Single Image Haze Removal Using Local Variance-to-Mean Ratio

摘要：

　　In this paper, we propose an effective and efficient method to remove haze from a single input image.By combining mean filter with local variance-to-mean ratio, we can directly estimate the depth map of the input hazy image and recover a high quality haze-free image.Results on a variety of hazy images demonstrate the effectiveness and efficiency of our method.

关键词： dehazing local variance-to-mean ratio mean filter

作者: Huang Dewei Lu Jianqiang Chen Kexin Wang Weixing

作者单位: College of Electronic Engineering, South China Agricultural University, Guangzhou 510642 College of Electronic Engineering, South China Agricultural University, Guangzhou 510642;Guangdong E College of Electronic Engineering, South China Agricultural University, Guangzhou 510642;Guangdong E

会议类型: 国内会议

会议名称: 2016年广东省测控与计量仪器学术研讨会

会议地点: 广州

会议语种:英文

页码: 26-30

在线出版日期: 2016-12-01（万方平台首次上网日期，不代表论文的发表时间）