu's improved Canny operator was utilized to affect the edge weight factor of the weight-ed guided filtering to realize the adaptive edge-preserving filtering;the filtered image was segmented by double thresholds to obtain two images divided according to the luminance intervals,and then,they were processed by Retinex algorithm;image fusion was carried out to obtain the resultant image.The test results show that the peak signal-to-noise ratio of the image processed by the OCISF-WGIFR algo-rithm is 7.935;the structural identity is 0.493,and the root-mean-square error is 102.283.The edge in-formation is well preserved,which improves the problem of overall whiteness and serious distortion of the image processed by the traditional Retinex algorithm.关键词
图像处理/低对比度图像/亮度不均/加权引导滤波/RetinexKey words
image processing/low contrast image/uneven brightness/weighted guided filtering/Retinex分类
信息技术与安全科学引用本文复制引用
王元奇,王宸,钟毓宁..基于改进加权引导滤波Retinex的反光图像增强方法[J].湖北汽车工业学院学报,2025,39(3):7-13,7.基金项目
国家自然科学基金(52405590) （52405590）
湖北省重点研发计划资助项目(2021BAA056) （2021BAA056）
湖北省高等学校中青年科技创新团队计划资助项目(T20200018) （T20200018）
湖北汽车工业学院博士科研启动基金(BK201905) （BK201905）
