| 摘要: |
| 针对雾霾天气条件下大气散射和悬浮颗粒物引起的图像对比度、清晰度降低问题，提出通过采用独立分量分析(ICA)算法分解图像中具有相互独立分量的混合像元，估计图像有用信息分量。因乘性噪声信息的存在，会导致估计的图像有用信息有一定的偏差；采用基于噪声检测的局部自适应中值滤波对估计的图像有用信息进行了进一步校正。实验结果证明：新算法能有效去除雾霾，提高图像的清晰度和对比度。 |
| 关键词: 雾霾图像处理 去雾 独立分量分析 噪声检测 自适应中值滤波 |
| DOI： |
|
| 基金项目:河北省自然科学基金资助项目（F2013202254） |
|
| Clearness processing of haze-degraded images |
| SONG Xiaomin,ZHAO Hongdong,LU Qiao,XIA Shichao,XI Ruiyuan,LI Mengyu,XIAO Mengqi |
| () |
| Abstract: |
| The contrast and clarity of images are reduced in the hazy weather because of the atmospheric scattering and the suspended particulate matter．The independent component analysis(ICA) algorithm is used to estimate the useful information of image by disintegrating the mixed pixels which include many independent components．The adaptive median filter algorithm with noise detection is employed to eliminate the multiplicative noise information．Experimental results show that the new algorithm can meet the defogging goal and improve the contrast and clarity. |
| Key words: haze imaging processing defogging independent component analysis noise detection adaptive median filter |
