基于暗原色和直方图匹配的雾天图像增强算法  

Foggy Weather Image Enhancement Algorithm Based on Dark Channel Prior and Histogram Matching

作　　者：张洪坤 周浦城[2] 薛模根[2] 

机构地区：[1]解放军陆军军官学院研究生系,合肥230031 [2]解放军陆军军官学院信息工程系,合肥230031

出　　处：《计算机工程》2012年第1期215-216,219,共3页Computer Engineering

摘　　要：针对雾天图像景物容易退化的问题,提出一种基于暗原色和插值直方图匹配的雾天图像自适应增强算法。该算法基于暗原色先验信息寻找并分割出图像中的天空区域,利用插值直方图匹配方法对非天空区域进行自适应增强处理,采用主成分分析方法将处理前后的图像信息进行融合。实验结果表明,该算法不仅能避免天空噪声对图像的干扰,而且能有效提高图像对比度,获得满意的图像视觉效果。According to the degraded effect of images obtained in foggy weather,a new enhancement algorithm based on dark channel prior and local interpolating histogram matching is proposed.The sky region is separated from the degraded image using dark channel prior.The local interpolating histogram matching algorithm is adopted to deal with the non-sky region of the image.The disposals of after and before images are fused by principal component analysis.Experimental results show that the algorithm can not only efficiently avoid interfere with sky regions,but also enhance the contrast of degraded images and obtain satisfying visual effects.

关 键 词：去雾 暗原色 直方图匹配 图像增强 

分 类 号：N945[自然科学总论—系统科学]