摘要
针对海上图像利用带色彩恢复的多尺度Retinex算法(multi-scale Retinex with color restoration,MSRCR)不能有效去除雾及存在颜色纠偏过度问题,提出了一种基于全局亮度自适应均衡化的海上图像改进MSRCR算法。该算法首先计算海上雾天图像的取反图;其次对原图像和取反后图像进行MSRCR运算;然后利用全局亮度自适应直方图均衡化处理,并将处理后的亮度与经MSRCR处理后的反射分量进行低频信号线性叠加;最后计算叠加后图像的均值和标准差,并采用自适应拉伸图像灰度实现图像色彩对比度的提升。实验证明该算法处理后的图像,前景突出、细节清晰、色彩丰富,对于海上图像除雾具有一定的意义。
A modified image multi-scale Retinex with color restoration(MSRCR)algorithm based on global brightness adaptive equalization was proposed to solve the problem of excessive color correction and ineffective removal of sea-fog.Firstly,the algorithm inverted the original sea-foggy image.Secondly,the original image and the inverse image were processed by MSRCR algorithm.Then the adaptive histogram equalization of global luminance was proposed and the processed luminance and the reflected component processed by MSRCR were linearly superimposed.Finally,the mean and variance were calculated to decide the contrast stretching degree adaptively.The results show that the image processed by this algorithm has prominent foreground,clear details and bright color,which is of certain significance for the defogging of sea image.
作者
林昌
陈武
周海峰
LIN Chang;CHEN Wu;ZHOU Hai-feng(Marine Engineering College and Key Laboratory of Fujian Province Marine and Ocean Engineering,Jimei University,Xiamen 361021,China;School of Mechanical and Electrical Engineering,Putian University,Putian 351100,China;Key Laboratory of Modern Precision Measurement and Laser Nondestructive Detection Colleges and Universities in Fujian Province,Putian 351100,China;Merchant Marine College,Shanghai Maritime University,Shanghai 200135,China)
出处
《科学技术与工程》
北大核心
2020年第33期13712-13717,共6页
Science Technology and Engineering
基金
国家自然科学基金(51179074)
交通运输部交通运输行业高层次技术人才培养项目
福建省自然科学基金(2018J01495)
福建省教育厅中青年教师项目(JAT170507,JAT170507(p))
莆田市科技局项目(2018RP4002)
现代精密测量与激光无损检测福建省高校重点实验室开放课题(B17119)
集美大学博士科研启动基金(ZQ2013007)。
