Fusion-based underwater image enhancement by wavelet decomposition
Fusion-based underwater image enhancement by wavelet decomposition
复制标题
DOI：
10.1109/icit.2017.7915500
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Yafei Wang;Xueyan Ding;Ruoqian Wang;Jun Zhang;Xianping Fu
中科院分区：
文献类型：
--
作者：
Yafei Wang;Xueyan Ding;Ruoqian Wang;Jun Zhang;Xianping Fu
水下图像能见度差主要有两个原因：一是光线吸收导致的色彩衰减，二是水下环境中存在的粒子散射导致的对比度低和模糊。为了实现水下图像的增强，提出了一种基于频域融合的水下图像增强策略。该融合过程包括两个输入，分别表示为从原始水下图像中提取的彩色校正图像和对比度增强图像。采用三尺度小波算子将色彩校正图像和对比度增强图像分解为低频和高频分量。低频和高频成分通过多尺度融合过程融合。低频分量采用加权平均融合，高频分量采用局部方差融合。这些融合的低频和高频分量可以重建为最终的增强图像。实验结果表明，该算法能显著提高水下图像的可见性。此外，该方法在水下环境下的图像特征点检测与匹配方面也取得了较好的效果。
Underwater images suffer from poor visibility due to two main factors: one is the color attenuation caused by light absorption, and the other one is low contrast and blur caused by particles scattering existing in underwater environments. To achieve underwater image enhancement, a fusion-based strategy applied to frequency domain is proposed. The proposed fusion process involves two inputs which are represented as color corrected and contrast enhanced images extracted from original underwater image. Both the color corrected and contrast enhanced images are decomposed into low frequency and high frequency components by three-scale wavelet operator. The low frequency and high frequency components are fused via a multi-scale fusion process. The low frequency components are fused by weighted average, and the high frequency components are fused by local variance. These fused low frequency and high frequency components can be reconstructed as final enhanced image. The experimental results show that the proposed algorithm can improve the visibility of underwater images significantly. In addition, the proposed approach arrives a good result in image feature points detection and matching in underwater environments.