基于小波变换的改进暗通道去雾算法

针对暗通道先验算法在景深较大处会出现颜色失真,且易受噪声干扰和运行时间久等问题,提出了一种基于多尺度小波变换的改进融合暗通道去雾方法。首先对有雾图像作二级小波分解,再对得到的高频分量利用软阈值去噪,对低频分量利用改进的自适应融合暗通道进行去雾。最后利用一个局部线性模型将高低频分量系数关联进行小波重构。实验结果表明,提出的算法具有较高的去雾效率,且能很好的提高去雾图像的质量。

Image defogging algorithm based on wavelet transform and improved dark channel1

Aiming at the problems of color distortion, noise interference and long running time in the dark channel prior algorithm with large depth of field, an image defogging method based on multi-scale wavelet transform and improved fusion dark channel is proposed. Firstly, the foggy image is decomposed by two-level wavelet transform, the high-frequency component is denoised by soft threshold, and the low-frequency component is defogged by improved adaptive fusion dark channel. Finally, a local linear model is used to correlate the high-frequency and low-frequency component coefficients for wavelet reconstruction. The experiment show that the proposed algorithm has high defogging effect and can improve the quality of defogging image.