摘要
针对暗原色先验理论在处理去雾图像后图像的整体视觉效果偏暗的缺陷,为了提高去雾图像的质量,提出一种改进的雾天图像增强算法。首先采用改进的暗原色先验理论做预处理;其次在Lab颜色空间使用Retinex理论提高图像清晰度;最后使用直方图均衡化在RGB颜色空间内提高图像的对比度。仿真结果表明,该算法不仅仅解决了图像整体偏暗的问题,也提高了图像的对比度。
Since the overall visual effect of the defogged image tends to be dark after the defogged image is processed with the dark channel prior theory,an improved image enhancement algorithm in foggy days is proposed to improve the image quality.In the algorithm,the improved dark channel prior theory is used for preprocessing first,and then the Retinex theory is used in the Lab color space to improve the image sharpness.Finally,the histogram equalization is used in RGB color space to improve the image contrast.Simulation results show that the proposed algorithm can not only solve the problem of overall darkening of the image,but also improve its contrast.
作者
吕东
王萍
王宇航
王智文
张灿龙
潘绍明
Lü Dong;WANG Ping;WANG Yuhang;WANG Zhiwen;ZHANG Canlong;PAN Shaoming(College of Electrical and Information Engineering,Guangxi University of Science and Technology,Liuzhou 545006,China;School of Computer Science and Information Technology/School of Software,Guangxi Normal University,Guilin 541004,China;College of Computer Science and Communication Engineering,Guangxi University of Science and Technology,Liuzhou 545006,China)
出处
《现代电子技术》
2021年第11期56-61,共6页
Modern Electronics Technique
基金
国家自然科学基金项目(61962007)
国家自然科学基金项目(61462008)
国家自然科学基金项目(61751213)
国家自然科学基金项目(61866004)
广西自然科学基金重点项目(2018GXNSFDA294001,2018GXNSFDA281009)
广西自然科学基金项目(2018GXNSFAA294050,2017GXNSFAA198365)
广西教育厅科研项目(YB2014209)
广西科技大学创新团队“图像处理与智能认知及应用”(gxkjdxcxtd201504)
2017年广西科技大学硕士研究生创新项目(GKYC2017)。
关键词
图像增强
图像对比度
图像去雾
直方图均衡化
导向滤波
对比实验
image enhancement
image contrast
image defogging
histogram equalization
guided image filtering
contrast experiment
