首页 | 本学科首页   官方微博 | 高级检索  
     

基于特征融合的快速图像去雾方法
引用本文:马书一,郝巧红,管庆吉,齐妙. 基于特征融合的快速图像去雾方法[J]. 吉林大学学报(理学版), 2016, 54(1): 100-106
作者姓名:马书一  郝巧红  管庆吉  齐妙
作者单位:东北师范大学 计算机科学与信息技术学院, 长春 130117
摘    要:针对图像去雾问题, 提出一种基于特征融合的快速单幅图像去雾方法, 解决了暗通道方法存在的块效应问题. 该方法先采用基于K均值聚类的暗通道先验求得粗尺度下的透射率, 再通过分析雾对成像的影响, 提取有雾图像自身能反映景深变化的饱和度作为细尺度的透射率, 最后通过图像融合技术得到精确的透射率. 通过对
各种真实有雾场景进行测试的实验结果表明, 该方法简单且有效, 能得到理想的去雾效果.

关 键 词:图像去雾  K均值聚类  多尺度  特征融合  
收稿时间:2015-05-12

Fast Image Dehazing Method Based on Feature Fusion
MA Shuyi,HAO Qiaohong,GUAN Qingji,QI Miao. Fast Image Dehazing Method Based on Feature Fusion[J]. Journal of Jilin University: Sci Ed, 2016, 54(1): 100-106
Authors:MA Shuyi  HAO Qiaohong  GUAN Qingji  QI Miao
Affiliation:School of Computer Science and Information Technology, Northeast Normal University, Changchun 130117, China
Abstract:Aiming at the problem of image processing, we proposeda fast single image dehazing method based on feature fusion, and solved the problem of the block effect of dark channel method. By means of the dark channel prior based on K-means clustering, the coarse scale transmission was obtained. By analyzing the effect of haze on imaging, we extracted the saturation of hazy image itself as fine scale transmission, which could reflect the change of scene depth effectively. Finally, we obtained accurate transmission via image fusion technique. Through the test of a variety of real scene images, the experiment results show that the method is simple and effective, and can get ideal dehazing result.
Keywords:image dehazing  K-means clustering  multi scale  feature fusion
本文献已被 CNKI 等数据库收录!
点击此处可从《吉林大学学报(理学版)》浏览原始摘要信息
点击此处可从《吉林大学学报(理学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号