摘要
在研究图像去雾算法的基础上,根据暗通道先验理论(DCP)提出了一种改进的暗通道去雾算法.将原算法中估计全局大气光值以及透射率进行新的估计和细化,解决了暗通道算法中容易出现的块效应和严重的色彩偏离现象,同时缓解存在于物体边缘的晕现象等问题.通过实验对比表明,该算法优于原算法,有较好的去雾效果.
This paper proposed a new image haze removal algorithm based on a physical model and dark channel prior （DCP）. The new algorithm is used to estimate and refine the global atmospheric light value and transmittance, which can solve the block effect and serious color deviation in the DCP. At the same time , it can reduce the halo phenomenon existing in the edge of the object, and the experimental results show that the algorithm is superior to the original, and has a better haze removal.
作者
白荣鑫
杨峰
Bai Rongxin;Yang Feng(School of Information Science and Engineering, Shandong Normal University,250358, Jinan, Chin)
出处
《山东师范大学学报（自然科学版）》
CAS
2017年第4期32-36,共5页
Journal of Shandong Normal University(Natural Science)
关键词
图像去雾
暗通道先验
大气光值
image haze removal
dark channel prior
atmospheric light value
